From 83d157689c5d1dc4a2a10d8176e81dff97e2b9c6 Mon Sep 17 00:00:00 2001 From: chentang Date: Thu, 18 Dec 2025 14:38:19 +0800 Subject: [PATCH 01/47] fix bugs: try to fix bugs in _submit_web_logs --- src/memos/mem_scheduler/base_scheduler.py | 37 ++++++++++------------- 1 file changed, 16 insertions(+), 21 deletions(-) diff --git a/src/memos/mem_scheduler/base_scheduler.py b/src/memos/mem_scheduler/base_scheduler.py index 81defaa0f..9ab356f1d 100644 --- a/src/memos/mem_scheduler/base_scheduler.py +++ b/src/memos/mem_scheduler/base_scheduler.py @@ -846,28 +846,23 @@ def _submit_web_logs( f"[DIAGNOSTIC] base_scheduler._submit_web_logs called. Message to publish: {message.model_dump_json(indent=2)}" ) - if self.rabbitmq_config is None: - logger.info( - "[DIAGNOSTIC] base_scheduler._submit_web_logs: RabbitMQ config not loaded; skipping publish." - ) - return - - for message in messages: - message_info = message.debug_info() - logger.info(f"[DIAGNOSTIC] base_scheduler._submit_web_logs: submitted {message_info}") + try: + for message in messages: + # Always call publish; the publisher now caches when offline and flushes after reconnect + logger.info( + f"[DIAGNOSTIC] base_scheduler._submit_web_logs: enqueue publish {message.model_dump_json(indent=2)}" + ) + self.rabbitmq_publish_message(message=message.to_dict()) + logger.info( + "[DIAGNOSTIC] base_scheduler._submit_web_logs: publish dispatched " + "item_id=%s task_id=%s label=%s", + message.item_id, + message.task_id, + message.label, + ) + except Exception as e: + logger.error(f"[DIAGNOSTIC] base_scheduler._submit_web_logs failed: {e}", exc_info=True) - # Always call publish; the publisher now caches when offline and flushes after reconnect - logger.info( - f"[DIAGNOSTIC] base_scheduler._submit_web_logs: enqueue publish {message_info}" - ) - self.rabbitmq_publish_message(message=message.to_dict()) - logger.info( - "[DIAGNOSTIC] base_scheduler._submit_web_logs: publish dispatched " - "item_id=%s task_id=%s label=%s", - message.item_id, - message.task_id, - message.label, - ) logger.debug( f"{len(messages)} submitted. {self._web_log_message_queue.qsize()} in queue. additional_log_info: {additional_log_info}" ) From e50c56cf817cb6d63b8e8e882aeaa4de12c444b8 Mon Sep 17 00:00:00 2001 From: chentang Date: Thu, 18 Dec 2025 15:00:28 +0800 Subject: [PATCH 02/47] fix bugs: try to address bugs --- src/memos/mem_scheduler/base_scheduler.py | 13 +++++-------- .../webservice_modules/rabbitmq_service.py | 6 ++++-- 2 files changed, 9 insertions(+), 10 deletions(-) diff --git a/src/memos/mem_scheduler/base_scheduler.py b/src/memos/mem_scheduler/base_scheduler.py index 9ab356f1d..1e0ecaadb 100644 --- a/src/memos/mem_scheduler/base_scheduler.py +++ b/src/memos/mem_scheduler/base_scheduler.py @@ -842,12 +842,7 @@ def _submit_web_logs( messages = [messages] # transform single message to list for message in messages: - logger.info( - f"[DIAGNOSTIC] base_scheduler._submit_web_logs called. Message to publish: {message.model_dump_json(indent=2)}" - ) - - try: - for message in messages: + try: # Always call publish; the publisher now caches when offline and flushes after reconnect logger.info( f"[DIAGNOSTIC] base_scheduler._submit_web_logs: enqueue publish {message.model_dump_json(indent=2)}" @@ -860,8 +855,10 @@ def _submit_web_logs( message.task_id, message.label, ) - except Exception as e: - logger.error(f"[DIAGNOSTIC] base_scheduler._submit_web_logs failed: {e}", exc_info=True) + except Exception as e: + logger.error( + f"[DIAGNOSTIC] base_scheduler._submit_web_logs failed: {e}", exc_info=True + ) logger.debug( f"{len(messages)} submitted. {self._web_log_message_queue.qsize()} in queue. additional_log_info: {additional_log_info}" diff --git a/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py b/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py index a8a09760c..db8320879 100644 --- a/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py +++ b/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py @@ -7,6 +7,8 @@ from pathlib import Path from queue import Empty +from pyglet.libs.win32.constants import FALSE + from memos.configs.mem_scheduler import AuthConfig, RabbitMQConfig from memos.context.context import ContextThread from memos.dependency import require_python_package @@ -325,14 +327,14 @@ def rabbitmq_publish_message(self, message: dict): f"[DIAGNOSTIC] Publishing {label} message in Cloud Env. " f"Exchange: {exchange_name}, Routing Key: '{routing_key}'." ) - logger.info(f" - Message Content: {json.dumps(message, indent=2)}") + logger.info(f" - Message Content: {json.dumps(message, indent=2, ensure_ascii=FALSE)}") elif label == "knowledgeBaseUpdate": # Original diagnostic logging for knowledgeBaseUpdate if NOT in cloud env logger.info( f"[DIAGNOSTIC] Publishing knowledgeBaseUpdate message (Local Env). " f"Current configured Exchange: {exchange_name}, Routing Key: '{routing_key}'." ) - logger.info(f" - Message Content: {json.dumps(message, indent=2)}") + logger.info(f" - Message Content: {json.dumps(message, indent=2, ensure_ascii=FALSE)}") with self._rabbitmq_lock: logger.info( From 58eb6b81af34437677e929e629f25dd3ddf0c1ff Mon Sep 17 00:00:00 2001 From: chentang Date: Thu, 18 Dec 2025 15:13:21 +0800 Subject: [PATCH 03/47] fix bugs --- .../mem_scheduler/webservice_modules/rabbitmq_service.py | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py b/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py index db8320879..43d24c5b9 100644 --- a/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py +++ b/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py @@ -7,8 +7,6 @@ from pathlib import Path from queue import Empty -from pyglet.libs.win32.constants import FALSE - from memos.configs.mem_scheduler import AuthConfig, RabbitMQConfig from memos.context.context import ContextThread from memos.dependency import require_python_package @@ -327,14 +325,14 @@ def rabbitmq_publish_message(self, message: dict): f"[DIAGNOSTIC] Publishing {label} message in Cloud Env. " f"Exchange: {exchange_name}, Routing Key: '{routing_key}'." ) - logger.info(f" - Message Content: {json.dumps(message, indent=2, ensure_ascii=FALSE)}") + logger.info(f" - Message Content: {json.dumps(message, indent=2, ensure_ascii=False)}") elif label == "knowledgeBaseUpdate": # Original diagnostic logging for knowledgeBaseUpdate if NOT in cloud env logger.info( f"[DIAGNOSTIC] Publishing knowledgeBaseUpdate message (Local Env). " f"Current configured Exchange: {exchange_name}, Routing Key: '{routing_key}'." ) - logger.info(f" - Message Content: {json.dumps(message, indent=2, ensure_ascii=FALSE)}") + logger.info(f" - Message Content: {json.dumps(message, indent=2, ensure_ascii=False)}") with self._rabbitmq_lock: logger.info( From 0d72ce7669f3a9b30aa6849893a0e6ec6f991063 Mon Sep 17 00:00:00 2001 From: chentang Date: Thu, 18 Dec 2025 15:59:20 +0800 Subject: [PATCH 04/47] refactor: modify examples --- examples/mem_scheduler/memos_w_scheduler.py | 40 --------------------- 1 file changed, 40 deletions(-) diff --git a/examples/mem_scheduler/memos_w_scheduler.py b/examples/mem_scheduler/memos_w_scheduler.py index 09aec4cba..ef7d853df 100644 --- a/examples/mem_scheduler/memos_w_scheduler.py +++ b/examples/mem_scheduler/memos_w_scheduler.py @@ -4,7 +4,6 @@ from datetime import datetime from pathlib import Path -from queue import Queue from memos.configs.mem_cube import GeneralMemCubeConfig from memos.configs.mem_os import MOSConfig @@ -12,7 +11,6 @@ from memos.log import get_logger from memos.mem_cube.general import GeneralMemCube from memos.mem_os.main import MOS -from memos.mem_scheduler.general_scheduler import GeneralScheduler from memos.mem_scheduler.schemas.message_schemas import ScheduleLogForWebItem from memos.mem_scheduler.schemas.task_schemas import ( ADD_TASK_LABEL, @@ -160,42 +158,6 @@ def _first_content() -> str: return title, _truncate_with_rules(_first_content()) -def show_web_logs(mem_scheduler: GeneralScheduler): - """Display all web log entries from the scheduler's log queue. - - Args: - mem_scheduler: The scheduler instance containing web logs to display - """ - if mem_scheduler._web_log_message_queue.empty(): - print("Web log queue is currently empty.") - return - - print("\n" + "=" * 50 + " WEB LOGS " + "=" * 50) - - # Create a temporary queue to preserve the original queue contents - temp_queue = Queue() - collected: list[ScheduleLogForWebItem] = [] - - while not mem_scheduler._web_log_message_queue.empty(): - log_item: ScheduleLogForWebItem = mem_scheduler._web_log_message_queue.get() - collected.append(log_item) - temp_queue.put(log_item) - - for idx, log_item in enumerate(sorted(collected, key=lambda x: x.timestamp, reverse=True), 1): - title, content = _format_entry(log_item) - print(f"\nLog Entry #{idx}:") - print(title) - print(content) - print("-" * 50) - - # Restore items back to the original queue - while not temp_queue.empty(): - mem_scheduler._web_log_message_queue.put(temp_queue.get()) - - print(f"\nTotal {len(collected)} web log entries displayed.") - print("=" * 110 + "\n") - - def run_with_scheduler_init(): print("==== run_with_automatic_scheduler_init ====") conversations, questions = init_task() @@ -253,8 +215,6 @@ def run_with_scheduler_init(): response = mos.chat(query=query, user_id=user_id) print(f"Answer:\n {response}\n") - show_web_logs(mem_scheduler=mos.mem_scheduler) - mos.mem_scheduler.stop() From 2fe965be240ea0e68c511b5573d88e9599b7cbd2 Mon Sep 17 00:00:00 2001 From: chentang Date: Thu, 18 Dec 2025 20:06:40 +0800 Subject: [PATCH 05/47] revise add operation and fix an unbelievable bug --- .../mem_scheduler/try_schedule_modules.py | 47 ------------------- src/memos/mem_reader/simple_struct.py | 2 +- .../webservice_modules/rabbitmq_service.py | 3 +- src/memos/templates/mem_reader_prompts.py | 39 ++++++++------- 4 files changed, 21 insertions(+), 70 deletions(-) diff --git a/examples/mem_scheduler/try_schedule_modules.py b/examples/mem_scheduler/try_schedule_modules.py index a5c5bc737..d942aad4e 100644 --- a/examples/mem_scheduler/try_schedule_modules.py +++ b/examples/mem_scheduler/try_schedule_modules.py @@ -1,8 +1,6 @@ import sys from pathlib import Path -from queue import Queue -from typing import TYPE_CHECKING from tqdm import tqdm @@ -11,18 +9,11 @@ ) from memos.log import get_logger from memos.mem_scheduler.analyzer.api_analyzer import DirectSearchMemoriesAnalyzer -from memos.mem_scheduler.base_scheduler import BaseScheduler from memos.mem_scheduler.optimized_scheduler import OptimizedScheduler from memos.mem_scheduler.schemas.message_schemas import ScheduleMessageItem from memos.mem_scheduler.schemas.task_schemas import MEM_UPDATE_TASK_LABEL -if TYPE_CHECKING: - from memos.mem_scheduler.schemas import ( - ScheduleLogForWebItem, - ) - - FILE_PATH = Path(__file__).absolute() BASE_DIR = FILE_PATH.parent.parent.parent sys.path.insert(0, str(BASE_DIR)) # Enable execution from any working directory @@ -105,41 +96,6 @@ def init_task(): return conversations, questions -def show_web_logs(mem_scheduler: BaseScheduler): - """Display all web log entries from the scheduler's log queue. - - Args: - mem_scheduler: The scheduler instance containing web logs to display - """ - if mem_scheduler._web_log_message_queue.empty(): - print("Web log queue is currently empty.") - return - - print("\n" + "=" * 50 + " WEB LOGS " + "=" * 50) - - # Create a temporary queue to preserve the original queue contents - temp_queue = Queue() - log_count = 0 - - while not mem_scheduler._web_log_message_queue.empty(): - log_item: ScheduleLogForWebItem = mem_scheduler._web_log_message_queue.get() - temp_queue.put(log_item) - log_count += 1 - - # Print log entry details - print(f"\nLog Entry #{log_count}:") - print(f'- "{log_item.label}" log: {log_item}') - - print("-" * 50) - - # Restore items back to the original queue - while not temp_queue.empty(): - mem_scheduler._web_log_message_queue.put(temp_queue.get()) - - print(f"\nTotal {log_count} web log entries displayed.") - print("=" * 110 + "\n") - - class ScheduleModulesRunner(DirectSearchMemoriesAnalyzer): def __init__(self): super().__init__() @@ -215,6 +171,3 @@ def add_msgs( mem_scheduler._memory_update_consumer( messages=[message], ) - - # Show accumulated web logs - show_web_logs(mem_scheduler) diff --git a/src/memos/mem_reader/simple_struct.py b/src/memos/mem_reader/simple_struct.py index ac79c246b..b870bf70a 100644 --- a/src/memos/mem_reader/simple_struct.py +++ b/src/memos/mem_reader/simple_struct.py @@ -522,7 +522,7 @@ def filter_hallucination_in_memories( raw = self.llm.generate([{"role": "user", "content": prompt}]) success, parsed = self._parse_hallucination_filter_response(raw) logger.info( - f"[filter_hallucination_in_memories] Hallucination filter parsed successfully: {success}" + f"[filter_hallucination_in_memories] Hallucination filter parsed successfully: {success}；prompt: {prompt}" ) if success: logger.info(f"Hallucination filter result: {parsed}") diff --git a/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py b/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py index 43d24c5b9..46b2ad3d1 100644 --- a/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py +++ b/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py @@ -108,8 +108,7 @@ def initialize_rabbitmq( elif Path(config_path).exists(): auth_config = AuthConfig.from_local_config(config_path=config_path) else: - logger.error("Fail to initialize auth_config") - return + auth_config = AuthConfig.from_local_env() self.rabbitmq_config = auth_config.rabbitmq elif isinstance(config, RabbitMQConfig): self.rabbitmq_config = config diff --git a/src/memos/templates/mem_reader_prompts.py b/src/memos/templates/mem_reader_prompts.py index 12c445df7..fef3ee6c0 100644 --- a/src/memos/templates/mem_reader_prompts.py +++ b/src/memos/templates/mem_reader_prompts.py @@ -625,21 +625,20 @@ SIMPLE_STRUCT_HALLUCINATION_FILTER_PROMPT = """ You are a strict, language-preserving memory validator and rewriter. -Your task is to compare each memory against the provided user messages (the ground truth) and produce a corrected version only when necessary. Always preserve the original language of the memory—do not translate. +Your task is to eliminate hallucinations and tighten memories by grounding them strictly in the user’s explicit messages. Memories must be factual, unambiguous, and free of any inferred or speculative content. Rules: -1. **Language Consistency**: The rewritten memory must be in the exact same language as the original input memory. Never switch languages. -2. **Strict Grounding**: Only use information explicitly stated in the user messages. Do not introduce external facts, assumptions, or common sense. -3. **Ambiguity Resolution**: - - Replace vague pronouns (e.g., "he", "it", "they") or unclear references with specific, unambiguous entities based solely on the messages. - - Convert relative time expressions (e.g., "yesterday", "last week", "in two days") into absolute dates or times **only if the messages provide enough context** (e.g., current date is known or implied). -4. **Handling Assistant Inferences**: - - If a memory contains any content **not directly stated by the user**—such as interpretations, summaries, emotional attributions, predictions, causal claims, or generalizations—this is considered an assistant inference. - - In such cases, you **must** set `need_rewrite = true`. - - The `rewritten` text **must explicitly indicate that the statement is an inference**, using a clear and natural prefix in the memory’s language. For English memories, use: - > "The assistant inferred that [rest of the memory]." - - Do **not** present inferred content as factual user statements. -5. **No Rewrite Needed**: If the memory is factually accurate, fully grounded in the messages, unambiguous, and contains no unsupported content, set `need_rewrite = false` and copy the original memory exactly. +1. **Language Consistency**: Keep the exact original language of each memory—no translation or language switching. +2. **Strict Factual Grounding**: Include only what the user explicitly stated. Remove or flag anything not directly present in the messages—no assumptions, interpretations, predictions, emotional labels, summaries, or generalizations. +3. **Ambiguity Elimination**: + - Replace vague pronouns (e.g., “he”, “it”, “they”) with clear, specific entities **only if** the messages identify them. + - Convert relative time expressions (e.g., “yesterday”) to absolute dates **only if** the messages provide enough temporal context. +4. **Hallucination Removal**: + - If a memory contains **any content not verbatim or directly implied by the user**, it must be rewritten. + - Do **not** rephrase inferences as facts. Instead, either: + - Remove the unsupported part and retain only the grounded core, or + - If the entire memory is ungrounded, mark it for rewrite and make the lack of user support explicit. +5. **No Change if Fully Grounded**: If the memory is concise, unambiguous, and fully supported by the user’s messages, keep it unchanged. Inputs: messages: @@ -649,15 +648,15 @@ {memories_inline} Output Format: -- Return a JSON object with string keys ("0", "1", "2", ...) corresponding to the input memory indices. +- Return a JSON object with string keys ("0", "1", "2", ...) matching input memory indices. - Each value must be: {{ "need_rewrite": boolean, "rewritten": string, "reason": string }} -- The "reason" should be concise and specific, e.g.: - - "contains assistant inference not stated by user" - - "pronoun 'it' has no clear referent in messages" - - "relative time 'yesterday' converted to 2025-12-16" - - "accurate and directly supported by user message" +- The "reason" must be brief and precise, e.g.: + - "contains unsupported inference" + - "vague pronoun with no referent in messages" + - "relative time resolved to 2025-12-16" + - "fully grounded and concise" -Important: Output **only** the JSON. No additional text, explanations, markdown, or fields. +Important: Output **only** the JSON. No extra text, explanations, markdown, or fields. """ From eecfa5136d9065fefd82867068a8deb12efae8a2 Mon Sep 17 00:00:00 2001 From: chentang Date: Mon, 22 Dec 2025 10:37:34 +0800 Subject: [PATCH 06/47] address the bug issues --- .../task_schedule_modules/redis_queue.py | 38 +++++++++---------- 1 file changed, 17 insertions(+), 21 deletions(-) diff --git a/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py b/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py index ed8171ade..1c57f18f0 100644 --- a/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py +++ b/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py @@ -699,27 +699,23 @@ def _batch_claim_pending_messages( results = [] try: results = pipe.execute() - except Exception as e: - err_msg = str(e).lower() - if "nogroup" in err_msg or "no such key" in err_msg: - # Fallback: attempt sequential xautoclaim for robustness - for stream_key, need_count, label in claims_spec: - try: - self._ensure_consumer_group(stream_key=stream_key) - res = self._redis_conn.xautoclaim( - name=stream_key, - groupname=self.consumer_group, - consumername=self.consumer_name, - min_idle_time=self.orchestrator.get_task_idle_min(task_label=label), - start_id="0-0", - count=need_count, - justid=False, - ) - results.append(res) - except Exception: - continue - else: - logger.error(f"Pipeline xautoclaim failed: {e}") + except Exception: + # Fallback: attempt sequential xautoclaim for robustness + for stream_key, need_count, label in claims_spec: + try: + self._ensure_consumer_group(stream_key=stream_key) + res = self._redis_conn.xautoclaim( + name=stream_key, + groupname=self.consumer_group, + consumername=self.consumer_name, + min_idle_time=self.orchestrator.get_task_idle_min(task_label=label), + start_id="0-0", + count=need_count, + justid=False, + ) + results.append(res) + except Exception: + continue claimed_pairs: list[tuple[str, list[tuple[str, dict]]]] = [] for (stream_key, _need_count, _label), claimed_result in zip( From f2da3a7bd718cf663b29fb285e602e847f4dc91a Mon Sep 17 00:00:00 2001 From: chentang Date: Wed, 24 Dec 2025 19:35:40 +0800 Subject: [PATCH 07/47] the doc file has a format problem which has been fixed in this commit --- docs/README.md | 2 +- .../{task_stop_rerun.py => scheduler_for_async_tasks.py} | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) rename examples/mem_scheduler/{task_stop_rerun.py => scheduler_for_async_tasks.py} (98%) diff --git a/docs/README.md b/docs/README.md index bf5fea70d..8be17ffb7 100644 --- a/docs/README.md +++ b/docs/README.md @@ -1,3 +1,3 @@ All documentation has been moved to a separate repository: https://github.com/MemTensor/MemOS-Docs. Please edit documentation there. -所有文档已迁移至独立仓库：https://github.com/MemTensor/MemOS-Docs。请在该仓库中编辑文档。 +所有文档已迁移至独立仓库 https://github.com/MemTensor/MemOS-Docs 。请在该仓库中编辑文档。 diff --git a/examples/mem_scheduler/task_stop_rerun.py b/examples/mem_scheduler/scheduler_for_async_tasks.py similarity index 98% rename from examples/mem_scheduler/task_stop_rerun.py rename to examples/mem_scheduler/scheduler_for_async_tasks.py index b5e62ff8f..a767b57c4 100644 --- a/examples/mem_scheduler/task_stop_rerun.py +++ b/examples/mem_scheduler/scheduler_for_async_tasks.py @@ -25,7 +25,7 @@ def my_test_handler(messages: list[ScheduleMessageItem]): task_id = str(msg.item_id) file_path = tmp_dir / f"{task_id}.txt" try: - sleep(1) + sleep(5) file_path.write_text(f"Task {task_id} processed.\n") print(f"writing {file_path} done") except Exception as e: @@ -58,7 +58,7 @@ def submit_tasks(): mem_scheduler.register_handlers({TEST_HANDLER_LABEL: my_test_handler}) # 10s to restart -mem_scheduler.orchestrator.tasks_min_idle_ms[TEST_HANDLER_LABEL] = 10_000 +mem_scheduler.orchestrator.tasks_min_idle_ms[TEST_HANDLER_LABEL] = 5_000 tmp_dir = Path("./tmp") tmp_dir.mkdir(exist_ok=True) @@ -88,6 +88,6 @@ def submit_tasks(): print(f"[Result] Final files in tmp: {len(list(tmp_dir.glob('*.txt')))})") # 7. Stop the scheduler +sleep(20) print("Stopping the scheduler...") -sleep(5) mem_scheduler.stop() From a6881b4b064145f032c9b9e58ed0f9772ef33612 Mon Sep 17 00:00:00 2001 From: chentang Date: Wed, 24 Dec 2025 19:45:48 +0800 Subject: [PATCH 08/47] add a range of new feats for the add operation --- src/memos/api/config.py | 21 +- src/memos/llms/openai.py | 6 +- src/memos/mem_reader/simple_struct.py | 354 ++++++++++-------- src/memos/mem_reader/utils.py | 210 +++++++++++ .../mem_scheduler/schemas/general_schemas.py | 4 +- .../task_schedule_modules/redis_queue.py | 69 ++-- .../textual/prefer_text_memory/extractor.py | 4 + src/memos/templates/mem_reader_prompts.py | 156 +++++++- 8 files changed, 624 insertions(+), 200 deletions(-) create mode 100644 src/memos/mem_reader/utils.py diff --git a/src/memos/api/config.py b/src/memos/api/config.py index b795c2be6..0cdcb9a92 100644 --- a/src/memos/api/config.py +++ b/src/memos/api/config.py @@ -7,16 +7,19 @@ import re import time -from typing import Any +from typing import TYPE_CHECKING, Any import requests from dotenv import load_dotenv -from memos.configs.mem_cube import GeneralMemCubeConfig -from memos.configs.mem_os import MOSConfig from memos.context.context import ContextThread -from memos.mem_cube.general import GeneralMemCube + + +if TYPE_CHECKING: + from memos.configs.mem_cube import GeneralMemCubeConfig + from memos.configs.mem_os import MOSConfig + from memos.mem_cube.general import GeneralMemCube # Load environment variables @@ -805,8 +808,12 @@ def get_start_default_config() -> dict[str, Any]: return config @staticmethod - def create_user_config(user_name: str, user_id: str) -> tuple[MOSConfig, GeneralMemCube]: + def create_user_config(user_name: str, user_id: str) -> tuple["MOSConfig", "GeneralMemCube"]: """Create configuration for a specific user.""" + from memos.configs.mem_cube import GeneralMemCubeConfig + from memos.configs.mem_os import MOSConfig + from memos.mem_cube.general import GeneralMemCube + openai_config = APIConfig.get_openai_config() qwen_config = APIConfig.qwen_config() vllm_config = APIConfig.vllm_config() @@ -933,12 +940,14 @@ def create_user_config(user_name: str, user_id: str) -> tuple[MOSConfig, General return default_config, default_mem_cube @staticmethod - def get_default_cube_config() -> GeneralMemCubeConfig | None: + def get_default_cube_config() -> "GeneralMemCubeConfig | None": """Get default cube configuration for product initialization. Returns: GeneralMemCubeConfig | None: Default cube configuration if enabled, None otherwise. """ + from memos.configs.mem_cube import GeneralMemCubeConfig + if not APIConfig.is_default_cube_config_enabled(): return None diff --git a/src/memos/llms/openai.py b/src/memos/llms/openai.py index 1d180eebd..752386c91 100644 --- a/src/memos/llms/openai.py +++ b/src/memos/llms/openai.py @@ -57,8 +57,8 @@ def generate(self, messages: MessageList, **kwargs) -> str: if self.config.remove_think_prefix: return remove_thinking_tags(response_content) if reasoning_content: - return reasoning_content + response_content - return response_content + return reasoning_content + (response_content or "") + return response_content or "" @timed_with_status( log_prefix="OpenAI LLM", @@ -146,7 +146,7 @@ def generate(self, messages: MessageList, **kwargs) -> str: if self.config.remove_think_prefix: return remove_thinking_tags(response_content) else: - return response_content + return response_content or "" def generate_stream(self, messages: MessageList, **kwargs) -> Generator[str, None, None]: """Stream response from Azure OpenAI LLM with optional reasoning support.""" diff --git a/src/memos/mem_reader/simple_struct.py b/src/memos/mem_reader/simple_struct.py index b870bf70a..866b6d988 100644 --- a/src/memos/mem_reader/simple_struct.py +++ b/src/memos/mem_reader/simple_struct.py @@ -2,7 +2,6 @@ import copy import json import os -import re import traceback from abc import ABC @@ -18,6 +17,13 @@ from memos.llms.factory import LLMFactory from memos.mem_reader.base import BaseMemReader from memos.mem_reader.read_multi_modal import coerce_scene_data, detect_lang +from memos.mem_reader.utils import ( + count_tokens_text, + derive_key, + parse_json_result, + parse_keep_filter_response, + parse_rewritten_response, +) from memos.memories.textual.item import ( SourceMessage, TextualMemoryItem, @@ -89,27 +95,6 @@ def from_config(_config): } -try: - import tiktoken - - try: - _ENC = tiktoken.encoding_for_model("gpt-4o-mini") - except Exception: - _ENC = tiktoken.get_encoding("cl100k_base") - - def _count_tokens_text(s: str) -> int: - return len(_ENC.encode(s or "", disallowed_special=())) -except Exception: - # Heuristic fallback: zh chars ~1 token, others ~1 token per ~4 chars - def _count_tokens_text(s: str) -> int: - if not s: - return 0 - zh_chars = re.findall(r"[\u4e00-\u9fff]", s) - zh = len(zh_chars) - rest = len(s) - zh - return zh + max(1, rest // 4) - - def _build_node(idx, message, info, source_info, llm, parse_json_result, embedder): # generate try: @@ -172,14 +157,6 @@ def _build_node(idx, message, info, source_info, llm, parse_json_result, embedde return None -def _derive_key(text: str, max_len: int = 80) -> str: - """default key when without LLM: first max_len words""" - if not text: - return "" - sent = re.split(r"[。！？!?]\s*|\n", text.strip())[0] - return (sent[:max_len]).strip() - - class SimpleStructMemReader(BaseMemReader, ABC): """Naive implementation of MemReader.""" @@ -197,7 +174,8 @@ def __init__(self, config: SimpleStructMemReaderConfig): self.memory_max_length = 8000 # Use token-based windowing; default to ~5000 tokens if not configured self.chat_window_max_tokens = getattr(self.config, "chat_window_max_tokens", 1024) - self._count_tokens = _count_tokens_text + self._count_tokens = count_tokens_text + self.searcher = None def _make_memory_item( self, @@ -224,7 +202,7 @@ def _make_memory_item( memory_type=memory_type, status="activated", tags=tags or [], - key=key if key is not None else _derive_key(value), + key=key if key is not None else derive_key(value), embedding=self.embedder.embed([value])[0], usage=[], sources=sources or [], @@ -254,7 +232,7 @@ def _get_llm_response(self, mem_str: str, custom_tags: list[str] | None) -> dict messages = [{"role": "user", "content": prompt}] try: response_text = self.llm.generate(messages) - response_json = self.parse_json_result(response_text) + response_json = parse_json_result(response_text) except Exception as e: logger.error(f"[LLM] Exception during chat generation: {e}") response_json = { @@ -456,47 +434,73 @@ def get_memory( standard_scene_data = coerce_scene_data(scene_data, type) return self._read_memory(standard_scene_data, type, info, mode) - @staticmethod - def _parse_hallucination_filter_response(text: str) -> tuple[bool, dict[int, dict]]: - """Parse index-keyed JSON from hallucination filter response. - Expected shape: { "0": {"need_rewrite": bool, "rewritten": str, "reason": str}, ... } - Returns (success, parsed_dict) with int keys. - """ + def rewrite_memories( + self, messages: list[dict], memory_list: list[TextualMemoryItem], user_only: bool = True + ) -> list[TextualMemoryItem]: + # Build input objects with memory text and metadata (timestamps, sources, etc.) + if user_only: + template = PROMPT_MAPPING["rewrite_user_only"] + filtered_messages = [m for m in messages if m.get("role") != "assistant"] + if len(filtered_messages) < 1: + return memory_list + else: + template = PROMPT_MAPPING["rewrite"] + filtered_messages = messages + if len(filtered_messages) < 2: + return memory_list + + prompt_args = { + "messages_inline": "\n".join( + [f"- [{message['role']}]: {message['content']}" for message in filtered_messages] + ), + "memories_inline": json.dumps( + {idx: mem.memory for idx, mem in enumerate(memory_list)}, + ensure_ascii=False, + indent=2, + ), + } + prompt = template.format(**prompt_args) + + # Optionally run filter and parse the output try: - data = json.loads(text) - except Exception: - return False, {} + raw = self.llm.generate([{"role": "user", "content": prompt}]) + success, parsed = parse_rewritten_response(raw) + logger.info( + f"[rewrite_memories] Hallucination filter parsed successfully: {success}；prompt: {prompt}" + ) + if success: + logger.info(f"Rewrite filter result: {parsed}") - if not isinstance(data, dict): - return False, {} + new_memory_list = [] + for mem_idx, content in parsed.items(): + if mem_idx < 0 or mem_idx >= len(memory_list): + logger.warning( + f"[rewrite_memories] Invalid memory index {mem_idx} for memory_list {len(memory_list)}, skipping." + ) + continue - result: dict[int, dict] = {} - for k, v in data.items(): - try: - idx = int(k) - except Exception: - # allow integer keys as-is - if isinstance(k, int): - idx = k - else: - continue - if not isinstance(v, dict): - continue - need_rewrite = v.get("need_rewrite") - rewritten = v.get("rewritten", "") - reason = v.get("reason", "") - if ( - isinstance(need_rewrite, bool) - and isinstance(rewritten, str) - and isinstance(reason, str) - ): - result[idx] = { - "need_rewrite": need_rewrite, - "rewritten": rewritten, - "reason": reason, - } + need_rewrite = content.get("need_rewrite", False) + rewritten_text = content.get("rewritten", "") + reason = content.get("reason", "") + original_text = memory_list[mem_idx].memory + + # Replace memory text with rewritten content when rewrite is needed + if need_rewrite and isinstance(rewritten_text, str): + logger.info( + f"[rewrite_memories] index={mem_idx}, need_rewrite={need_rewrite}, rewritten='{rewritten_text}', reason='{reason}', original memory='{original_text}', action='replace_text'" + ) + if len(rewritten_text.strip()) != 0: + memory_list[mem_idx].memory = rewritten_text + new_memory_list.append(memory_list[mem_idx]) + else: + new_memory_list.append(memory_list[mem_idx]) + return new_memory_list + else: + logger.warning("Rewrite filter parsing failed or returned empty result.") + except Exception as e: + logger.error(f"Rewrite filter execution error: {e}", stack_info=True) - return (len(result) > 0), result + return memory_list def filter_hallucination_in_memories( self, messages: list[dict], memory_list: list[TextualMemoryItem] @@ -520,32 +524,32 @@ def filter_hallucination_in_memories( # Optionally run filter and parse the output try: raw = self.llm.generate([{"role": "user", "content": prompt}]) - success, parsed = self._parse_hallucination_filter_response(raw) + success, parsed = parse_keep_filter_response(raw) logger.info( f"[filter_hallucination_in_memories] Hallucination filter parsed successfully: {success}；prompt: {prompt}" ) if success: logger.info(f"Hallucination filter result: {parsed}") - assert len(parsed) == len(memory_list) - for mem_idx, content in parsed.items(): - need_rewrite = content.get("need_rewrite", False) - rewritten_text = content.get("rewritten", "") - reason = content.get("reason", "") - # Replace memory text with rewritten content when rewrite is needed - if ( - need_rewrite - and isinstance(rewritten_text, str) - and len(rewritten_text.strip()) > 0 - ): - original_text = memory_list[mem_idx].memory + filtered_list = [] + for mem_idx, mem in enumerate(memory_list): + content = parsed.get(mem_idx) + if not content: + logger.warning(f"No verdict for memory {mem_idx}, keeping it.") + filtered_list.append(mem) + continue + keep = content.get("keep", True) + reason = content.get("reason", "") + + if keep: + filtered_list.append(mem) + else: logger.info( - f"[filter_hallucination_in_memories] index={mem_idx}, need_rewrite={need_rewrite}, rewritten='{rewritten_text}', reason='{reason}', original memory='{original_text}', action='replace_text'" + f"[filter_hallucination_in_memories] Dropping memory index={mem_idx}, reason='{reason}', memory='{mem.memory}'" ) - memory_list[mem_idx].memory = rewritten_text - return memory_list + return filtered_list else: logger.warning("Hallucination filter parsing failed or returned empty result.") except Exception as e: @@ -553,6 +557,103 @@ def filter_hallucination_in_memories( return memory_list + def add_before_search( + self, + messages: list[dict], + memory_list: list[TextualMemoryItem], + ) -> list[TextualMemoryItem]: + # Build input objects with memory text and metadata (timestamps, sources, etc.) + template = PROMPT_MAPPING["add_before_search"] + + if not self.searcher: + try: + from memos.mem_reader.utils import init_searcher + + self.searcher = init_searcher(self.llm, self.embedder) + except Exception as e: + logger.error(f"[add_before_search] Failed to init searcher: {e}") + return memory_list + + # 1. Gather candidates and search for related memories + candidates_data = [] + for idx, mem in enumerate(memory_list): + try: + related_memories = self.searcher.search( + query=mem.memory, top_k=3, mode="fast", info={"user_id": "", "session_id": ""} + ) + related_text = "None" + if related_memories: + related_text = "\n".join([f"- {r.memory}" for r in related_memories]) + + candidates_data.append( + {"idx": idx, "new_memory": mem.memory, "related_memories": related_text} + ) + except Exception as e: + logger.error(f"[add_before_search] Search error for memory '{mem.memory}': {e}") + # If search fails, we can either skip this check or treat related as empty + candidates_data.append( + { + "idx": idx, + "new_memory": mem.memory, + "related_memories": "None (Search Failed)", + } + ) + + if not candidates_data: + return memory_list + + # 2. Build Prompt + messages_inline = "\n".join( + [ + f"- [{message.get('role', 'unknown')}]: {message.get('content', '')}" + for message in messages + ] + ) + + candidates_inline_dict = { + str(item["idx"]): { + "new_memory": item["new_memory"], + "related_memories": item["related_memories"], + } + for item in candidates_data + } + + candidates_inline = json.dumps(candidates_inline_dict, ensure_ascii=False, indent=2) + + prompt = template.format( + messages_inline=messages_inline, candidates_inline=candidates_inline + ) + + # 3. Call LLM + try: + raw = self.llm.generate([{"role": "user", "content": prompt}]) + success, parsed_result = parse_keep_filter_response(raw) + + if not success: + logger.warning("[add_before_search] Failed to parse LLM response, keeping all.") + return memory_list + + # 4. Filter + filtered_list = [] + for idx, mem in enumerate(memory_list): + res = parsed_result.get(idx) + if not res: + filtered_list.append(mem) + continue + + if res.get("keep", True): + filtered_list.append(mem) + else: + logger.info( + f"[add_before_search] Dropping memory: '{mem.memory}', reason: '{res.get('reason')}'" + ) + + return filtered_list + + except Exception as e: + logger.error(f"[add_before_search] LLM execution error: {e}") + return memory_list + def _read_memory( self, messages: list[MessagesType], type: str, info: dict[str, Any], mode: str = "fine" ) -> list[list[TextualMemoryItem]]: @@ -606,29 +707,27 @@ def _read_memory( for group_id in range(len(memory_list)): try: - revised_memory_list = self.filter_hallucination_in_memories( + original_memory_group = copy.deepcopy(memory_list[group_id]) + serialized_origin_memories = json.dumps( + [one.memory for one in original_memory_group], indent=2 + ) + revised_memory_list = self.rewrite_memories( messages=combined_messages, - memory_list=memory_list[group_id], + memory_list=original_memory_group, + user_only=os.getenv("SIMPLE_STRUCT_REWRITE_USER_ONLY", "true").lower() + == "true", + ) + serialized_revised_memories = json.dumps( + [one.memory for one in revised_memory_list], indent=2 ) - if len(revised_memory_list) != len(memory_list[group_id]): - original_serialized = [ - one.memory if hasattr(one, "memory") else str(one) - for one in memory_list[group_id] - ] - filtered_serialized = [ - one.memory if hasattr(one, "memory") else str(one) - for one in revised_memory_list - ] - logger.error( - f"Length mismatch after hallucination filtering for group_id={group_id}: " - f"original={len(memory_list[group_id])}, filtered={len(revised_memory_list)}" - f"\noriginal_memory_list(serialized): {original_serialized}" - f"\nfiltered_memory_list(serialized): {filtered_serialized}" - f"\nmessages: {combined_messages}" - f"\nSkipping update and keeping original memory." + if serialized_origin_memories != serialized_revised_memories: + memory_list[group_id] = revised_memory_list + logger.info( + f"[SIMPLE_STRUCT_ADD_FILTER] Modified the list for group_id={group_id}: " + f"\noriginal={serialized_origin_memories}," + f"\nrevised={serialized_revised_memories}" ) - continue - memory_list[group_id] = revised_memory_list + except Exception as e: group_serialized = [ one.memory if hasattr(one, "memory") else str(one) @@ -847,7 +946,7 @@ def _process_doc_data(self, scene_data_info, info, **kwargs): info, source_info_list, self.llm, - self.parse_json_result, + parse_json_result, self.embedder, ): idx for idx, msg in enumerate(messages) @@ -870,44 +969,3 @@ def _process_transfer_doc_data( self, raw_node: TextualMemoryItem, custom_tags: list[str] | None = None ): raise NotImplementedError - - def parse_json_result(self, response_text: str) -> dict: - s = (response_text or "").strip() - - m = re.search(r"```(?:json)?\s*([\s\S]*?)```", s, flags=re.I) - s = (m.group(1) if m else s.replace("```", "")).strip() - - i = s.find("{") - if i == -1: - return {} - s = s[i:].strip() - - try: - return json.loads(s) - except json.JSONDecodeError: - pass - - j = max(s.rfind("}"), s.rfind("]")) - if j != -1: - try: - return json.loads(s[: j + 1]) - except json.JSONDecodeError: - pass - - def _cheap_close(t: str) -> str: - t += "}" * max(0, t.count("{") - t.count("}")) - t += "]" * max(0, t.count("[") - t.count("]")) - return t - - t = _cheap_close(s) - try: - return json.loads(t) - except json.JSONDecodeError as e: - if "Invalid \\escape" in str(e): - s = s.replace("\\", "\\\\") - return json.loads(s) - logger.error( - f"[JSONParse] Failed to decode JSON: {e}\nTail: Raw {response_text} \ - json: {s}" - ) - return {} diff --git a/src/memos/mem_reader/utils.py b/src/memos/mem_reader/utils.py new file mode 100644 index 000000000..843345ec4 --- /dev/null +++ b/src/memos/mem_reader/utils.py @@ -0,0 +1,210 @@ +import json +import os +import re + +from typing import Any + +from memos import log +from memos.api.config import APIConfig +from memos.configs.graph_db import GraphDBConfigFactory +from memos.configs.reranker import RerankerConfigFactory +from memos.graph_dbs.factory import GraphStoreFactory +from memos.memories.textual.tree_text_memory.retrieve.searcher import Searcher +from memos.reranker.factory import RerankerFactory + + +logger = log.get_logger(__name__) + +try: + import tiktoken + + try: + _ENC = tiktoken.encoding_for_model("gpt-4o-mini") + except Exception: + _ENC = tiktoken.get_encoding("cl100k_base") + + def count_tokens_text(s: str) -> int: + return len(_ENC.encode(s or "", disallowed_special=())) +except Exception: + # Heuristic fallback: zh chars ~1 token, others ~1 token per ~4 chars + def count_tokens_text(s: str) -> int: + if not s: + return 0 + zh_chars = re.findall(r"[\u4e00-\u9fff]", s) + zh = len(zh_chars) + rest = len(s) - zh + return zh + max(1, rest // 4) + + +def derive_key(text: str, max_len: int = 80) -> str: + """default key when without LLM: first max_len words""" + if not text: + return "" + sent = re.split(r"[。！？!?]\s*|\n", text.strip())[0] + return (sent[:max_len]).strip() + + +def parse_json_result(response_text: str) -> dict: + s = (response_text or "").strip() + + m = re.search(r"```(?:json)?\s*([\s\S]*?)```", s, flags=re.I) + s = (m.group(1) if m else s.replace("```", "")).strip() + + i = s.find("{") + if i == -1: + return {} + s = s[i:].strip() + + try: + return json.loads(s) + except json.JSONDecodeError: + pass + + j = max(s.rfind("}"), s.rfind("]")) + if j != -1: + try: + return json.loads(s[: j + 1]) + except json.JSONDecodeError: + pass + + def _cheap_close(t: str) -> str: + t += "}" * max(0, t.count("{") - t.count("}")) + t += "]" * max(0, t.count("[") - t.count("]")) + return t + + t = _cheap_close(s) + try: + return json.loads(t) + except json.JSONDecodeError as e: + if "Invalid \\escape" in str(e): + s = s.replace("\\", "\\\\") + return json.loads(s) + logger.error( + f"[JSONParse] Failed to decode JSON: {e}\nTail: Raw {response_text} \ + json: {s}" + ) + return {} + + +def parse_rewritten_response(text: str) -> tuple[bool, dict[int, dict]]: + """Parse index-keyed JSON from hallucination filter response. + Expected shape: { "0": {"need_rewrite": bool, "rewritten": str, "reason": str}, ... } + Returns (success, parsed_dict) with int keys. + """ + try: + m = re.search(r"```(?:json)?\s*([\s\S]*?)```", text, flags=re.I) + s = (m.group(1) if m else text).strip() + data = json.loads(s) + except Exception: + return False, {} + + if not isinstance(data, dict): + return False, {} + + result: dict[int, dict] = {} + for k, v in data.items(): + try: + idx = int(k) + except Exception: + # allow integer keys as-is + if isinstance(k, int): + idx = k + else: + continue + if not isinstance(v, dict): + continue + need_rewrite = v.get("need_rewrite") + rewritten = v.get("rewritten", "") + reason = v.get("reason", "") + if ( + isinstance(need_rewrite, bool) + and isinstance(rewritten, str) + and isinstance(reason, str) + ): + result[idx] = { + "need_rewrite": need_rewrite, + "rewritten": rewritten, + "reason": reason, + } + + return (len(result) > 0), result + + +def parse_keep_filter_response(text: str) -> tuple[bool, dict[int, dict]]: + """Parse index-keyed JSON from keep filter response. + Expected shape: { "0": {"keep": bool, "reason": str}, ... } + Returns (success, parsed_dict) with int keys. + """ + try: + m = re.search(r"```(?:json)?\s*([\s\S]*?)```", text, flags=re.I) + s = (m.group(1) if m else text).strip() + data = json.loads(s) + except Exception: + return False, {} + + if not isinstance(data, dict): + return False, {} + + result: dict[int, dict] = {} + for k, v in data.items(): + try: + idx = int(k) + except Exception: + if isinstance(k, int): + idx = k + else: + continue + if not isinstance(v, dict): + continue + keep = v.get("keep") + reason = v.get("reason", "") + if isinstance(keep, bool): + result[idx] = { + "keep": keep, + "reason": reason, + } + return (len(result) > 0), result + + +def build_graph_db_config(user_id: str = "default") -> dict[str, Any]: + graph_db_backend_map = { + "neo4j-community": APIConfig.get_neo4j_community_config(user_id=user_id), + "neo4j": APIConfig.get_neo4j_config(user_id=user_id), + "nebular": APIConfig.get_nebular_config(user_id=user_id), + "polardb": APIConfig.get_polardb_config(user_id=user_id), + } + + graph_db_backend = os.getenv("NEO4J_BACKEND", "nebular").lower() + return GraphDBConfigFactory.model_validate( + { + "backend": graph_db_backend, + "config": graph_db_backend_map[graph_db_backend], + } + ) + + +def build_reranker_config() -> dict[str, Any]: + return RerankerConfigFactory.model_validate(APIConfig.get_reranker_config()) + + +def init_searcher(llm, embedder) -> Searcher: + """Initialize a Searcher instance for SimpleStructMemReader.""" + + # Build configs + graph_db_config = build_graph_db_config() + reranker_config = build_reranker_config() + + # Create instances + graph_db = GraphStoreFactory.from_config(graph_db_config) + reranker = RerankerFactory.from_config(reranker_config) + + # Create Searcher + searcher = Searcher( + dispatcher_llm=llm, + graph_store=graph_db, + embedder=embedder, + reranker=reranker, + manual_close_internet=os.getenv("ENABLE_INTERNET", "true").lower() == "false", + ) + + return searcher diff --git a/src/memos/mem_scheduler/schemas/general_schemas.py b/src/memos/mem_scheduler/schemas/general_schemas.py index f4ad9fe48..06910ba17 100644 --- a/src/memos/mem_scheduler/schemas/general_schemas.py +++ b/src/memos/mem_scheduler/schemas/general_schemas.py @@ -1,3 +1,5 @@ +import os + from pathlib import Path @@ -21,7 +23,7 @@ DEFAULT_MAX_INTERNAL_MESSAGE_QUEUE_SIZE = -1 DEFAULT_TOP_K = 5 DEFAULT_CONTEXT_WINDOW_SIZE = 5 -DEFAULT_USE_REDIS_QUEUE = True +DEFAULT_USE_REDIS_QUEUE = os.getenv("MEMSCHEDULER_USE_REDIS_QUEUE", "False").lower() == "true" DEFAULT_MULTI_TASK_RUNNING_TIMEOUT = 30 DEFAULT_SCHEDULER_RETRIEVER_BATCH_SIZE = 20 DEFAULT_SCHEDULER_RETRIEVER_RETRIES = 1 diff --git a/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py b/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py index 1c57f18f0..7923b3750 100644 --- a/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py +++ b/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py @@ -679,11 +679,6 @@ def _batch_claim_pending_messages( if not self._redis_conn or not claims_spec: return [] - # Ensure consumer groups exist to avoid NOGROUP errors during batch claim - for stream_key, _need_count, _label in claims_spec: - with contextlib.suppress(Exception): - self._ensure_consumer_group(stream_key=stream_key) - pipe = self._redis_conn.pipeline(transaction=False) for stream_key, need_count, label in claims_spec: pipe.xautoclaim( @@ -696,26 +691,42 @@ def _batch_claim_pending_messages( justid=False, ) - results = [] try: - results = pipe.execute() - except Exception: - # Fallback: attempt sequential xautoclaim for robustness - for stream_key, need_count, label in claims_spec: - try: - self._ensure_consumer_group(stream_key=stream_key) - res = self._redis_conn.xautoclaim( - name=stream_key, - groupname=self.consumer_group, - consumername=self.consumer_name, - min_idle_time=self.orchestrator.get_task_idle_min(task_label=label), - start_id="0-0", - count=need_count, - justid=False, - ) - results.append(res) - except Exception: - continue + # Execute with raise_on_error=False so we get exceptions in the results list + # instead of aborting the whole batch. + results = pipe.execute(raise_on_error=False) + except Exception as e: + logger.error(f"Pipeline execution critical failure: {e}") + results = [e] * len(claims_spec) + + # Handle individual failures (e.g. NOGROUP) by retrying just that stream + final_results = [] + for i, res in enumerate(results): + if isinstance(res, Exception): + err_msg = str(res).lower() + if "nogroup" in err_msg or "no such key" in err_msg: + stream_key, need_count, label = claims_spec[i] + try: + self._ensure_consumer_group(stream_key=stream_key) + retry_res = self._redis_conn.xautoclaim( + name=stream_key, + groupname=self.consumer_group, + consumername=self.consumer_name, + min_idle_time=self.orchestrator.get_task_idle_min(task_label=label), + start_id="0-0", + count=need_count, + justid=False, + ) + final_results.append(retry_res) + except Exception as retry_err: + logger.warning(f"Retry xautoclaim failed for {stream_key}: {retry_err}") + final_results.append(None) + else: + final_results.append(None) + else: + final_results.append(res) + + results = final_results claimed_pairs: list[tuple[str, list[tuple[str, dict]]]] = [] for (stream_key, _need_count, _label), claimed_result in zip( @@ -1189,9 +1200,7 @@ def _update_stream_cache_with_log( self._stream_keys_cache = active_stream_keys self._stream_keys_last_refresh = time.time() cache_count = len(self._stream_keys_cache) - logger.info( - f"[REDIS_QUEUE] Stream keys refresh: prefix='{stream_key_prefix}', " - f"total={len(candidate_keys)}, active={len(active_stream_keys)}, cached={cache_count}, " - f"active_threshold_sec={int(active_threshold_sec)}, deleted={deleted_count}, " - f"inactive_threshold_sec={int(DEFAULT_STREAM_INACTIVITY_DELETE_SECONDS)}" - ) + logger.info( + f"Refreshed stream keys cache: {cache_count} active keys, " + f"{deleted_count} deleted, {len(candidate_keys)} candidates examined." + ) diff --git a/src/memos/memories/textual/prefer_text_memory/extractor.py b/src/memos/memories/textual/prefer_text_memory/extractor.py index 144bfad7f..3404c6d4c 100644 --- a/src/memos/memories/textual/prefer_text_memory/extractor.py +++ b/src/memos/memories/textual/prefer_text_memory/extractor.py @@ -69,6 +69,8 @@ def extract_explicit_preference(self, qa_pair: MessageList | str) -> dict[str, A try: response = self.llm_provider.generate([{"role": "user", "content": prompt}]) + if not response: + return None response = response.strip().replace("```json", "").replace("```", "").strip() result = json.loads(response) for d in result: @@ -92,6 +94,8 @@ def extract_implicit_preference(self, qa_pair: MessageList | str) -> dict[str, A try: response = self.llm_provider.generate([{"role": "user", "content": prompt}]) + if not response: + return None response = response.strip().replace("```json", "").replace("```", "").strip() result = json.loads(response) for d in result: diff --git a/src/memos/templates/mem_reader_prompts.py b/src/memos/templates/mem_reader_prompts.py index fef3ee6c0..40971c77e 100644 --- a/src/memos/templates/mem_reader_prompts.py +++ b/src/memos/templates/mem_reader_prompts.py @@ -622,23 +622,56 @@ 专注于从图像中提取事实性、可观察的信息。除非与用户记忆明显相关，否则避免推测。""" -SIMPLE_STRUCT_HALLUCINATION_FILTER_PROMPT = """ +SIMPLE_STRUCT_REWRITE_MEMORY_PROMPT = """ +You are a strict, language-preserving memory validator and rewriter. + +Your task is to eliminate hallucinations and tighten memories by grounding them strictly in the user’s explicit messages. Memories must be factual, unambiguous, and free of any inferred or speculative content. + +Rules: +1. **Language Consistency**: Keep the exact original language of each memory—no translation or language switching. +2. **Strict Factual Grounding**: Include only what the user explicitly stated. Remove or flag anything not directly present in the messages—no assumptions, interpretations, predictions, or generalizations NOT supported by the text. However, **you MUST retain specific details, reasons, explanations, and feelings if the user explicitly expressed them.** Minor formatting corrections (e.g., adding missing spaces between names, fixing obvious typos) are ALLOWED. +4. **Hallucination Removal**: +- If a memory contains **any content not supported by the user's explicit statements**, it must be rewritten. +- **Do NOT remove** details, reasons, or explanations that the user explicitly provided, even if they are subjective or specific. +- Do **not** rephrase inferences as facts. Instead, either: +- Remove the unsupported part and retain only the grounded core. +5. **No Change if Fully Grounded**: If the memory is concise, unambiguous, and fully supported by the user’s messages, keep it unchanged. +6. **Timestamp Exception**: Memories may include timestamps (e.g., dates like "On December 19, 2026") derived from conversation metadata. If the date in the memory is likely the conversation time (even if not shown in the `messages` list), do NOT treat it as a hallucination or require a rewrite. + +Inputs: +messages: +{messages_inline} + +memories: +{memories_inline} + +Output Format: +- Return a JSON object with string keys ("0", "1", "2", ...) matching input memory indices. +- Each value must be: {{ "need_rewrite": boolean, "rewritten": string, "reason": string }} +- The "reason" must be brief and precise, e.g.: + - "contains unsupported inference ...." + - "fully grounded and concise" + +Important: Output **only** the JSON. No extra text, explanations, markdown, or fields. +""" + +SIMPLE_STRUCT_REWRITE_MEMORY_USER_ONLY_PROMPT = """ You are a strict, language-preserving memory validator and rewriter. Your task is to eliminate hallucinations and tighten memories by grounding them strictly in the user’s explicit messages. Memories must be factual, unambiguous, and free of any inferred or speculative content. +Note: The provided messages contain only user messages. The assistant's responses are intentionally omitted, not because the assistant didn't answer, but to focus strictly on validating memories against user input. + Rules: 1. **Language Consistency**: Keep the exact original language of each memory—no translation or language switching. -2. **Strict Factual Grounding**: Include only what the user explicitly stated. Remove or flag anything not directly present in the messages—no assumptions, interpretations, predictions, emotional labels, summaries, or generalizations. -3. **Ambiguity Elimination**: - - Replace vague pronouns (e.g., “he”, “it”, “they”) with clear, specific entities **only if** the messages identify them. - - Convert relative time expressions (e.g., “yesterday”) to absolute dates **only if** the messages provide enough temporal context. +2. **Strict Factual Grounding**: Include only what the user explicitly stated. Remove or flag anything not directly present in the messages—no assumptions, interpretations, predictions, or generalizations NOT supported by the text. However, **you MUST retain specific details, reasons, explanations, and feelings if the user explicitly expressed them.** Minor formatting corrections (e.g., adding missing spaces between names, fixing obvious typos) are ALLOWED. 4. **Hallucination Removal**: - - If a memory contains **any content not verbatim or directly implied by the user**, it must be rewritten. - - Do **not** rephrase inferences as facts. Instead, either: - - Remove the unsupported part and retain only the grounded core, or - - If the entire memory is ungrounded, mark it for rewrite and make the lack of user support explicit. +- If a memory contains **any content not supported by the user's explicit statements**, it must be rewritten. +- **Do NOT remove** details, reasons, or explanations that the user explicitly provided, even if they are subjective or specific. +- Do **not** rephrase inferences as facts. Instead, either: +- Remove the unsupported part and retain only the grounded core. 5. **No Change if Fully Grounded**: If the memory is concise, unambiguous, and fully supported by the user’s messages, keep it unchanged. +6. **Timestamp Exception**: Memories may include timestamps (e.g., dates like "On December 19, 2026") derived from conversation metadata. If the date in the memory is likely the conversation time (even if not shown in the `messages` list), do NOT treat it as a hallucination or require a rewrite. Inputs: messages: @@ -651,16 +684,115 @@ - Return a JSON object with string keys ("0", "1", "2", ...) matching input memory indices. - Each value must be: {{ "need_rewrite": boolean, "rewritten": string, "reason": string }} - The "reason" must be brief and precise, e.g.: - - "contains unsupported inference" - - "vague pronoun with no referent in messages" - - "relative time resolved to 2025-12-16" + - "contains unsupported inference ...." - "fully grounded and concise" Important: Output **only** the JSON. No extra text, explanations, markdown, or fields. """ +SIMPLE_STRUCT_REWRITE_MEMORY_PROMPT_BACKUP = """ +You are a strict, language-preserving memory validator and rewriter. + +Your task is to eliminate hallucinations and tighten memories by grounding them strictly in the user’s explicit messages. Memories must be factual, unambiguous, and free of any inferred or speculative content. + +Rules: +1. **Language Consistency**: Keep the exact original language of each memory—no translation or language switching. +2. **Strict Factual Grounding**: Include only what the user explicitly stated. Remove or flag anything not directly present in the messages—no assumptions, interpretations, predictions, or generalizations NOT supported by the text. However, **you MUST retain specific details, reasons, explanations, and feelings if the user explicitly expressed them.** Minor formatting corrections (e.g., adding missing spaces between names, fixing obvious typos) are ALLOWED. +4. **Hallucination Removal**: +- If a memory contains **any content not supported by the user's explicit statements**, it must be rewritten. +- **Do NOT remove** details, reasons, or explanations that the user explicitly provided, even if they are subjective or specific. +- Do **not** rephrase inferences as facts. Instead, either: +- Remove the unsupported part and retain only the grounded core. +5. **No Change if Fully Grounded**: If the memory is concise, unambiguous, and fully supported by the user’s messages, keep it unchanged. +6. **Timestamp Exception**: Memories may include timestamps (e.g., dates like "On December 19, 2026") derived from conversation metadata. If the date in the memory is likely the conversation time (even if not shown in the `messages` list), do NOT treat it as a hallucination or require a rewrite. + +Inputs: +messages: +{messages_inline} + +memories: +{memories_inline} + +Output Format: +- Return a JSON object with string keys ("0", "1", "2", ...) matching input memory indices. +- Each value must be: {{ "need_rewrite": boolean, "rewritten": string, "reason": string }} +- The "reason" must be brief and precise, e.g.: + - "contains unsupported inference ...." + - "fully grounded and concise" + +Important: Output **only** the JSON. No extra text, explanations, markdown, or fields. +""" + +SIMPLE_STRUCT_HALLUCINATION_FILTER_PROMPT = """ +You are a strict memory validator. +Your task is to identify and delete hallucinated memories that are not explicitly stated by the user in the provided messages. + +Rules: +1. **User-Only Origin**: Verify facts against USER messages ONLY. If the Assistant repeats a User fact, it is VALID. If the Assistant introduces a new detail (e.g., 'philanthropy') that the User did not explicitly confirm, it is INVALID. +2. **No Inference Allowed**: Do NOT keep memories based on implication, emotion, preference, or generalization. Only verbatim or direct restatements of user-provided facts are valid. However, minor formatting corrections (e.g., adding missing spaces between names, fixing obvious typos) are ALLOWED. +3. **Hallucination = Deletion**: If a memory contains any detail not directly expressed by the user, mark it for deletion. +4. **Timestamp Exception**: Memories may include timestamps (e.g., dates like "On December 19, 2026") derived from conversation metadata. If the date in the memory is likely the conversation time (even if not shown in the `messages` list), do NOT treat it as a hallucination or require a rewrite. + +Examples: +Messages: +- [user]: I love coding in Python. +- [assistant]: That's great! I assume you also contribute to open source projects? +Memory: User enjoys Python and contributes to open source. +Result: {{"keep": false, "reason": "User never stated they contribute to open source; this came from Assistant's assumption."}} + +Messages: +- [user]: I am tired. +- [assistant]: I hear you are tired. Rest is important. +Memory: User stated they are tired. +Result: {{"keep": true, "reason": "Direct restatement of user input, even if Assistant repeated it."}} + +Inputs: +messages: +{messages_inline} + +memories: +{memories_inline} + +Output Format: +- Return a JSON object with string keys ("0", "1", "2", ...) matching the input memory indices. +- Each value must be: {{ "keep": boolean, "reason": string }} +- "keep": true only if the memory is a direct reflection of the user's explicit words. +- "reason": brief, factual, and cites missing or unsupported content. + +Important: Output **only** the JSON. No extra text, explanations, markdown, or fields. +""" + + +SIMPLE_STRUCT_ADD_BEFORE_SEARCH_PROMPT = """ +You are a memory manager. +Your task is to decide if a new memory should be added to the long-term memory, given a list of existing related memories. + +Rules: +1. **Redundancy Check**: If the new memory is completely redundant, already known, or covered by the existing memories, discard it. +2. **New Information**: If the new memory provides new information, details, or updates compared to the existing memories, keep it. +3. **Contradiction**: If the new memory contradicts existing memories but seems valid/newer, keep it (updates). +4. **Context Check**: Use the provided conversation messages to verify if the new memory is grounded in the user's explicit statements. + +Inputs: +Messages: +{messages_inline} + +Candidate Memories (to be evaluated): +{candidates_inline} + +Output Format: +- Return a JSON object with string keys ("0", "1", "2", ...) matching the input candidate memory indices. +- Each value must be: {{ "keep": boolean, "reason": string }} +- "keep": true if the memory should be added. +- "reason": brief explanation. + +Important: Output **only** the JSON. No extra text. +""" # Prompt mapping for specialized tasks (e.g., hallucination filtering) PROMPT_MAPPING = { "hallucination_filter": SIMPLE_STRUCT_HALLUCINATION_FILTER_PROMPT, + "rewrite": SIMPLE_STRUCT_REWRITE_MEMORY_PROMPT, + "rewrite_user_only": SIMPLE_STRUCT_REWRITE_MEMORY_USER_ONLY_PROMPT, + "add_before_search": SIMPLE_STRUCT_ADD_BEFORE_SEARCH_PROMPT, } From 7f39e7ecc052d2e85e7bbeb2ca73f586db143875 Mon Sep 17 00:00:00 2001 From: chentang Date: Wed, 24 Dec 2025 20:04:56 +0800 Subject: [PATCH 09/47] address the incompatible issue of local scheduler --- src/memos/mem_scheduler/base_scheduler.py | 20 +++-- .../task_schedule_modules/local_queue.py | 75 +++++++++++++++++-- .../task_schedule_modules/task_queue.py | 23 +----- .../mem_scheduler/utils/status_tracker.py | 26 ++++++- tests/test_local_queue_full.py | 54 +++++++++++++ 5 files changed, 164 insertions(+), 34 deletions(-) create mode 100644 tests/test_local_queue_full.py diff --git a/src/memos/mem_scheduler/base_scheduler.py b/src/memos/mem_scheduler/base_scheduler.py index 1e0ecaadb..728203f5b 100644 --- a/src/memos/mem_scheduler/base_scheduler.py +++ b/src/memos/mem_scheduler/base_scheduler.py @@ -1009,14 +1009,24 @@ def _monitor_loop(self): q_sizes = self.memos_message_queue.qsize() for stream_key, queue_length in q_sizes.items(): - # Expected format: "memos:stream:{user_id}:{mem_cube_id}" or "{user_id}" + # Skip aggregate keys like 'total_size' + if stream_key == "total_size": + continue + + # Key format: ...:{user_id}:{mem_cube_id}:{task_label} + # We want to extract user_id, which is the 3rd component from the end. parts = stream_key.split(":") if len(parts) >= 3: - user_id = parts[2] - self.metrics.update_queue_length(queue_length, user_id) - elif not self.use_redis_queue: # local queue - user_id = stream_key + user_id = parts[-3] self.metrics.update_queue_length(queue_length, user_id) + else: + # Fallback for unexpected key formats (e.g. legacy or testing) + # Try to use the key itself if it looks like a user_id (no colons) + # or just log a warning? + # For now, let's assume if it's not total_size and short, it might be a direct user_id key + # (though that shouldn't happen with current queue implementations) + if ":" not in stream_key: + self.metrics.update_queue_length(queue_length, stream_key) except Exception as e: logger.error(f"Error in metrics monitor loop: {e}", exc_info=True) diff --git a/src/memos/mem_scheduler/task_schedule_modules/local_queue.py b/src/memos/mem_scheduler/task_schedule_modules/local_queue.py index 69cfc0af9..32d79cef3 100644 --- a/src/memos/mem_scheduler/task_schedule_modules/local_queue.py +++ b/src/memos/mem_scheduler/task_schedule_modules/local_queue.py @@ -62,7 +62,7 @@ def put( Exception: Any underlying error during queue.put() operation. """ stream_key = self.get_stream_key( - user_id=message.user_id, mem_cube_id=message.mem_cube_id, task_label=message.task_label + user_id=message.user_id, mem_cube_id=message.mem_cube_id, task_label=message.label ) message.stream_key = stream_key @@ -108,35 +108,95 @@ def get( ) return res - def get_nowait(self, batch_size: int | None = None) -> list[ScheduleMessageItem]: + def get_nowait( + self, stream_key: str, batch_size: int | None = None + ) -> list[ScheduleMessageItem]: """ - Non-blocking version of get(). Equivalent to get(block=False, batch_size=batch_size). + Non-blocking version of get(). Equivalent to get(stream_key, block=False, batch_size=batch_size). Returns immediately with available messages or an empty list if queue is empty. Args: + stream_key (str): The stream/queue identifier. batch_size (int | None): Number of messages to retrieve in a batch. If None, retrieves one message. Returns: List[ScheduleMessageItem]: Retrieved messages or empty list if queue is empty. """ - logger.debug(f"get_nowait() called with batch_size: {batch_size}") - return self.get(block=False, batch_size=batch_size) + logger.debug(f"get_nowait() called for {stream_key} with batch_size: {batch_size}") + return self.get(stream_key=stream_key, block=False, batch_size=batch_size) + + def get_messages(self, batch_size: int) -> list[ScheduleMessageItem]: + """ + Get messages from all streams in round-robin or sequential fashion. + Equivalent to SchedulerRedisQueue.get_messages. + """ + messages = [] + # Snapshot keys to avoid runtime modification issues + stream_keys = list(self.queue_streams.keys()) + + # Simple strategy: try to get up to batch_size messages across all streams + # We can just iterate and collect. + + # Calculate how many to get per stream to be fair? + # Or just greedy? Redis implementation uses a complex logic. + # For local, let's keep it simple: just iterate and take what's available (non-blocking) + + for stream_key in stream_keys: + if len(messages) >= batch_size: + break + + needed = batch_size - len(messages) + # Use get_nowait to avoid blocking + fetched = self.get_nowait(stream_key=stream_key, batch_size=needed) + messages.extend(fetched) + + return messages def qsize(self) -> dict: """ Return the current size of all internal queues as a dictionary. Each key is the stream name, and each value is the number of messages in that queue. + Also includes 'total_size'. Returns: Dict[str, int]: Mapping from stream name to current queue size. """ sizes = {stream: queue.qsize() for stream, queue in self.queue_streams.items()} + total_size = sum(sizes.values()) + sizes["total_size"] = total_size logger.debug(f"Current queue sizes: {sizes}") return sizes + def size(self) -> int: + """ + Get the current size of the queue (total message count). + Compatible with SchedulerRedisQueue. + """ + return self.unfinished_tasks + + def empty(self) -> bool: + """ + Check if the queue is empty. + Compatible with SchedulerRedisQueue. + """ + return self.size() == 0 + + def full(self) -> bool: + """ + Check if the queue is full. + Compatible with SchedulerRedisQueue. + + Returns True if all internal queues are full. + If there are no queues, returns False. + """ + if not self.queue_streams: + return False + + return all(queue.full() for queue in self.queue_streams.values()) + def clear(self) -> None: for queue in self.queue_streams.values(): queue.clear() @@ -151,6 +211,9 @@ def unfinished_tasks(self) -> int: Returns: int: Sum of all message counts in all internal queues. """ - total = sum(self.qsize().values()) + # qsize() now includes "total_size", so we need to be careful not to double count if we use qsize() values + # But qsize() implementation above sums values from queue_streams, then adds total_size. + # So sum(self.queue_streams.values().qsize()) is safer. + total = sum(queue.qsize() for queue in self.queue_streams.values()) logger.debug(f"Total unfinished tasks across all queues: {total}") return total diff --git a/src/memos/mem_scheduler/task_schedule_modules/task_queue.py b/src/memos/mem_scheduler/task_schedule_modules/task_queue.py index c20243242..b49db2b36 100644 --- a/src/memos/mem_scheduler/task_schedule_modules/task_queue.py +++ b/src/memos/mem_scheduler/task_schedule_modules/task_queue.py @@ -153,28 +153,7 @@ def submit_messages(self, messages: ScheduleMessageItem | list[ScheduleMessageIt ) def get_messages(self, batch_size: int) -> list[ScheduleMessageItem]: - if isinstance(self.memos_message_queue, SchedulerRedisQueue): - return self.memos_message_queue.get_messages(batch_size=batch_size) - stream_keys = self.get_stream_keys() - - if len(stream_keys) == 0: - return [] - - messages: list[ScheduleMessageItem] = [] - - for stream_key in stream_keys: - fetched = self.memos_message_queue.get( - stream_key=stream_key, - block=False, - batch_size=batch_size, - ) - - messages.extend(fetched) - if len(messages) > 0: - logger.debug( - f"Fetched {len(messages)} messages across users with per-user batch_size={batch_size}" - ) - return messages + return self.memos_message_queue.get_messages(batch_size=batch_size) def clear(self): self.memos_message_queue.clear() diff --git a/src/memos/mem_scheduler/utils/status_tracker.py b/src/memos/mem_scheduler/utils/status_tracker.py index d8c8d2cee..2a995b239 100644 --- a/src/memos/mem_scheduler/utils/status_tracker.py +++ b/src/memos/mem_scheduler/utils/status_tracker.py @@ -13,7 +13,7 @@ class TaskStatusTracker: @require_python_package(import_name="redis", install_command="pip install redis") - def __init__(self, redis_client: "redis.Redis"): + def __init__(self, redis_client: "redis.Redis | None"): self.redis = redis_client def _get_key(self, user_id: str) -> str: @@ -41,6 +41,9 @@ def task_submitted( mem_cube_id: Memory cube identifier business_task_id: Optional business-level task ID (one task_id can have multiple item_ids) """ + if not self.redis: + return + key = self._get_key(user_id) payload = { "status": "waiting", @@ -61,6 +64,9 @@ def task_submitted( self.redis.expire(key, timedelta(days=7)) def task_started(self, task_id: str, user_id: str): + if not self.redis: + return + key = self._get_key(user_id) existing_data_json = self.redis.hget(key, task_id) if not existing_data_json: @@ -77,6 +83,9 @@ def task_started(self, task_id: str, user_id: str): self.redis.expire(key, timedelta(days=7)) def task_completed(self, task_id: str, user_id: str): + if not self.redis: + return + key = self._get_key(user_id) existing_data_json = self.redis.hget(key, task_id) if not existing_data_json: @@ -91,6 +100,9 @@ def task_completed(self, task_id: str, user_id: str): self.redis.expire(key, timedelta(days=7)) def task_failed(self, task_id: str, user_id: str, error_message: str): + if not self.redis: + return + key = self._get_key(user_id) existing_data_json = self.redis.hget(key, task_id) if not existing_data_json: @@ -108,11 +120,17 @@ def task_failed(self, task_id: str, user_id: str, error_message: str): self.redis.expire(key, timedelta(days=7)) def get_task_status(self, task_id: str, user_id: str) -> dict | None: + if not self.redis: + return None + key = self._get_key(user_id) data = self.redis.hget(key, task_id) return json.loads(data) if data else None def get_all_tasks_for_user(self, user_id: str) -> dict[str, dict]: + if not self.redis: + return {} + key = self._get_key(user_id) all_tasks = self.redis.hgetall(key) return {tid: json.loads(t_data) for tid, t_data in all_tasks.items()} @@ -132,6 +150,9 @@ def get_task_status_by_business_id(self, business_task_id: str, user_id: str) -> - If any item is 'failed' → 'failed' Returns None if task_id not found. """ + if not self.redis: + return None + # Get all item_ids for this task_id task_items_key = self._get_task_items_key(user_id, business_task_id) item_ids = self.redis.smembers(task_items_key) @@ -180,6 +201,9 @@ def get_all_tasks_global(self) -> dict[str, dict[str, dict]]: Returns: dict: {user_id: {task_id: task_data, ...}, ...} """ + if not self.redis: + return {} + all_users_tasks = {} cursor: int | str = 0 while True: diff --git a/tests/test_local_queue_full.py b/tests/test_local_queue_full.py new file mode 100644 index 000000000..6c523046a --- /dev/null +++ b/tests/test_local_queue_full.py @@ -0,0 +1,54 @@ +import unittest + +from datetime import datetime, timezone + +from memos.mem_scheduler.schemas.message_schemas import ScheduleMessageItem +from memos.mem_scheduler.task_schedule_modules.local_queue import SchedulerLocalQueue + + +class TestLocalQueueFull(unittest.TestCase): + def test_full_behavior(self): + # Create a queue with very small maxsize for testing + lq = SchedulerLocalQueue(maxsize=1) + + # Initially empty + self.assertFalse(lq.full()) + + # Add message to stream 1 + msg1 = ScheduleMessageItem( + user_id="u1", + mem_cube_id="c1", + label="l1", + content="m1", + timestamp=datetime.now(timezone.utc), + ) + lq.put(msg1) + + # Now stream 1 is full (maxsize=1). + # Since it's the only stream, and it's full, lq.full() should be True. + self.assertTrue(lq.full()) + + # Add message to stream 2 + msg2 = ScheduleMessageItem( + user_id="u2", + mem_cube_id="c2", + label="l2", + content="m2", + timestamp=datetime.now(timezone.utc), + ) + lq.put(msg2) + + # Now both stream 1 and stream 2 are full. lq.full() should be True. + self.assertTrue(lq.full()) + + # Remove message from stream 1 + stream1_key = lq.get_stream_key("u1", "c1", "l1") + lq.get(stream1_key) + + # Now stream 1 is empty, stream 2 is full. + # "all streams are full" is False. + self.assertFalse(lq.full()) + + +if __name__ == "__main__": + unittest.main() From 3fe9cb09b4f1864db8225be7e64b0959e50c358f Mon Sep 17 00:00:00 2001 From: chentang Date: Wed, 24 Dec 2025 20:25:07 +0800 Subject: [PATCH 10/47] feat(scheduler): optimize redis queue consumer group management - Proactively ensure consumer groups exist in '_refresh_stream_keys' for newly discovered streams. - Remove redundant consumer group checks in '_read_new_messages_batch' to improve read performance. - Clean up 'seen_streams' cache when streams are deleted to ensure correct group recreation. - This change reduces unnecessary Redis calls during high-frequency polling. --- .../task_schedule_modules/redis_queue.py | 28 +++++++++++++++---- 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py b/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py index 7923b3750..2f4318003 100644 --- a/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py +++ b/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py @@ -5,7 +5,6 @@ the local memos_message_queue functionality in BaseScheduler. """ -import contextlib import os import re import threading @@ -201,6 +200,20 @@ def _refresh_stream_keys( recent_seconds=DEFAULT_STREAM_RECENT_ACTIVE_SECONDS, now_sec=now_sec, ) + + # Ensure consumer groups for newly discovered active streams + with self._stream_keys_lock: + # Identify keys we haven't seen yet + new_streams = [k for k in active_stream_keys if k not in self.seen_streams] + + # Create groups outside the lock to avoid blocking + for key in new_streams: + self._ensure_consumer_group(key) + + if new_streams: + with self._stream_keys_lock: + self.seen_streams.update(new_streams) + deleted_count = self._delete_streams(keys_to_delete) self._update_stream_cache_with_log( stream_key_prefix=stream_key_prefix, @@ -560,10 +573,7 @@ def _read_new_messages_batch( return {} # Pre-ensure consumer groups to avoid NOGROUP during batch reads - for stream_key in stream_keys: - with contextlib.suppress(Exception): - self._ensure_consumer_group(stream_key=stream_key) - + # (Optimization: rely on put() and _refresh_stream_keys() to ensure groups) pipe = self._redis_conn.pipeline(transaction=False) for stream_key in stream_keys: pipe.xreadgroup( @@ -1170,10 +1180,14 @@ def _delete_streams(self, keys_to_delete: list[str]) -> int: del_pipe.delete(key) del_pipe.execute() deleted_count = len(keys_to_delete) - # Clean up empty-tracking state for deleted keys + # Clean up empty-tracking state and seen_streams for deleted keys with self._empty_stream_seen_lock: for key in keys_to_delete: self._empty_stream_seen_times.pop(key, None) + + with self._stream_keys_lock: + for key in keys_to_delete: + self.seen_streams.discard(key) except Exception: for key in keys_to_delete: try: @@ -1181,6 +1195,8 @@ def _delete_streams(self, keys_to_delete: list[str]) -> int: deleted_count += 1 with self._empty_stream_seen_lock: self._empty_stream_seen_times.pop(key, None) + with self._stream_keys_lock: + self.seen_streams.discard(key) except Exception: pass return deleted_count From b35096fa61d3d3aeea3297354b0d10a78916a0f8 Mon Sep 17 00:00:00 2001 From: chentang Date: Wed, 24 Dec 2025 20:34:05 +0800 Subject: [PATCH 11/47] fix(tests): resolve AttributeError in SimpleStructMemReader tests - Import 'parse_json_result' from 'memos.mem_reader.utils' instead of accessing it as an instance attribute. - Fixes 'AttributeError: 'SimpleStructMemReader' object has no attribute 'parse_json_result'' in 'test_parse_json_result_success' and 'test_parse_json_result_failure'. - Remove incorrect mock assignment of 'parse_json_result' in 'test_process_chat_data'. --- tests/mem_reader/test_simple_structure.py | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/tests/mem_reader/test_simple_structure.py b/tests/mem_reader/test_simple_structure.py index f81356886..fd07fbf41 100644 --- a/tests/mem_reader/test_simple_structure.py +++ b/tests/mem_reader/test_simple_structure.py @@ -1,4 +1,3 @@ -import json import unittest from unittest.mock import MagicMock, patch @@ -8,6 +7,7 @@ from memos.embedders.factory import EmbedderFactory from memos.llms.factory import LLMFactory from memos.mem_reader.simple_struct import SimpleStructMemReader +from memos.mem_reader.utils import parse_json_result from memos.memories.textual.item import TextualMemoryItem @@ -57,7 +57,6 @@ def test_process_chat_data(self): '"summary": "Tom is currently focused on managing a new project with a tight schedule."}' ) self.reader.llm.generate.return_value = mock_response - self.reader.parse_json_result = lambda x: json.loads(x) result = self.reader._process_chat_data(scene_data_info, info) @@ -105,7 +104,7 @@ def test_get_scene_data_info_with_chat(self): def test_parse_json_result_success(self): """Test successful JSON parsing.""" raw_response = '{"summary": "Test summary", "tags": ["test"]}' - result = self.reader.parse_json_result(raw_response) + result = parse_json_result(raw_response) self.assertIsInstance(result, dict) self.assertIn("summary", result) @@ -113,7 +112,7 @@ def test_parse_json_result_success(self): def test_parse_json_result_failure(self): """Test failure in JSON parsing.""" raw_response = "Invalid JSON string" - result = self.reader.parse_json_result(raw_response) + result = parse_json_result(raw_response) self.assertEqual(result, {}) From 8943ba8b437d9b0f2bfe3ec4e93901c36b976314 Mon Sep 17 00:00:00 2001 From: chentang Date: Wed, 24 Dec 2025 20:49:32 +0800 Subject: [PATCH 12/47] fix(mem_reader): pass info dict to add_before_search for correct user_id usage - Update 'add_before_search' signature in 'SimpleStructMemReader' to accept 'info' dict. - Pass 'info' (containing 'user_id' and 'session_id') to 'self.searcher.search' instead of using empty strings. - Add 'test_add_before_search' to 'TestSimpleStructMemReader' to verify the fix and ensure 'searcher.search' receives the correct 'info'. - This ensures that memory searches are scoped to the correct user and session. --- src/memos/mem_reader/simple_struct.py | 3 +- tests/mem_reader/test_simple_structure.py | 92 +++++++++++++++++++++++ 2 files changed, 94 insertions(+), 1 deletion(-) diff --git a/src/memos/mem_reader/simple_struct.py b/src/memos/mem_reader/simple_struct.py index 866b6d988..18bad7ab7 100644 --- a/src/memos/mem_reader/simple_struct.py +++ b/src/memos/mem_reader/simple_struct.py @@ -561,6 +561,7 @@ def add_before_search( self, messages: list[dict], memory_list: list[TextualMemoryItem], + info: dict[str, Any], ) -> list[TextualMemoryItem]: # Build input objects with memory text and metadata (timestamps, sources, etc.) template = PROMPT_MAPPING["add_before_search"] @@ -579,7 +580,7 @@ def add_before_search( for idx, mem in enumerate(memory_list): try: related_memories = self.searcher.search( - query=mem.memory, top_k=3, mode="fast", info={"user_id": "", "session_id": ""} + query=mem.memory, top_k=3, mode="fast", info=info ) related_text = "None" if related_memories: diff --git a/tests/mem_reader/test_simple_structure.py b/tests/mem_reader/test_simple_structure.py index fd07fbf41..987ff25ae 100644 --- a/tests/mem_reader/test_simple_structure.py +++ b/tests/mem_reader/test_simple_structure.py @@ -116,6 +116,98 @@ def test_parse_json_result_failure(self): self.assertEqual(result, {}) + def test_add_before_search(self): + """Test add_before_search method.""" + import json + + from memos.memories.textual.item import TextualMemoryItem, TreeNodeTextualMemoryMetadata + + # Mock searcher + self.reader.searcher = MagicMock() + self.reader.searcher.search.return_value = [ + TextualMemoryItem( + memory="Related memory 1", + metadata=TreeNodeTextualMemoryMetadata( + user_id="user1", + session_id="session1", + memory_type="LongTermMemory", + status="activated", + tags=[], + key="key1", + embedding=[0.1], + usage=[], + sources=[], + background="", + confidence=0.99, + type="fact", + info={}, + ), + ) + ] + + # Mock LLM response for filter + # The method expects a JSON response with keep/drop decisions + mock_response = json.dumps( + { + "0": {"keep": True, "reason": "Relevant"}, + "1": {"keep": False, "reason": "Duplicate"}, + } + ) + self.reader.llm.generate.return_value = mock_response + + messages = [{"role": "user", "content": "test message"}] + memory_list = [ + TextualMemoryItem( + memory="Mem 1", + metadata=TreeNodeTextualMemoryMetadata( + user_id="user1", + session_id="session1", + memory_type="LongTermMemory", + status="activated", + tags=[], + key="key1", + embedding=[0.1], + usage=[], + sources=[], + background="", + confidence=0.99, + type="fact", + info={}, + ), + ), + TextualMemoryItem( + memory="Mem 2", + metadata=TreeNodeTextualMemoryMetadata( + user_id="user1", + session_id="session1", + memory_type="LongTermMemory", + status="activated", + tags=[], + key="key2", + embedding=[0.1], + usage=[], + sources=[], + background="", + confidence=0.99, + type="fact", + info={}, + ), + ), + ] + info = {"user_id": "user1", "session_id": "session1"} + + # Call the method + result = self.reader.add_before_search(messages, memory_list, info) + + # Assertions + # Check if searcher.search was called with correct info + self.reader.searcher.search.assert_called_with( + query="Mem 2", top_k=3, mode="fast", info=info + ) + # Check result + self.assertEqual(len(result), 1) + self.assertEqual(result[0].memory, "Mem 1") + if __name__ == "__main__": unittest.main() From 78a43275f5d9550cda6514ea51b05ee64417d979 Mon Sep 17 00:00:00 2001 From: chentang Date: Wed, 24 Dec 2025 21:25:35 +0800 Subject: [PATCH 13/47] refactor add_before_search from mem_reader to SingleCubeView --- src/memos/mem_reader/simple_struct.py | 3 +- src/memos/mem_reader/utils.py | 53 ------------- src/memos/multi_mem_cube/single_cube.py | 101 ++++++++++++++++++++++++ 3 files changed, 103 insertions(+), 54 deletions(-) diff --git a/src/memos/mem_reader/simple_struct.py b/src/memos/mem_reader/simple_struct.py index 18bad7ab7..fdd109079 100644 --- a/src/memos/mem_reader/simple_struct.py +++ b/src/memos/mem_reader/simple_struct.py @@ -561,6 +561,7 @@ def add_before_search( self, messages: list[dict], memory_list: list[TextualMemoryItem], + user_name: str, info: dict[str, Any], ) -> list[TextualMemoryItem]: # Build input objects with memory text and metadata (timestamps, sources, etc.) @@ -580,7 +581,7 @@ def add_before_search( for idx, mem in enumerate(memory_list): try: related_memories = self.searcher.search( - query=mem.memory, top_k=3, mode="fast", info=info + query=mem.memory, top_k=3, mode="fast", user_nam=user_name, info=info ) related_text = "None" if related_memories: diff --git a/src/memos/mem_reader/utils.py b/src/memos/mem_reader/utils.py index 843345ec4..4e5a78af2 100644 --- a/src/memos/mem_reader/utils.py +++ b/src/memos/mem_reader/utils.py @@ -1,16 +1,7 @@ import json -import os import re -from typing import Any - from memos import log -from memos.api.config import APIConfig -from memos.configs.graph_db import GraphDBConfigFactory -from memos.configs.reranker import RerankerConfigFactory -from memos.graph_dbs.factory import GraphStoreFactory -from memos.memories.textual.tree_text_memory.retrieve.searcher import Searcher -from memos.reranker.factory import RerankerFactory logger = log.get_logger(__name__) @@ -164,47 +155,3 @@ def parse_keep_filter_response(text: str) -> tuple[bool, dict[int, dict]]: "reason": reason, } return (len(result) > 0), result - - -def build_graph_db_config(user_id: str = "default") -> dict[str, Any]: - graph_db_backend_map = { - "neo4j-community": APIConfig.get_neo4j_community_config(user_id=user_id), - "neo4j": APIConfig.get_neo4j_config(user_id=user_id), - "nebular": APIConfig.get_nebular_config(user_id=user_id), - "polardb": APIConfig.get_polardb_config(user_id=user_id), - } - - graph_db_backend = os.getenv("NEO4J_BACKEND", "nebular").lower() - return GraphDBConfigFactory.model_validate( - { - "backend": graph_db_backend, - "config": graph_db_backend_map[graph_db_backend], - } - ) - - -def build_reranker_config() -> dict[str, Any]: - return RerankerConfigFactory.model_validate(APIConfig.get_reranker_config()) - - -def init_searcher(llm, embedder) -> Searcher: - """Initialize a Searcher instance for SimpleStructMemReader.""" - - # Build configs - graph_db_config = build_graph_db_config() - reranker_config = build_reranker_config() - - # Create instances - graph_db = GraphStoreFactory.from_config(graph_db_config) - reranker = RerankerFactory.from_config(reranker_config) - - # Create Searcher - searcher = Searcher( - dispatcher_llm=llm, - graph_store=graph_db, - embedder=embedder, - reranker=reranker, - manual_close_internet=os.getenv("ENABLE_INTERNET", "true").lower() == "false", - ) - - return searcher diff --git a/src/memos/multi_mem_cube/single_cube.py b/src/memos/multi_mem_cube/single_cube.py index 57f2cdba1..ab3d0ce03 100644 --- a/src/memos/multi_mem_cube/single_cube.py +++ b/src/memos/multi_mem_cube/single_cube.py @@ -15,6 +15,7 @@ ) from memos.context.context import ContextThreadPoolExecutor from memos.log import get_logger +from memos.mem_reader.utils import parse_keep_filter_response from memos.mem_scheduler.schemas.message_schemas import ScheduleMessageItem from memos.mem_scheduler.schemas.task_schemas import ( ADD_TASK_LABEL, @@ -23,6 +24,7 @@ PREF_ADD_TASK_LABEL, ) from memos.multi_mem_cube.views import MemCubeView +from memos.templates.mem_reader_prompts import PROMPT_MAPPING from memos.types.general_types import ( FINE_STRATEGY, FineStrategy, @@ -41,6 +43,7 @@ from memos.mem_cube.navie import NaiveMemCube from memos.mem_reader.simple_struct import SimpleStructMemReader from memos.mem_scheduler.optimized_scheduler import OptimizedScheduler + from memos.memories.textual.item import TextualMemoryItem @dataclass @@ -631,6 +634,104 @@ def _process_pref_mem( for memory_id, memory in zip(pref_ids_local, pref_memories_local, strict=False) ] + def add_before_search( + self, + messages: list[dict], + memory_list: list[TextualMemoryItem], + user_name: str, + info: dict[str, Any], + ) -> list[TextualMemoryItem]: + # Build input objects with memory text and metadata (timestamps, sources, etc.) + template = PROMPT_MAPPING["add_before_search"] + + if not self.searcher: + self.logger.warning("[add_before_search] Searcher is not initialized, skipping check.") + return memory_list + + # 1. Gather candidates and search for related memories + candidates_data = [] + for idx, mem in enumerate(memory_list): + try: + related_memories = self.searcher.search( + query=mem.memory, top_k=3, mode="fast", user_name=user_name, info=info + ) + related_text = "None" + if related_memories: + related_text = "\n".join([f"- {r.memory}" for r in related_memories]) + + candidates_data.append( + {"idx": idx, "new_memory": mem.memory, "related_memories": related_text} + ) + except Exception as e: + self.logger.error( + f"[add_before_search] Search error for memory '{mem.memory}': {e}" + ) + # If search fails, we can either skip this check or treat related as empty + candidates_data.append( + { + "idx": idx, + "new_memory": mem.memory, + "related_memories": "None (Search Failed)", + } + ) + + if not candidates_data: + return memory_list + + # 2. Build Prompt + messages_inline = "\n".join( + [ + f"- [{message.get('role', 'unknown')}]: {message.get('content', '')}" + for message in messages + ] + ) + + candidates_inline_dict = { + str(item["idx"]): { + "new_memory": item["new_memory"], + "related_memories": item["related_memories"], + } + for item in candidates_data + } + + candidates_inline = json.dumps(candidates_inline_dict, ensure_ascii=False, indent=2) + + prompt = template.format( + messages_inline=messages_inline, candidates_inline=candidates_inline + ) + + # 3. Call LLM + try: + raw = self.mem_reader.llm.generate([{"role": "user", "content": prompt}]) + success, parsed_result = parse_keep_filter_response(raw) + + if not success: + self.logger.warning( + "[add_before_search] Failed to parse LLM response, keeping all." + ) + return memory_list + + # 4. Filter + filtered_list = [] + for idx, mem in enumerate(memory_list): + res = parsed_result.get(idx) + if not res: + filtered_list.append(mem) + continue + + if res.get("keep", True): + filtered_list.append(mem) + else: + self.logger.info( + f"[add_before_search] Dropping memory: '{mem.memory}', reason: '{res.get('reason')}'" + ) + + return filtered_list + + except Exception as e: + self.logger.error(f"[add_before_search] LLM execution error: {e}") + return memory_list + def _process_text_mem( self, add_req: APIADDRequest, From a5fc4c09c94c4ded8d153cf34f5c09dc19cc979a Mon Sep 17 00:00:00 2001 From: chentang Date: Wed, 24 Dec 2025 21:36:07 +0800 Subject: [PATCH 14/47] address bugs --- src/memos/mem_reader/simple_struct.py | 99 ----------------------- tests/mem_reader/test_simple_structure.py | 92 --------------------- 2 files changed, 191 deletions(-) diff --git a/src/memos/mem_reader/simple_struct.py b/src/memos/mem_reader/simple_struct.py index fdd109079..70472958e 100644 --- a/src/memos/mem_reader/simple_struct.py +++ b/src/memos/mem_reader/simple_struct.py @@ -557,105 +557,6 @@ def filter_hallucination_in_memories( return memory_list - def add_before_search( - self, - messages: list[dict], - memory_list: list[TextualMemoryItem], - user_name: str, - info: dict[str, Any], - ) -> list[TextualMemoryItem]: - # Build input objects with memory text and metadata (timestamps, sources, etc.) - template = PROMPT_MAPPING["add_before_search"] - - if not self.searcher: - try: - from memos.mem_reader.utils import init_searcher - - self.searcher = init_searcher(self.llm, self.embedder) - except Exception as e: - logger.error(f"[add_before_search] Failed to init searcher: {e}") - return memory_list - - # 1. Gather candidates and search for related memories - candidates_data = [] - for idx, mem in enumerate(memory_list): - try: - related_memories = self.searcher.search( - query=mem.memory, top_k=3, mode="fast", user_nam=user_name, info=info - ) - related_text = "None" - if related_memories: - related_text = "\n".join([f"- {r.memory}" for r in related_memories]) - - candidates_data.append( - {"idx": idx, "new_memory": mem.memory, "related_memories": related_text} - ) - except Exception as e: - logger.error(f"[add_before_search] Search error for memory '{mem.memory}': {e}") - # If search fails, we can either skip this check or treat related as empty - candidates_data.append( - { - "idx": idx, - "new_memory": mem.memory, - "related_memories": "None (Search Failed)", - } - ) - - if not candidates_data: - return memory_list - - # 2. Build Prompt - messages_inline = "\n".join( - [ - f"- [{message.get('role', 'unknown')}]: {message.get('content', '')}" - for message in messages - ] - ) - - candidates_inline_dict = { - str(item["idx"]): { - "new_memory": item["new_memory"], - "related_memories": item["related_memories"], - } - for item in candidates_data - } - - candidates_inline = json.dumps(candidates_inline_dict, ensure_ascii=False, indent=2) - - prompt = template.format( - messages_inline=messages_inline, candidates_inline=candidates_inline - ) - - # 3. Call LLM - try: - raw = self.llm.generate([{"role": "user", "content": prompt}]) - success, parsed_result = parse_keep_filter_response(raw) - - if not success: - logger.warning("[add_before_search] Failed to parse LLM response, keeping all.") - return memory_list - - # 4. Filter - filtered_list = [] - for idx, mem in enumerate(memory_list): - res = parsed_result.get(idx) - if not res: - filtered_list.append(mem) - continue - - if res.get("keep", True): - filtered_list.append(mem) - else: - logger.info( - f"[add_before_search] Dropping memory: '{mem.memory}', reason: '{res.get('reason')}'" - ) - - return filtered_list - - except Exception as e: - logger.error(f"[add_before_search] LLM execution error: {e}") - return memory_list - def _read_memory( self, messages: list[MessagesType], type: str, info: dict[str, Any], mode: str = "fine" ) -> list[list[TextualMemoryItem]]: diff --git a/tests/mem_reader/test_simple_structure.py b/tests/mem_reader/test_simple_structure.py index 987ff25ae..fd07fbf41 100644 --- a/tests/mem_reader/test_simple_structure.py +++ b/tests/mem_reader/test_simple_structure.py @@ -116,98 +116,6 @@ def test_parse_json_result_failure(self): self.assertEqual(result, {}) - def test_add_before_search(self): - """Test add_before_search method.""" - import json - - from memos.memories.textual.item import TextualMemoryItem, TreeNodeTextualMemoryMetadata - - # Mock searcher - self.reader.searcher = MagicMock() - self.reader.searcher.search.return_value = [ - TextualMemoryItem( - memory="Related memory 1", - metadata=TreeNodeTextualMemoryMetadata( - user_id="user1", - session_id="session1", - memory_type="LongTermMemory", - status="activated", - tags=[], - key="key1", - embedding=[0.1], - usage=[], - sources=[], - background="", - confidence=0.99, - type="fact", - info={}, - ), - ) - ] - - # Mock LLM response for filter - # The method expects a JSON response with keep/drop decisions - mock_response = json.dumps( - { - "0": {"keep": True, "reason": "Relevant"}, - "1": {"keep": False, "reason": "Duplicate"}, - } - ) - self.reader.llm.generate.return_value = mock_response - - messages = [{"role": "user", "content": "test message"}] - memory_list = [ - TextualMemoryItem( - memory="Mem 1", - metadata=TreeNodeTextualMemoryMetadata( - user_id="user1", - session_id="session1", - memory_type="LongTermMemory", - status="activated", - tags=[], - key="key1", - embedding=[0.1], - usage=[], - sources=[], - background="", - confidence=0.99, - type="fact", - info={}, - ), - ), - TextualMemoryItem( - memory="Mem 2", - metadata=TreeNodeTextualMemoryMetadata( - user_id="user1", - session_id="session1", - memory_type="LongTermMemory", - status="activated", - tags=[], - key="key2", - embedding=[0.1], - usage=[], - sources=[], - background="", - confidence=0.99, - type="fact", - info={}, - ), - ), - ] - info = {"user_id": "user1", "session_id": "session1"} - - # Call the method - result = self.reader.add_before_search(messages, memory_list, info) - - # Assertions - # Check if searcher.search was called with correct info - self.reader.searcher.search.assert_called_with( - query="Mem 2", top_k=3, mode="fast", info=info - ) - # Check result - self.assertEqual(len(result), 1) - self.assertEqual(result[0].memory, "Mem 1") - if __name__ == "__main__": unittest.main() From 45224ddb6880fee5dbe6e5580b47357c2bac25d7 Mon Sep 17 00:00:00 2001 From: chentang Date: Thu, 25 Dec 2025 11:45:01 +0800 Subject: [PATCH 15/47] fix: fix the qsize bug of task queue, and accept change from hotfix/scheduler --- src/memos/mem_scheduler/base_scheduler.py | 3 + .../task_schedule_modules/dispatcher.py | 3 - .../task_schedule_modules/local_queue.py | 111 +++++++++++------- 3 files changed, 73 insertions(+), 44 deletions(-) diff --git a/src/memos/mem_scheduler/base_scheduler.py b/src/memos/mem_scheduler/base_scheduler.py index 728203f5b..a2621eefc 100644 --- a/src/memos/mem_scheduler/base_scheduler.py +++ b/src/memos/mem_scheduler/base_scheduler.py @@ -1008,6 +1008,9 @@ def _monitor_loop(self): try: q_sizes = self.memos_message_queue.qsize() + if not isinstance(q_sizes, dict): + continue + for stream_key, queue_length in q_sizes.items(): # Skip aggregate keys like 'total_size' if stream_key == "total_size": diff --git a/src/memos/mem_scheduler/task_schedule_modules/dispatcher.py b/src/memos/mem_scheduler/task_schedule_modules/dispatcher.py index 35df3db64..e2c1621d4 100644 --- a/src/memos/mem_scheduler/task_schedule_modules/dispatcher.py +++ b/src/memos/mem_scheduler/task_schedule_modules/dispatcher.py @@ -128,9 +128,6 @@ def status_tracker(self) -> TaskStatusTracker | None: if self._status_tracker is None: try: self._status_tracker = TaskStatusTracker(self.redis) - # Propagate to submodules when created lazily - if self.dispatcher: - self.dispatcher.status_tracker = self._status_tracker if self.memos_message_queue: self.memos_message_queue.set_status_tracker(self._status_tracker) except Exception as e: diff --git a/src/memos/mem_scheduler/task_schedule_modules/local_queue.py b/src/memos/mem_scheduler/task_schedule_modules/local_queue.py index eae70f8ef..791cedf41 100644 --- a/src/memos/mem_scheduler/task_schedule_modules/local_queue.py +++ b/src/memos/mem_scheduler/task_schedule_modules/local_queue.py @@ -4,9 +4,18 @@ the local memos_message_queue functionality in BaseScheduler. """ +from typing import TYPE_CHECKING + + +if TYPE_CHECKING: + from collections.abc import Callable + from memos.log import get_logger from memos.mem_scheduler.general_modules.misc import AutoDroppingQueue as Queue from memos.mem_scheduler.schemas.message_schemas import ScheduleMessageItem +from memos.mem_scheduler.schemas.task_schemas import DEFAULT_STREAM_KEY_PREFIX +from memos.mem_scheduler.task_schedule_modules.orchestrator import SchedulerOrchestrator +from memos.mem_scheduler.utils.status_tracker import TaskStatusTracker from memos.mem_scheduler.webservice_modules.redis_service import RedisSchedulerModule @@ -16,26 +25,38 @@ class SchedulerLocalQueue(RedisSchedulerModule): def __init__( self, - maxsize: int, + maxsize: int = 0, + stream_key_prefix: str = DEFAULT_STREAM_KEY_PREFIX, + orchestrator: SchedulerOrchestrator | None = None, + status_tracker: TaskStatusTracker | None = None, ): """ Initialize the SchedulerLocalQueue with a maximum queue size limit. + Arguments match SchedulerRedisQueue for compatibility. Args: - maxsize (int): Maximum number of messages allowed - in each individual queue. - If exceeded, subsequent puts will block - or raise an exception based on `block` parameter. + maxsize (int): Maximum number of messages allowed in each individual queue. + stream_key_prefix (str): Prefix for stream keys (simulated). + orchestrator: SchedulerOrchestrator instance (ignored). + status_tracker: TaskStatusTracker instance (ignored). """ super().__init__() - self.stream_key_prefix = "local_queue" + self.stream_key_prefix = stream_key_prefix or "local_queue" self.max_internal_message_queue_size = maxsize + # Dictionary to hold per-stream queues: key = stream_key, value = Queue[ScheduleMessageItem] self.queue_streams: dict[str, Queue[ScheduleMessageItem]] = {} + + self.orchestrator = orchestrator + self.status_tracker = status_tracker + + self._is_listening = False + self._message_handler: Callable[[ScheduleMessageItem], None] | None = None + logger.info( - f"SchedulerLocalQueue initialized with max_internal_message_queue_size={maxsize}" + f"SchedulerLocalQueue initialized with max_internal_message_queue_size={self.max_internal_message_queue_size}" ) def get_stream_key(self, user_id: str, mem_cube_id: str, task_label: str) -> str: @@ -86,7 +107,7 @@ def get( stream_key: str, block: bool = True, timeout: float | None = None, - batch_size: int | None = None, + batch_size: int | None = 1, ) -> list[ScheduleMessageItem]: if batch_size is not None and batch_size <= 0: logger.warning( @@ -99,18 +120,19 @@ def get( logger.error(f"Stream {stream_key} does not exist when trying to get messages.") return [] + # Ensure we always request a batch so we get a list back + effective_batch_size = batch_size if batch_size is not None else 1 + # Note: Assumes custom Queue implementation supports batch_size parameter res = self.queue_streams[stream_key].get( - block=block, timeout=timeout, batch_size=batch_size + block=block, timeout=timeout, batch_size=effective_batch_size ) logger.debug( f"Retrieved {len(res)} messages from queue '{stream_key}'. Current size: {self.queue_streams[stream_key].qsize()}" ) return res - def get_nowait( - self, stream_key: str, batch_size: int | None = None - ) -> list[ScheduleMessageItem]: + def get_nowait(self, stream_key: str, batch_size: int | None = 1) -> list[ScheduleMessageItem]: """ Non-blocking version of get(). Equivalent to get(stream_key, block=False, batch_size=batch_size). @@ -170,35 +192,13 @@ def qsize(self) -> dict: logger.debug(f"Current queue sizes: {sizes}") return sizes - def size(self) -> int: - """ - Get the current size of the queue (total message count). - Compatible with SchedulerRedisQueue. - """ - return self.unfinished_tasks - - def empty(self) -> bool: - """ - Check if the queue is empty. - Compatible with SchedulerRedisQueue. - """ - return self.size() == 0 - - def full(self) -> bool: - """ - Check if the queue is full. - Compatible with SchedulerRedisQueue. - """ - # Local queue limits are per-stream (max_internal_message_queue_size). - # It is considered full only if all streams are full. - if not self.queue_streams: - return False - - return all(queue.full() for queue in self.queue_streams.values()) - - def clear(self) -> None: - for queue in self.queue_streams.values(): - queue.clear() + def clear(self, stream_key: str | None = None) -> None: + if stream_key: + if stream_key in self.queue_streams: + self.queue_streams[stream_key].clear() + else: + for queue in self.queue_streams.values(): + queue.clear() @property def unfinished_tasks(self) -> int: @@ -216,3 +216,32 @@ def unfinished_tasks(self) -> int: total = sum(queue.qsize() for queue in self.queue_streams.values()) logger.debug(f"Total unfinished tasks across all queues: {total}") return total + + def get_stream_keys(self, stream_key_prefix: str | None = None) -> list[str]: + """ + Return list of active stream keys. + """ + prefix = stream_key_prefix or self.stream_key_prefix + return [k for k in self.queue_streams if k.startswith(prefix)] + + def size(self) -> int: + """ + Total size of all queues. + """ + return sum(q.qsize() for q in self.queue_streams.values()) + + def empty(self) -> bool: + """ + Check if all queues are empty. + """ + return self.size() == 0 + + def full(self) -> bool: + """ + Check if any queue is full (approximate). + """ + if self.max_internal_message_queue_size <= 0: + return False + return any( + q.qsize() >= self.max_internal_message_queue_size for q in self.queue_streams.values() + ) From f3c4f6ce4f7dc05686ddd94f98a1832a9bd2e08a Mon Sep 17 00:00:00 2001 From: chentang Date: Fri, 26 Dec 2025 17:33:13 +0800 Subject: [PATCH 16/47] fix: address some issues to run old scheduler example and kv cache example --- .../config/mem_scheduler/mem_cube_config.yaml | 21 ++ .../memos_config_w_scheduler.yaml | 12 +- .../mem_scheduler/quick_start_examples.py | 240 ++++++++++++++++++ src/memos/llms/hf.py | 13 +- src/memos/mem_os/core.py | 6 +- src/memos/mem_os/main.py | 2 +- src/memos/mem_os/utils/format_utils.py | 82 ++++-- src/memos/mem_reader/simple_struct.py | 2 +- src/memos/mem_scheduler/base_scheduler.py | 39 ++- .../general_modules/scheduler_logger.py | 30 ++- src/memos/mem_scheduler/general_scheduler.py | 65 +++-- .../mem_scheduler/monitors/general_monitor.py | 22 +- .../task_schedule_modules/redis_queue.py | 2 +- src/memos/memories/activation/kv.py | 32 ++- 14 files changed, 485 insertions(+), 83 deletions(-) create mode 100644 examples/data/config/mem_scheduler/mem_cube_config.yaml create mode 100644 examples/mem_scheduler/quick_start_examples.py diff --git a/examples/data/config/mem_scheduler/mem_cube_config.yaml b/examples/data/config/mem_scheduler/mem_cube_config.yaml new file mode 100644 index 000000000..398d8dbb3 --- /dev/null +++ b/examples/data/config/mem_scheduler/mem_cube_config.yaml @@ -0,0 +1,21 @@ +user_id: "user_test" +cube_id: "user_test/mem_cube_naive" +text_mem: + backend: "naive_text" + config: + extractor_llm: + backend: "huggingface_singleton" + config: + model_name_or_path: "Qwen/Qwen3-0.6B" + temperature: 0.1 + max_tokens: 1024 +act_mem: + backend: "kv_cache" + config: + memory_filename: "activation_memory.pickle" + extractor_llm: + backend: "huggingface_singleton" + config: + model_name_or_path: "Qwen/Qwen3-0.6B" + temperature: 0.8 + max_tokens: 1024 diff --git a/examples/data/config/mem_scheduler/memos_config_w_scheduler.yaml b/examples/data/config/mem_scheduler/memos_config_w_scheduler.yaml index bd9910300..a5e91dc4e 100644 --- a/examples/data/config/mem_scheduler/memos_config_w_scheduler.yaml +++ b/examples/data/config/mem_scheduler/memos_config_w_scheduler.yaml @@ -10,16 +10,12 @@ mem_reader: backend: "simple_struct" config: llm: - backend: "openai" + backend: "huggingface_singleton" config: - model_name_or_path: "gpt-4o-mini" - temperature: 0.8 - max_tokens: 4096 - top_p: 0.9 - top_k: 50 + model_name_or_path: "Qwen/Qwen3-1.7B" + temperature: 0.1 remove_think_prefix: true - api_key: "sk-xxxxxx" - api_base: "https://api.openai.com/v1" + max_tokens: 4096 embedder: backend: "ollama" config: diff --git a/examples/mem_scheduler/quick_start_examples.py b/examples/mem_scheduler/quick_start_examples.py new file mode 100644 index 000000000..c4142d2cd --- /dev/null +++ b/examples/mem_scheduler/quick_start_examples.py @@ -0,0 +1,240 @@ +import json +import shutil +import sys +import uuid + +from pathlib import Path + +from transformers import DynamicCache + +from memos.configs.mem_cube import GeneralMemCubeConfig +from memos.configs.mem_os import MOSConfig +from memos.configs.memory import MemoryConfigFactory +from memos.mem_cube.general import GeneralMemCube +from memos.mem_os.main import MOS +from memos.mem_scheduler.schemas.message_schemas import ScheduleMessageItem +from memos.mem_scheduler.schemas.task_schemas import ( + ANSWER_TASK_LABEL, + MEM_UPDATE_TASK_LABEL, + QUERY_TASK_LABEL, +) +from memos.mem_scheduler.utils.misc_utils import parse_yaml +from memos.memories.activation.item import KVCacheItem +from memos.memories.factory import MemoryFactory + + +FILE_PATH = Path(__file__).absolute() +BASE_DIR = FILE_PATH.parent.parent.parent +sys.path.insert(0, str(BASE_DIR)) # Enable execution from any working directory + + +def get_cache_info(cache): + if not cache: + return None + + num_layers = 0 + total_size_bytes = 0 + + if hasattr(cache, "layers"): + num_layers = len(cache.layers) + for layer in cache.layers: + if hasattr(layer, "key_cache") and layer.key_cache is not None: + total_size_bytes += layer.key_cache.nelement() * layer.key_cache.element_size() + if hasattr(layer, "value_cache") and layer.value_cache is not None: + total_size_bytes += layer.value_cache.nelement() * layer.value_cache.element_size() + + if hasattr(layer, "keys") and layer.keys is not None: + total_size_bytes += layer.keys.nelement() * layer.keys.element_size() + if hasattr(layer, "values") and layer.values is not None: + total_size_bytes += layer.values.nelement() * layer.values.element_size() + + elif hasattr(cache, "key_cache") and hasattr(cache, "value_cache"): + num_layers = len(cache.key_cache) + for k, v in zip(cache.key_cache, cache.value_cache, strict=False): + if k is not None: + total_size_bytes += k.nelement() * k.element_size() + if v is not None: + total_size_bytes += v.nelement() * v.element_size() + + return { + "num_layers": num_layers, + "size_bytes": total_size_bytes, + "size_mb": f"{total_size_bytes / (1024 * 1024):.2f} MB", + } + + +def serialize_item(obj): + if isinstance(obj, list): + return [serialize_item(x) for x in obj] + + if isinstance(obj, KVCacheItem): + return { + "id": obj.id, + "metadata": obj.metadata, + "records": obj.records.model_dump() + if hasattr(obj.records, "model_dump") + else obj.records, + "memory": get_cache_info(obj.memory), + } + + if isinstance(obj, DynamicCache): + return get_cache_info(obj) + + return str(obj) + + +def kv_cache_only(): + # 为 KVCacheMemory(HuggingFace 后端)创建配置 + config = MemoryConfigFactory( + backend="kv_cache", + config={ + "extractor_llm": { + "backend": "huggingface", + "config": { + "model_name_or_path": "Qwen/Qwen3-0.6B", + "max_tokens": 32, + "add_generation_prompt": True, + "remove_think_prefix": True, + }, + }, + }, + ) + + # 实例化 KVCacheMemory + kv_mem = MemoryFactory.from_config(config) + + # 提取一个 KVCacheItem(DynamicCache) + prompt = [ + {"role": "user", "content": "What is MemOS?"}, + {"role": "assistant", "content": "MemOS is a memory operating system for LLMs."}, + ] + print("===== Extract KVCacheItem =====") + cache_item = kv_mem.extract(prompt) + print(json.dumps(serialize_item(cache_item), indent=2, default=str)) + + # 将缓存添加到内存中 + kv_mem.add([cache_item]) + print("All caches:") + print(json.dumps(serialize_item(kv_mem.get_all()), indent=2, default=str)) + + # 通过 ID 获取 + retrieved = kv_mem.get(cache_item.id) + print("Retrieved:") + print(json.dumps(serialize_item(retrieved), indent=2, default=str)) + + # 合并缓存 + item2 = kv_mem.extract([{"role": "user", "content": "Tell me a joke."}]) + kv_mem.add([item2]) + merged = kv_mem.get_cache([cache_item.id, item2.id]) + print("Merged cache:") + print(json.dumps(serialize_item(merged), indent=2, default=str)) + + # 删除其中一个 + kv_mem.delete([cache_item.id]) + print("After delete:") + print(json.dumps(serialize_item(kv_mem.get_all()), indent=2, default=str)) + + # 导出和加载缓存 + kv_mem.dump("tmp/kv_mem") + print("Dumped to tmp/kv_mem") + kv_mem.delete_all() + kv_mem.load("tmp/kv_mem") + print("Loaded caches:") + print(json.dumps(serialize_item(kv_mem.get_all()), indent=2, default=str)) + + +def run_scheduler_example(): + # 使用 MemScheduler 加载主 MOS 配置 + config = parse_yaml( + f"{BASE_DIR}/examples/data/config/mem_scheduler/memos_config_w_scheduler.yaml" + ) + mos_config = MOSConfig(**config) + mos = MOS(mos_config) + + # 创建动态用户 ID + user_id = str(uuid.uuid4()) + mos.create_user(user_id=user_id) + + # 创建 MemCube 配置并导出 + config = GeneralMemCubeConfig.from_yaml_file( + f"{BASE_DIR}/examples/data/config/mem_scheduler/mem_cube_config.yaml" + ) + mem_cube_id = "mem_cube_5" + mem_cube_name_or_path = f"{BASE_DIR}/outputs/mem_scheduler/{user_id}/{mem_cube_id}" + + # 若存在旧目录则删除 + if Path(mem_cube_name_or_path).exists(): + shutil.rmtree(mem_cube_name_or_path) + print(f"{mem_cube_name_or_path} is not empty, and has been removed.") + + # 导出新的 MemCube + mem_cube = GeneralMemCube(config) + mem_cube.dump(mem_cube_name_or_path) + + # 为该用户注册 MemCube + mos.register_mem_cube( + mem_cube_name_or_path=mem_cube_name_or_path, mem_cube_id=mem_cube_id, user_id=user_id + ) + + # Define custom scheduler handlers + def custom_query_handler(messages: list[ScheduleMessageItem]): + for msg in messages: + print(f"\n[scheduler] 用户输入了query： {msg.content}") + # Trigger mem_update manually + new_msg = msg.model_copy(update={"label": MEM_UPDATE_TASK_LABEL}) + mos.mem_scheduler.submit_messages([new_msg]) + + def custom_answer_handler(messages: list[ScheduleMessageItem]): + for msg in messages: + print(f"\n[scheduler] LLM回复了answer：{msg.content}") + + def custom_mem_update_handler(messages: list[ScheduleMessageItem]): + for msg in messages: + mem_cube = mos.mem_cubes.get(msg.mem_cube_id) + if mem_cube and mem_cube.text_mem: + results = mem_cube.text_mem.search(msg.content, top_k=3) + for mem in results: + print( + f"\n[scheduler] transform {mem.metadata.type} to working memory: {mem.memory} " + ) + + # Register custom handlers + mos.mem_scheduler.dispatcher.register_handlers( + { + QUERY_TASK_LABEL: custom_query_handler, + ANSWER_TASK_LABEL: custom_answer_handler, + MEM_UPDATE_TASK_LABEL: custom_mem_update_handler, + } + ) + + # 添加消息 + messages = [ + {"role": "user", "content": "I like playing football."}, + {"role": "assistant", "content": "I like playing football too."}, + ] + mos.add(messages, user_id=user_id, mem_cube_id=mem_cube_id) + + # 聊天循环: 展示 TreeTextMemory 节点 + KVCache + while True: + user_input = input("👤 [You] ").strip() + print() + response = mos.chat(user_input, user_id=user_id) + retrieved_memories = mos.get_all(mem_cube_id=mem_cube_id, user_id=user_id) + + print(f"🤖 [Assistant] {response}") + + # 展示 TreeTextMemory 中的各类型节点 + text_memories = retrieved_memories["text_mem"][0]["memories"] + # Handle different memory structures (NaiveTextMemory returns list, TreeTextMemory returns dict with nodes) + if isinstance(text_memories, dict) and "nodes" in text_memories: + for node in text_memories["nodes"]: + mem_type = node["metadata"].get("memory_type", "Unknown") + print(f"[{mem_type}] {node['memory']}") + elif isinstance(text_memories, list): + for mem in text_memories: + # Naive memory items might not have memory_type metadata, or it might be different + print(f"[TextMemory] {mem.memory if hasattr(mem, 'memory') else mem}") + + +if __name__ == "__main__": + run_scheduler_example() diff --git a/src/memos/llms/hf.py b/src/memos/llms/hf.py index d46db7c9e..7dcf09940 100644 --- a/src/memos/llms/hf.py +++ b/src/memos/llms/hf.py @@ -1,6 +1,8 @@ from collections.abc import Generator from typing import Any +import torch + from transformers import ( AutoModelForCausalLM, AutoTokenizer, @@ -37,9 +39,14 @@ def __init__(self, config: HFLLMConfig): self.config.model_name_or_path = "Qwen/Qwen3-1.7B" # Initialize hf model - self.model = AutoModelForCausalLM.from_pretrained( - self.config.model_name_or_path, torch_dtype="auto", device_map="auto" - ) + if torch.backends.mps.is_available(): + self.model = AutoModelForCausalLM.from_pretrained( + self.config.model_name_or_path, torch_dtype="auto" + ).to("mps") + else: + self.model = AutoModelForCausalLM.from_pretrained( + self.config.model_name_or_path, torch_dtype="auto", device_map="auto" + ) self.tokenizer = AutoTokenizer.from_pretrained( self.config.model_name_or_path, use_fast=True ) diff --git a/src/memos/mem_os/core.py b/src/memos/mem_os/core.py index 1a88fa831..e7f01ec3e 100644 --- a/src/memos/mem_os/core.py +++ b/src/memos/mem_os/core.py @@ -311,7 +311,7 @@ def chat(self, query: str, user_id: str | None = None, base_prompt: str | None = past_key_values = None if self.config.enable_activation_memory: - if self.config.chat_model.backend != "huggingface": + if self.config.chat_model.backend not in ["huggingface", "huggingface_singleton"]: logger.error( "Activation memory only used for huggingface backend. Skipping activation memory." ) @@ -498,7 +498,9 @@ def register_mem_cube( existing_cube = self.user_manager.get_cube(mem_cube_id) # check the embedder is it consistent with MOSConfig - if self.config.mem_reader.config.embedder != ( + if hasattr( + self.mem_cubes[mem_cube_id].text_mem.config, "embedder" + ) and self.config.mem_reader.config.embedder != ( cube_embedder := self.mem_cubes[mem_cube_id].text_mem.config.embedder ): logger.warning( diff --git a/src/memos/mem_os/main.py b/src/memos/mem_os/main.py index 0114fc0da..0dc6ab209 100644 --- a/src/memos/mem_os/main.py +++ b/src/memos/mem_os/main.py @@ -310,7 +310,7 @@ def _generate_enhanced_response_with_context( # Handle activation memory if enabled (same as core method) past_key_values = None if self.config.enable_activation_memory: - if self.config.chat_model.backend != "huggingface": + if self.config.chat_model.backend not in ["huggingface", "huggingface_singleton"]: logger.error( "Activation memory only used for huggingface backend. Skipping activation memory." ) diff --git a/src/memos/mem_os/utils/format_utils.py b/src/memos/mem_os/utils/format_utils.py index 5fdb59058..f6e33bb31 100644 --- a/src/memos/mem_os/utils/format_utils.py +++ b/src/memos/mem_os/utils/format_utils.py @@ -1087,38 +1087,64 @@ def convert_activation_memory_to_serializable( serializable_items = [] for item in act_mem_items: + key_layers = 0 + val_layers = 0 + device = "unknown" + dtype = "unknown" + key_shapes = [] + value_shapes = [] + + if item.memory: + if hasattr(item.memory, "layers"): + key_layers = len(item.memory.layers) + val_layers = len(item.memory.layers) + if key_layers > 0: + l0 = item.memory.layers[0] + k0 = getattr(l0, "key_cache", getattr(l0, "keys", None)) + if k0 is not None: + device = str(k0.device) + dtype = str(k0.dtype) + + for i, layer in enumerate(item.memory.layers): + k = getattr(layer, "key_cache", getattr(layer, "keys", None)) + v = getattr(layer, "value_cache", getattr(layer, "values", None)) + if k is not None: + key_shapes.append({"layer": i, "shape": list(k.shape)}) + if v is not None: + value_shapes.append({"layer": i, "shape": list(v.shape)}) + + elif hasattr(item.memory, "key_cache"): + key_layers = len(item.memory.key_cache) + val_layers = len(item.memory.value_cache) + if key_layers > 0 and item.memory.key_cache[0] is not None: + device = str(item.memory.key_cache[0].device) + dtype = str(item.memory.key_cache[0].dtype) + + for i, key_tensor in enumerate(item.memory.key_cache): + if key_tensor is not None: + key_shapes.append({"layer": i, "shape": list(key_tensor.shape)}) + + for i, val_tensor in enumerate(item.memory.value_cache): + if val_tensor is not None: + value_shapes.append({"layer": i, "shape": list(val_tensor.shape)}) + # Extract basic information that can be serialized serializable_item = { "id": item.id, "metadata": item.metadata, "memory_info": { "type": "DynamicCache", - "key_cache_layers": len(item.memory.key_cache) if item.memory else 0, - "value_cache_layers": len(item.memory.value_cache) if item.memory else 0, - "device": str(item.memory.key_cache[0].device) - if item.memory and item.memory.key_cache - else "unknown", - "dtype": str(item.memory.key_cache[0].dtype) - if item.memory and item.memory.key_cache - else "unknown", + "key_cache_layers": key_layers, + "value_cache_layers": val_layers, + "device": device, + "dtype": dtype, }, } # Add tensor shape information if available - if item.memory and item.memory.key_cache: - key_shapes = [] - value_shapes = [] - - for i, key_tensor in enumerate(item.memory.key_cache): - if key_tensor is not None: - key_shapes.append({"layer": i, "shape": list(key_tensor.shape)}) - - if i < len(item.memory.value_cache) and item.memory.value_cache[i] is not None: - value_shapes.append( - {"layer": i, "shape": list(item.memory.value_cache[i].shape)} - ) - + if key_shapes: serializable_item["memory_info"]["key_shapes"] = key_shapes + if value_shapes: serializable_item["memory_info"]["value_shapes"] = value_shapes serializable_items.append(serializable_item) @@ -1144,7 +1170,19 @@ def convert_activation_memory_summary(act_mem_items: list[KVCacheItem]) -> dict[ total_parameters = 0 for item in act_mem_items: - if item.memory and item.memory.key_cache: + if not item.memory: + continue + + if hasattr(item.memory, "layers"): + total_layers += len(item.memory.layers) + for layer in item.memory.layers: + k = getattr(layer, "key_cache", getattr(layer, "keys", None)) + v = getattr(layer, "value_cache", getattr(layer, "values", None)) + if k is not None: + total_parameters += k.numel() + if v is not None: + total_parameters += v.numel() + elif hasattr(item.memory, "key_cache"): total_layers += len(item.memory.key_cache) # Calculate approximate parameter count diff --git a/src/memos/mem_reader/simple_struct.py b/src/memos/mem_reader/simple_struct.py index 70472958e..61a7d2b6d 100644 --- a/src/memos/mem_reader/simple_struct.py +++ b/src/memos/mem_reader/simple_struct.py @@ -618,7 +618,7 @@ def _read_memory( messages=combined_messages, memory_list=original_memory_group, user_only=os.getenv("SIMPLE_STRUCT_REWRITE_USER_ONLY", "true").lower() - == "true", + == "false", ) serialized_revised_memories = json.dumps( [one.memory for one in revised_memory_list], indent=2 diff --git a/src/memos/mem_scheduler/base_scheduler.py b/src/memos/mem_scheduler/base_scheduler.py index a2621eefc..3f5c90b67 100644 --- a/src/memos/mem_scheduler/base_scheduler.py +++ b/src/memos/mem_scheduler/base_scheduler.py @@ -74,6 +74,7 @@ from memos.mem_scheduler.webservice_modules.redis_service import RedisSchedulerModule from memos.memories.activation.kv import KVCacheMemory from memos.memories.activation.vllmkv import VLLMKVCacheItem, VLLMKVCacheMemory +from memos.memories.textual.naive import NaiveTextMemory from memos.memories.textual.tree import TextualMemoryItem, TreeTextMemory from memos.memories.textual.tree_text_memory.retrieve.searcher import Searcher from memos.templates.mem_scheduler_prompts import MEMORY_ASSEMBLY_TEMPLATE @@ -198,13 +199,16 @@ def init_mem_cube( logger.error("mem_cube is None, cannot initialize", stack_info=True) self.mem_cube = mem_cube self.text_mem: TreeTextMemory = self.mem_cube.text_mem - self.reranker: HTTPBGEReranker = self.text_mem.reranker + self.reranker: HTTPBGEReranker = getattr(self.text_mem, "reranker", None) if searcher is None: - self.searcher: Searcher = self.text_mem.get_searcher( - manual_close_internet=os.getenv("ENABLE_INTERNET", "true").lower() == "false", - moscube=False, - process_llm=self.process_llm, - ) + if hasattr(self.text_mem, "get_searcher"): + self.searcher: Searcher = self.text_mem.get_searcher( + manual_close_internet=os.getenv("ENABLE_INTERNET", "true").lower() == "false", + moscube=False, + process_llm=self.process_llm, + ) + else: + self.searcher = None else: self.searcher = searcher self.feedback_server = feedback_server @@ -540,6 +544,29 @@ def replace_working_memory( mem_cube=mem_cube, log_func_callback=self._submit_web_logs, ) + elif isinstance(text_mem_base, NaiveTextMemory): + # For NaiveTextMemory, we populate the monitors with the new candidates so activation memory can pick them up + logger.info( + f"NaiveTextMemory: Updating working memory monitors with {len(new_memory)} candidates." + ) + + # Use query keywords if available, otherwise just basic monitoring + query_db_manager = self.monitor.query_monitors[user_id][mem_cube_id] + query_db_manager.sync_with_orm() + query_keywords = query_db_manager.obj.get_keywords_collections() + + new_working_memory_monitors = self.transform_working_memories_to_monitors( + query_keywords=query_keywords, + memories=new_memory, + ) + + self.monitor.update_working_memory_monitors( + new_working_memory_monitors=new_working_memory_monitors, + user_id=user_id, + mem_cube_id=mem_cube_id, + mem_cube=mem_cube, + ) + memories_with_new_order = new_memory else: logger.error("memory_base is not supported") memories_with_new_order = new_memory diff --git a/src/memos/mem_scheduler/general_modules/scheduler_logger.py b/src/memos/mem_scheduler/general_modules/scheduler_logger.py index 57d78676f..fd83ec86f 100644 --- a/src/memos/mem_scheduler/general_modules/scheduler_logger.py +++ b/src/memos/mem_scheduler/general_modules/scheduler_logger.py @@ -55,7 +55,11 @@ def create_autofilled_log_item( "mem_cube is None — this should not happen in production!", stack_info=True ) text_mem_base: TreeTextMemory = mem_cube.text_mem - current_memory_sizes = text_mem_base.get_current_memory_size(user_name=mem_cube_id) + + current_memory_sizes = {} + if hasattr(text_mem_base, "get_current_memory_size"): + current_memory_sizes = text_mem_base.get_current_memory_size(user_name=mem_cube_id) + current_memory_sizes = { "long_term_memory_size": current_memory_sizes.get("LongTermMemory", 0), "user_memory_size": current_memory_sizes.get("UserMemory", 0), @@ -63,14 +67,32 @@ def create_autofilled_log_item( "transformed_act_memory_size": NOT_INITIALIZED, "parameter_memory_size": NOT_INITIALIZED, } + memory_capacities = { - "long_term_memory_capacity": text_mem_base.memory_manager.memory_size["LongTermMemory"], - "user_memory_capacity": text_mem_base.memory_manager.memory_size["UserMemory"], - "working_memory_capacity": text_mem_base.memory_manager.memory_size["WorkingMemory"], + "long_term_memory_capacity": 0, + "user_memory_capacity": 0, + "working_memory_capacity": 0, "transformed_act_memory_capacity": NOT_INITIALIZED, "parameter_memory_capacity": NOT_INITIALIZED, } + if hasattr(text_mem_base, "memory_manager") and hasattr( + text_mem_base.memory_manager, "memory_size" + ): + memory_capacities.update( + { + "long_term_memory_capacity": text_mem_base.memory_manager.memory_size.get( + "LongTermMemory", 0 + ), + "user_memory_capacity": text_mem_base.memory_manager.memory_size.get( + "UserMemory", 0 + ), + "working_memory_capacity": text_mem_base.memory_manager.memory_size.get( + "WorkingMemory", 0 + ), + } + ) + if hasattr(self, "monitor"): if ( user_id in self.monitor.activation_memory_monitors diff --git a/src/memos/mem_scheduler/general_scheduler.py b/src/memos/mem_scheduler/general_scheduler.py index 86066f346..9b19e9ecb 100644 --- a/src/memos/mem_scheduler/general_scheduler.py +++ b/src/memos/mem_scheduler/general_scheduler.py @@ -34,6 +34,7 @@ is_cloud_env, ) from memos.memories.textual.item import TextualMemoryItem +from memos.memories.textual.naive import NaiveTextMemory from memos.memories.textual.preference import PreferenceTextMemory from memos.memories.textual.tree import TreeTextMemory from memos.types import ( @@ -846,7 +847,9 @@ def _process_memories_with_reader( memory_item = text_mem.get(mem_id, user_name=user_name) memory_items.append(memory_item) except Exception as e: - logger.warning(f"Failed to get memory {mem_id}: {e}") + logger.warning( + f"[_process_memories_with_reader] Failed to get memory {mem_id}: {e}" + ) continue if not memory_items: @@ -1364,22 +1367,31 @@ def process_session_turn( text_mem_base = mem_cube.text_mem if not isinstance(text_mem_base, TreeTextMemory): - logger.error( - f"Not implemented! Expected TreeTextMemory but got {type(text_mem_base).__name__} " - f"for mem_cube_id={mem_cube_id}, user_id={user_id}. " - f"text_mem_base value: {text_mem_base}", - exc_info=True, + if isinstance(text_mem_base, NaiveTextMemory): + logger.debug( + f"NaiveTextMemory used for mem_cube_id={mem_cube_id}, processing session turn with simple search." + ) + # Treat NaiveTextMemory similar to TreeTextMemory but with simpler logic + # We will perform retrieval to get "working memory" candidates for activation memory + # But we won't have a distinct "current working memory" + cur_working_memory = [] + else: + logger.warning( + f"Not implemented! Expected TreeTextMemory but got {type(text_mem_base).__name__} " + f"for mem_cube_id={mem_cube_id}, user_id={user_id}. " + f"text_mem_base value: {text_mem_base}" + ) + return [], [] + else: + cur_working_memory: list[TextualMemoryItem] = text_mem_base.get_working_memory( + user_name=mem_cube_id ) - return + cur_working_memory = cur_working_memory[:top_k] logger.info( f"[process_session_turn] Processing {len(queries)} queries for user_id={user_id}, mem_cube_id={mem_cube_id}" ) - cur_working_memory: list[TextualMemoryItem] = text_mem_base.get_working_memory( - user_name=mem_cube_id - ) - cur_working_memory = cur_working_memory[:top_k] text_working_memory: list[str] = [w_m.memory for w_m in cur_working_memory] intent_result = self.monitor.detect_intent( q_list=queries, text_working_memory=text_working_memory @@ -1419,15 +1431,28 @@ def process_session_turn( ) search_args = {} - results: list[TextualMemoryItem] = self.retriever.search( - query=item, - user_id=user_id, - mem_cube_id=mem_cube_id, - mem_cube=mem_cube, - top_k=k_per_evidence, - method=self.search_method, - search_args=search_args, - ) + if isinstance(text_mem_base, NaiveTextMemory): + # NaiveTextMemory doesn't support complex search args usually, but let's see + # self.retriever.search calls mem_cube.text_mem.search + # NaiveTextMemory.search takes query and top_k + # SchedulerRetriever.search handles method dispatch + # For NaiveTextMemory, we might need to bypass retriever or extend it + # But let's try calling naive memory directly if retriever fails or doesn't support it + try: + results = text_mem_base.search(query=item, top_k=k_per_evidence) + except Exception as e: + logger.warning(f"NaiveTextMemory search failed: {e}") + results = [] + else: + results: list[TextualMemoryItem] = self.retriever.search( + query=item, + user_id=user_id, + mem_cube_id=mem_cube_id, + mem_cube=mem_cube, + top_k=k_per_evidence, + method=self.search_method, + search_args=search_args, + ) logger.info( f"[process_session_turn] Search results for missing evidence '{item}': " diff --git a/src/memos/mem_scheduler/monitors/general_monitor.py b/src/memos/mem_scheduler/monitors/general_monitor.py index b097b1e2d..d75d6ee75 100644 --- a/src/memos/mem_scheduler/monitors/general_monitor.py +++ b/src/memos/mem_scheduler/monitors/general_monitor.py @@ -200,15 +200,19 @@ def update_working_memory_monitors( mem_cube_id: str, mem_cube: GeneralMemCube, ): - text_mem_base: TreeTextMemory = mem_cube.text_mem - assert isinstance(text_mem_base, TreeTextMemory) - self.working_mem_monitor_capacity = min( - DEFAULT_WORKING_MEM_MONITOR_SIZE_LIMIT, - ( - int(text_mem_base.memory_manager.memory_size["WorkingMemory"]) - + self.partial_retention_number - ), - ) + text_mem_base = mem_cube.text_mem + + if isinstance(text_mem_base, TreeTextMemory): + self.working_mem_monitor_capacity = min( + DEFAULT_WORKING_MEM_MONITOR_SIZE_LIMIT, + ( + int(text_mem_base.memory_manager.memory_size["WorkingMemory"]) + + self.partial_retention_number + ), + ) + else: + # Fallback for NaiveTextMemory and others + self.working_mem_monitor_capacity = DEFAULT_WORKING_MEM_MONITOR_SIZE_LIMIT # register monitors self.register_memory_manager_if_not_exists( diff --git a/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py b/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py index 2f4318003..941c52164 100644 --- a/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py +++ b/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py @@ -787,7 +787,7 @@ def qsize(self) -> dict: Total number of messages across all matching streams. """ if not self._redis_conn: - return 0 + return {} total_size = 0 try: diff --git a/src/memos/memories/activation/kv.py b/src/memos/memories/activation/kv.py index 98d611dbf..1981b958f 100644 --- a/src/memos/memories/activation/kv.py +++ b/src/memos/memories/activation/kv.py @@ -2,9 +2,7 @@ import pickle from datetime import datetime -from importlib.metadata import version -from packaging.version import Version from transformers import DynamicCache from memos.configs.memory import KVCacheMemoryConfig @@ -211,10 +209,24 @@ def _concat_caches(self, caches: list[DynamicCache]) -> DynamicCache: return caches[0] merged = DynamicCache() - num_layers = len(caches[0].key_cache) - if Version(version("transformers")) >= Version("4.54.0"): - merged.append_new_layers(num_layers - 1) + # Check for new structure (layers) + if hasattr(caches[0], "layers"): + num_layers = len(caches[0].layers) + + # Ensure merged has layers attribute and populate it + if not hasattr(merged, "layers"): + merged.layers = [] + + if num_layers > 0: + # Get the class of the layer from the first cache + # We assume all caches use the same layer class + layer_cls = type(caches[0].layers[0]) + + # Populate merged.layers + while len(merged.layers) < num_layers: + merged.layers.append(layer_cls()) + for layer in range(num_layers): # gather all K and V for this layer keys = [c.layers[layer].keys for c in caches] @@ -223,7 +235,10 @@ def _concat_caches(self, caches: list[DynamicCache]) -> DynamicCache: merged.layers[layer].keys = torch.cat(keys, dim=-2) merged.layers[layer].values = torch.cat(vals, dim=-2) - else: + # Check for old structure (key_cache) + elif hasattr(caches[0], "key_cache"): + num_layers = len(caches[0].key_cache) + for layer in range(num_layers): # gather all K and V for this layer keys = [c.key_cache[layer] for c in caches] @@ -232,6 +247,11 @@ def _concat_caches(self, caches: list[DynamicCache]) -> DynamicCache: merged.key_cache.append(torch.cat(keys, dim=-2)) merged.value_cache.append(torch.cat(vals, dim=-2)) + else: + raise AttributeError( + "DynamicCache object has neither 'layers' nor 'key_cache' attributes" + ) + return merged From e9b60db165c98e6a8f70602e2c838bdf004adc78 Mon Sep 17 00:00:00 2001 From: chentang Date: Fri, 26 Dec 2025 17:57:04 +0800 Subject: [PATCH 17/47] fix: address the issue of Top-level import of unavailable module 'torch' --- src/memos/llms/hf.py | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/src/memos/llms/hf.py b/src/memos/llms/hf.py index 7dcf09940..b5fc4ba13 100644 --- a/src/memos/llms/hf.py +++ b/src/memos/llms/hf.py @@ -1,16 +1,8 @@ from collections.abc import Generator from typing import Any -import torch - from transformers import ( - AutoModelForCausalLM, - AutoTokenizer, DynamicCache, - LogitsProcessorList, - TemperatureLogitsWarper, - TopKLogitsWarper, - TopPLogitsWarper, ) from memos.configs.llm import HFLLMConfig @@ -32,6 +24,17 @@ def __init__(self, config: HFLLMConfig): """ Initialize the HFLLM model and tokenizer, and set up logits processors for sampling. """ + import torch + + from transformers import ( + AutoModelForCausalLM, + AutoTokenizer, + LogitsProcessorList, + TemperatureLogitsWarper, + TopKLogitsWarper, + TopPLogitsWarper, + ) + self.config = config # Default model if not specified @@ -362,6 +365,7 @@ def build_kv_cache(self, messages) -> DynamicCache: DynamicCache: The constructed KV cache object. """ import torch + import transformers # Accept multiple input types and convert to standard chat messages if isinstance(messages, str): @@ -398,7 +402,7 @@ def build_kv_cache(self, messages) -> DynamicCache: # Convert from legacy tuple format to DynamicCache if needed if isinstance(kv, tuple): - kv = DynamicCache.from_legacy_cache(kv) + kv = transformers.DynamicCache.from_legacy_cache(kv) # Handle compatibility between old and new transformers versions # In newer versions, DynamicCache uses 'layers' attribute From c6bdb22e14a13481b85cc96166d06d630dfc3c39 Mon Sep 17 00:00:00 2001 From: chentang Date: Fri, 26 Dec 2025 18:13:47 +0800 Subject: [PATCH 18/47] fix: resolve linting errors and make optional dependencies lazy loaded - Fix ambiguous characters and commented-out code in examples/mem_scheduler/quick_start_examples.py - Fix nested if statements in src/memos/mem_os/core.py - Move torch and transformers imports to method scope in src/memos/llms/hf.py to support optional dependencies - Update tests/llms/test_hf.py to patch transformers module directly --- tests/llms/test_hf.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tests/llms/test_hf.py b/tests/llms/test_hf.py index 595995ad1..375bf2247 100644 --- a/tests/llms/test_hf.py +++ b/tests/llms/test_hf.py @@ -11,8 +11,8 @@ from memos.llms.hf import HFLLM -@patch("memos.llms.hf.AutoModelForCausalLM", MagicMock()) -@patch("memos.llms.hf.AutoTokenizer", MagicMock()) +@patch("transformers.AutoModelForCausalLM", MagicMock()) +@patch("transformers.AutoTokenizer", MagicMock()) class TestHFLLM(unittest.TestCase): def setUp(self): self.mock_inputs = MagicMock() From ad3620aaceb240403c5831a0d729222b1708669f Mon Sep 17 00:00:00 2001 From: chentang Date: Mon, 29 Dec 2025 20:51:19 +0800 Subject: [PATCH 19/47] refactor: revise the rewrite prompt to make it better --- src/memos/templates/mem_reader_prompts.py | 35 ++++++++++++++++++++++- 1 file changed, 34 insertions(+), 1 deletion(-) diff --git a/src/memos/templates/mem_reader_prompts.py b/src/memos/templates/mem_reader_prompts.py index 40971c77e..26795a2b1 100644 --- a/src/memos/templates/mem_reader_prompts.py +++ b/src/memos/templates/mem_reader_prompts.py @@ -622,7 +622,7 @@ 专注于从图像中提取事实性、可观察的信息。除非与用户记忆明显相关，否则避免推测。""" -SIMPLE_STRUCT_REWRITE_MEMORY_PROMPT = """ +SIMPLE_STRUCT_REWRITE_MEMORY_PROMPT_BACKUP = """ You are a strict, language-preserving memory validator and rewriter. Your task is to eliminate hallucinations and tighten memories by grounding them strictly in the user’s explicit messages. Memories must be factual, unambiguous, and free of any inferred or speculative content. @@ -655,6 +655,39 @@ Important: Output **only** the JSON. No extra text, explanations, markdown, or fields. """ +SIMPLE_STRUCT_REWRITE_MEMORY_PROMPT = """ +You are a strict, language-preserving memory validator and rewriter. + +Your task is to eliminate hallucinations and tighten memories by grounding them strictly in the user’s explicit messages. Memories must be factual, unambiguous, and free of any inferred or speculative content. + +Rules: +1. **Language Consistency**: Keep the exact original language of each memory—no translation or language switching. +2. **Strict Factual Grounding**: Include only what is explicitly stated by the user in messages marked as [user]. Remove or flag anything not directly present in the user’s utterances—no assumptions, interpretations, predictions, generalizations, or content originating solely from [assistant]. +3. **Source Attribution Requirement**: + - Every memory must be clearly traceable to its source: + - If a fact appears **only in [assistant] messages** and **is not affirmed by [user]**, label it as “[assistant] memory”. + - If [assistant] states something and [user] explicitly contradicts or denies it, label it as “[assistant] memory, but [user] [brief quote or summary of denial]”. + - If a fact is stated by [user] —whether or not [assistant] also mentions it— it is attributed to “[user]” and may be retained without qualification. +4. **Timestamp Exception**: Memories may include timestamps (e.g., "On December 19, 2026") derived from conversation metadata. If such a date likely reflects the conversation time (even if not in the `messages` list), do NOT treat it as hallucinated—but still attribute it to “[user]” only if the user mentioned or confirmed the date. + +Inputs: +messages: +{messages_inline} + +memories: +{memories_inline} + +Output Format: +- Return a JSON object with string keys ("0", "1", "2", ...) matching input memory indices. +- Each value must be: {{ "need_rewrite": boolean, "rewritten": string, "reason": string }} +- The "reason" must be brief and precise, e.g.: + - "contains unsupported inference from [assistant]" + - "[assistant] memory, but [user] said 'I don't have a dog'" + - "fully grounded in [user]" + +Important: Output **only** the JSON. No extra text, explanations, markdown, or fields. +""" + SIMPLE_STRUCT_REWRITE_MEMORY_USER_ONLY_PROMPT = """ You are a strict, language-preserving memory validator and rewriter. From 24752864e4870961fdc43fc814713725acec7432 Mon Sep 17 00:00:00 2001 From: chentang Date: Tue, 30 Dec 2025 10:57:35 +0800 Subject: [PATCH 20/47] refactor: update examples --- .../mem_scheduler/quick_start_examples.py | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/examples/mem_scheduler/quick_start_examples.py b/examples/mem_scheduler/quick_start_examples.py index c4142d2cd..c71869e76 100644 --- a/examples/mem_scheduler/quick_start_examples.py +++ b/examples/mem_scheduler/quick_start_examples.py @@ -18,6 +18,7 @@ MEM_UPDATE_TASK_LABEL, QUERY_TASK_LABEL, ) +from memos.mem_scheduler.utils.db_utils import get_utc_now from memos.mem_scheduler.utils.misc_utils import parse_yaml from memos.memories.activation.item import KVCacheItem from memos.memories.factory import MemoryFactory @@ -186,17 +187,27 @@ def custom_query_handler(messages: list[ScheduleMessageItem]): def custom_answer_handler(messages: list[ScheduleMessageItem]): for msg in messages: + mem_cube = mos.mem_cubes.get(msg.mem_cube_id) + kv_mem = mem_cube.act_mem + for cache_item in kv_mem.get_all(): + print( + f"[scheduler] act memory: {get_cache_info(cache_item.memory)} ({cache_item.records})" + ) print(f"\n[scheduler] LLM回复了answer：{msg.content}") def custom_mem_update_handler(messages: list[ScheduleMessageItem]): for msg in messages: mem_cube = mos.mem_cubes.get(msg.mem_cube_id) + kv_mem = mem_cube.act_mem if mem_cube and mem_cube.text_mem: results = mem_cube.text_mem.search(msg.content, top_k=3) for mem in results: - print( - f"\n[scheduler] transform {mem.metadata.type} to working memory: {mem.memory} " - ) + print(f"\n[scheduler] searched memories: {mem.memory}") + + cache_item = kv_mem.extract(mem.memory) + cache_item.records.text_memories = [mem.memory] + cache_item.records.timestamp = get_utc_now() + kv_mem.add([cache_item]) # Register custom handlers mos.mem_scheduler.dispatcher.register_handlers( @@ -237,4 +248,6 @@ def custom_mem_update_handler(messages: list[ScheduleMessageItem]): if __name__ == "__main__": + kv_cache_only() + run_scheduler_example() From a196dcbc0eb1b9da7ed21231cc0f2a048ab0d86b Mon Sep 17 00:00:00 2001 From: chentang Date: Tue, 30 Dec 2025 15:12:40 +0800 Subject: [PATCH 21/47] refactor: update examples for scheduler --- .../mem_scheduler/quick_start_examples.py | 139 ++++++++++++------ 1 file changed, 98 insertions(+), 41 deletions(-) diff --git a/examples/mem_scheduler/quick_start_examples.py b/examples/mem_scheduler/quick_start_examples.py index c71869e76..fbfef4d76 100644 --- a/examples/mem_scheduler/quick_start_examples.py +++ b/examples/mem_scheduler/quick_start_examples.py @@ -145,106 +145,163 @@ def kv_cache_only(): def run_scheduler_example(): - # 使用 MemScheduler 加载主 MOS 配置 - config = parse_yaml( - f"{BASE_DIR}/examples/data/config/mem_scheduler/memos_config_w_scheduler.yaml" - ) + # 使用 MemScheduler 加载主 MOS(Memory-Oriented System)配置文件 + config = parse_yaml("./examples/data/config/mem_scheduler/memos_config_w_scheduler.yaml") + # 将解析出的配置字典传入 MOSConfig 构造器, 构建配置对象 mos_config = MOSConfig(**config) + # 使用配置对象初始化 MOS 系统实例 mos = MOS(mos_config) - # 创建动态用户 ID + # 生成一个唯一的动态用户 ID(使用 UUID4) user_id = str(uuid.uuid4()) + # 在 MOS 系统中为该用户创建账户 mos.create_user(user_id=user_id) - # 创建 MemCube 配置并导出 + # 从 YAML 文件加载 MemCube(记忆立方体)的通用配置 config = GeneralMemCubeConfig.from_yaml_file( - f"{BASE_DIR}/examples/data/config/mem_scheduler/mem_cube_config.yaml" + "./examples/data/config/mem_scheduler/mem_cube_config.yaml" ) + # 定义 MemCube 的唯一标识符 mem_cube_id = "mem_cube_5" - mem_cube_name_or_path = f"{BASE_DIR}/outputs/mem_scheduler/{user_id}/{mem_cube_id}" + # 定义 MemCube 的本地存储路径(路径中包含用户 ID 和 MemCube ID) + mem_cube_name_or_path = f"./outputs/mem_scheduler/{user_id}/{mem_cube_id}" - # 若存在旧目录则删除 + # 如果该路径已存在, 则先删除旧目录 if Path(mem_cube_name_or_path).exists(): shutil.rmtree(mem_cube_name_or_path) - print(f"{mem_cube_name_or_path} is not empty, and has been removed.") + print(f"{mem_cube_name_or_path} 目录非空，已被删除。") - # 导出新的 MemCube + # 根据加载的配置创建一个新的 MemCube 实例 mem_cube = GeneralMemCube(config) + # 将该 MemCube 实例序列化并保存到指定路径 mem_cube.dump(mem_cube_name_or_path) - # 为该用户注册 MemCube + # 在 MOS 系统中为当前用户注册这个 MemCube mos.register_mem_cube( mem_cube_name_or_path=mem_cube_name_or_path, mem_cube_id=mem_cube_id, user_id=user_id ) - # Define custom scheduler handlers + # 定义一个辅助函数, 用于获取缓存(如 KV Cache)的内存信息 + def get_cache_info(cache): + # 如果缓存为空, 则直接返回 None + if not cache: + return None + + num_layers = 0 # 记录缓存的层数 + total_size_bytes = 0 # 记录总字节数 + + # 情况一: 缓存结构包含 layers 属性(如 HuggingFace 的缓存格式) + if hasattr(cache, "layers"): + num_layers = len(cache.layers) + for layer in cache.layers: + # 统计 key_cache 的内存占用(如果存在) + if hasattr(layer, "key_cache") and layer.key_cache is not None: + total_size_bytes += layer.key_cache.nelement() * layer.key_cache.element_size() + # 统计 value_cache 的内存占用(如果存在) + if hasattr(layer, "value_cache") and layer.value_cache is not None: + total_size_bytes += ( + layer.value_cache.nelement() * layer.value_cache.element_size() + ) + + # 兼容其他可能的缓存命名方式(如 keys/values) + if hasattr(layer, "keys") and layer.keys is not None: + total_size_bytes += layer.keys.nelement() * layer.keys.element_size() + if hasattr(layer, "values") and layer.values is not None: + total_size_bytes += layer.values.nelement() * layer.values.element_size() + + # 情况二: 缓存结构直接包含 key_cache 和 value_cache 列表(如某些自定义格式) + elif hasattr(cache, "key_cache") and hasattr(cache, "value_cache"): + num_layers = len(cache.key_cache) + for k, v in zip(cache.key_cache, cache.value_cache, strict=False): + if k is not None: + total_size_bytes += k.nelement() * k.element_size() + if v is not None: + total_size_bytes += v.nelement() * v.element_size() + + # 返回结构化的缓存信息, 包括层数, 字节数和以 MB 为单位的可读格式 + return { + "num_layers": num_layers, + "size_bytes": total_size_bytes, + "size_mb": f"{total_size_bytes / (1024 * 1024):.2f} MB", + } + + # 定义自定义的查询(query)处理函数 def custom_query_handler(messages: list[ScheduleMessageItem]): for msg in messages: - print(f"\n[scheduler] 用户输入了query： {msg.content}") - # Trigger mem_update manually + # 打印用户输入内容 + print(f"\n[scheduler] 用户输入了查询：{msg.content}") + # 手动构造一个带有 MEM_UPDATE 标签的新消息, 用于触发记忆更新 new_msg = msg.model_copy(update={"label": MEM_UPDATE_TASK_LABEL}) + # 将该消息提交给调度器处理 mos.mem_scheduler.submit_messages([new_msg]) + # 定义自定义的回答(answer)处理函数 def custom_answer_handler(messages: list[ScheduleMessageItem]): for msg in messages: - mem_cube = mos.mem_cubes.get(msg.mem_cube_id) - kv_mem = mem_cube.act_mem - for cache_item in kv_mem.get_all(): - print( - f"[scheduler] act memory: {get_cache_info(cache_item.memory)} ({cache_item.records})" - ) - print(f"\n[scheduler] LLM回复了answer：{msg.content}") + # 打印 LLM 的回复内容 + print(f"\n[scheduler] LLM 回复了答案：{msg.content}") + # 定义自定义的记忆更新(mem_update)处理函数 def custom_mem_update_handler(messages: list[ScheduleMessageItem]): for msg in messages: mem_cube = mos.mem_cubes.get(msg.mem_cube_id) kv_mem = mem_cube.act_mem + # 如果该 MemCube 配置了文本记忆(TreeTextMemory / NaiveTextMemory) if mem_cube and mem_cube.text_mem: + # 在文本记忆中搜索与当前内容相关的记忆(返回 top_k=3 条) results = mem_cube.text_mem.search(msg.content, top_k=3) for mem in results: - print(f"\n[scheduler] searched memories: {mem.memory}") - + print(f"\n[scheduler] 检索到的记忆：{mem.memory}") + print("\n[scheduler] 转换为激活记忆......") + # 从文本记忆中提取对应的 KV 缓存项 cache_item = kv_mem.extract(mem.memory) + # 附加元信息 cache_item.records.text_memories = [mem.memory] cache_item.records.timestamp = get_utc_now() + # 将该缓存项添加到激活记忆中 kv_mem.add([cache_item]) + print("\n[scheduler] 完成！") - # Register custom handlers + # 将上述三个自定义处理器注册到调度器的分发器中, 分别对应不同任务标签 mos.mem_scheduler.dispatcher.register_handlers( { - QUERY_TASK_LABEL: custom_query_handler, - ANSWER_TASK_LABEL: custom_answer_handler, - MEM_UPDATE_TASK_LABEL: custom_mem_update_handler, + QUERY_TASK_LABEL: custom_query_handler, # 查询任务 + ANSWER_TASK_LABEL: custom_answer_handler, # 回答任务 + MEM_UPDATE_TASK_LABEL: custom_mem_update_handler, # 记忆更新任务 } ) - # 添加消息 + # 初始添加两条测试消息(用户和助手的对话)到系统中 messages = [ {"role": "user", "content": "I like playing football."}, {"role": "assistant", "content": "I like playing football too."}, ] mos.add(messages, user_id=user_id, mem_cube_id=mem_cube_id) - # 聊天循环: 展示 TreeTextMemory 节点 + KVCache + # 进入聊天循环: 展示 TreeTextMemory 的记忆节点结构 + KV Cache 的状态 while True: + # 获取用户输入并去除首尾空格 user_input = input("👤 [You] ").strip() print() + # 调用 MOS 系统进行聊天响应 response = mos.chat(user_input, user_id=user_id) + # 获取该用户当前 MemCube 中的所有记忆内容 retrieved_memories = mos.get_all(mem_cube_id=mem_cube_id, user_id=user_id) + # 打印助手的回复 print(f"🤖 [Assistant] {response}") - # 展示 TreeTextMemory 中的各类型节点 - text_memories = retrieved_memories["text_mem"][0]["memories"] - # Handle different memory structures (NaiveTextMemory returns list, TreeTextMemory returns dict with nodes) - if isinstance(text_memories, dict) and "nodes" in text_memories: - for node in text_memories["nodes"]: - mem_type = node["metadata"].get("memory_type", "Unknown") - print(f"[{mem_type}] {node['memory']}") - elif isinstance(text_memories, list): - for mem in text_memories: - # Naive memory items might not have memory_type metadata, or it might be different - print(f"[TextMemory] {mem.memory if hasattr(mem, 'memory') else mem}") + # 获取文本记忆部分 - TreeTextMemory + memories = retrieved_memories["text_mem"][0]["memories"] + for mem in memories: + print(f"[文本记忆] {mem.memory}") + + # 获取对应的 MemCube 和其激活记忆(KV Cache) + mem_cube = mos.mem_scheduler.mem_cube + kv_mem = mem_cube.act_mem + # 遍历所有激活记忆项, 打印其缓存信息和记录 + for cache_item in kv_mem.get_all(): + print(f"[激活记忆] {get_cache_info(cache_item.memory)} （记录：{cache_item.records}）") if __name__ == "__main__": From 6139af87d0101e73b33ee1160aef3af4c0a2c9d2 Mon Sep 17 00:00:00 2001 From: chentang Date: Tue, 6 Jan 2026 10:48:44 +0800 Subject: [PATCH 22/47] fix bugs: address the unsupported xautoclaim command when redis version larger than 6.2.0 via adding a new feature of manul auto claim with the combination of xpending + xclaim --- .../task_schedule_modules/redis_queue.py | 270 ++++++++++++++---- 1 file changed, 222 insertions(+), 48 deletions(-) diff --git a/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py b/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py index 941c52164..3d233cfa4 100644 --- a/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py +++ b/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py @@ -81,6 +81,7 @@ def __init__( # Consumer state self._is_listening = False self._message_handler: Callable[[ScheduleMessageItem], None] | None = None + self.supports_xautoclaim = False # Connection state self._is_connected = False @@ -105,6 +106,7 @@ def __init__( # Auto-initialize Redis connection if self.auto_initialize_redis(): self._is_connected = True + self._check_xautoclaim_support() self.seen_streams = set() @@ -143,6 +145,33 @@ def __init__( logger.debug(f"Initial stream keys refresh failed: {e}") self._start_stream_keys_refresh_thread() + def _check_xautoclaim_support(self): + """Check if the Redis server supports xautoclaim (v6.2+).""" + if not self._redis_conn: + return + + try: + info = self._redis_conn.info("server") + version_str = info.get("redis_version", "0.0.0") + # Simple version parsing + parts = [int(p) for p in version_str.split(".") if p.isdigit()] + while len(parts) < 3: + parts.append(0) + + major, minor, _ = parts[:3] + if major > 6 or (major == 6 and minor >= 2): + self.supports_xautoclaim = True + else: + self.supports_xautoclaim = False + + logger.info( + f"[REDIS_QUEUE] Redis version {version_str}. " + f"Supports xautoclaim: {self.supports_xautoclaim}" + ) + except Exception as e: + logger.warning(f"Failed to check Redis version: {e}") + self.supports_xautoclaim = False + def get_stream_key(self, user_id: str, mem_cube_id: str, task_label: str) -> str: stream_key = f"{self.stream_key_prefix}:{user_id}:{mem_cube_id}:{task_label}" return stream_key @@ -623,41 +652,58 @@ def _compute_pending_need( need_pending = max(0, batch_size - new_count) return need_pending if need_pending > 0 else 0 + def _manual_xautoclaim( + self, stream_key: str, min_idle_time: int, count: int + ) -> tuple[str, list[tuple[str, dict]], list[str]]: + """ + Simulate xautoclaim using xpending and xclaim for compatibility with older Redis versions. + """ + # 1. Get pending entries (fetch slightly more to increase chance of finding idle ones) + fetch_count = count * 3 + pending_entries = self._redis_conn.xpending_range( + stream_key, self.consumer_group, "-", "+", fetch_count + ) + + if not pending_entries: + return "0-0", [], [] + + claim_ids = [] + for entry in pending_entries: + # entry structure depends on redis-py version/decoding + # Assuming list of dicts: {'message_id': '...', 'time_since_delivered': ms, ...} + # or list of tuples + msg_id = entry.get("message_id") if isinstance(entry, dict) else entry[0] + idle_time = entry.get("time_since_delivered") if isinstance(entry, dict) else entry[2] + + if idle_time >= min_idle_time: + claim_ids.append(msg_id) + if len(claim_ids) >= count: + break + + if not claim_ids: + return "0-0", [], [] + + # 2. Claim messages + claimed_messages = self._redis_conn.xclaim( + stream_key, self.consumer_group, self.consumer_name, min_idle_time, claim_ids + ) + + return "0-0", claimed_messages, [] + def _claim_pending_messages( self, stream_key: str, need_pending_count: int, task_label: str ) -> list[tuple[str, list[tuple[str, dict]]]]: """Claim pending messages exceeding idle threshold, with group existence handling.""" - try: - claimed_result = self._redis_conn.xautoclaim( - name=stream_key, - groupname=self.consumer_group, - consumername=self.consumer_name, - min_idle_time=self.orchestrator.get_task_idle_min(task_label=task_label), - start_id="0-0", - count=need_pending_count, - justid=False, - ) - if len(claimed_result) == 2: - next_id, claimed = claimed_result - deleted_ids = [] - elif len(claimed_result) == 3: - next_id, claimed, deleted_ids = claimed_result - else: - raise ValueError(f"Unexpected xautoclaim response length: {len(claimed_result)}") + min_idle = self.orchestrator.get_task_idle_min(task_label=task_label) - return [(stream_key, claimed)] if claimed else [] - except Exception as read_err: - err_msg = str(read_err).lower() - if "nogroup" in err_msg or "no such key" in err_msg: - logger.warning( - f"Consumer group or stream missing for '{stream_key}/{self.consumer_group}'. Attempting to create and retry (xautoclaim)." - ) - self._ensure_consumer_group(stream_key=stream_key) + # Use native xautoclaim if supported (Redis 6.2+) + if self.supports_xautoclaim: + try: claimed_result = self._redis_conn.xautoclaim( name=stream_key, groupname=self.consumer_group, consumername=self.consumer_name, - min_idle_time=self.orchestrator.get_task_idle_min(task_label=task_label), + min_idle_time=min_idle, start_id="0-0", count=need_pending_count, justid=False, @@ -670,25 +716,64 @@ def _claim_pending_messages( else: raise ValueError( f"Unexpected xautoclaim response length: {len(claimed_result)}" - ) from read_err + ) return [(stream_key, claimed)] if claimed else [] - return [] - - def _batch_claim_pending_messages( - self, claims_spec: list[tuple[str, int, str]] - ) -> list[tuple[str, list[tuple[str, dict]]]]: - """Batch-claim pending messages across multiple streams. + except Exception as read_err: + err_msg = str(read_err).lower() + if "nogroup" in err_msg or "no such key" in err_msg: + logger.warning( + f"Consumer group or stream missing for '{stream_key}/{self.consumer_group}'. Attempting to create and retry (xautoclaim)." + ) + self._ensure_consumer_group(stream_key=stream_key) + claimed_result = self._redis_conn.xautoclaim( + name=stream_key, + groupname=self.consumer_group, + consumername=self.consumer_name, + min_idle_time=min_idle, + start_id="0-0", + count=need_pending_count, + justid=False, + ) + if len(claimed_result) == 2: + next_id, claimed = claimed_result + deleted_ids = [] + elif len(claimed_result) == 3: + next_id, claimed, deleted_ids = claimed_result + else: + raise ValueError( + f"Unexpected xautoclaim response length: {len(claimed_result)}" + ) from read_err - Args: - claims_spec: List of tuples (stream_key, need_pending_count, task_label) + return [(stream_key, claimed)] if claimed else [] + return [] - Returns: - A list of (stream_key, claimed_entries) pairs for all successful claims. - """ - if not self._redis_conn or not claims_spec: + # Fallback to manual xautoclaim for older Redis versions + try: + _next, claimed, _deleted = self._manual_xautoclaim( + stream_key, min_idle, need_pending_count + ) + return [(stream_key, claimed)] if claimed else [] + except Exception as read_err: + err_msg = str(read_err).lower() + if "nogroup" in err_msg or "no such key" in err_msg: + logger.warning( + f"Consumer group or stream missing for '{stream_key}/{self.consumer_group}'. Attempting to create and retry (manual xautoclaim)." + ) + self._ensure_consumer_group(stream_key=stream_key) + try: + _next, claimed, _deleted = self._manual_xautoclaim( + stream_key, min_idle, need_pending_count + ) + return [(stream_key, claimed)] if claimed else [] + except Exception: + return [] return [] + def _batch_claim_native( + self, claims_spec: list[tuple[str, int, str]] + ) -> list[tuple[str, list[tuple[str, dict]]]]: + """Batch-claim pending messages using Redis xautoclaim pipeline (Redis 6.2+).""" pipe = self._redis_conn.pipeline(transaction=False) for stream_key, need_count, label in claims_spec: pipe.xautoclaim( @@ -702,14 +787,11 @@ def _batch_claim_pending_messages( ) try: - # Execute with raise_on_error=False so we get exceptions in the results list - # instead of aborting the whole batch. results = pipe.execute(raise_on_error=False) except Exception as e: logger.error(f"Pipeline execution critical failure: {e}") results = [e] * len(claims_spec) - # Handle individual failures (e.g. NOGROUP) by retrying just that stream final_results = [] for i, res in enumerate(results): if isinstance(res, Exception): @@ -736,12 +818,8 @@ def _batch_claim_pending_messages( else: final_results.append(res) - results = final_results - - claimed_pairs: list[tuple[str, list[tuple[str, dict]]]] = [] - for (stream_key, _need_count, _label), claimed_result in zip( - claims_spec, results, strict=False - ): + claimed_pairs = [] + for (stream_key, _, _), claimed_result in zip(claims_spec, final_results, strict=False): try: if not claimed_result: continue @@ -760,6 +838,101 @@ def _batch_claim_pending_messages( return claimed_pairs + def _batch_claim_manual( + self, claims_spec: list[tuple[str, int, str]] + ) -> list[tuple[str, list[tuple[str, dict]]]]: + """Batch-claim pending messages using 2-phase pipeline (Redis < 6.2).""" + # Phase 1: Fetch pending messages for all streams + pending_pipe = self._redis_conn.pipeline(transaction=False) + for stream_key, need_count, _label in claims_spec: + fetch_count = need_count * 3 + pending_pipe.xpending_range(stream_key, self.consumer_group, "-", "+", fetch_count) + + try: + pending_results = pending_pipe.execute(raise_on_error=False) + except Exception as e: + logger.error(f"Pending fetch pipeline failed: {e}") + return [] + + # Phase 2: Filter and prepare claim pipeline + claim_pipe = self._redis_conn.pipeline(transaction=False) + streams_to_claim_indices = [] + claimed_pairs: list[tuple[str, list[tuple[str, dict]]]] = [] + + for i, (stream_key, need_count, label) in enumerate(claims_spec): + pending_res = pending_results[i] + min_idle = self.orchestrator.get_task_idle_min(task_label=label) + + if isinstance(pending_res, Exception): + err_msg = str(pending_res).lower() + if "nogroup" in err_msg or "no such key" in err_msg: + try: + self._ensure_consumer_group(stream_key) + _next, claimed, _ = self._manual_xautoclaim( + stream_key, min_idle, need_count + ) + if claimed: + claimed_pairs.append((stream_key, claimed)) + except Exception as retry_err: + logger.warning(f"Retry manual claim failed for {stream_key}: {retry_err}") + continue + + if not pending_res: + continue + + claim_ids = [] + for entry in pending_res: + msg_id = entry.get("message_id") if isinstance(entry, dict) else entry[0] + idle_time = ( + entry.get("time_since_delivered") if isinstance(entry, dict) else entry[2] + ) + if idle_time >= min_idle: + claim_ids.append(msg_id) + if len(claim_ids) >= need_count: + break + + if claim_ids: + claim_pipe.xclaim( + stream_key, + self.consumer_group, + self.consumer_name, + min_idle, + claim_ids, + ) + streams_to_claim_indices.append(i) + + if streams_to_claim_indices: + try: + claim_results = claim_pipe.execute(raise_on_error=False) + for idx_in_results, original_idx in enumerate(streams_to_claim_indices): + res = claim_results[idx_in_results] + stream_key = claims_spec[original_idx][0] + if isinstance(res, list) and res: + claimed_pairs.append((stream_key, res)) + except Exception as e: + logger.error(f"Claim pipeline failed: {e}") + + return claimed_pairs + + def _batch_claim_pending_messages( + self, claims_spec: list[tuple[str, int, str]] + ) -> list[tuple[str, list[tuple[str, dict]]]]: + """Batch-claim pending messages across multiple streams. + + Args: + claims_spec: List of tuples (stream_key, need_pending_count, task_label) + + Returns: + A list of (stream_key, claimed_entries) pairs for all successful claims. + """ + if not self._redis_conn or not claims_spec: + return [] + + if self.supports_xautoclaim: + return self._batch_claim_native(claims_spec) + + return self._batch_claim_manual(claims_spec) + def _convert_messages( self, messages: list[tuple[str, list[tuple[str, dict]]]] ) -> list[ScheduleMessageItem]: @@ -994,6 +1167,7 @@ def connect(self) -> None: # Test the connection self._redis_conn.ping() self._is_connected = True + self._check_xautoclaim_support() logger.debug("Redis connection established successfully") # Start stream keys refresher when connected self._start_stream_keys_refresh_thread() From 686d7c1182b176bd07760588fe0b5a6c25576a29 Mon Sep 17 00:00:00 2001 From: chentang Date: Wed, 7 Jan 2026 20:31:17 +0800 Subject: [PATCH 23/47] refactor: review settings --- .gitignore | 1 + docker/.env.example | 1 + 2 files changed, 2 insertions(+) diff --git a/.gitignore b/.gitignore index 8319a4d2f..ac31eb41a 100644 --- a/.gitignore +++ b/.gitignore @@ -204,6 +204,7 @@ cython_debug/ # and can be added to the global gitignore or merged into this file. For a more nuclear # option (not recommended) you can uncomment the following to ignore the entire idea folder. .idea/ +.trae # VSCode .vscode* diff --git a/docker/.env.example b/docker/.env.example index dc4252133..204e8d06f 100644 --- a/docker/.env.example +++ b/docker/.env.example @@ -92,6 +92,7 @@ MOS_SCHEDULER_ENABLE_ACTIVATION_MEMORY=false API_SCHEDULER_ON=true API_SEARCH_WINDOW_SIZE=5 API_SEARCH_HISTORY_TURNS=5 +MEMSCHEDULER_USE_REDIS_QUEUE=false ## Graph / vector stores NEO4J_BACKEND=neo4j-community # neo4j-community | neo4j | nebular | polardb From 3dd506801659fb8e5817eaa30690641e8e139f1b Mon Sep 17 00:00:00 2001 From: chentang Date: Wed, 7 Jan 2026 20:34:10 +0800 Subject: [PATCH 24/47] refactor: adjust examples to make it run better for code debugging --- examples/mem_scheduler/quick_start_examples.py | 8 +++++--- examples/mem_scheduler/scheduler_for_async_tasks.py | 2 +- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/examples/mem_scheduler/quick_start_examples.py b/examples/mem_scheduler/quick_start_examples.py index fbfef4d76..724663be6 100644 --- a/examples/mem_scheduler/quick_start_examples.py +++ b/examples/mem_scheduler/quick_start_examples.py @@ -146,7 +146,9 @@ def kv_cache_only(): def run_scheduler_example(): # 使用 MemScheduler 加载主 MOS(Memory-Oriented System)配置文件 - config = parse_yaml("./examples/data/config/mem_scheduler/memos_config_w_scheduler.yaml") + config = parse_yaml( + f"{BASE_DIR}/examples/data/config/mem_scheduler/memos_config_w_scheduler.yaml" + ) # 将解析出的配置字典传入 MOSConfig 构造器, 构建配置对象 mos_config = MOSConfig(**config) # 使用配置对象初始化 MOS 系统实例 @@ -159,12 +161,12 @@ def run_scheduler_example(): # 从 YAML 文件加载 MemCube(记忆立方体)的通用配置 config = GeneralMemCubeConfig.from_yaml_file( - "./examples/data/config/mem_scheduler/mem_cube_config.yaml" + f"{BASE_DIR}/examples/data/config/mem_scheduler/mem_cube_config.yaml" ) # 定义 MemCube 的唯一标识符 mem_cube_id = "mem_cube_5" # 定义 MemCube 的本地存储路径(路径中包含用户 ID 和 MemCube ID) - mem_cube_name_or_path = f"./outputs/mem_scheduler/{user_id}/{mem_cube_id}" + mem_cube_name_or_path = f"{BASE_DIR}/outputs/mem_scheduler/{user_id}/{mem_cube_id}" # 如果该路径已存在, 则先删除旧目录 if Path(mem_cube_name_or_path).exists(): diff --git a/examples/mem_scheduler/scheduler_for_async_tasks.py b/examples/mem_scheduler/scheduler_for_async_tasks.py index a767b57c4..7f544c3da 100644 --- a/examples/mem_scheduler/scheduler_for_async_tasks.py +++ b/examples/mem_scheduler/scheduler_for_async_tasks.py @@ -57,7 +57,7 @@ def submit_tasks(): TEST_HANDLER_LABEL = "test_handler" mem_scheduler.register_handlers({TEST_HANDLER_LABEL: my_test_handler}) -# 10s to restart +# 5s to restart mem_scheduler.orchestrator.tasks_min_idle_ms[TEST_HANDLER_LABEL] = 5_000 tmp_dir = Path("./tmp") From 211b4dc204e0b1ce0d5899a4cee4e101ac0a26ba Mon Sep 17 00:00:00 2001 From: chentang Date: Wed, 7 Jan 2026 20:42:56 +0800 Subject: [PATCH 25/47] refactor: review slow add apis to get a better performance on Halumen --- src/memos/mem_reader/simple_struct.py | 4 +- src/memos/templates/mem_reader_prompts.py | 79 ++++++++++++----------- 2 files changed, 43 insertions(+), 40 deletions(-) diff --git a/src/memos/mem_reader/simple_struct.py b/src/memos/mem_reader/simple_struct.py index 61a7d2b6d..fa72bd063 100644 --- a/src/memos/mem_reader/simple_struct.py +++ b/src/memos/mem_reader/simple_struct.py @@ -614,11 +614,9 @@ def _read_memory( serialized_origin_memories = json.dumps( [one.memory for one in original_memory_group], indent=2 ) - revised_memory_list = self.rewrite_memories( + revised_memory_list = self.filter_hallucination_in_memories( messages=combined_messages, memory_list=original_memory_group, - user_only=os.getenv("SIMPLE_STRUCT_REWRITE_USER_ONLY", "true").lower() - == "false", ) serialized_revised_memories = json.dumps( [one.memory for one in revised_memory_list], indent=2 diff --git a/src/memos/templates/mem_reader_prompts.py b/src/memos/templates/mem_reader_prompts.py index 26795a2b1..0fa39b588 100644 --- a/src/memos/templates/mem_reader_prompts.py +++ b/src/memos/templates/mem_reader_prompts.py @@ -757,43 +757,48 @@ """ SIMPLE_STRUCT_HALLUCINATION_FILTER_PROMPT = """ -You are a strict memory validator. -Your task is to identify and delete hallucinated memories that are not explicitly stated by the user in the provided messages. - -Rules: -1. **User-Only Origin**: Verify facts against USER messages ONLY. If the Assistant repeats a User fact, it is VALID. If the Assistant introduces a new detail (e.g., 'philanthropy') that the User did not explicitly confirm, it is INVALID. -2. **No Inference Allowed**: Do NOT keep memories based on implication, emotion, preference, or generalization. Only verbatim or direct restatements of user-provided facts are valid. However, minor formatting corrections (e.g., adding missing spaces between names, fixing obvious typos) are ALLOWED. -3. **Hallucination = Deletion**: If a memory contains any detail not directly expressed by the user, mark it for deletion. -4. **Timestamp Exception**: Memories may include timestamps (e.g., dates like "On December 19, 2026") derived from conversation metadata. If the date in the memory is likely the conversation time (even if not shown in the `messages` list), do NOT treat it as a hallucination or require a rewrite. - -Examples: -Messages: -- [user]: I love coding in Python. -- [assistant]: That's great! I assume you also contribute to open source projects? -Memory: User enjoys Python and contributes to open source. -Result: {{"keep": false, "reason": "User never stated they contribute to open source; this came from Assistant's assumption."}} - -Messages: -- [user]: I am tired. -- [assistant]: I hear you are tired. Rest is important. -Memory: User stated they are tired. -Result: {{"keep": true, "reason": "Direct restatement of user input, even if Assistant repeated it."}} - -Inputs: -messages: -{messages_inline} - -memories: -{memories_inline} - -Output Format: -- Return a JSON object with string keys ("0", "1", "2", ...) matching the input memory indices. -- Each value must be: {{ "keep": boolean, "reason": string }} -- "keep": true only if the memory is a direct reflection of the user's explicit words. -- "reason": brief, factual, and cites missing or unsupported content. - -Important: Output **only** the JSON. No extra text, explanations, markdown, or fields. -""" + You are a strict memory validator. + Your task is to identify and delete hallucinated memories that are not explicitly stated by the user in the provided messages. + + Rules: + 1. **Explicit Denial & Inconsistency**: If a memory claims something that the user explicitly denied or is clearly inconsistent with the user's statements, mark it for deletion. + 2. **Timestamp Exception**: Memories may include timestamps (e.g., dates like "On December 19, 2026") derived from conversation metadata. If the date in the memory is likely the conversation time (even if not shown in the `messages` list), do NOT treat it as a hallucination or require a rewrite. + + Example: + Messages: + [user]: I'm planning a trip to Japan next month for about a week. + [assistant]: That sounds great! Are you planning to visit Tokyo Disneyland? + [user]: No, I won't be going to Tokyo this time. I plan to stay in Kyoto and Osaka to avoid crowds. + + Memories: + {{ + "0": "User plans to travel to Japan for a week next month.", + "1": "User intends to visit Tokyo Disneyland.", + "2": "User plans to stay in Kyoto and Osaka." + }} + + Output: + {{ + "0": {{ "keep": true, "reason": "Explicitly stated by user." }}, + "1": {{ "keep": false, "reason": "User explicitly denied visiting Tokyo." }}, + "2": {{ "keep": true, "reason": "Explicitly stated by user." }} + }} + + Inputs: + Messages: + {messages_inline} + + Memories: + {memories_inline} + + Output Format: + - Return a JSON object with string keys ("0", "1", "2", ...) matching the input memory indices. + - Each value must be: {{ "keep": boolean, "reason": string }} + - "keep": true only if the memory is a direct reflection of the user's explicit words. + - "reason": brief, factual, and cites missing or unsupported content. + + Important: Output **only** the JSON. No extra text, explanations, markdown, or fields. + """ SIMPLE_STRUCT_ADD_BEFORE_SEARCH_PROMPT = """ From f0a9c1388d2b9168e31d09160b9b59e75f24631f Mon Sep 17 00:00:00 2001 From: chentang Date: Wed, 7 Jan 2026 21:13:01 +0800 Subject: [PATCH 26/47] fix bugs: address the issue when set user_redis_queue to false, the status_tracker is still using --- src/memos/mem_scheduler/base_scheduler.py | 20 ++++++------- .../task_schedule_modules/dispatcher.py | 30 ------------------- 2 files changed, 9 insertions(+), 41 deletions(-) diff --git a/src/memos/mem_scheduler/base_scheduler.py b/src/memos/mem_scheduler/base_scheduler.py index 3f5c90b67..130ad98da 100644 --- a/src/memos/mem_scheduler/base_scheduler.py +++ b/src/memos/mem_scheduler/base_scheduler.py @@ -225,7 +225,7 @@ def initialize_modules( process_llm = chat_llm try: - if redis_client: + if redis_client and self.use_redis_queue: self.status_tracker = TaskStatusTracker(redis_client) if self.dispatcher: self.dispatcher.status_tracker = self.status_tracker @@ -305,16 +305,14 @@ def status_tracker(self) -> TaskStatusTracker | None: available via RedisSchedulerModule. This mirrors the lazy pattern used by `mem_cube` so downstream modules can safely access the tracker. """ - if self._status_tracker is None: - try: - self._status_tracker = TaskStatusTracker(self.redis) - # Propagate to submodules when created lazily - if self.dispatcher: - self.dispatcher.status_tracker = self._status_tracker - if self.memos_message_queue: - self.memos_message_queue.set_status_tracker(self._status_tracker) - except Exception as e: - logger.warning(f"Failed to lazily initialize status_tracker: {e}", exc_info=True) + if self._status_tracker is None and self.use_redis_queue: + self._status_tracker = TaskStatusTracker(self.redis) + # Propagate to submodules when created lazily + if self.dispatcher: + self.dispatcher.status_tracker = self._status_tracker + if self.memos_message_queue: + self.memos_message_queue.set_status_tracker(self._status_tracker) + return self._status_tracker @status_tracker.setter diff --git a/src/memos/mem_scheduler/task_schedule_modules/dispatcher.py b/src/memos/mem_scheduler/task_schedule_modules/dispatcher.py index e2c1621d4..2099da5a1 100644 --- a/src/memos/mem_scheduler/task_schedule_modules/dispatcher.py +++ b/src/memos/mem_scheduler/task_schedule_modules/dispatcher.py @@ -108,8 +108,6 @@ def __init__( ) self.metrics = metrics - self._status_tracker: TaskStatusTracker | None = None - # Use setter to allow propagation and keep a single source of truth self.status_tracker = status_tracker self.submit_web_logs = submit_web_logs # ADDED @@ -118,34 +116,6 @@ def on_messages_enqueued(self, msgs: list[ScheduleMessageItem]) -> None: return # This is handled in BaseScheduler now - @property - def status_tracker(self) -> TaskStatusTracker | None: - """Lazy-initialized status tracker for the dispatcher. - - If the tracker is None, attempt to initialize from the Redis-backed - components available to the dispatcher (queue or orchestrator). - """ - if self._status_tracker is None: - try: - self._status_tracker = TaskStatusTracker(self.redis) - if self.memos_message_queue: - self.memos_message_queue.set_status_tracker(self._status_tracker) - except Exception as e: - logger.warning(f"Failed to lazily initialize status_tracker: {e}", exc_info=True) - return self._status_tracker - - @status_tracker.setter - def status_tracker(self, value: TaskStatusTracker | None) -> None: - self._status_tracker = value - # Propagate to the queue if possible - try: - if self.memos_message_queue and hasattr(self.memos_message_queue, "status_tracker"): - self.memos_message_queue.status_tracker = value - except Exception as e: - logger.warning( - f"Failed to propagate dispatcher status_tracker to queue: {e}", exc_info=True - ) - def _create_task_wrapper(self, handler: Callable, task_item: RunningTaskItem): """ Create a wrapper around the handler to track task execution and capture results. From 079a3e39582f2678d49637d574e1696863de50e0 Mon Sep 17 00:00:00 2001 From: chentang Date: Thu, 8 Jan 2026 11:06:47 +0800 Subject: [PATCH 27/47] refactor: allow the code to run without rabbitmq --- src/memos/mem_scheduler/base_scheduler.py | 2 ++ .../webservice_modules/rabbitmq_service.py | 17 ++++++++++------- 2 files changed, 12 insertions(+), 7 deletions(-) diff --git a/src/memos/mem_scheduler/base_scheduler.py b/src/memos/mem_scheduler/base_scheduler.py index 130ad98da..e2658abc4 100644 --- a/src/memos/mem_scheduler/base_scheduler.py +++ b/src/memos/mem_scheduler/base_scheduler.py @@ -867,6 +867,8 @@ def _submit_web_logs( messages = [messages] # transform single message to list for message in messages: + if self.rabbitmq_config is None: + return try: # Always call publish; the publisher now caches when offline and flushes after reconnect logger.info( diff --git a/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py b/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py index 46b2ad3d1..f3508124a 100644 --- a/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py +++ b/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py @@ -103,13 +103,16 @@ def initialize_rabbitmq( from pika.adapters.select_connection import SelectConnection if config is None: - if config_path is None and AuthConfig.default_config_exists(): - auth_config = AuthConfig.from_local_config() - elif Path(config_path).exists(): - auth_config = AuthConfig.from_local_config(config_path=config_path) + if self.auth_config_path is not None and Path(self.auth_config_path).exists(): + self.auth_config = AuthConfig.from_local_config( + config_path=self.auth_config_path + ) + elif AuthConfig.default_config_exists(): + self.auth_config = AuthConfig.from_local_config() else: - auth_config = AuthConfig.from_local_env() - self.rabbitmq_config = auth_config.rabbitmq + self.auth_config = AuthConfig.from_local_env() + self.rabbitmq_config = self.auth_config.rabbitmq + elif isinstance(config, RabbitMQConfig): self.rabbitmq_config = config elif isinstance(config, dict): @@ -148,7 +151,7 @@ def initialize_rabbitmq( self._io_loop_thread.start() logger.info("RabbitMQ connection process started") except Exception: - logger.error("Fail to initialize auth_config", exc_info=True) + logger.debug("Fail to initialize auth_config", exc_info=True) finally: with self._rabbitmq_lock: self._rabbitmq_initializing = False From d2e6c68999ade2cce236f04d5a1ad9de77b32287 Mon Sep 17 00:00:00 2001 From: chentang Date: Thu, 8 Jan 2026 20:55:35 +0800 Subject: [PATCH 28/47] refactor: create a _parse_pending_entry for redis queue --- .../task_schedule_modules/redis_queue.py | 18 ++++++--- .../webservice_modules/rabbitmq_service.py | 37 ++++++++++++------- 2 files changed, 36 insertions(+), 19 deletions(-) diff --git a/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py b/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py index 06fbce4dc..1c9683542 100644 --- a/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py +++ b/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py @@ -652,6 +652,16 @@ def _compute_pending_need( need_pending = max(0, batch_size - new_count) return need_pending if need_pending > 0 else 0 + def _parse_pending_entry(self, entry) -> tuple[str, int]: + """Extract message_id and idle_time from a pending entry (dict, tuple, or object).""" + if isinstance(entry, dict): + return entry.get("message_id"), entry.get("time_since_delivered") + elif isinstance(entry, tuple | list): + return entry[0], entry[2] + else: + # Assume object (redis-py 5.x+ PendingMessage) + return getattr(entry, "message_id", None), getattr(entry, "time_since_delivered", 0) + def _manual_xautoclaim( self, stream_key: str, min_idle_time: int, count: int ) -> tuple[str, list[tuple[str, dict]], list[str]]: @@ -672,8 +682,7 @@ def _manual_xautoclaim( # entry structure depends on redis-py version/decoding # Assuming list of dicts: {'message_id': '...', 'time_since_delivered': ms, ...} # or list of tuples - msg_id = entry.get("message_id") if isinstance(entry, dict) else entry[0] - idle_time = entry.get("time_since_delivered") if isinstance(entry, dict) else entry[2] + msg_id, idle_time = self._parse_pending_entry(entry) if idle_time >= min_idle_time: claim_ids.append(msg_id) @@ -882,10 +891,7 @@ def _batch_claim_manual( claim_ids = [] for entry in pending_res: - msg_id = entry.get("message_id") if isinstance(entry, dict) else entry[0] - idle_time = ( - entry.get("time_since_delivered") if isinstance(entry, dict) else entry[2] - ) + msg_id, idle_time = self._parse_pending_entry(entry) if idle_time >= min_idle: claim_ids.append(msg_id) if len(claim_ids) >= need_count: diff --git a/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py b/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py index 8aac18522..a07934b8e 100644 --- a/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py +++ b/src/memos/mem_scheduler/webservice_modules/rabbitmq_service.py @@ -30,6 +30,7 @@ def __init__(self): Initialize RabbitMQ connection settings. """ super().__init__() + self.auth_config = None # RabbitMQ settings self.rabbitmq_config: RabbitMQConfig | None = None @@ -99,25 +100,35 @@ def initialize_rabbitmq( ) return + if self.is_rabbitmq_connected(): + logger.warning("RabbitMQ is already connected. Skipping initialization.") + return + from pika.adapters.select_connection import SelectConnection - if config is None: - if self.auth_config_path is not None and Path(self.auth_config_path).exists(): - self.auth_config = AuthConfig.from_local_config( - config_path=self.auth_config_path - ) + if config is not None: + if isinstance(config, RabbitMQConfig): + self.rabbitmq_config = config + elif isinstance(config, dict): + self.rabbitmq_config = AuthConfig.from_dict(config).rabbitmq + else: + logger.error(f"Unsupported config type: {type(config)}") + return + + else: + if config_path is not None and Path(config_path).exists(): + self.auth_config = AuthConfig.from_local_config(config_path=config_path) elif AuthConfig.default_config_exists(): self.auth_config = AuthConfig.from_local_config() else: self.auth_config = AuthConfig.from_local_env() self.rabbitmq_config = self.auth_config.rabbitmq - elif isinstance(config, RabbitMQConfig): - self.rabbitmq_config = config - elif isinstance(config, dict): - self.rabbitmq_config = AuthConfig.from_dict(config).rabbitmq - else: - logger.error("Not implemented") + if self.rabbitmq_config is None: + logger.error( + "Failed to load RabbitMQ configuration. Please check your config file or environment variables." + ) + return # Load exchange configuration from config if self.rabbitmq_config: @@ -143,7 +154,7 @@ def initialize_rabbitmq( self.rabbitmq_exchange_type = env_exchange_type logger.info(f"Using env exchange type override: {self.rabbitmq_exchange_type}") - # Start connection process + # Start connection process parameters = self.get_rabbitmq_connection_param() self.rabbitmq_connection = SelectConnection( parameters, @@ -159,7 +170,7 @@ def initialize_rabbitmq( self._io_loop_thread.start() logger.info("RabbitMQ connection process started") except Exception: - logger.debug("Fail to initialize auth_config", exc_info=True) + logger.error("Failed to initialize RabbitMQ connection", exc_info=True) finally: with self._rabbitmq_lock: self._rabbitmq_initializing = False From 412b05a0dcdaf3fb9899d32d95fba5235f729bc1 Mon Sep 17 00:00:00 2001 From: chentang Date: Thu, 8 Jan 2026 21:04:00 +0800 Subject: [PATCH 29/47] refactor: add a try/catch for status_tracker --- src/memos/mem_scheduler/base_scheduler.py | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/src/memos/mem_scheduler/base_scheduler.py b/src/memos/mem_scheduler/base_scheduler.py index e2658abc4..4c9310cbb 100644 --- a/src/memos/mem_scheduler/base_scheduler.py +++ b/src/memos/mem_scheduler/base_scheduler.py @@ -306,12 +306,15 @@ def status_tracker(self) -> TaskStatusTracker | None: by `mem_cube` so downstream modules can safely access the tracker. """ if self._status_tracker is None and self.use_redis_queue: - self._status_tracker = TaskStatusTracker(self.redis) - # Propagate to submodules when created lazily - if self.dispatcher: - self.dispatcher.status_tracker = self._status_tracker - if self.memos_message_queue: - self.memos_message_queue.set_status_tracker(self._status_tracker) + try: + self._status_tracker = TaskStatusTracker(self.redis) + # Propagate to submodules when created lazily + if self.dispatcher: + self.dispatcher.status_tracker = self._status_tracker + if self.memos_message_queue: + self.memos_message_queue.set_status_tracker(self._status_tracker) + except Exception as e: + logger.warning(f"Failed to lazy-initialize status_tracker: {e}", exc_info=True) return self._status_tracker From 1f1a81dc345db3e8dc1c8b4e39ed0c8a657595bb Mon Sep 17 00:00:00 2001 From: chentang Date: Fri, 9 Jan 2026 17:20:35 +0800 Subject: [PATCH 30/47] fix: revise examples of textual memories to run normally --- .../core_memories/general_textual_memory.py | 61 ++++++++++---- .../core_memories/naive_textual_memory.py | 79 +++++++++++++------ 2 files changed, 102 insertions(+), 38 deletions(-) diff --git a/examples/core_memories/general_textual_memory.py b/examples/core_memories/general_textual_memory.py index f71e2ef2e..d5c765b01 100644 --- a/examples/core_memories/general_textual_memory.py +++ b/examples/core_memories/general_textual_memory.py @@ -1,14 +1,25 @@ +import os +import pprint + from memos.configs.memory import MemoryConfigFactory from memos.memories.factory import MemoryFactory +# Initialize the memory configuration +# This configuration specifies the extractor, vector database, and embedder backend. +# Here we use OpenAI for extraction, Qdrant for vector storage, and Ollama for embedding. config = MemoryConfigFactory( backend="general_text", config={ "extractor_llm": { - "backend": "ollama", + "backend": "openai", "config": { - "model_name_or_path": "qwen3:0.6b", + "model_name_or_path": "gpt-4o-mini", + "api_key": os.environ.get("OPENAI_API_KEY"), + "api_base": os.environ.get( + "OPENAI_BASE_URL", + os.environ.get("OPENAI_API_BASE", "https://api.openai.com/v1"), + ), "temperature": 0.0, "remove_think_prefix": True, "max_tokens": 8192, @@ -30,6 +41,8 @@ }, }, ) + +# Create the memory instance from the configuration m = MemoryFactory.from_config(config) example_memories = [ @@ -52,20 +65,25 @@ }, }, ] + example_id = "a19b6caa-5d59-42ad-8c8a-e4f7118435b4" print("===== Extract memories =====") +# Extract memories from a conversation +# The extractor LLM processes the conversation to identify relevant information. memories = m.extract( [ {"role": "user", "content": "I love tomatoes."}, {"role": "assistant", "content": "Great! Tomatoes are delicious."}, ] ) -print(memories) +pprint.pprint(memories) print() print("==== Add memories ====") +# Add the extracted memories to the memory store m.add(memories) +# Add a manually created memory item m.add( [ { @@ -80,19 +98,27 @@ } ] ) -print(m.get_all()) +print("All memories after addition:") +pprint.pprint(m.get_all()) print() + print("==== Search memories ====") +# Search for memories related to a query search_results = m.search("Tell me more about the user", top_k=2) -print(search_results) +pprint.pprint(search_results) print() print("==== Get memories ====") -print(m.get(example_id)) -print(m.get_by_ids([example_id])) +# Retrieve a specific memory by its ID +print(f"Memory with ID {example_id}:") +pprint.pprint(m.get(example_id)) +# Retrieve multiple memories by IDs +print(f"Memories by IDs [{example_id}]:") +pprint.pprint(m.get_by_ids([example_id])) print() print("==== Update memories ====") +# Update an existing memory m.update( example_id, { @@ -106,19 +132,26 @@ }, }, ) -print(m.get(example_id)) +print(f"Memory after update (ID {example_id}):") +pprint.pprint(m.get(example_id)) +print() + +print("==== Dump memory ====") +# Dump the current state of memory to a file +m.dump("tmp/general_mem") +print("Memory dumped to 'tmp/general_mem'.") print() print("==== Delete memories ====") +# Delete a memory by its ID m.delete([example_id]) -print(m.get_all()) +print("All memories after deletion:") +pprint.pprint(m.get_all()) print() print("==== Delete all memories ====") +# Clear all memories from the store m.delete_all() -print(m.get_all()) +print("All memories after delete_all:") +pprint.pprint(m.get_all()) print() - -print("==== Dump memory ====") -m.dump("tmp/mem") -print("Memory dumped to 'tmp/mem'.") diff --git a/examples/core_memories/naive_textual_memory.py b/examples/core_memories/naive_textual_memory.py index ff61334dc..ab73060c7 100644 --- a/examples/core_memories/naive_textual_memory.py +++ b/examples/core_memories/naive_textual_memory.py @@ -1,53 +1,77 @@ +import json +import os import uuid from memos.configs.memory import MemoryConfigFactory from memos.memories.factory import MemoryFactory +def print_result(title, result): + """Helper function: Pretty print the result.""" + print(f"\n{'=' * 10} {title} {'=' * 10}") + if isinstance(result, list | dict): + print(json.dumps(result, indent=2, ensure_ascii=False, default=str)) + else: + print(result) + + +# Configure memory backend with OpenAI extractor config = MemoryConfigFactory( backend="naive_text", config={ "extractor_llm": { - "backend": "ollama", + "backend": "openai", "config": { - "model_name_or_path": "qwen3:0.6b", + "model_name_or_path": "gpt-4o-mini", + "api_key": os.environ.get("OPENAI_API_KEY"), + "api_base": os.environ.get( + "OPENAI_BASE_URL", + os.environ.get("OPENAI_API_BASE", "https://api.openai.com/v1"), + ), "temperature": 0.0, "remove_think_prefix": True, }, } }, ) + +# Create memory instance m = MemoryFactory.from_config(config) -print("===== Extract memories =====") +# Extract memories from a simulated conversation memories = m.extract( [ {"role": "user", "content": "I love tomatoes."}, {"role": "assistant", "content": "Great! Tomatoes are delicious."}, ] ) -print(memories) -print() +print_result("Extract memories", memories) + -print("==== Add memories ====") +# Add the extracted memories to storage m.add(memories) + +# Manually create a memory item and add it example_id = str(uuid.uuid4()) -m.add([{"id": example_id, "memory": "User is Chinese.", "metadata": {"type": "opinion"}}]) -print(m.get_all()) -print() +manual_memory = [{"id": example_id, "memory": "User is Chinese.", "metadata": {"type": "opinion"}}] +m.add(manual_memory) + +# Print all current memories +print_result("Add memories (Check all after adding)", m.get_all()) -print("==== Search memories ====") + +# Search for relevant memories based on the query search_results = m.search("Tell me more about the user", top_k=2) -print(search_results) -print() +print_result("Search memories", search_results) + + +# Get specific memory item by ID +memory_item = m.get(example_id) +print_result("Get memory", memory_item) -print("==== Get memories ====") -memories = m.get(example_id) -print(memories) -print() -print("==== Update memories ====") +# Update the memory content for the specified ID m.update( example_id, { @@ -56,15 +80,22 @@ "metadata": {"type": "opinion", "confidence": 85}, }, ) -print(m.get(example_id)) +updated_memory = m.get(example_id) +print_result("Update memory", updated_memory) + + +print("==== Dump memory ====") +# Dump the current state of memory to a file +m.dump("tmp/naive_mem") +print("Memory dumped to 'tmp/naive_mem'.") print() -print("==== Delete memories ====") + +# Delete memory with the specified ID m.delete([example_id]) -print(m.get_all()) -print() +print_result("Delete memory (Check all after deleting)", m.get_all()) -print("==== Delete all memories ====") + +# Delete all memories in storage m.delete_all() -print(m.get_all()) -print() +print_result("Delete all", m.get_all()) From 5c85fc9cd06d5419d1e5fecf2ac4833b2486c157 Mon Sep 17 00:00:00 2001 From: Zehao Lin Date: Wed, 14 Jan 2026 14:10:03 +0800 Subject: [PATCH 31/47] feat: improve MemCube examples with View architecture (#859) * feat: improve MemCube examples with View architecture - Add load_cube.py: demonstrate loading MemCube and using SingleCubeView - Add dump_cube.py: demonstrate persisting MemCube to disk - Deprecate old examples: move load_from_folder.py, load_from_remote.py, load_lazily.py to _deprecated/ - Add _deprecated/README.md with migration guide - All code in English with ruff check and format passed - Use 80-char separator lines consistent with server_router_api.py style * feat: improve MemCube examples with SingleCubeView - dump_cube.py: export cube data via graph_store.export_graph() - load_cube.py: import and display graph data - Add example data in examples/data/mem_cube_tree/ --------- Co-authored-by: glin1993@outlook.com <> --- .../data/mem_cube_tree/textual_memory.json | 4219 +++++++++++++++++ examples/mem_cube/_deprecated/README.md | 81 + .../{ => _deprecated}/load_from_folder.py | 0 .../{ => _deprecated}/load_from_remote.py | 0 .../mem_cube/{ => _deprecated}/load_lazily.py | 0 examples/mem_cube/dump_cube.py | 137 + examples/mem_cube/load_cube.py | 137 + 7 files changed, 4574 insertions(+) create mode 100644 examples/data/mem_cube_tree/textual_memory.json create mode 100644 examples/mem_cube/_deprecated/README.md rename examples/mem_cube/{ => _deprecated}/load_from_folder.py (100%) rename examples/mem_cube/{ => _deprecated}/load_from_remote.py (100%) rename examples/mem_cube/{ => _deprecated}/load_lazily.py (100%) create mode 100644 examples/mem_cube/dump_cube.py create mode 100644 examples/mem_cube/load_cube.py diff --git a/examples/data/mem_cube_tree/textual_memory.json b/examples/data/mem_cube_tree/textual_memory.json new file mode 100644 index 000000000..91f426ca2 --- /dev/null +++ b/examples/data/mem_cube_tree/textual_memory.json @@ -0,0 +1,4219 @@ +{ + "nodes": [ + { + "id": "c1e2bfb3-4dd7-40f9-a347-a25a72223b2c", + "memory": "On January 13, 2026, at 8:51 PM, the user added another memory to demonstrate the concept of persistence.", + "metadata": { + "sources": [ + "\"{\\\"type\\\": \\\"chat\\\", \\\"role\\\": \\\"user\\\", \\\"chat_time\\\": \\\"08:51 PM on 13 January, 2026\\\", \\\"content\\\": \\\"This is a test memory for dump example\\\", \\\"lang\\\": \\\"en\\\"}\"", + "\"{\\\"type\\\": \\\"chat\\\", \\\"role\\\": \\\"user\\\", \\\"chat_time\\\": \\\"08:51 PM on 13 January, 2026\\\", \\\"content\\\": \\\"Another memory to demonstrate persistence\\\", \\\"lang\\\": \\\"en\\\"}\"" + ], + "confidence": 0.99, + "usage": [], + "created_at": "2026-01-13T20:51:42.394870000+00:00", + "session_id": "default_session", + "memory_type": "UserMemory", + "type": "fact", + "tags": [ + "persistence", + "memory", + "demonstration" + ], + "updated_at": "2026-01-13T20:51:42.396309000+00:00", + "user_id": "example_user", + "background": "On January 13, 2026, at 8:51 PM, the user engaged in a memory demonstration by creating a test memory example and another memory to illustrate the concept of persistence. These actions reflect the user's interest in exploring and demonstrating memory-related concepts.", + "file_ids": [], + "embedding": [ + -0.022425159811973572, + 0.01004026923328638, + 0.013415387831628323, + -0.013093948364257812, + -0.04768655076622963, + -0.047837819904088974, + 0.02147974818944931, + 0.019097311422228813, + 0.005332120228558779, + -0.005180854815989733, + 0.0216499213129282, + -0.006977136246860027, + -0.014067722484469414, + 0.014010997489094734, + -0.01164746843278408, + 0.037948813289403915, + 0.049539558589458466, + -0.028778323903679848, + -0.0363227054476738, + -0.006282258778810501, + 0.03201163187623024, + -0.043678008019924164, + 0.06640569865703583, + 0.04734620451927185, + -0.03552856296300888, + 0.008948319591581821, + -0.018199170008301735, + 0.015788370743393898, + 0.08047342300415039, + 0.04632515832781792, + -0.01887986622750759, + 0.00966683216392994, + -0.02516685239970684, + -0.00974719226360321, + -0.01631780155003071, + -0.01085332315415144, + 0.0284947007894516, + 0.012914320454001427, + -0.02427816577255726, + 0.006589517462998629, + -0.013954272493720055, + -0.0017856458434835076, + 0.004043997265398502, + -0.004202353768050671, + 0.032805778086185455, + -0.00395891023799777, + -0.002543156733736396, + -0.018889321014285088, + -0.02066669426858425, + -0.006225534249097109, + 0.008262895978987217, + 0.0266795102506876, + 0.055325478315353394, + -0.019683465361595154, + -0.013576108030974865, + 0.015372389927506447, + -0.05816170945763588, + -0.00842361617833376, + -0.009548655711114407, + -0.0019262757850810885, + -0.047535285353660583, + 0.026603877544403076, + -0.0035098399966955185, + -0.030290981754660606, + -0.015334573574364185, + 0.04798908531665802, + 0.028400158509612083, + -0.00544084282591939, + 0.008106903173029423, + -0.03639834001660347, + 0.011515110731124878, + 0.042278800159692764, + -0.07343956083059311, + -0.02628243714570999, + -0.08886867761611938, + 0.02773837186396122, + -0.0017962816637009382, + -0.007761827670037746, + -0.011363845318555832, + 0.031860366463661194, + 0.017783189192414284, + -0.026849685236811638, + 0.04144683852791786, + -0.00212244875729084, + 0.03042333945631981, + 0.026755142956972122, + -0.04500158503651619, + 0.03989636152982712, + 0.04318639263510704, + -0.03339193016290665, + 0.025412660092115402, + -0.01126930397003889, + 0.027587104588747025, + -0.03471550717949867, + -0.006041178945451975, + -0.007709830068051815, + -0.02686859294772148, + 0.0020196351688355207, + 0.05143038183450699, + 0.029402295127511024, + 0.059598736464977264, + 0.01989145576953888, + 0.013944818638265133, + -0.010550791397690773, + 0.011004588566720486, + -0.02439161390066147, + 0.05952310189604759, + -0.0021389934699982405, + -0.011723102070391178, + 0.007941455580294132, + 0.010248259641230106, + 0.029893908649683, + 0.033032674342393875, + 0.008130538277328014, + 0.025242485105991364, + -0.009198852814733982, + 0.04307294636964798, + 0.005294303875416517, + -0.030272074043750763, + -0.004263805691152811, + 0.04027452692389488, + 0.017197033390402794, + 0.06016598269343376, + -0.025620650500059128, + -0.02253860794007778, + -0.015088766813278198, + -0.007000771816819906, + -0.018870411440730095, + -0.015325118787586689, + -0.0027582377661019564, + 0.025734098628163338, + -0.017972271889448166, + 0.014824051409959793, + -0.025072310119867325, + -0.05165728181600571, + -0.00673132948577404, + 0.004667968954890966, + 0.03293813392519951, + 0.02083686739206314, + -0.03785427287220955, + 0.013188489712774754, + -0.02533702552318573, + 0.002592790871858597, + -0.03611471503973007, + 0.022084811702370644, + -0.007724011316895485, + 0.0028811413794755936, + 0.007497112732380629, + 0.026755142956972122, + 0.014861867763102055, + -0.012413252145051956, + 0.014880775474011898, + -0.03142547607421875, + -0.03377009555697441, + -0.024202533066272736, + 0.0020539062097668648, + 0.02323821373283863, + 0.09204525500535965, + -0.03365664556622505, + -0.031633466482162476, + -0.005308485124260187, + -0.06735111027956009, + -0.06126265972852707, + 0.04545538127422333, + 0.03220071271061897, + 0.028343435376882553, + 0.010843869298696518, + 0.02891068160533905, + -0.034488607197999954, + 0.006887322291731834, + -0.0065280660055577755, + -0.003923457581549883, + 0.02036416158080101, + 0.008220352232456207, + 0.0012183990329504013, + 0.0293266624212265, + 0.04390490800142288, + 0.01639343425631523, + -0.0038076445925980806, + -0.04159810394048691, + -0.057556647807359695, + -0.01890822872519493, + 0.04326202720403671, + -0.025355935096740723, + -0.045379746705293655, + -0.014578244648873806, + -0.0410686731338501, + 0.03469659760594368, + 0.01117476262152195, + 0.036190349608659744, + 0.020439794287085533, + -0.013093948364257812, + -0.03879968449473381, + 0.005251760594546795, + -0.028040902689099312, + -0.028229985386133194, + 0.005209216848015785, + -0.00709531269967556, + -0.029875000938773155, + 0.0010895866435021162, + -0.012006725184619427, + 0.07343956083059311, + 0.010541337542235851, + 0.02246297523379326, + -0.02633916214108467, + -0.020401978865265846, + -0.01178928092122078, + 0.025715190917253494, + 0.01966455765068531, + -0.07551946491003036, + -0.02388109266757965, + 0.005265941843390465, + -0.0036445611622184515, + -0.004528520628809929, + 0.018482793122529984, + -0.04511503502726555, + 0.012120174244046211, + 0.010635878890752792, + -0.008995589800179005, + -0.01553311012685299, + -0.030158624053001404, + 0.060014717280864716, + -0.056913767009973526, + 0.004339438397437334, + 0.032975949347019196, + -0.008612697944045067, + 0.0023138944525271654, + 0.03199272230267525, + 0.004360710270702839, + -0.008277077227830887, + 0.018066812306642532, + 0.02879723161458969, + 0.02745474874973297, + -0.010200989432632923, + 0.022746598348021507, + -0.03348647430539131, + -0.04084177315235138, + -0.006783327087759972, + 0.005696103908121586, + 0.0018281893571838737, + -0.01589236594736576, + -0.03482895717024803, + 0.0062491693533957005, + 0.0023871639277786016, + -0.034091535955667496, + -0.03195490688085556, + -0.014294620603322983, + 0.01899331621825695, + 0.017537381500005722, + 0.006069541443139315, + 0.03144438564777374, + 0.02019398845732212, + -0.06375854462385178, + -0.032087262719869614, + 0.005927729420363903, + 0.02123394049704075, + 0.034091535955667496, + -0.010465704835951328, + 0.041219938546419144, + 0.03170910105109215, + 0.03439406678080559, + -0.024996677413582802, + -0.0038998222444206476, + 0.03887531906366348, + 0.041219938546419144, + -0.01626107655465603, + -0.01804790459573269, + -0.0051997629925608635, + 0.023502927273511887, + -0.026547152549028397, + 0.029572470113635063, + -0.03140656650066376, + -0.023105856031179428, + 0.017924999818205833, + -0.005507021676748991, + -0.010134810581803322, + -0.024315981194376945, + -0.007908366620540619, + -0.024259258061647415, + 0.0360390841960907, + 0.02802199497818947, + -0.03195490688085556, + 0.023200396448373795, + -0.018123537302017212, + 0.022576425224542618, + -0.0413333885371685, + -0.03955601528286934, + 5.5653712479397655e-05, + 0.0209503173828125, + -0.04159810394048691, + -0.024070175364613533, + 0.02679296024143696, + 0.06493085622787476, + -0.033789005130529404, + -0.01567492075264454, + -0.02656606025993824, + -0.005653560161590576, + -0.16155190765857697, + 0.010730419307947159, + -0.021025950089097023, + 0.028532516211271286, + -0.010900593362748623, + -0.008319620974361897, + -0.03637943044304848, + -0.01583564095199108, + -0.04239225015044212, + 0.07003607600927353, + -0.03594454377889633, + -0.04863196238875389, + 0.027360206469893456, + 0.021252848207950592, + -0.02497776970267296, + -0.004530884325504303, + -0.02703876607120037, + -0.019815823063254356, + -0.03985854610800743, + -0.030877137556672096, + 0.012186353094875813, + -0.01614762656390667, + 0.03165237605571747, + -0.035131487995386124, + -0.008636333048343658, + 0.008645787835121155, + 0.002212262712419033, + -0.009577018208801746, + -0.055438924580812454, + 0.006929865572601557, + -0.010834414511919022, + 0.03229525312781334, + -0.011987816542387009, + -0.015410206280648708, + 0.02745474874973297, + 0.05207326263189316, + 0.009000317193567753, + -0.01176091842353344, + 0.023068038746714592, + -0.030971677973866463, + 0.026849685236811638, + 0.05237579345703125, + -0.024561788886785507, + 0.0284947007894516, + 0.020874684676527977, + -0.02405126579105854, + -0.020685601979494095, + 0.0006671059527434409, + -0.049653008580207825, + -0.010815506801009178, + -0.02312476374208927, + -0.028475793078541756, + -0.01626107655465603, + -0.008579608984291553, + -0.02042088657617569, + 0.011486749164760113, + -0.0293266624212265, + 0.013538291677832603, + -0.035377293825149536, + 0.009870095178484917, + -0.012413252145051956, + 0.00476250983774662, + -0.0022571696899831295, + 0.006447705905884504, + -0.04447215422987938, + 0.016828322783112526, + 0.033505380153656006, + -0.04341329261660576, + 7.6445379818324e-05, + -0.034791141748428345, + 0.05759446322917938, + -0.006835324689745903, + 0.002079905243590474, + -0.01290486566722393, + 0.010768236592411995, + 0.07635142654180527, + -0.011609652079641819, + -0.04632515832781792, + 0.01966455765068531, + -0.10089430958032608, + 0.019929273054003716, + 0.050711870193481445, + -0.0033467565663158894, + 0.00785164162516594, + -0.03653069585561752, + 0.022368434816598892, + 0.006537519861012697, + 0.004381982143968344, + 0.03955601528286934, + 0.2114696353673935, + 0.031690191477537155, + -0.05438006669282913, + 0.013112856075167656, + 0.041219938546419144, + -0.005327393300831318, + -0.01223362423479557, + 0.025242485105991364, + -0.056270889937877655, + -0.046552058309316635, + 0.015154944732785225, + -0.016459612175822258, + 0.00955338217318058, + 0.013727374374866486, + 0.03424280136823654, + 0.004329984541982412, + -0.024675238877534866, + 0.015438568778336048, + 0.08584335446357727, + 0.012999407015740871, + 0.016686512157320976, + -0.009118493646383286, + -0.004190536215901375, + 0.005601562559604645, + -0.034318435937166214, + -0.01955110765993595, + -0.004864141810685396, + 0.045606646686792374, + 0.02949683740735054, + 0.053396835923194885, + -0.01936202682554722, + 0.030688054859638214, + -0.002644788473844528, + 0.0024911591317504644, + -0.0174617487937212, + -0.014861867763102055, + -0.025488292798399925, + -0.06754019111394882, + -0.011590744368731976, + 0.018123537302017212, + 0.02720894105732441, + -0.009737737476825714, + 0.0340726263821125, + 0.0259799063205719, + -0.01553311012685299, + -0.011316575109958649, + 0.017471203580498695, + -0.03048006445169449, + -0.04371582344174385, + -0.022954588755965233, + -0.022028086706995964, + 0.024372706189751625, + 0.02620680443942547, + -0.023086946457624435, + 0.019967088475823402, + -0.03685213625431061, + -0.005171400494873524, + -0.010541337542235851, + 0.0012302165850996971, + 0.06027943268418312, + 0.029875000938773155, + 0.03199272230267525, + -0.0051146759651601315, + 0.03204944729804993, + -0.0076814680360257626, + 0.0007687376928515732, + 0.029515745118260384, + -0.02446724846959114, + 0.03348647430539131, + 0.02340838685631752, + 0.03902658447623253, + 0.013377571478486061, + 0.01896495372056961, + 0.020515428856015205, + 0.010938410647213459, + -0.0005574973183684051, + 0.02427816577255726, + 0.021876821294426918, + 0.016128718852996826, + 0.05600617453455925, + -0.011921637691557407, + -0.02773837186396122, + -0.07733465731143951, + 0.007166218478232622, + 0.020969225093722343, + -0.04950174316763878, + -0.04844288155436516, + 0.07752373814582825, + -0.0036587421782314777, + -0.03898876905441284, + -0.01647852174937725, + 0.049010127782821655, + -0.0048286886885762215, + -0.019626740366220474, + 0.05732974782586098, + -0.020628876984119415, + 0.07241851836442947, + 0.0036209258250892162, + -0.036549605429172516, + -0.016610879451036453, + -0.0497286394238472, + -0.026225712150335312, + 0.01734829880297184, + -0.0354718379676342, + -0.026433704420924187, + -0.005355755798518658, + -0.023673102259635925, + -0.0011675831628963351, + -0.0009330029133707285, + 0.005828461609780788, + 0.01135439146310091, + 0.011278758756816387, + -0.059371836483478546, + 0.010787144303321838, + 0.01670541986823082, + 0.008470886386930943, + -0.005596835631877184, + 0.005970273166894913, + -0.016270531341433525, + 0.026055539026856422, + 0.014701147563755512, + 0.004741238430142403, + 0.02008053846657276, + 0.05604398995637894, + 0.004296895116567612, + -0.002104722196236253, + 0.016043631359934807, + -0.019182397052645683, + -0.009676286019384861, + -0.01740502379834652, + 0.02580973133444786, + -0.019570017233490944, + 0.04764873534440994, + -0.022746598348021507, + 0.04935047775506973, + -0.009510839357972145, + 0.014578244648873806, + 0.017660286277532578, + -0.0019392751855775714, + 0.02645261213183403, + 0.008243987336754799, + -0.06999826431274414, + -0.00033325751428492367, + 0.010739874094724655, + 0.013169581070542336, + 0.03482895717024803, + -0.0050059533677995205, + -0.01709303818643093, + -0.021971361711621284, + 0.016941772773861885, + 0.0410686731338501, + 0.026698417961597443, + 0.04243006557226181, + -0.049426108598709106, + -0.03530166298151016, + -0.021631013602018356, + -0.038648419082164764, + 0.022860048338770866, + 0.02896740660071373, + -0.0329570434987545, + 0.0008916411316022277, + 0.025677373632788658, + 0.05101440101861954, + 0.0709436759352684, + 0.057443197816610336, + -0.0075018396601080894, + -0.019702374935150146, + 0.008073813281953335, + -0.02323821373283863, + 0.0043016220442950726, + 0.005232852417975664, + -0.018671875819563866, + -0.01896495372056961, + 0.012696875259280205, + -0.003824189305305481, + -0.021498655900359154, + -0.040463607758283615, + 0.06292658299207687, + -0.008726147934794426, + 0.00958174467086792, + 0.008849050849676132, + -0.021044857800006866, + -0.025355935096740723, + -0.02193354442715645, + 0.041219938546419144, + 0.03013971634209156, + 0.03628489002585411, + -0.03866732865571976, + 0.03148220106959343, + -0.006480795331299305, + -0.06251060217618942, + 0.0854651927947998, + 0.028248893097043037, + -0.01910676434636116, + 0.02620680443942547, + -0.05116566643118858, + 0.019380934536457062, + 0.021555380895733833, + 0.0031009495723992586, + -0.0020385433454066515, + -0.021801186725497246, + 0.013935364782810211, + -0.015400752425193787, + -0.0027086036279797554, + -0.001123857800848782, + 0.022028086706995964, + 0.01639343425631523, + 0.01609090156853199, + -0.016998497769236565, + -0.02265205793082714, + -0.0029922272078692913, + -0.04299731180071831, + -0.021460838615894318, + 0.017282120883464813, + -0.04364019259810448, + -0.019475474953651428, + 0.06614098697900772, + 0.03450751677155495, + -1.5242912922985852e-05, + -0.016941772773861885, + 0.0027251483406871557, + 0.03061242215335369, + 0.03271123394370079, + -0.051695097237825394, + -0.011023497208952904, + 0.017527928575873375, + 0.027133308351039886, + -0.027757279574871063, + 0.023313846439123154, + 0.017887184396386147, + -0.01006863173097372, + -0.030536789447069168, + -0.022084811702370644, + -0.0037651010788977146, + 0.04095522314310074, + -0.06035506725311279, + 0.015485838986933231, + 0.014285166747868061, + 0.0011563563020899892, + -0.02253860794007778, + -0.005549564957618713, + -0.015079312026500702, + 0.0031553106382489204, + 0.012895411811769009, + 0.03948038071393967, + 0.04492595046758652, + -0.006863687187433243, + -0.02352183684706688, + 0.018331527709960938, + 0.0300262663513422, + 0.004287440795451403, + 0.004887776914983988, + -0.0340726263821125, + -0.024958861991763115, + 0.0438670888543129, + 0.03278686851263046, + 0.020742326974868774, + -0.013519383035600185, + -0.06307785212993622, + -0.04855633154511452, + -0.004703422077000141, + 0.036133624613285065, + -0.03594454377889633, + 0.0012633060105144978, + -0.06288877129554749, + -0.0413333885371685, + 0.01810462959110737, + -0.06330475211143494, + 0.000763419724535197, + -0.027171123772859573, + 0.0096384696662426, + -0.009543928317725658, + -0.012971044518053532, + -0.03136875107884407, + 0.058426424860954285, + 0.03386463597416878, + -0.007010225672274828, + -0.05173291265964508, + 0.05850205942988396, + 0.03488568216562271, + -0.011751463636755943, + 0.046438608318567276, + 0.039934176951646805, + 0.04927484318614006, + -0.043980538845062256, + -0.00198654574342072, + 0.01614762656390667, + 0.0009625470265746117, + 0.03339193016290665, + -0.0865996852517128, + 0.021252848207950592, + 0.007208762224763632, + -0.03583109378814697, + 0.04904794320464134, + 0.006003362592309713, + 0.008792325854301453, + -0.0311418529599905, + 0.01097622700035572, + -0.02458069659769535, + 0.018085720017552376, + -0.017669739201664925, + -0.011430024169385433, + -0.039820730686187744, + -0.04084177315235138, + -0.005908821243792772, + -0.003512203460559249, + -0.00965265091508627, + -0.0047388747334480286, + 0.0592205710709095, + -0.0059135486371815205, + -0.021517563611268997, + -0.04401835426688194, + 0.04284604638814926, + 0.04632515832781792, + -0.011458386667072773, + -0.018482793122529984, + 0.027927452698349953, + -0.06493085622787476, + 0.0351882129907608, + 0.0034814774990081787, + 0.03804335743188858, + 0.025885364040732384, + -0.04159810394048691, + 0.008589062839746475, + -0.0035500198137015104, + -0.008442523889243603, + 0.005483386106789112, + -0.026320254430174828, + 0.008669422939419746, + -0.027492564171552658, + -0.012148536741733551, + -0.015495292842388153, + -0.029648102819919586, + -0.006665150634944439, + 0.05721629783511162, + 0.026603877544403076, + 0.015240032225847244, + -0.024429431185126305, + 0.04295949637889862, + -0.04927484318614006, + -0.05165728181600571, + -0.036719780415296555, + 0.036833230406045914, + -0.04791345074772835, + -0.02650933712720871, + 0.020855776965618134, + -0.0036776503548026085, + 0.006182990502566099, + -0.029893908649683, + 0.007118948269635439, + 0.0009324120474047959, + 0.04556883126497269, + -0.024202533066272736, + -0.07865823060274124, + -0.004027452785521746, + -0.004242533817887306, + -0.03898876905441284, + -0.006078995298594236, + 0.033618830144405365, + -0.013245213776826859, + -0.01378409843891859, + 0.01681886985898018, + -0.014842959120869637, + 0.0032687599305063486, + -0.04700585454702377, + 0.009071222506463528, + 0.026471519842743874, + 0.030045175924897194, + 0.006863687187433243, + -0.03429952636361122, + 0.018842048943042755, + -0.01849224790930748, + 0.004533248022198677, + -0.021574288606643677, + -0.023673102259635925, + -0.010730419307947159, + 0.012243078090250492, + -0.03978291153907776, + 0.03781645745038986, + 0.047724369913339615, + -0.03592563420534134, + -0.021215032786130905, + 0.014757872559130192, + -0.040652692317962646, + 0.004173991270363331, + -0.04352674260735512, + -0.028116535395383835, + -0.009619561024010181, + 0.011836551129817963, + 0.022897865623235703, + -0.05528765916824341, + -0.025355935096740723, + -0.017442841082811356, + 0.017111947759985924, + -0.16896392405033112, + 0.029856093227863312, + 0.016194898635149002, + 0.016866140067577362, + -0.04326202720403671, + -0.013509929180145264, + -0.05611962080001831, + 0.006154628470540047, + 0.014616061002016068, + -0.021290665492415428, + 0.0066131530329585075, + -0.04564446210861206, + 0.06096012890338898, + -0.03384573012590408, + -0.027416931465268135, + 0.010229351930320263, + 0.006901503540575504, + 0.057027217000722885, + -0.05388845130801201, + 0.06186772510409355, + 0.009699921123683453, + -0.01977800764143467, + -0.0142473503947258, + -0.0002583632303867489, + -0.017244303598999977, + -0.01770755648612976, + 0.019796915352344513, + 0.03055569715797901, + -0.030158624053001404, + 0.05131693184375763, + 0.0026967860758304596, + 0.02441052347421646, + 0.019182397052645683, + 0.041749369353055954, + 0.03246542811393738, + 0.0048452336341142654, + -0.0012266712728887796, + -0.03808117285370827, + -0.0015800188994035125, + -0.01989145576953888, + -0.021044857800006866, + 0.02153647318482399, + -0.01650688424706459, + -0.01559928897768259, + 0.004192899446934462, + 0.09136456251144409, + -0.028929589316248894, + -0.003526384709402919, + -0.02592318132519722, + 0.03384573012590408, + 0.015240032225847244, + 0.03781645745038986, + 0.009520293213427067, + 0.011524565517902374, + -0.017631923779845238, + -0.005559019278734922, + 0.01158128958195448, + -0.019031131640076637, + -0.024032358080148697, + 0.014776780270040035, + 0.014086630195379257, + -0.019314754754304886, + -0.03161455690860748, + -0.0729101300239563, + -0.017074130475521088, + 0.006750237662345171, + -0.07007389515638351, + -0.007246578577905893, + -0.025091219693422318, + -0.013349208980798721, + -0.025885364040732384, + 0.029950633645057678, + 0.026887500658631325, + -0.0005920638795942068, + -0.012838686816394329, + 0.048064716160297394, + 0.03757065162062645, + 0.01751847378909588, + -0.013821914792060852, + -0.026244621723890305, + -0.027019858360290527, + -0.011808188632130623, + -0.0006871959194540977, + -0.03278686851263046, + 0.035377293825149536, + 0.013056132011115551, + -0.025960998609662056, + -0.012469977140426636, + -0.0031482200138270855, + -0.0007728738128207624, + -0.08077595382928848, + 0.015088766813278198, + 0.056497786194086075, + 0.01623271405696869, + -0.009293394163250923, + 0.06659477949142456, + -0.01989145576953888, + -0.008598516695201397, + -0.015192762017250061, + -0.0026802413631230593, + 0.00839525368064642, + -0.001349574769847095, + 0.02866487391293049, + 0.005842642392963171, + -0.025942089036107063, + 0.0029638647101819515, + -0.024240348488092422, + -0.03524493798613548, + 0.021876821294426918, + -0.010720965452492237, + -0.005984454415738583, + -0.025771915912628174, + -0.04863196238875389, + 0.008239260874688625, + -0.06856123358011246, + -0.03305158391594887, + -0.032162897288799286, + 0.03318393975496292, + -0.0441318042576313, + -0.02000490576028824, + 0.03225743770599365, + 0.03131202608346939, + 0.048896677792072296, + -0.03499913215637207, + 0.024297073483467102, + 0.000977909890934825, + 0.030101899057626724, + 0.015882911160588264, + 0.018000634387135506, + -0.006197171751409769, + -0.006892049219459295, + -0.00835270993411541, + 0.02195245400071144, + 0.039593830704689026, + -0.010238805785775185, + 0.00586627796292305, + 0.0156465582549572, + 0.005800099112093449, + -0.015230578370392323, + -0.031690191477537155, + 0.006849505938589573, + -0.028986314311623573, + 0.02253860794007778, + -0.01421898789703846, + -0.014795688912272453, + -0.019872548058629036, + 0.018331527709960938, + -0.01570328325033188, + -0.019116219133138657, + -0.011864913627505302, + 0.002848051954060793, + 0.00756329158321023, + 0.032919224351644516, + 0.06387199461460114, + -0.01949438452720642, + -0.013112856075167656, + 0.004374891519546509, + 0.022311709821224213, + 0.01765083149075508, + 0.02304913103580475, + -0.034564241766929626, + -0.00717094587162137, + -0.05332120507955551, + -0.05154383182525635, + -0.003493295283988118, + 0.022444067522883415, + 0.037589557468891144, + -0.0087970532476902, + -0.06220807135105133, + 0.004157446790486574, + 0.009151582606136799, + 0.06288877129554749, + -0.030820412561297417, + 0.011902729980647564, + 0.003717830404639244, + -0.056157439947128296, + 0.024883229285478592, + 0.0030016812961548567, + 0.02505340240895748, + -0.026717327535152435, + 0.025185760110616684, + -0.01331139262765646, + 0.005445569753646851, + 0.02475087158381939, + 0.024202533066272736, + 0.036833230406045914, + -0.002345802029594779, + 0.023427294567227364, + -0.011184217408299446, + -0.01375573594123125, + 0.02312476374208927, + -0.029515745118260384, + -0.05910712108016014, + -0.017631923779845238, + 0.01743338629603386, + -0.024486156180500984, + -0.0026613331865519285, + 0.01509822066873312, + -0.011042405851185322, + 0.03392136096954346, + -0.036247074604034424, + -0.04787563532590866, + 0.030064083635807037, + -0.022670965641736984, + 0.005308485124260187, + 0.014786235056817532, + -0.027284573763608932, + 0.009671558625996113, + -0.0360390841960907, + 0.02153647318482399, + -0.05188417807221413, + -0.008995589800179005, + 0.011051859706640244, + -0.0006470159278251231, + -0.020269621163606644, + 0.02229280211031437, + 0.011108584702014923, + -0.013736828230321407, + -0.009841732680797577, + 0.034148260951042175, + -0.0014807506231591105, + -0.0018388251774013042, + 0.013500475324690342, + -0.026849685236811638, + -0.060014717280864716, + -0.008404707536101341, + 0.011212579905986786, + 0.02047761157155037, + -0.0016426523216068745, + 0.0483294315636158, + 0.022444067522883415, + 0.036719780415296555, + -0.03861060366034508, + 0.037362661212682724, + -0.006286986172199249, + -0.02773837186396122, + 0.033448655158281326, + 0.019985998049378395, + -0.03745720162987709, + -0.005204489920288324, + 0.016487974673509598, + -0.019314754754304886, + -0.0555901937186718, + -0.008636333048343658 + ], + "key": "Persistence Demonstration", + "status": "activated" + } + }, + { + "id": "76374204-35a7-49af-a437-29410ae353e3", + "memory": "On January 13, 2026, at 8:51 PM, the user added another memory to demonstrate the concept of persistence.", + "metadata": { + "sources": [ + "\"{\\\"type\\\": \\\"chat\\\", \\\"role\\\": \\\"user\\\", \\\"chat_time\\\": \\\"08:51 PM on 13 January, 2026\\\", \\\"content\\\": \\\"This is a test memory for dump example\\\", \\\"lang\\\": \\\"en\\\"}\"", + "\"{\\\"type\\\": \\\"chat\\\", \\\"role\\\": \\\"user\\\", \\\"chat_time\\\": \\\"08:51 PM on 13 January, 2026\\\", \\\"content\\\": \\\"Another memory to demonstrate persistence\\\", \\\"lang\\\": \\\"en\\\"}\"" + ], + "confidence": 0.99, + "usage": [], + "created_at": "2026-01-13T20:51:42.394870000+00:00", + "session_id": "default_session", + "memory_type": "WorkingMemory", + "type": "fact", + "tags": [ + "persistence", + "memory", + "demonstration" + ], + "updated_at": "2026-01-13T20:51:42.396281000+00:00", + "user_id": "example_user", + "background": "On January 13, 2026, at 8:51 PM, the user engaged in a memory demonstration by creating a test memory example and another memory to illustrate the concept of persistence. These actions reflect the user's interest in exploring and demonstrating memory-related concepts.", + "file_ids": [], + "embedding": [ + -0.022425159811973572, + 0.01004026923328638, + 0.013415387831628323, + -0.013093948364257812, + -0.04768655076622963, + -0.047837819904088974, + 0.02147974818944931, + 0.019097311422228813, + 0.005332120228558779, + -0.005180854815989733, + 0.0216499213129282, + -0.006977136246860027, + -0.014067722484469414, + 0.014010997489094734, + -0.01164746843278408, + 0.037948813289403915, + 0.049539558589458466, + -0.028778323903679848, + -0.0363227054476738, + -0.006282258778810501, + 0.03201163187623024, + -0.043678008019924164, + 0.06640569865703583, + 0.04734620451927185, + -0.03552856296300888, + 0.008948319591581821, + -0.018199170008301735, + 0.015788370743393898, + 0.08047342300415039, + 0.04632515832781792, + -0.01887986622750759, + 0.00966683216392994, + -0.02516685239970684, + -0.00974719226360321, + -0.01631780155003071, + -0.01085332315415144, + 0.0284947007894516, + 0.012914320454001427, + -0.02427816577255726, + 0.006589517462998629, + -0.013954272493720055, + -0.0017856458434835076, + 0.004043997265398502, + -0.004202353768050671, + 0.032805778086185455, + -0.00395891023799777, + -0.002543156733736396, + -0.018889321014285088, + -0.02066669426858425, + -0.006225534249097109, + 0.008262895978987217, + 0.0266795102506876, + 0.055325478315353394, + -0.019683465361595154, + -0.013576108030974865, + 0.015372389927506447, + -0.05816170945763588, + -0.00842361617833376, + -0.009548655711114407, + -0.0019262757850810885, + -0.047535285353660583, + 0.026603877544403076, + -0.0035098399966955185, + -0.030290981754660606, + -0.015334573574364185, + 0.04798908531665802, + 0.028400158509612083, + -0.00544084282591939, + 0.008106903173029423, + -0.03639834001660347, + 0.011515110731124878, + 0.042278800159692764, + -0.07343956083059311, + -0.02628243714570999, + -0.08886867761611938, + 0.02773837186396122, + -0.0017962816637009382, + -0.007761827670037746, + -0.011363845318555832, + 0.031860366463661194, + 0.017783189192414284, + -0.026849685236811638, + 0.04144683852791786, + -0.00212244875729084, + 0.03042333945631981, + 0.026755142956972122, + -0.04500158503651619, + 0.03989636152982712, + 0.04318639263510704, + -0.03339193016290665, + 0.025412660092115402, + -0.01126930397003889, + 0.027587104588747025, + -0.03471550717949867, + -0.006041178945451975, + -0.007709830068051815, + -0.02686859294772148, + 0.0020196351688355207, + 0.05143038183450699, + 0.029402295127511024, + 0.059598736464977264, + 0.01989145576953888, + 0.013944818638265133, + -0.010550791397690773, + 0.011004588566720486, + -0.02439161390066147, + 0.05952310189604759, + -0.0021389934699982405, + -0.011723102070391178, + 0.007941455580294132, + 0.010248259641230106, + 0.029893908649683, + 0.033032674342393875, + 0.008130538277328014, + 0.025242485105991364, + -0.009198852814733982, + 0.04307294636964798, + 0.005294303875416517, + -0.030272074043750763, + -0.004263805691152811, + 0.04027452692389488, + 0.017197033390402794, + 0.06016598269343376, + -0.025620650500059128, + -0.02253860794007778, + -0.015088766813278198, + -0.007000771816819906, + -0.018870411440730095, + -0.015325118787586689, + -0.0027582377661019564, + 0.025734098628163338, + -0.017972271889448166, + 0.014824051409959793, + -0.025072310119867325, + -0.05165728181600571, + -0.00673132948577404, + 0.004667968954890966, + 0.03293813392519951, + 0.02083686739206314, + -0.03785427287220955, + 0.013188489712774754, + -0.02533702552318573, + 0.002592790871858597, + -0.03611471503973007, + 0.022084811702370644, + -0.007724011316895485, + 0.0028811413794755936, + 0.007497112732380629, + 0.026755142956972122, + 0.014861867763102055, + -0.012413252145051956, + 0.014880775474011898, + -0.03142547607421875, + -0.03377009555697441, + -0.024202533066272736, + 0.0020539062097668648, + 0.02323821373283863, + 0.09204525500535965, + -0.03365664556622505, + -0.031633466482162476, + -0.005308485124260187, + -0.06735111027956009, + -0.06126265972852707, + 0.04545538127422333, + 0.03220071271061897, + 0.028343435376882553, + 0.010843869298696518, + 0.02891068160533905, + -0.034488607197999954, + 0.006887322291731834, + -0.0065280660055577755, + -0.003923457581549883, + 0.02036416158080101, + 0.008220352232456207, + 0.0012183990329504013, + 0.0293266624212265, + 0.04390490800142288, + 0.01639343425631523, + -0.0038076445925980806, + -0.04159810394048691, + -0.057556647807359695, + -0.01890822872519493, + 0.04326202720403671, + -0.025355935096740723, + -0.045379746705293655, + -0.014578244648873806, + -0.0410686731338501, + 0.03469659760594368, + 0.01117476262152195, + 0.036190349608659744, + 0.020439794287085533, + -0.013093948364257812, + -0.03879968449473381, + 0.005251760594546795, + -0.028040902689099312, + -0.028229985386133194, + 0.005209216848015785, + -0.00709531269967556, + -0.029875000938773155, + 0.0010895866435021162, + -0.012006725184619427, + 0.07343956083059311, + 0.010541337542235851, + 0.02246297523379326, + -0.02633916214108467, + -0.020401978865265846, + -0.01178928092122078, + 0.025715190917253494, + 0.01966455765068531, + -0.07551946491003036, + -0.02388109266757965, + 0.005265941843390465, + -0.0036445611622184515, + -0.004528520628809929, + 0.018482793122529984, + -0.04511503502726555, + 0.012120174244046211, + 0.010635878890752792, + -0.008995589800179005, + -0.01553311012685299, + -0.030158624053001404, + 0.060014717280864716, + -0.056913767009973526, + 0.004339438397437334, + 0.032975949347019196, + -0.008612697944045067, + 0.0023138944525271654, + 0.03199272230267525, + 0.004360710270702839, + -0.008277077227830887, + 0.018066812306642532, + 0.02879723161458969, + 0.02745474874973297, + -0.010200989432632923, + 0.022746598348021507, + -0.03348647430539131, + -0.04084177315235138, + -0.006783327087759972, + 0.005696103908121586, + 0.0018281893571838737, + -0.01589236594736576, + -0.03482895717024803, + 0.0062491693533957005, + 0.0023871639277786016, + -0.034091535955667496, + -0.03195490688085556, + -0.014294620603322983, + 0.01899331621825695, + 0.017537381500005722, + 0.006069541443139315, + 0.03144438564777374, + 0.02019398845732212, + -0.06375854462385178, + -0.032087262719869614, + 0.005927729420363903, + 0.02123394049704075, + 0.034091535955667496, + -0.010465704835951328, + 0.041219938546419144, + 0.03170910105109215, + 0.03439406678080559, + -0.024996677413582802, + -0.0038998222444206476, + 0.03887531906366348, + 0.041219938546419144, + -0.01626107655465603, + -0.01804790459573269, + -0.0051997629925608635, + 0.023502927273511887, + -0.026547152549028397, + 0.029572470113635063, + -0.03140656650066376, + -0.023105856031179428, + 0.017924999818205833, + -0.005507021676748991, + -0.010134810581803322, + -0.024315981194376945, + -0.007908366620540619, + -0.024259258061647415, + 0.0360390841960907, + 0.02802199497818947, + -0.03195490688085556, + 0.023200396448373795, + -0.018123537302017212, + 0.022576425224542618, + -0.0413333885371685, + -0.03955601528286934, + 5.5653712479397655e-05, + 0.0209503173828125, + -0.04159810394048691, + -0.024070175364613533, + 0.02679296024143696, + 0.06493085622787476, + -0.033789005130529404, + -0.01567492075264454, + -0.02656606025993824, + -0.005653560161590576, + -0.16155190765857697, + 0.010730419307947159, + -0.021025950089097023, + 0.028532516211271286, + -0.010900593362748623, + -0.008319620974361897, + -0.03637943044304848, + -0.01583564095199108, + -0.04239225015044212, + 0.07003607600927353, + -0.03594454377889633, + -0.04863196238875389, + 0.027360206469893456, + 0.021252848207950592, + -0.02497776970267296, + -0.004530884325504303, + -0.02703876607120037, + -0.019815823063254356, + -0.03985854610800743, + -0.030877137556672096, + 0.012186353094875813, + -0.01614762656390667, + 0.03165237605571747, + -0.035131487995386124, + -0.008636333048343658, + 0.008645787835121155, + 0.002212262712419033, + -0.009577018208801746, + -0.055438924580812454, + 0.006929865572601557, + -0.010834414511919022, + 0.03229525312781334, + -0.011987816542387009, + -0.015410206280648708, + 0.02745474874973297, + 0.05207326263189316, + 0.009000317193567753, + -0.01176091842353344, + 0.023068038746714592, + -0.030971677973866463, + 0.026849685236811638, + 0.05237579345703125, + -0.024561788886785507, + 0.0284947007894516, + 0.020874684676527977, + -0.02405126579105854, + -0.020685601979494095, + 0.0006671059527434409, + -0.049653008580207825, + -0.010815506801009178, + -0.02312476374208927, + -0.028475793078541756, + -0.01626107655465603, + -0.008579608984291553, + -0.02042088657617569, + 0.011486749164760113, + -0.0293266624212265, + 0.013538291677832603, + -0.035377293825149536, + 0.009870095178484917, + -0.012413252145051956, + 0.00476250983774662, + -0.0022571696899831295, + 0.006447705905884504, + -0.04447215422987938, + 0.016828322783112526, + 0.033505380153656006, + -0.04341329261660576, + 7.6445379818324e-05, + -0.034791141748428345, + 0.05759446322917938, + -0.006835324689745903, + 0.002079905243590474, + -0.01290486566722393, + 0.010768236592411995, + 0.07635142654180527, + -0.011609652079641819, + -0.04632515832781792, + 0.01966455765068531, + -0.10089430958032608, + 0.019929273054003716, + 0.050711870193481445, + -0.0033467565663158894, + 0.00785164162516594, + -0.03653069585561752, + 0.022368434816598892, + 0.006537519861012697, + 0.004381982143968344, + 0.03955601528286934, + 0.2114696353673935, + 0.031690191477537155, + -0.05438006669282913, + 0.013112856075167656, + 0.041219938546419144, + -0.005327393300831318, + -0.01223362423479557, + 0.025242485105991364, + -0.056270889937877655, + -0.046552058309316635, + 0.015154944732785225, + -0.016459612175822258, + 0.00955338217318058, + 0.013727374374866486, + 0.03424280136823654, + 0.004329984541982412, + -0.024675238877534866, + 0.015438568778336048, + 0.08584335446357727, + 0.012999407015740871, + 0.016686512157320976, + -0.009118493646383286, + -0.004190536215901375, + 0.005601562559604645, + -0.034318435937166214, + -0.01955110765993595, + -0.004864141810685396, + 0.045606646686792374, + 0.02949683740735054, + 0.053396835923194885, + -0.01936202682554722, + 0.030688054859638214, + -0.002644788473844528, + 0.0024911591317504644, + -0.0174617487937212, + -0.014861867763102055, + -0.025488292798399925, + -0.06754019111394882, + -0.011590744368731976, + 0.018123537302017212, + 0.02720894105732441, + -0.009737737476825714, + 0.0340726263821125, + 0.0259799063205719, + -0.01553311012685299, + -0.011316575109958649, + 0.017471203580498695, + -0.03048006445169449, + -0.04371582344174385, + -0.022954588755965233, + -0.022028086706995964, + 0.024372706189751625, + 0.02620680443942547, + -0.023086946457624435, + 0.019967088475823402, + -0.03685213625431061, + -0.005171400494873524, + -0.010541337542235851, + 0.0012302165850996971, + 0.06027943268418312, + 0.029875000938773155, + 0.03199272230267525, + -0.0051146759651601315, + 0.03204944729804993, + -0.0076814680360257626, + 0.0007687376928515732, + 0.029515745118260384, + -0.02446724846959114, + 0.03348647430539131, + 0.02340838685631752, + 0.03902658447623253, + 0.013377571478486061, + 0.01896495372056961, + 0.020515428856015205, + 0.010938410647213459, + -0.0005574973183684051, + 0.02427816577255726, + 0.021876821294426918, + 0.016128718852996826, + 0.05600617453455925, + -0.011921637691557407, + -0.02773837186396122, + -0.07733465731143951, + 0.007166218478232622, + 0.020969225093722343, + -0.04950174316763878, + -0.04844288155436516, + 0.07752373814582825, + -0.0036587421782314777, + -0.03898876905441284, + -0.01647852174937725, + 0.049010127782821655, + -0.0048286886885762215, + -0.019626740366220474, + 0.05732974782586098, + -0.020628876984119415, + 0.07241851836442947, + 0.0036209258250892162, + -0.036549605429172516, + -0.016610879451036453, + -0.0497286394238472, + -0.026225712150335312, + 0.01734829880297184, + -0.0354718379676342, + -0.026433704420924187, + -0.005355755798518658, + -0.023673102259635925, + -0.0011675831628963351, + -0.0009330029133707285, + 0.005828461609780788, + 0.01135439146310091, + 0.011278758756816387, + -0.059371836483478546, + 0.010787144303321838, + 0.01670541986823082, + 0.008470886386930943, + -0.005596835631877184, + 0.005970273166894913, + -0.016270531341433525, + 0.026055539026856422, + 0.014701147563755512, + 0.004741238430142403, + 0.02008053846657276, + 0.05604398995637894, + 0.004296895116567612, + -0.002104722196236253, + 0.016043631359934807, + -0.019182397052645683, + -0.009676286019384861, + -0.01740502379834652, + 0.02580973133444786, + -0.019570017233490944, + 0.04764873534440994, + -0.022746598348021507, + 0.04935047775506973, + -0.009510839357972145, + 0.014578244648873806, + 0.017660286277532578, + -0.0019392751855775714, + 0.02645261213183403, + 0.008243987336754799, + -0.06999826431274414, + -0.00033325751428492367, + 0.010739874094724655, + 0.013169581070542336, + 0.03482895717024803, + -0.0050059533677995205, + -0.01709303818643093, + -0.021971361711621284, + 0.016941772773861885, + 0.0410686731338501, + 0.026698417961597443, + 0.04243006557226181, + -0.049426108598709106, + -0.03530166298151016, + -0.021631013602018356, + -0.038648419082164764, + 0.022860048338770866, + 0.02896740660071373, + -0.0329570434987545, + 0.0008916411316022277, + 0.025677373632788658, + 0.05101440101861954, + 0.0709436759352684, + 0.057443197816610336, + -0.0075018396601080894, + -0.019702374935150146, + 0.008073813281953335, + -0.02323821373283863, + 0.0043016220442950726, + 0.005232852417975664, + -0.018671875819563866, + -0.01896495372056961, + 0.012696875259280205, + -0.003824189305305481, + -0.021498655900359154, + -0.040463607758283615, + 0.06292658299207687, + -0.008726147934794426, + 0.00958174467086792, + 0.008849050849676132, + -0.021044857800006866, + -0.025355935096740723, + -0.02193354442715645, + 0.041219938546419144, + 0.03013971634209156, + 0.03628489002585411, + -0.03866732865571976, + 0.03148220106959343, + -0.006480795331299305, + -0.06251060217618942, + 0.0854651927947998, + 0.028248893097043037, + -0.01910676434636116, + 0.02620680443942547, + -0.05116566643118858, + 0.019380934536457062, + 0.021555380895733833, + 0.0031009495723992586, + -0.0020385433454066515, + -0.021801186725497246, + 0.013935364782810211, + -0.015400752425193787, + -0.0027086036279797554, + -0.001123857800848782, + 0.022028086706995964, + 0.01639343425631523, + 0.01609090156853199, + -0.016998497769236565, + -0.02265205793082714, + -0.0029922272078692913, + -0.04299731180071831, + -0.021460838615894318, + 0.017282120883464813, + -0.04364019259810448, + -0.019475474953651428, + 0.06614098697900772, + 0.03450751677155495, + -1.5242912922985852e-05, + -0.016941772773861885, + 0.0027251483406871557, + 0.03061242215335369, + 0.03271123394370079, + -0.051695097237825394, + -0.011023497208952904, + 0.017527928575873375, + 0.027133308351039886, + -0.027757279574871063, + 0.023313846439123154, + 0.017887184396386147, + -0.01006863173097372, + -0.030536789447069168, + -0.022084811702370644, + -0.0037651010788977146, + 0.04095522314310074, + -0.06035506725311279, + 0.015485838986933231, + 0.014285166747868061, + 0.0011563563020899892, + -0.02253860794007778, + -0.005549564957618713, + -0.015079312026500702, + 0.0031553106382489204, + 0.012895411811769009, + 0.03948038071393967, + 0.04492595046758652, + -0.006863687187433243, + -0.02352183684706688, + 0.018331527709960938, + 0.0300262663513422, + 0.004287440795451403, + 0.004887776914983988, + -0.0340726263821125, + -0.024958861991763115, + 0.0438670888543129, + 0.03278686851263046, + 0.020742326974868774, + -0.013519383035600185, + -0.06307785212993622, + -0.04855633154511452, + -0.004703422077000141, + 0.036133624613285065, + -0.03594454377889633, + 0.0012633060105144978, + -0.06288877129554749, + -0.0413333885371685, + 0.01810462959110737, + -0.06330475211143494, + 0.000763419724535197, + -0.027171123772859573, + 0.0096384696662426, + -0.009543928317725658, + -0.012971044518053532, + -0.03136875107884407, + 0.058426424860954285, + 0.03386463597416878, + -0.007010225672274828, + -0.05173291265964508, + 0.05850205942988396, + 0.03488568216562271, + -0.011751463636755943, + 0.046438608318567276, + 0.039934176951646805, + 0.04927484318614006, + -0.043980538845062256, + -0.00198654574342072, + 0.01614762656390667, + 0.0009625470265746117, + 0.03339193016290665, + -0.0865996852517128, + 0.021252848207950592, + 0.007208762224763632, + -0.03583109378814697, + 0.04904794320464134, + 0.006003362592309713, + 0.008792325854301453, + -0.0311418529599905, + 0.01097622700035572, + -0.02458069659769535, + 0.018085720017552376, + -0.017669739201664925, + -0.011430024169385433, + -0.039820730686187744, + -0.04084177315235138, + -0.005908821243792772, + -0.003512203460559249, + -0.00965265091508627, + -0.0047388747334480286, + 0.0592205710709095, + -0.0059135486371815205, + -0.021517563611268997, + -0.04401835426688194, + 0.04284604638814926, + 0.04632515832781792, + -0.011458386667072773, + -0.018482793122529984, + 0.027927452698349953, + -0.06493085622787476, + 0.0351882129907608, + 0.0034814774990081787, + 0.03804335743188858, + 0.025885364040732384, + -0.04159810394048691, + 0.008589062839746475, + -0.0035500198137015104, + -0.008442523889243603, + 0.005483386106789112, + -0.026320254430174828, + 0.008669422939419746, + -0.027492564171552658, + -0.012148536741733551, + -0.015495292842388153, + -0.029648102819919586, + -0.006665150634944439, + 0.05721629783511162, + 0.026603877544403076, + 0.015240032225847244, + -0.024429431185126305, + 0.04295949637889862, + -0.04927484318614006, + -0.05165728181600571, + -0.036719780415296555, + 0.036833230406045914, + -0.04791345074772835, + -0.02650933712720871, + 0.020855776965618134, + -0.0036776503548026085, + 0.006182990502566099, + -0.029893908649683, + 0.007118948269635439, + 0.0009324120474047959, + 0.04556883126497269, + -0.024202533066272736, + -0.07865823060274124, + -0.004027452785521746, + -0.004242533817887306, + -0.03898876905441284, + -0.006078995298594236, + 0.033618830144405365, + -0.013245213776826859, + -0.01378409843891859, + 0.01681886985898018, + -0.014842959120869637, + 0.0032687599305063486, + -0.04700585454702377, + 0.009071222506463528, + 0.026471519842743874, + 0.030045175924897194, + 0.006863687187433243, + -0.03429952636361122, + 0.018842048943042755, + -0.01849224790930748, + 0.004533248022198677, + -0.021574288606643677, + -0.023673102259635925, + -0.010730419307947159, + 0.012243078090250492, + -0.03978291153907776, + 0.03781645745038986, + 0.047724369913339615, + -0.03592563420534134, + -0.021215032786130905, + 0.014757872559130192, + -0.040652692317962646, + 0.004173991270363331, + -0.04352674260735512, + -0.028116535395383835, + -0.009619561024010181, + 0.011836551129817963, + 0.022897865623235703, + -0.05528765916824341, + -0.025355935096740723, + -0.017442841082811356, + 0.017111947759985924, + -0.16896392405033112, + 0.029856093227863312, + 0.016194898635149002, + 0.016866140067577362, + -0.04326202720403671, + -0.013509929180145264, + -0.05611962080001831, + 0.006154628470540047, + 0.014616061002016068, + -0.021290665492415428, + 0.0066131530329585075, + -0.04564446210861206, + 0.06096012890338898, + -0.03384573012590408, + -0.027416931465268135, + 0.010229351930320263, + 0.006901503540575504, + 0.057027217000722885, + -0.05388845130801201, + 0.06186772510409355, + 0.009699921123683453, + -0.01977800764143467, + -0.0142473503947258, + -0.0002583632303867489, + -0.017244303598999977, + -0.01770755648612976, + 0.019796915352344513, + 0.03055569715797901, + -0.030158624053001404, + 0.05131693184375763, + 0.0026967860758304596, + 0.02441052347421646, + 0.019182397052645683, + 0.041749369353055954, + 0.03246542811393738, + 0.0048452336341142654, + -0.0012266712728887796, + -0.03808117285370827, + -0.0015800188994035125, + -0.01989145576953888, + -0.021044857800006866, + 0.02153647318482399, + -0.01650688424706459, + -0.01559928897768259, + 0.004192899446934462, + 0.09136456251144409, + -0.028929589316248894, + -0.003526384709402919, + -0.02592318132519722, + 0.03384573012590408, + 0.015240032225847244, + 0.03781645745038986, + 0.009520293213427067, + 0.011524565517902374, + -0.017631923779845238, + -0.005559019278734922, + 0.01158128958195448, + -0.019031131640076637, + -0.024032358080148697, + 0.014776780270040035, + 0.014086630195379257, + -0.019314754754304886, + -0.03161455690860748, + -0.0729101300239563, + -0.017074130475521088, + 0.006750237662345171, + -0.07007389515638351, + -0.007246578577905893, + -0.025091219693422318, + -0.013349208980798721, + -0.025885364040732384, + 0.029950633645057678, + 0.026887500658631325, + -0.0005920638795942068, + -0.012838686816394329, + 0.048064716160297394, + 0.03757065162062645, + 0.01751847378909588, + -0.013821914792060852, + -0.026244621723890305, + -0.027019858360290527, + -0.011808188632130623, + -0.0006871959194540977, + -0.03278686851263046, + 0.035377293825149536, + 0.013056132011115551, + -0.025960998609662056, + -0.012469977140426636, + -0.0031482200138270855, + -0.0007728738128207624, + -0.08077595382928848, + 0.015088766813278198, + 0.056497786194086075, + 0.01623271405696869, + -0.009293394163250923, + 0.06659477949142456, + -0.01989145576953888, + -0.008598516695201397, + -0.015192762017250061, + -0.0026802413631230593, + 0.00839525368064642, + -0.001349574769847095, + 0.02866487391293049, + 0.005842642392963171, + -0.025942089036107063, + 0.0029638647101819515, + -0.024240348488092422, + -0.03524493798613548, + 0.021876821294426918, + -0.010720965452492237, + -0.005984454415738583, + -0.025771915912628174, + -0.04863196238875389, + 0.008239260874688625, + -0.06856123358011246, + -0.03305158391594887, + -0.032162897288799286, + 0.03318393975496292, + -0.0441318042576313, + -0.02000490576028824, + 0.03225743770599365, + 0.03131202608346939, + 0.048896677792072296, + -0.03499913215637207, + 0.024297073483467102, + 0.000977909890934825, + 0.030101899057626724, + 0.015882911160588264, + 0.018000634387135506, + -0.006197171751409769, + -0.006892049219459295, + -0.00835270993411541, + 0.02195245400071144, + 0.039593830704689026, + -0.010238805785775185, + 0.00586627796292305, + 0.0156465582549572, + 0.005800099112093449, + -0.015230578370392323, + -0.031690191477537155, + 0.006849505938589573, + -0.028986314311623573, + 0.02253860794007778, + -0.01421898789703846, + -0.014795688912272453, + -0.019872548058629036, + 0.018331527709960938, + -0.01570328325033188, + -0.019116219133138657, + -0.011864913627505302, + 0.002848051954060793, + 0.00756329158321023, + 0.032919224351644516, + 0.06387199461460114, + -0.01949438452720642, + -0.013112856075167656, + 0.004374891519546509, + 0.022311709821224213, + 0.01765083149075508, + 0.02304913103580475, + -0.034564241766929626, + -0.00717094587162137, + -0.05332120507955551, + -0.05154383182525635, + -0.003493295283988118, + 0.022444067522883415, + 0.037589557468891144, + -0.0087970532476902, + -0.06220807135105133, + 0.004157446790486574, + 0.009151582606136799, + 0.06288877129554749, + -0.030820412561297417, + 0.011902729980647564, + 0.003717830404639244, + -0.056157439947128296, + 0.024883229285478592, + 0.0030016812961548567, + 0.02505340240895748, + -0.026717327535152435, + 0.025185760110616684, + -0.01331139262765646, + 0.005445569753646851, + 0.02475087158381939, + 0.024202533066272736, + 0.036833230406045914, + -0.002345802029594779, + 0.023427294567227364, + -0.011184217408299446, + -0.01375573594123125, + 0.02312476374208927, + -0.029515745118260384, + -0.05910712108016014, + -0.017631923779845238, + 0.01743338629603386, + -0.024486156180500984, + -0.0026613331865519285, + 0.01509822066873312, + -0.011042405851185322, + 0.03392136096954346, + -0.036247074604034424, + -0.04787563532590866, + 0.030064083635807037, + -0.022670965641736984, + 0.005308485124260187, + 0.014786235056817532, + -0.027284573763608932, + 0.009671558625996113, + -0.0360390841960907, + 0.02153647318482399, + -0.05188417807221413, + -0.008995589800179005, + 0.011051859706640244, + -0.0006470159278251231, + -0.020269621163606644, + 0.02229280211031437, + 0.011108584702014923, + -0.013736828230321407, + -0.009841732680797577, + 0.034148260951042175, + -0.0014807506231591105, + -0.0018388251774013042, + 0.013500475324690342, + -0.026849685236811638, + -0.060014717280864716, + -0.008404707536101341, + 0.011212579905986786, + 0.02047761157155037, + -0.0016426523216068745, + 0.0483294315636158, + 0.022444067522883415, + 0.036719780415296555, + -0.03861060366034508, + 0.037362661212682724, + -0.006286986172199249, + -0.02773837186396122, + 0.033448655158281326, + 0.019985998049378395, + -0.03745720162987709, + -0.005204489920288324, + 0.016487974673509598, + -0.019314754754304886, + -0.0555901937186718, + -0.008636333048343658 + ], + "key": "Persistence Demonstration", + "status": "activated" + } + }, + { + "id": "6c0c977f-2e75-4e3a-a661-88674da5b14e", + "memory": "On January 13, 2026, at 8:51 PM, the user created a test memory for a demonstration purpose.", + "metadata": { + "sources": [ + "\"{\\\"type\\\": \\\"chat\\\", \\\"role\\\": \\\"user\\\", \\\"chat_time\\\": \\\"08:51 PM on 13 January, 2026\\\", \\\"content\\\": \\\"This is a test memory for dump example\\\", \\\"lang\\\": \\\"en\\\"}\"", + "\"{\\\"type\\\": \\\"chat\\\", \\\"role\\\": \\\"user\\\", \\\"chat_time\\\": \\\"08:51 PM on 13 January, 2026\\\", \\\"content\\\": \\\"Another memory to demonstrate persistence\\\", \\\"lang\\\": \\\"en\\\"}\"" + ], + "confidence": 0.99, + "usage": [], + "created_at": "2026-01-13T20:51:42.359643000+00:00", + "session_id": "default_session", + "memory_type": "UserMemory", + "type": "fact", + "tags": [ + "test", + "memory", + "demonstration" + ], + "updated_at": "2026-01-13T20:51:42.396236000+00:00", + "user_id": "example_user", + "background": "On January 13, 2026, at 8:51 PM, the user engaged in a memory demonstration by creating a test memory example and another memory to illustrate the concept of persistence. These actions reflect the user's interest in exploring and demonstrating memory-related concepts.", + "file_ids": [], + "embedding": [ + -0.023225771263241768, + 0.009711744263768196, + 0.01401975005865097, + -0.023113388568162918, + -0.044953107833862305, + -0.025454696267843246, + 0.004780950024724007, + 0.012184164486825466, + 0.003397237276658416, + 0.006766378879547119, + 0.033059265464544296, + -0.0018625102238729596, + -0.00135678774677217, + -0.0159396231174469, + -0.0017864176770672202, + 0.03302180394530296, + 0.05941302329301834, + -0.013467201963067055, + -0.011341294273734093, + -0.03324656933546066, + 0.01599581353366375, + -0.05263259634375572, + 0.07222465425729752, + 0.022851161658763885, + -0.007220592815428972, + 0.0017969536129385233, + -0.012418295256793499, + 0.013214340433478355, + 0.08645980805158615, + 0.0018215373856946826, + 0.02071589045226574, + -0.028620144352316856, + -0.015490091405808926, + -0.025454696267843246, + -0.04469088092446327, + -0.02105303853750229, + 0.027945848181843758, + 3.424162423470989e-05, + -0.028526492416858673, + -0.019479678943753242, + -0.008882921189069748, + 0.012596234679222107, + 0.015480726025998592, + 0.006949000991880894, + 0.015499456785619259, + 0.014825159683823586, + -0.012549408711493015, + -0.02382514625787735, + -0.025342313572764397, + -0.013364183716475964, + 0.002884491113945842, + 0.03133606165647507, + 0.04525279253721237, + -0.037179965525865555, + 0.027009325101971626, + 0.021689873188734055, + -0.05034748092293739, + -0.043342288583517075, + -0.019816827028989792, + 0.007492184638977051, + -0.03575645014643669, + 0.007862110622227192, + 0.0021774161141365767, + 0.01226845197379589, + -0.013504662550985813, + 0.03937143087387085, + 0.0068834442645311356, + 0.0019292375072836876, + -0.00272059952840209, + -0.023169580847024918, + 0.0013368866639211774, + 0.04581470787525177, + -0.05514247715473175, + -0.01210924331098795, + -0.0809905156493187, + 0.01955460198223591, + 0.0017419328214600682, + -0.015677396208047867, + -0.009426104836165905, + 0.021408917382359505, + 0.03892189636826515, + -0.022476553916931152, + 0.01390736736357212, + -0.0002572511730249971, + 0.047350604087114334, + 0.01260560005903244, + -0.06349626183509827, + 0.057502515614032745, + 0.040345411747694016, + -0.04274291172623634, + 0.028788719326257706, + 0.0003658293280750513, + 0.010807476006448269, + -0.02504262700676918, + 0.004296299535781145, + 0.010404771193861961, + -0.05158368870615959, + 0.003305926453322172, + 0.029069675132632256, + 0.011032241396605968, + 0.05813935026526451, + 0.022532744333148003, + 0.02037874236702919, + -0.017878225073218346, + -0.0010945613030344248, + -0.028788719326257706, + 0.02927570976316929, + 0.014375628903508186, + -0.009627456776797771, + 0.0005191849777474999, + 0.001597942435182631, + 0.04281783476471901, + 0.04918619245290756, + 0.01210924331098795, + 0.04203115403652191, + 0.013766888529062271, + 0.013485931791365147, + -0.01013317983597517, + -0.05083446949720383, + -0.014778333716094494, + 0.017484884709119797, + 0.014703411608934402, + 0.038341253995895386, + -0.03693646937608719, + -0.06076161563396454, + -0.014787699095904827, + -0.01294274814426899, + -0.023019736632704735, + -0.0010770015651360154, + -0.004511700011789799, + 0.016042640432715416, + -0.000730487983673811, + 0.00883141253143549, + -0.008058780804276466, + -0.026971863582730293, + -0.021614952012896538, + 0.011247641406953335, + 0.05281990021467209, + -0.010498423129320145, + -0.03399578854441643, + 0.020341280847787857, + -0.003252076217904687, + -0.008681568317115307, + -0.026859480887651443, + 0.015930257737636566, + -0.02498643472790718, + 0.005469294730573893, + -0.003645415883511305, + 0.02721535973250866, + 0.001160117913968861, + -0.01229654811322689, + 0.019891750067472458, + -0.02288862317800522, + -0.04469088092446327, + -0.022851161658763885, + -0.003551763715222478, + 0.01916126161813736, + 0.06192290410399437, + -0.01468468178063631, + 0.012624330818653107, + -0.0015429217601194978, + -0.048511892557144165, + -0.06076161563396454, + 0.0465264655649662, + 0.02032255008816719, + 0.02860141359269619, + 0.013457836583256721, + 0.025248661637306213, + -0.0460769347846508, + 0.03639328479766846, + 0.002751036547124386, + -0.008306959643959999, + -0.008747125044465065, + -0.008157115429639816, + -0.008611329831182957, + 0.033845942467451096, + 0.038734592497348785, + -0.000227984826778993, + -0.01032984908670187, + -0.0321040116250515, + -0.05158368870615959, + 0.0031490586698055267, + 0.030287155881524086, + 0.013794984668493271, + -0.04135685786604881, + -0.003430015640333295, + -0.012390200048685074, + 0.004427412524819374, + 0.015049925073981285, + 0.01107906736433506, + 0.008161798119544983, + -0.03180432319641113, + -0.000778484798502177, + 0.00315842404961586, + -0.005722155794501305, + -0.027908386662602425, + -0.0014211736852303147, + 0.0008768197149038315, + -0.02448071353137493, + 0.005408420693129301, + -0.011060337536036968, + 0.035737719386816025, + 0.015668030828237534, + 0.02127780392765999, + -0.01746615581214428, + -0.013823079876601696, + -0.01416022889316082, + 0.0026854798197746277, + 0.0031677891965955496, + -0.0812152773141861, + -0.024836590513586998, + 0.0003201738290954381, + -0.016014544293284416, + -0.011032241396605968, + 0.02238290011882782, + -0.013261166401207447, + -0.0022523379884660244, + -0.005698742810636759, + 0.012764809653162956, + -0.015499456785619259, + -0.05371896177530289, + 0.04941095784306526, + -0.017447425052523613, + 0.030343346297740936, + 0.030811607837677002, + -0.01826220005750656, + 0.008536407724022865, + 0.05016017332673073, + 0.02848903089761734, + -0.0326659232378006, + 0.026110263541340828, + 0.018721096217632294, + 0.012015590444207191, + -0.007585836574435234, + 0.03513834625482559, + -0.020847003906965256, + -0.04154416173696518, + 0.0050150807946920395, + 0.02605407126247883, + 0.0016857414739206433, + -0.01627677120268345, + 0.004181575495749712, + 0.01961079239845276, + 0.018365217372775078, + -0.04154416173696518, + -0.026241375133395195, + 0.0030554065015167, + 0.01035794522613287, + 0.02227051742374897, + 0.01488135103136301, + 0.01074191927909851, + 0.007899572141468525, + -0.05918825790286064, + -0.001568676088936627, + 0.01715710200369358, + 0.009051495231688023, + 0.029032215476036072, + -0.006073351949453354, + 0.03877205401659012, + -0.0013439105823636055, + 0.04064510017633438, + -0.03774188086390495, + 0.025810575112700462, + 0.03341514244675636, + 0.022944815456867218, + -0.019854288548231125, + -0.019535871222615242, + -0.013411009684205055, + 0.014591028913855553, + -0.008742442354559898, + 0.02993127703666687, + -0.05525486171245575, + -0.02365657314658165, + 0.03487611934542656, + -0.015705492347478867, + 0.008349102921783924, + -0.02970651164650917, + 5.427992618933786e-06, + -0.020584776997566223, + 0.038846977055072784, + 0.016632650047540665, + -0.026409950107336044, + 0.031298600137233734, + -0.0122216260060668, + 0.0071503533981740475, + -0.017335042357444763, + -0.027796003967523575, + -0.027140438556671143, + 0.03952127322554588, + -0.019704444333910942, + -0.019460948184132576, + 0.01024556253105402, + 0.06357118487358093, + -0.04360451176762581, + -0.018206007778644562, + -0.021952100098133087, + 0.00883141253143549, + -0.15463869273662567, + -0.008232037536799908, + -0.013879271224141121, + -0.0018063188763335347, + -0.014413089491426945, + 0.016632650047540665, + -0.04682615399360657, + -0.0486617386341095, + -0.010479693301022053, + 0.08968144655227661, + -0.005267942324280739, + -0.04244322329759598, + 0.017306946218013763, + 0.026353757828474045, + -0.025866767391562462, + -0.005651916842907667, + -0.03865967318415642, + -0.027908386662602425, + -0.024312138557434082, + -0.011931303888559341, + 0.010030161589384079, + -0.02148383855819702, + 0.05424341559410095, + -0.01921745389699936, + -0.002258191118016839, + -0.00631684809923172, + 0.04941095784306526, + 0.009739839471876621, + -0.020734621211886406, + 0.002176245441660285, + -0.014169593341648579, + 0.04128193482756615, + -0.006579074542969465, + -0.005895412527024746, + -0.008999986574053764, + 0.05971270799636841, + -0.0005150876822881401, + 0.007473453879356384, + 0.011453676968812943, + -0.020416202023625374, + 0.015396438539028168, + 0.066230908036232, + -0.03858475014567375, + 0.045964550226926804, + 0.03455770015716553, + 0.0163891538977623, + -0.004703687038272619, + -0.012184164486825466, + -0.0476502925157547, + -0.011369389481842518, + -0.007332975510507822, + -0.020022863522171974, + -0.015096751973032951, + -0.036505669355392456, + -0.020528584718704224, + -0.013401645235717297, + -0.054955173283815384, + 0.017035353928804398, + -0.08526106178760529, + 0.021614952012896538, + -0.0310363732278347, + -0.05192083865404129, + -0.010760650038719177, + 0.040345411747694016, + -0.02970651164650917, + 0.00763734569773078, + 0.04030795395374298, + -0.06394579261541367, + -0.0025051990523934364, + -0.03637455403804779, + 0.04847443476319313, + -0.018449503928422928, + 0.012736713513731956, + 0.001112121157348156, + 0.021352725103497505, + 0.06166067719459534, + 0.002046302892267704, + -0.03247861936688423, + 0.011013510636985302, + -0.08885730803012848, + -0.027796003967523575, + 0.053681500256061554, + -0.015452630817890167, + -0.03388340398669243, + -0.01715710200369358, + 0.00902808178216219, + -0.01121954619884491, + 0.008096241392195225, + 0.04113209247589111, + 0.20933163166046143, + -0.0004925525863654912, + -0.0620727464556694, + -0.013055131770670414, + 0.03787299245595932, + -0.010076988488435745, + -0.053606580942869186, + 0.01327053178101778, + -0.04233084246516228, + -0.04536517709493637, + 0.020285088568925858, + -0.0007509744027629495, + 0.01352339331060648, + 0.010208101011812687, + 0.0115192336961627, + -0.0243870597332716, + -0.01263369619846344, + -0.007501549553126097, + 0.08908206969499588, + 0.016585823148489, + 0.035793911665678024, + -0.014338168315589428, + -0.001372006256133318, + -0.001101585221476853, + -0.04525279253721237, + -0.02648487128317356, + -0.00762329762801528, + 0.07971683889627457, + -0.012708617374300957, + 0.056565992534160614, + -0.018917765468358994, + 0.011697173118591309, + 0.007997906766831875, + 0.004799680784344673, + 0.023469267413020134, + 0.009664918296039104, + 0.007894889451563358, + -0.04281783476471901, + -0.017569173127412796, + 0.02921951934695244, + 0.040794942528009415, + -0.023787684738636017, + 0.013841810636222363, + 0.04124447703361511, + -0.002535636071115732, + 0.01271798275411129, + 0.011978129856288433, + -0.02232670970261097, + -0.04135685786604881, + -0.002619923325255513, + -0.03480119630694389, + 0.016838684678077698, + 0.0310363732278347, + -0.016005178913474083, + 0.013682601973414421, + -0.006705504842102528, + -0.011097798123955727, + -0.02687821164727211, + 0.002102494239807129, + 0.03644947707653046, + 0.03888443857431412, + 0.0315420962870121, + -0.028751257807016373, + 0.051995761692523956, + -0.014937542378902435, + 0.0018285613041371107, + 0.0020779105834662914, + -0.05240783095359802, + 0.03425801172852516, + 0.026953132823109627, + 0.06267212331295013, + 0.010020796209573746, + 0.03259100392460823, + 0.0234318058937788, + 0.008007272146642208, + 0.012689887546002865, + 0.03985841944813728, + 0.05488025024533272, + 0.021858448162674904, + 0.07214973866939545, + 0.0159115269780159, + -0.020453663542866707, + -0.04027049243450165, + 0.008372516371309757, + 0.005876682233065367, + -0.05701552331447601, + -0.024143563583493233, + 0.052445292472839355, + -0.024518173187971115, + -0.03463262319564819, + -0.0329468809068203, + 0.045739784836769104, + -0.025510888546705246, + -0.027833465486764908, + 0.048174746334552765, + 0.0156586654484272, + 0.04124447703361511, + -0.0003596833848860115, + -0.029743971303105354, + 0.0014972662320360541, + -0.05083446949720383, + -0.02843284048140049, + 0.013663871213793755, + -0.0015663348603993654, + -0.010320483706891537, + -0.03315291553735733, + -0.028414109721779823, + -0.003565811552107334, + 0.008011954836547375, + 0.012764809653162956, + -0.0057455687783658504, + 0.03433293476700783, + -0.07361071556806564, + -0.04446611553430557, + -0.0036758529022336006, + 0.003003897611051798, + -0.014619125053286552, + 0.009084274061024189, + -0.009491661563515663, + 0.047425527125597, + 0.009936509653925896, + 0.00795576348900795, + 0.010620171204209328, + 0.05540470406413078, + 0.009861587546765804, + -0.022364171221852303, + -0.0022628738079220057, + -0.012006225995719433, + 0.004530430305749178, + -0.01372006256133318, + 0.026615984737873077, + -0.036187250167131424, + 0.04094478860497475, + -0.03877205401659012, + 0.02732774242758751, + 0.014862621203064919, + 0.021858448162674904, + 0.01667010970413685, + -0.01502182986587286, + 0.033621177077293396, + 0.0031748132314532995, + -0.09402691572904587, + -0.000989787746220827, + 0.027346473187208176, + 0.025585809722542763, + 0.01667947508394718, + 0.024181025102734566, + -0.02427467703819275, + -0.01249321736395359, + 0.02448071353137493, + 0.03933396935462952, + 0.01710091158747673, + 0.02449944242835045, + -0.05960032716393471, + -0.03335895016789436, + -0.039071742445230484, + -0.04547755792737007, + 0.017475519329309464, + 0.03644947707653046, + -0.04236830398440361, + -0.006752331275492907, + 0.031841784715652466, + 0.03397705778479576, + 0.08226418495178223, + 0.0621851310133934, + -0.04214353859424591, + -0.011397485621273518, + 0.030006198212504387, + 0.0031162805389612913, + -0.023356884717941284, + 0.006532248109579086, + -0.005928190890699625, + -0.016407884657382965, + 0.021184151992201805, + 0.0018777287332341075, + -0.047425527125597, + -0.04903634637594223, + 0.026840750128030777, + -0.021502569317817688, + -0.01077001541852951, + -0.008461485616862774, + -0.02521120011806488, + -0.037685688585042953, + -0.011650347150862217, + 0.02054731547832489, + 0.021090500056743622, + 0.01893649622797966, + -0.028357917442917824, + 0.012689887546002865, + -0.001998306019231677, + -0.08511121571063995, + 0.06967731565237045, + 0.030399538576602936, + -0.015471360646188259, + 0.04203115403652191, + -0.043791819363832474, + 0.02854522317647934, + 0.010301753878593445, + 0.011388120241463184, + 0.022233057767152786, + -0.012661791406571865, + 0.0016037956811487675, + -0.019685715436935425, + -0.01944221928715706, + -0.019292375072836876, + -0.012905287556350231, + 0.009908413514494896, + 0.0161643885076046, + -0.0068834442645311356, + 0.02015397697687149, + -0.018589982762932777, + -0.019966671243309975, + 0.0020123538561165333, + 0.014328802935779095, + -0.050722088664770126, + -0.014890716411173344, + 0.07177512347698212, + 0.044503577053546906, + -0.011921938508749008, + 0.010320483706891537, + -0.014478646218776703, + 0.01338291447609663, + 0.010526519268751144, + -0.01812172122299671, + -0.02142764814198017, + 0.01088239811360836, + 0.00478329136967659, + -0.05225798487663269, + 0.02693440392613411, + 0.022682588547468185, + -0.005764299537986517, + -0.02238290011882782, + -0.024087373167276382, + -0.019311105832457542, + 0.05296974256634712, + -0.0651070848107338, + 0.020809542387723923, + 0.015780413523316383, + -0.024780400097370148, + -0.0027042103465646505, + -0.02914459817111492, + 0.014207054860889912, + 0.020079053938388824, + 0.04768775403499603, + 0.0315982885658741, + 0.03526945784687996, + 0.013439105823636055, + 0.012886556796729565, + 0.007670123595744371, + 0.023974990472197533, + 0.017597267404198647, + 0.007866793312132359, + -0.048174746334552765, + -0.0489988848567009, + 0.040457796305418015, + 0.08016636967658997, + 0.013682601973414421, + -0.018046800047159195, + -0.06683028489351273, + -0.034351665526628494, + -0.006799157243221998, + 0.0028048865497112274, + -0.020341280847787857, + 0.01605200581252575, + -0.04637662321329117, + -0.06993953883647919, + 0.017569173127412796, + -0.06008731946349144, + -0.006916222628206015, + -0.03309672325849533, + -0.027758542448282242, + 0.004675591364502907, + -0.00883141253143549, + -0.03899681940674782, + 0.07012684643268585, + -0.0009002327569760382, + -0.02620391547679901, + -0.025023896247148514, + 0.06802903115749359, + 0.030193503946065903, + -0.00706606637686491, + 0.052332907915115356, + 0.02976270206272602, + 0.03502596169710159, + -0.012886556796729565, + -3.263197504566051e-05, + 0.019179992377758026, + -0.02637248858809471, + 0.017278850078582764, + -0.06031208485364914, + -0.012249721214175224, + 0.00553953368216753, + -0.029182057827711105, + 0.040907327085733414, + -0.010788745246827602, + 0.01755044236779213, + -0.042293380945920944, + 0.02043493278324604, + -0.0234318058937788, + 0.02427467703819275, + -0.030455728992819786, + 0.011584790423512459, + -0.045515019446611404, + -0.015181038528680801, + 0.0005320621421560645, + 0.00795576348900795, + -0.01710091158747673, + 0.017082180827856064, + 0.029687780886888504, + 0.003418309148401022, + 0.020734621211886406, + -0.07994160801172256, + 0.007215910125523806, + 0.022457823157310486, + -0.0006052280077710748, + -0.015817875042557716, + 0.02682201936841011, + -0.058176811784505844, + 0.05413103103637695, + -0.004389951936900616, + 0.03639328479766846, + 0.011172720231115818, + -0.0489988848567009, + -0.005675329826772213, + -0.031111296266317368, + -0.0019268961623311043, + -0.0032825132366269827, + -0.017981242388486862, + 0.036955200135707855, + -0.03377101942896843, + -0.030418269336223602, + 0.003273148089647293, + -0.02464928664267063, + -0.0011630445951595902, + 0.04394166171550751, + 0.020416202023625374, + 0.021034307777881622, + 0.0008352614822797477, + 0.05083446949720383, + -0.03319037705659866, + -0.009290308691561222, + -0.02464928664267063, + 0.04083240404725075, + -0.049785565584897995, + -0.031298600137233734, + 0.02560454048216343, + -0.01760663278400898, + 0.014263246208429337, + -0.01757853850722313, + -0.00598438223823905, + -0.005591042805463076, + 0.02594168856739998, + -0.012867826968431473, + -0.0477626770734787, + 0.033902134746313095, + -0.025061357766389847, + -0.05274497717618942, + 0.031523365527391434, + 0.03970857709646225, + 0.01596771739423275, + 0.013888636603951454, + 0.03877205401659012, + -0.009739839471876621, + -0.009786665439605713, + -0.04761283099651337, + -0.008143068291246891, + 0.032684653997421265, + 0.03822886943817139, + 0.009163877926766872, + -0.028170613572001457, + 0.005843903869390488, + 0.020753350108861923, + -0.007281466852873564, + -0.014216420240700245, + -0.014057210646569729, + -0.006424548104405403, + -0.011172720231115818, + -0.03332148864865303, + 0.03974603861570358, + 0.013757524080574512, + -0.015012464486062527, + 0.0028165930416435003, + 0.01327053178101778, + -0.019910480827093124, + 0.006625900510698557, + -0.022626396268606186, + -0.011912573128938675, + -0.02537977509200573, + -0.024574365466833115, + 0.007300197146832943, + -0.023169580847024918, + -0.047425527125597, + 0.0003184178494848311, + 0.02537977509200573, + -0.16213087737560272, + 0.02176479622721672, + 0.0014211736852303147, + 0.0010805134661495686, + -0.021952100098133087, + -0.02803950011730194, + -0.036280903965234756, + -0.023281963542103767, + 0.028245534747838974, + -0.02571692317724228, + 0.011734633706510067, + -0.03586883470416069, + 0.035793911665678024, + -0.030736686661839485, + -0.02288862317800522, + 0.02682201936841011, + 0.012006225995719433, + 0.04476580023765564, + -0.06004985794425011, + 0.09335261583328247, + -0.005075954832136631, + -0.030418269336223602, + -0.004537454340606928, + 0.005057224538177252, + -0.048624277114868164, + -0.0246118251234293, + 0.031017644330859184, + 0.02798330970108509, + -0.03510088473558426, + 0.03560660779476166, + -0.02120288275182247, + 0.031298600137233734, + 0.02449944242835045, + 0.05858888104557991, + 0.03335895016789436, + -0.01662328466773033, + 0.011725268326699734, + -0.04349213093519211, + -0.015340247191488743, + -0.00708011444658041, + -0.05031001940369606, + 0.01857125200331211, + -0.009627456776797771, + -0.015265326015651226, + 0.03616851940751076, + 0.06383340805768967, + -0.027833465486764908, + 0.009430787526071072, + -0.037685688585042953, + 0.02260766737163067, + -0.012202895246446133, + 0.021614952012896538, + -0.009009351953864098, + -0.009674282744526863, + -0.02116542123258114, + -0.017953146249055862, + -0.01185638178139925, + -0.013869906775653362, + -0.011453676968812943, + 0.016951067373156548, + -0.01976063661277294, + -0.012540043331682682, + -0.0244432520121336, + -0.042068615555763245, + -0.018955226987600327, + 0.011697173118591309, + -0.06926524639129639, + 0.0025239295791834593, + -0.015920892357826233, + 0.009945875033736229, + -0.035119615495204926, + 0.027009325101971626, + 0.02015397697687149, + -0.009777300991117954, + -0.015977082774043083, + 0.05308212712407112, + 0.06327150017023087, + 0.021558761596679688, + 0.017091546207666397, + -0.01766282506287098, + -0.013336088508367538, + 0.005932873580604792, + -0.0006385916494764388, + -0.015649300068616867, + 0.015049925073981285, + 0.03538184240460396, + -0.005164924543350935, + 0.003172471886500716, + -0.03903428092598915, + -0.01271798275411129, + -0.09005605429410934, + -0.008620694279670715, + 0.045664865523576736, + 0.003343387274071574, + -0.0031935435254126787, + 0.08196450024843216, + -0.023019736632704735, + -0.03611232712864876, + -0.037123773247003555, + -0.014216420240700245, + -0.009983335621654987, + 0.02026635967195034, + 0.00901871733367443, + 0.027964578941464424, + 0.009561900049448013, + 0.0246118251234293, + -0.01416022889316082, + -0.039558734744787216, + 0.006003112997859716, + 0.024087373167276382, + -0.036131057888269424, + -0.04008318483829498, + -0.04064510017633438, + -0.01315814908593893, + -0.08001653105020523, + -0.01819664239883423, + -0.020228898152709007, + 0.014759602956473827, + -0.05536724254488945, + -0.021577490493655205, + 0.035962484776973724, + 0.008822047151625156, + 0.01771901547908783, + -0.027908386662602425, + 0.019854288548231125, + 0.01024556253105402, + 0.029800163581967354, + 0.002376427175477147, + -0.007960446178913116, + 0.005197702907025814, + -0.019236182793974876, + 0.000641518272459507, + 0.04941095784306526, + 0.059113334864377975, + -0.0018589982064440846, + -0.006073351949453354, + -0.012024955824017525, + 0.013420375064015388, + -0.05192083865404129, + -0.03547549247741699, + -0.011425580829381943, + -0.008737759664654732, + 0.024836590513586998, + -0.014075941406190395, + -0.008587916381657124, + 0.013195609673857689, + 0.032628461718559265, + 0.003600931027904153, + -0.021633682772517204, + -0.0024490077048540115, + 0.018814748153090477, + -0.010835572145879269, + 0.036730434745550156, + 0.056116461753845215, + -0.047238223254680634, + 0.013729427941143513, + -0.006794474553316832, + 0.02987508475780487, + 0.008246085606515408, + 0.032347507774829865, + -0.04191877320408821, + 0.03465135395526886, + -0.061061304062604904, + -0.030792877078056335, + 0.013111323118209839, + 0.03854728862643242, + 0.03127986937761307, + 0.006546296179294586, + -0.062447357922792435, + 0.021970830857753754, + 0.021408917382359505, + 0.04547755792737007, + -0.034070707857608795, + -0.003069454338401556, + 0.006246608681976795, + -0.03761076554656029, + 0.017119640484452248, + 0.03736726939678192, + 0.018608713522553444, + -0.030774148181080818, + 0.021408917382359505, + -0.015321517363190651, + 0.019704444333910942, + 0.009730474092066288, + 0.02082827314734459, + 0.017110276967287064, + -0.012146703898906708, + 0.018589982762932777, + -0.006349626462906599, + 0.01249321736395359, + 0.025248661637306213, + -0.02309465780854225, + -0.053681500256061554, + -0.03335895016789436, + 0.04158162325620651, + -0.02916332706809044, + -0.02815188281238079, + 0.026110263541340828, + -0.014825159683823586, + 0.06844110786914825, + -0.04536517709493637, + -0.03854728862643242, + 0.013261166401207447, + -0.049785565584897995, + 0.008058780804276466, + 0.020453663542866707, + -0.010535884648561478, + 0.019517140462994576, + -0.04693853482604027, + 0.016342326998710632, + -0.020640967413783073, + -0.01554628275334835, + 0.017896955832839012, + 0.012184164486825466, + -0.02148383855819702, + 0.01065763272345066, + 0.0030835021752864122, + 0.019348565489053726, + -0.02071589045226574, + 0.05364403873682022, + -0.017054084688425064, + -0.004036414436995983, + 0.026335028931498528, + -0.03764822706580162, + -0.0230384673923254, + 0.00017208610370289534, + -0.0007825820939615369, + 0.0464140810072422, + 0.02110922895371914, + 0.048849042505025864, + 0.021633682772517204, + 0.024349600076675415, + -0.02910713665187359, + 0.022982275113463402, + -0.01966698467731476, + -0.011921938508749008, + 0.027065515518188477, + 0.017232025042176247, + -0.03560660779476166, + -0.01119145005941391, + 0.0029125867877155542, + -0.019123800098896027, + -0.04903634637594223, + -0.02921951934695244 + ], + "key": "Test Memory Example", + "status": "activated" + } + }, + { + "id": "3178a22f-4edb-46e1-89fd-a08009b131a1", + "memory": "On January 13, 2026, at 8:51 PM, the user created a test memory for a demonstration purpose.", + "metadata": { + "sources": [ + "\"{\\\"type\\\": \\\"chat\\\", \\\"role\\\": \\\"user\\\", \\\"chat_time\\\": \\\"08:51 PM on 13 January, 2026\\\", \\\"content\\\": \\\"This is a test memory for dump example\\\", \\\"lang\\\": \\\"en\\\"}\"", + "\"{\\\"type\\\": \\\"chat\\\", \\\"role\\\": \\\"user\\\", \\\"chat_time\\\": \\\"08:51 PM on 13 January, 2026\\\", \\\"content\\\": \\\"Another memory to demonstrate persistence\\\", \\\"lang\\\": \\\"en\\\"}\"" + ], + "confidence": 0.99, + "usage": [], + "created_at": "2026-01-13T20:51:42.359643000+00:00", + "session_id": "default_session", + "memory_type": "WorkingMemory", + "type": "fact", + "tags": [ + "test", + "memory", + "demonstration" + ], + "updated_at": "2026-01-13T20:51:42.396195000+00:00", + "user_id": "example_user", + "background": "On January 13, 2026, at 8:51 PM, the user engaged in a memory demonstration by creating a test memory example and another memory to illustrate the concept of persistence. These actions reflect the user's interest in exploring and demonstrating memory-related concepts.", + "file_ids": [], + "embedding": [ + -0.023225771263241768, + 0.009711744263768196, + 0.01401975005865097, + -0.023113388568162918, + -0.044953107833862305, + -0.025454696267843246, + 0.004780950024724007, + 0.012184164486825466, + 0.003397237276658416, + 0.006766378879547119, + 0.033059265464544296, + -0.0018625102238729596, + -0.00135678774677217, + -0.0159396231174469, + -0.0017864176770672202, + 0.03302180394530296, + 0.05941302329301834, + -0.013467201963067055, + -0.011341294273734093, + -0.03324656933546066, + 0.01599581353366375, + -0.05263259634375572, + 0.07222465425729752, + 0.022851161658763885, + -0.007220592815428972, + 0.0017969536129385233, + -0.012418295256793499, + 0.013214340433478355, + 0.08645980805158615, + 0.0018215373856946826, + 0.02071589045226574, + -0.028620144352316856, + -0.015490091405808926, + -0.025454696267843246, + -0.04469088092446327, + -0.02105303853750229, + 0.027945848181843758, + 3.424162423470989e-05, + -0.028526492416858673, + -0.019479678943753242, + -0.008882921189069748, + 0.012596234679222107, + 0.015480726025998592, + 0.006949000991880894, + 0.015499456785619259, + 0.014825159683823586, + -0.012549408711493015, + -0.02382514625787735, + -0.025342313572764397, + -0.013364183716475964, + 0.002884491113945842, + 0.03133606165647507, + 0.04525279253721237, + -0.037179965525865555, + 0.027009325101971626, + 0.021689873188734055, + -0.05034748092293739, + -0.043342288583517075, + -0.019816827028989792, + 0.007492184638977051, + -0.03575645014643669, + 0.007862110622227192, + 0.0021774161141365767, + 0.01226845197379589, + -0.013504662550985813, + 0.03937143087387085, + 0.0068834442645311356, + 0.0019292375072836876, + -0.00272059952840209, + -0.023169580847024918, + 0.0013368866639211774, + 0.04581470787525177, + -0.05514247715473175, + -0.01210924331098795, + -0.0809905156493187, + 0.01955460198223591, + 0.0017419328214600682, + -0.015677396208047867, + -0.009426104836165905, + 0.021408917382359505, + 0.03892189636826515, + -0.022476553916931152, + 0.01390736736357212, + -0.0002572511730249971, + 0.047350604087114334, + 0.01260560005903244, + -0.06349626183509827, + 0.057502515614032745, + 0.040345411747694016, + -0.04274291172623634, + 0.028788719326257706, + 0.0003658293280750513, + 0.010807476006448269, + -0.02504262700676918, + 0.004296299535781145, + 0.010404771193861961, + -0.05158368870615959, + 0.003305926453322172, + 0.029069675132632256, + 0.011032241396605968, + 0.05813935026526451, + 0.022532744333148003, + 0.02037874236702919, + -0.017878225073218346, + -0.0010945613030344248, + -0.028788719326257706, + 0.02927570976316929, + 0.014375628903508186, + -0.009627456776797771, + 0.0005191849777474999, + 0.001597942435182631, + 0.04281783476471901, + 0.04918619245290756, + 0.01210924331098795, + 0.04203115403652191, + 0.013766888529062271, + 0.013485931791365147, + -0.01013317983597517, + -0.05083446949720383, + -0.014778333716094494, + 0.017484884709119797, + 0.014703411608934402, + 0.038341253995895386, + -0.03693646937608719, + -0.06076161563396454, + -0.014787699095904827, + -0.01294274814426899, + -0.023019736632704735, + -0.0010770015651360154, + -0.004511700011789799, + 0.016042640432715416, + -0.000730487983673811, + 0.00883141253143549, + -0.008058780804276466, + -0.026971863582730293, + -0.021614952012896538, + 0.011247641406953335, + 0.05281990021467209, + -0.010498423129320145, + -0.03399578854441643, + 0.020341280847787857, + -0.003252076217904687, + -0.008681568317115307, + -0.026859480887651443, + 0.015930257737636566, + -0.02498643472790718, + 0.005469294730573893, + -0.003645415883511305, + 0.02721535973250866, + 0.001160117913968861, + -0.01229654811322689, + 0.019891750067472458, + -0.02288862317800522, + -0.04469088092446327, + -0.022851161658763885, + -0.003551763715222478, + 0.01916126161813736, + 0.06192290410399437, + -0.01468468178063631, + 0.012624330818653107, + -0.0015429217601194978, + -0.048511892557144165, + -0.06076161563396454, + 0.0465264655649662, + 0.02032255008816719, + 0.02860141359269619, + 0.013457836583256721, + 0.025248661637306213, + -0.0460769347846508, + 0.03639328479766846, + 0.002751036547124386, + -0.008306959643959999, + -0.008747125044465065, + -0.008157115429639816, + -0.008611329831182957, + 0.033845942467451096, + 0.038734592497348785, + -0.000227984826778993, + -0.01032984908670187, + -0.0321040116250515, + -0.05158368870615959, + 0.0031490586698055267, + 0.030287155881524086, + 0.013794984668493271, + -0.04135685786604881, + -0.003430015640333295, + -0.012390200048685074, + 0.004427412524819374, + 0.015049925073981285, + 0.01107906736433506, + 0.008161798119544983, + -0.03180432319641113, + -0.000778484798502177, + 0.00315842404961586, + -0.005722155794501305, + -0.027908386662602425, + -0.0014211736852303147, + 0.0008768197149038315, + -0.02448071353137493, + 0.005408420693129301, + -0.011060337536036968, + 0.035737719386816025, + 0.015668030828237534, + 0.02127780392765999, + -0.01746615581214428, + -0.013823079876601696, + -0.01416022889316082, + 0.0026854798197746277, + 0.0031677891965955496, + -0.0812152773141861, + -0.024836590513586998, + 0.0003201738290954381, + -0.016014544293284416, + -0.011032241396605968, + 0.02238290011882782, + -0.013261166401207447, + -0.0022523379884660244, + -0.005698742810636759, + 0.012764809653162956, + -0.015499456785619259, + -0.05371896177530289, + 0.04941095784306526, + -0.017447425052523613, + 0.030343346297740936, + 0.030811607837677002, + -0.01826220005750656, + 0.008536407724022865, + 0.05016017332673073, + 0.02848903089761734, + -0.0326659232378006, + 0.026110263541340828, + 0.018721096217632294, + 0.012015590444207191, + -0.007585836574435234, + 0.03513834625482559, + -0.020847003906965256, + -0.04154416173696518, + 0.0050150807946920395, + 0.02605407126247883, + 0.0016857414739206433, + -0.01627677120268345, + 0.004181575495749712, + 0.01961079239845276, + 0.018365217372775078, + -0.04154416173696518, + -0.026241375133395195, + 0.0030554065015167, + 0.01035794522613287, + 0.02227051742374897, + 0.01488135103136301, + 0.01074191927909851, + 0.007899572141468525, + -0.05918825790286064, + -0.001568676088936627, + 0.01715710200369358, + 0.009051495231688023, + 0.029032215476036072, + -0.006073351949453354, + 0.03877205401659012, + -0.0013439105823636055, + 0.04064510017633438, + -0.03774188086390495, + 0.025810575112700462, + 0.03341514244675636, + 0.022944815456867218, + -0.019854288548231125, + -0.019535871222615242, + -0.013411009684205055, + 0.014591028913855553, + -0.008742442354559898, + 0.02993127703666687, + -0.05525486171245575, + -0.02365657314658165, + 0.03487611934542656, + -0.015705492347478867, + 0.008349102921783924, + -0.02970651164650917, + 5.427992618933786e-06, + -0.020584776997566223, + 0.038846977055072784, + 0.016632650047540665, + -0.026409950107336044, + 0.031298600137233734, + -0.0122216260060668, + 0.0071503533981740475, + -0.017335042357444763, + -0.027796003967523575, + -0.027140438556671143, + 0.03952127322554588, + -0.019704444333910942, + -0.019460948184132576, + 0.01024556253105402, + 0.06357118487358093, + -0.04360451176762581, + -0.018206007778644562, + -0.021952100098133087, + 0.00883141253143549, + -0.15463869273662567, + -0.008232037536799908, + -0.013879271224141121, + -0.0018063188763335347, + -0.014413089491426945, + 0.016632650047540665, + -0.04682615399360657, + -0.0486617386341095, + -0.010479693301022053, + 0.08968144655227661, + -0.005267942324280739, + -0.04244322329759598, + 0.017306946218013763, + 0.026353757828474045, + -0.025866767391562462, + -0.005651916842907667, + -0.03865967318415642, + -0.027908386662602425, + -0.024312138557434082, + -0.011931303888559341, + 0.010030161589384079, + -0.02148383855819702, + 0.05424341559410095, + -0.01921745389699936, + -0.002258191118016839, + -0.00631684809923172, + 0.04941095784306526, + 0.009739839471876621, + -0.020734621211886406, + 0.002176245441660285, + -0.014169593341648579, + 0.04128193482756615, + -0.006579074542969465, + -0.005895412527024746, + -0.008999986574053764, + 0.05971270799636841, + -0.0005150876822881401, + 0.007473453879356384, + 0.011453676968812943, + -0.020416202023625374, + 0.015396438539028168, + 0.066230908036232, + -0.03858475014567375, + 0.045964550226926804, + 0.03455770015716553, + 0.0163891538977623, + -0.004703687038272619, + -0.012184164486825466, + -0.0476502925157547, + -0.011369389481842518, + -0.007332975510507822, + -0.020022863522171974, + -0.015096751973032951, + -0.036505669355392456, + -0.020528584718704224, + -0.013401645235717297, + -0.054955173283815384, + 0.017035353928804398, + -0.08526106178760529, + 0.021614952012896538, + -0.0310363732278347, + -0.05192083865404129, + -0.010760650038719177, + 0.040345411747694016, + -0.02970651164650917, + 0.00763734569773078, + 0.04030795395374298, + -0.06394579261541367, + -0.0025051990523934364, + -0.03637455403804779, + 0.04847443476319313, + -0.018449503928422928, + 0.012736713513731956, + 0.001112121157348156, + 0.021352725103497505, + 0.06166067719459534, + 0.002046302892267704, + -0.03247861936688423, + 0.011013510636985302, + -0.08885730803012848, + -0.027796003967523575, + 0.053681500256061554, + -0.015452630817890167, + -0.03388340398669243, + -0.01715710200369358, + 0.00902808178216219, + -0.01121954619884491, + 0.008096241392195225, + 0.04113209247589111, + 0.20933163166046143, + -0.0004925525863654912, + -0.0620727464556694, + -0.013055131770670414, + 0.03787299245595932, + -0.010076988488435745, + -0.053606580942869186, + 0.01327053178101778, + -0.04233084246516228, + -0.04536517709493637, + 0.020285088568925858, + -0.0007509744027629495, + 0.01352339331060648, + 0.010208101011812687, + 0.0115192336961627, + -0.0243870597332716, + -0.01263369619846344, + -0.007501549553126097, + 0.08908206969499588, + 0.016585823148489, + 0.035793911665678024, + -0.014338168315589428, + -0.001372006256133318, + -0.001101585221476853, + -0.04525279253721237, + -0.02648487128317356, + -0.00762329762801528, + 0.07971683889627457, + -0.012708617374300957, + 0.056565992534160614, + -0.018917765468358994, + 0.011697173118591309, + 0.007997906766831875, + 0.004799680784344673, + 0.023469267413020134, + 0.009664918296039104, + 0.007894889451563358, + -0.04281783476471901, + -0.017569173127412796, + 0.02921951934695244, + 0.040794942528009415, + -0.023787684738636017, + 0.013841810636222363, + 0.04124447703361511, + -0.002535636071115732, + 0.01271798275411129, + 0.011978129856288433, + -0.02232670970261097, + -0.04135685786604881, + -0.002619923325255513, + -0.03480119630694389, + 0.016838684678077698, + 0.0310363732278347, + -0.016005178913474083, + 0.013682601973414421, + -0.006705504842102528, + -0.011097798123955727, + -0.02687821164727211, + 0.002102494239807129, + 0.03644947707653046, + 0.03888443857431412, + 0.0315420962870121, + -0.028751257807016373, + 0.051995761692523956, + -0.014937542378902435, + 0.0018285613041371107, + 0.0020779105834662914, + -0.05240783095359802, + 0.03425801172852516, + 0.026953132823109627, + 0.06267212331295013, + 0.010020796209573746, + 0.03259100392460823, + 0.0234318058937788, + 0.008007272146642208, + 0.012689887546002865, + 0.03985841944813728, + 0.05488025024533272, + 0.021858448162674904, + 0.07214973866939545, + 0.0159115269780159, + -0.020453663542866707, + -0.04027049243450165, + 0.008372516371309757, + 0.005876682233065367, + -0.05701552331447601, + -0.024143563583493233, + 0.052445292472839355, + -0.024518173187971115, + -0.03463262319564819, + -0.0329468809068203, + 0.045739784836769104, + -0.025510888546705246, + -0.027833465486764908, + 0.048174746334552765, + 0.0156586654484272, + 0.04124447703361511, + -0.0003596833848860115, + -0.029743971303105354, + 0.0014972662320360541, + -0.05083446949720383, + -0.02843284048140049, + 0.013663871213793755, + -0.0015663348603993654, + -0.010320483706891537, + -0.03315291553735733, + -0.028414109721779823, + -0.003565811552107334, + 0.008011954836547375, + 0.012764809653162956, + -0.0057455687783658504, + 0.03433293476700783, + -0.07361071556806564, + -0.04446611553430557, + -0.0036758529022336006, + 0.003003897611051798, + -0.014619125053286552, + 0.009084274061024189, + -0.009491661563515663, + 0.047425527125597, + 0.009936509653925896, + 0.00795576348900795, + 0.010620171204209328, + 0.05540470406413078, + 0.009861587546765804, + -0.022364171221852303, + -0.0022628738079220057, + -0.012006225995719433, + 0.004530430305749178, + -0.01372006256133318, + 0.026615984737873077, + -0.036187250167131424, + 0.04094478860497475, + -0.03877205401659012, + 0.02732774242758751, + 0.014862621203064919, + 0.021858448162674904, + 0.01667010970413685, + -0.01502182986587286, + 0.033621177077293396, + 0.0031748132314532995, + -0.09402691572904587, + -0.000989787746220827, + 0.027346473187208176, + 0.025585809722542763, + 0.01667947508394718, + 0.024181025102734566, + -0.02427467703819275, + -0.01249321736395359, + 0.02448071353137493, + 0.03933396935462952, + 0.01710091158747673, + 0.02449944242835045, + -0.05960032716393471, + -0.03335895016789436, + -0.039071742445230484, + -0.04547755792737007, + 0.017475519329309464, + 0.03644947707653046, + -0.04236830398440361, + -0.006752331275492907, + 0.031841784715652466, + 0.03397705778479576, + 0.08226418495178223, + 0.0621851310133934, + -0.04214353859424591, + -0.011397485621273518, + 0.030006198212504387, + 0.0031162805389612913, + -0.023356884717941284, + 0.006532248109579086, + -0.005928190890699625, + -0.016407884657382965, + 0.021184151992201805, + 0.0018777287332341075, + -0.047425527125597, + -0.04903634637594223, + 0.026840750128030777, + -0.021502569317817688, + -0.01077001541852951, + -0.008461485616862774, + -0.02521120011806488, + -0.037685688585042953, + -0.011650347150862217, + 0.02054731547832489, + 0.021090500056743622, + 0.01893649622797966, + -0.028357917442917824, + 0.012689887546002865, + -0.001998306019231677, + -0.08511121571063995, + 0.06967731565237045, + 0.030399538576602936, + -0.015471360646188259, + 0.04203115403652191, + -0.043791819363832474, + 0.02854522317647934, + 0.010301753878593445, + 0.011388120241463184, + 0.022233057767152786, + -0.012661791406571865, + 0.0016037956811487675, + -0.019685715436935425, + -0.01944221928715706, + -0.019292375072836876, + -0.012905287556350231, + 0.009908413514494896, + 0.0161643885076046, + -0.0068834442645311356, + 0.02015397697687149, + -0.018589982762932777, + -0.019966671243309975, + 0.0020123538561165333, + 0.014328802935779095, + -0.050722088664770126, + -0.014890716411173344, + 0.07177512347698212, + 0.044503577053546906, + -0.011921938508749008, + 0.010320483706891537, + -0.014478646218776703, + 0.01338291447609663, + 0.010526519268751144, + -0.01812172122299671, + -0.02142764814198017, + 0.01088239811360836, + 0.00478329136967659, + -0.05225798487663269, + 0.02693440392613411, + 0.022682588547468185, + -0.005764299537986517, + -0.02238290011882782, + -0.024087373167276382, + -0.019311105832457542, + 0.05296974256634712, + -0.0651070848107338, + 0.020809542387723923, + 0.015780413523316383, + -0.024780400097370148, + -0.0027042103465646505, + -0.02914459817111492, + 0.014207054860889912, + 0.020079053938388824, + 0.04768775403499603, + 0.0315982885658741, + 0.03526945784687996, + 0.013439105823636055, + 0.012886556796729565, + 0.007670123595744371, + 0.023974990472197533, + 0.017597267404198647, + 0.007866793312132359, + -0.048174746334552765, + -0.0489988848567009, + 0.040457796305418015, + 0.08016636967658997, + 0.013682601973414421, + -0.018046800047159195, + -0.06683028489351273, + -0.034351665526628494, + -0.006799157243221998, + 0.0028048865497112274, + -0.020341280847787857, + 0.01605200581252575, + -0.04637662321329117, + -0.06993953883647919, + 0.017569173127412796, + -0.06008731946349144, + -0.006916222628206015, + -0.03309672325849533, + -0.027758542448282242, + 0.004675591364502907, + -0.00883141253143549, + -0.03899681940674782, + 0.07012684643268585, + -0.0009002327569760382, + -0.02620391547679901, + -0.025023896247148514, + 0.06802903115749359, + 0.030193503946065903, + -0.00706606637686491, + 0.052332907915115356, + 0.02976270206272602, + 0.03502596169710159, + -0.012886556796729565, + -3.263197504566051e-05, + 0.019179992377758026, + -0.02637248858809471, + 0.017278850078582764, + -0.06031208485364914, + -0.012249721214175224, + 0.00553953368216753, + -0.029182057827711105, + 0.040907327085733414, + -0.010788745246827602, + 0.01755044236779213, + -0.042293380945920944, + 0.02043493278324604, + -0.0234318058937788, + 0.02427467703819275, + -0.030455728992819786, + 0.011584790423512459, + -0.045515019446611404, + -0.015181038528680801, + 0.0005320621421560645, + 0.00795576348900795, + -0.01710091158747673, + 0.017082180827856064, + 0.029687780886888504, + 0.003418309148401022, + 0.020734621211886406, + -0.07994160801172256, + 0.007215910125523806, + 0.022457823157310486, + -0.0006052280077710748, + -0.015817875042557716, + 0.02682201936841011, + -0.058176811784505844, + 0.05413103103637695, + -0.004389951936900616, + 0.03639328479766846, + 0.011172720231115818, + -0.0489988848567009, + -0.005675329826772213, + -0.031111296266317368, + -0.0019268961623311043, + -0.0032825132366269827, + -0.017981242388486862, + 0.036955200135707855, + -0.03377101942896843, + -0.030418269336223602, + 0.003273148089647293, + -0.02464928664267063, + -0.0011630445951595902, + 0.04394166171550751, + 0.020416202023625374, + 0.021034307777881622, + 0.0008352614822797477, + 0.05083446949720383, + -0.03319037705659866, + -0.009290308691561222, + -0.02464928664267063, + 0.04083240404725075, + -0.049785565584897995, + -0.031298600137233734, + 0.02560454048216343, + -0.01760663278400898, + 0.014263246208429337, + -0.01757853850722313, + -0.00598438223823905, + -0.005591042805463076, + 0.02594168856739998, + -0.012867826968431473, + -0.0477626770734787, + 0.033902134746313095, + -0.025061357766389847, + -0.05274497717618942, + 0.031523365527391434, + 0.03970857709646225, + 0.01596771739423275, + 0.013888636603951454, + 0.03877205401659012, + -0.009739839471876621, + -0.009786665439605713, + -0.04761283099651337, + -0.008143068291246891, + 0.032684653997421265, + 0.03822886943817139, + 0.009163877926766872, + -0.028170613572001457, + 0.005843903869390488, + 0.020753350108861923, + -0.007281466852873564, + -0.014216420240700245, + -0.014057210646569729, + -0.006424548104405403, + -0.011172720231115818, + -0.03332148864865303, + 0.03974603861570358, + 0.013757524080574512, + -0.015012464486062527, + 0.0028165930416435003, + 0.01327053178101778, + -0.019910480827093124, + 0.006625900510698557, + -0.022626396268606186, + -0.011912573128938675, + -0.02537977509200573, + -0.024574365466833115, + 0.007300197146832943, + -0.023169580847024918, + -0.047425527125597, + 0.0003184178494848311, + 0.02537977509200573, + -0.16213087737560272, + 0.02176479622721672, + 0.0014211736852303147, + 0.0010805134661495686, + -0.021952100098133087, + -0.02803950011730194, + -0.036280903965234756, + -0.023281963542103767, + 0.028245534747838974, + -0.02571692317724228, + 0.011734633706510067, + -0.03586883470416069, + 0.035793911665678024, + -0.030736686661839485, + -0.02288862317800522, + 0.02682201936841011, + 0.012006225995719433, + 0.04476580023765564, + -0.06004985794425011, + 0.09335261583328247, + -0.005075954832136631, + -0.030418269336223602, + -0.004537454340606928, + 0.005057224538177252, + -0.048624277114868164, + -0.0246118251234293, + 0.031017644330859184, + 0.02798330970108509, + -0.03510088473558426, + 0.03560660779476166, + -0.02120288275182247, + 0.031298600137233734, + 0.02449944242835045, + 0.05858888104557991, + 0.03335895016789436, + -0.01662328466773033, + 0.011725268326699734, + -0.04349213093519211, + -0.015340247191488743, + -0.00708011444658041, + -0.05031001940369606, + 0.01857125200331211, + -0.009627456776797771, + -0.015265326015651226, + 0.03616851940751076, + 0.06383340805768967, + -0.027833465486764908, + 0.009430787526071072, + -0.037685688585042953, + 0.02260766737163067, + -0.012202895246446133, + 0.021614952012896538, + -0.009009351953864098, + -0.009674282744526863, + -0.02116542123258114, + -0.017953146249055862, + -0.01185638178139925, + -0.013869906775653362, + -0.011453676968812943, + 0.016951067373156548, + -0.01976063661277294, + -0.012540043331682682, + -0.0244432520121336, + -0.042068615555763245, + -0.018955226987600327, + 0.011697173118591309, + -0.06926524639129639, + 0.0025239295791834593, + -0.015920892357826233, + 0.009945875033736229, + -0.035119615495204926, + 0.027009325101971626, + 0.02015397697687149, + -0.009777300991117954, + -0.015977082774043083, + 0.05308212712407112, + 0.06327150017023087, + 0.021558761596679688, + 0.017091546207666397, + -0.01766282506287098, + -0.013336088508367538, + 0.005932873580604792, + -0.0006385916494764388, + -0.015649300068616867, + 0.015049925073981285, + 0.03538184240460396, + -0.005164924543350935, + 0.003172471886500716, + -0.03903428092598915, + -0.01271798275411129, + -0.09005605429410934, + -0.008620694279670715, + 0.045664865523576736, + 0.003343387274071574, + -0.0031935435254126787, + 0.08196450024843216, + -0.023019736632704735, + -0.03611232712864876, + -0.037123773247003555, + -0.014216420240700245, + -0.009983335621654987, + 0.02026635967195034, + 0.00901871733367443, + 0.027964578941464424, + 0.009561900049448013, + 0.0246118251234293, + -0.01416022889316082, + -0.039558734744787216, + 0.006003112997859716, + 0.024087373167276382, + -0.036131057888269424, + -0.04008318483829498, + -0.04064510017633438, + -0.01315814908593893, + -0.08001653105020523, + -0.01819664239883423, + -0.020228898152709007, + 0.014759602956473827, + -0.05536724254488945, + -0.021577490493655205, + 0.035962484776973724, + 0.008822047151625156, + 0.01771901547908783, + -0.027908386662602425, + 0.019854288548231125, + 0.01024556253105402, + 0.029800163581967354, + 0.002376427175477147, + -0.007960446178913116, + 0.005197702907025814, + -0.019236182793974876, + 0.000641518272459507, + 0.04941095784306526, + 0.059113334864377975, + -0.0018589982064440846, + -0.006073351949453354, + -0.012024955824017525, + 0.013420375064015388, + -0.05192083865404129, + -0.03547549247741699, + -0.011425580829381943, + -0.008737759664654732, + 0.024836590513586998, + -0.014075941406190395, + -0.008587916381657124, + 0.013195609673857689, + 0.032628461718559265, + 0.003600931027904153, + -0.021633682772517204, + -0.0024490077048540115, + 0.018814748153090477, + -0.010835572145879269, + 0.036730434745550156, + 0.056116461753845215, + -0.047238223254680634, + 0.013729427941143513, + -0.006794474553316832, + 0.02987508475780487, + 0.008246085606515408, + 0.032347507774829865, + -0.04191877320408821, + 0.03465135395526886, + -0.061061304062604904, + -0.030792877078056335, + 0.013111323118209839, + 0.03854728862643242, + 0.03127986937761307, + 0.006546296179294586, + -0.062447357922792435, + 0.021970830857753754, + 0.021408917382359505, + 0.04547755792737007, + -0.034070707857608795, + -0.003069454338401556, + 0.006246608681976795, + -0.03761076554656029, + 0.017119640484452248, + 0.03736726939678192, + 0.018608713522553444, + -0.030774148181080818, + 0.021408917382359505, + -0.015321517363190651, + 0.019704444333910942, + 0.009730474092066288, + 0.02082827314734459, + 0.017110276967287064, + -0.012146703898906708, + 0.018589982762932777, + -0.006349626462906599, + 0.01249321736395359, + 0.025248661637306213, + -0.02309465780854225, + -0.053681500256061554, + -0.03335895016789436, + 0.04158162325620651, + -0.02916332706809044, + -0.02815188281238079, + 0.026110263541340828, + -0.014825159683823586, + 0.06844110786914825, + -0.04536517709493637, + -0.03854728862643242, + 0.013261166401207447, + -0.049785565584897995, + 0.008058780804276466, + 0.020453663542866707, + -0.010535884648561478, + 0.019517140462994576, + -0.04693853482604027, + 0.016342326998710632, + -0.020640967413783073, + -0.01554628275334835, + 0.017896955832839012, + 0.012184164486825466, + -0.02148383855819702, + 0.01065763272345066, + 0.0030835021752864122, + 0.019348565489053726, + -0.02071589045226574, + 0.05364403873682022, + -0.017054084688425064, + -0.004036414436995983, + 0.026335028931498528, + -0.03764822706580162, + -0.0230384673923254, + 0.00017208610370289534, + -0.0007825820939615369, + 0.0464140810072422, + 0.02110922895371914, + 0.048849042505025864, + 0.021633682772517204, + 0.024349600076675415, + -0.02910713665187359, + 0.022982275113463402, + -0.01966698467731476, + -0.011921938508749008, + 0.027065515518188477, + 0.017232025042176247, + -0.03560660779476166, + -0.01119145005941391, + 0.0029125867877155542, + -0.019123800098896027, + -0.04903634637594223, + -0.02921951934695244 + ], + "key": "Test Memory Example", + "status": "activated" + } + } + ], + "edges": [], + "total_nodes": 4, + "total_edges": 0 +} \ No newline at end of file diff --git a/examples/mem_cube/_deprecated/README.md b/examples/mem_cube/_deprecated/README.md new file mode 100644 index 000000000..da02eebef --- /dev/null +++ b/examples/mem_cube/_deprecated/README.md @@ -0,0 +1,81 @@ +# Deprecated Examples + +⚠️ **These examples are deprecated and no longer maintained.** + +## Why deprecated? + +These examples demonstrate old APIs that directly access MemCube internals (e.g., `mem_cube.text_mem.get_all()`), which is no longer the recommended approach. + +## Current Best Practice + +**Use `SingleCubeView` / `CompositeCubeView` for all add/search operations.** + +The new View architecture provides: +- ✅ Unified API interface +- ✅ Multi-cube support +- ✅ Better integration with MemOS Server +- ✅ Consistent result format with `cube_id` tracking + +## Updated Examples + +See the following files in the parent directory: +- **`../load_cube.py`** - Load MemCube and operate via SingleCubeView +- **`../dump_cube.py`** - Persist MemCube to disk + +## Migration Guide + +### Old approach (deprecated): +```python +mem_cube = GeneralMemCube.init_from_dir("examples/data/mem_cube_2") +items = mem_cube.text_mem.get_all() # ❌ Direct access +for item in items: + print(item) +``` + +### New approach (recommended): +```python +import json +from memos.api.handlers import init_server +from memos.api.product_models import APISearchRequest +from memos.multi_mem_cube.single_cube import SingleCubeView +from memos.log import get_logger + +logger = get_logger(__name__) + +# Initialize server (uses .env configuration) +components = init_server() +naive = components["naive_mem_cube"] + +# Create View +view = SingleCubeView( + cube_id="my_cube", + naive_mem_cube=naive, + mem_reader=components["mem_reader"], + mem_scheduler=components["mem_scheduler"], + logger=logger, + searcher=components["searcher"], + feedback_server=components["feedback_server"], +) + +# Load data from exported JSON +with open("examples/data/mem_cube_tree/textual_memory.json") as f: + json_data = json.load(f) +naive.text_mem.graph_store.import_graph(json_data, user_name="my_cube") + +# Use View API for search +results = view.search_memories(APISearchRequest( + user_id="user", + readable_cube_ids=["my_cube"], + query="your query here", +)) +for group in results.get("text_mem", []): + for mem in group.get("memories", []): + print(mem.get("metadata", {}).get("memory", "N/A")) +``` + +> **Note on Embeddings**: The sample data uses **bge-m3** model with **1024 dimensions**. +> Ensure your environment uses the same embedding configuration for accurate search. + +--- + +For more information, see the [MemCube documentation](https://memos-doc.memoryos.ai/open_source/modules/mem_cube). diff --git a/examples/mem_cube/load_from_folder.py b/examples/mem_cube/_deprecated/load_from_folder.py similarity index 100% rename from examples/mem_cube/load_from_folder.py rename to examples/mem_cube/_deprecated/load_from_folder.py diff --git a/examples/mem_cube/load_from_remote.py b/examples/mem_cube/_deprecated/load_from_remote.py similarity index 100% rename from examples/mem_cube/load_from_remote.py rename to examples/mem_cube/_deprecated/load_from_remote.py diff --git a/examples/mem_cube/load_lazily.py b/examples/mem_cube/_deprecated/load_lazily.py similarity index 100% rename from examples/mem_cube/load_lazily.py rename to examples/mem_cube/_deprecated/load_lazily.py diff --git a/examples/mem_cube/dump_cube.py b/examples/mem_cube/dump_cube.py new file mode 100644 index 000000000..5a2967ff9 --- /dev/null +++ b/examples/mem_cube/dump_cube.py @@ -0,0 +1,137 @@ +""" +MemCube dump example using SingleCubeView. + +Demonstrates: +1. Initialize server and create SingleCubeView with NEW cube_id +2. Add memories via View +3. Dump ONLY this cube's data to directory + +Requirements: + - MemOS service environment (.env configured) + - Neo4j graph database (set NEO4J_BACKEND=neo4j in .env) + +Note on Embeddings: + This example exports embeddings along with memory data. + The sample data uses: bge-m3 model, 1024 dimensions. + If your environment uses a different embedding model or dimension, + you may need to re-embed the data after import, or the semantic + search results may be inaccurate or fail. +""" + +import contextlib +import json +import os +import shutil + +from memos.api.handlers import init_server +from memos.api.product_models import APIADDRequest +from memos.log import get_logger +from memos.multi_mem_cube.single_cube import SingleCubeView + + +logger = get_logger(__name__) + +# NEW cube_id to avoid dumping existing data +EXAMPLE_CUBE_ID = "example_dump_cube" +EXAMPLE_USER_ID = "example_user" + +# ============================================================================= +# Step 1: Initialize server +# ============================================================================= +print("=" * 60) +print("Step 1: Initialize server") +print("=" * 60) + +components = init_server() +print("✓ Server initialized") + +# ============================================================================= +# Step 2: Create SingleCubeView with NEW cube_id +# ============================================================================= +print("\n" + "=" * 60) +print(f"Step 2: Create SingleCubeView (cube_id={EXAMPLE_CUBE_ID})") +print("=" * 60) + +naive = components["naive_mem_cube"] +view = SingleCubeView( + cube_id=EXAMPLE_CUBE_ID, # NEW cube_id + naive_mem_cube=naive, + mem_reader=components["mem_reader"], + mem_scheduler=components["mem_scheduler"], + logger=logger, + searcher=components["searcher"], + feedback_server=components["feedback_server"], +) +print("✓ SingleCubeView created") + +# ============================================================================= +# Step 3: Add memories via View +# ============================================================================= +print("\n" + "=" * 60) +print("Step 3: Add memories via SingleCubeView") +print("=" * 60) + +result = view.add_memories( + APIADDRequest( + user_id=EXAMPLE_USER_ID, + writable_cube_ids=[EXAMPLE_CUBE_ID], + messages=[ + {"role": "user", "content": "This is a test memory for dump example"}, + {"role": "user", "content": "Another memory to demonstrate persistence"}, + ], + async_mode="sync", + ) +) +print(f"✓ Added {len(result)} memories") + +# ============================================================================= +# Step 4: Dump ONLY this cube's data +# ============================================================================= +print("\n" + "=" * 60) +print("Step 4: Dump cube data (filtered by cube_id)") +print("=" * 60) + +output_dir = "tmp/mem_cube_dump" +if os.path.exists(output_dir): + shutil.rmtree(output_dir) +os.makedirs(output_dir, exist_ok=True) + +# Export only this cube's data using user_name filter +text_mem = naive.text_mem +json_data = text_mem.graph_store.export_graph( + include_embedding=True, # Include embeddings for semantic search + user_name=EXAMPLE_CUBE_ID, # Filter by cube_id +) + +# Fix embedding format: parse string to list for import compatibility +# (export_graph stores embedding as string in metadata, but add_node expects list) +for node in json_data.get("nodes", []): + metadata = node.get("metadata", {}) + if "embedding" in metadata and isinstance(metadata["embedding"], str): + with contextlib.suppress(json.JSONDecodeError): + metadata["embedding"] = json.loads(metadata["embedding"]) + +print(f"✓ Exported {len(json_data.get('nodes', []))} nodes") + +# Save to file +memory_file = os.path.join(output_dir, "textual_memory.json") +with open(memory_file, "w", encoding="utf-8") as f: + json.dump(json_data, f, indent=2, ensure_ascii=False) +print(f"✓ Saved to: {memory_file}") + +# Save config (user can modify sensitive fields before sharing) +config = components["default_cube_config"].model_copy(deep=True) +config.user_id = EXAMPLE_USER_ID +config.cube_id = EXAMPLE_CUBE_ID +config_file = os.path.join(output_dir, "config.json") +config.to_json_file(config_file) +print(f"✓ Config saved to: {config_file}") + +# ============================================================================= +# Done +# ============================================================================= +print("\n" + "=" * 60) +print("✅ Example completed!") +print("=" * 60) +print(f"\nDumped to: {output_dir}") +print("Run load_cube.py to load this data") diff --git a/examples/mem_cube/load_cube.py b/examples/mem_cube/load_cube.py new file mode 100644 index 000000000..c7552a4a2 --- /dev/null +++ b/examples/mem_cube/load_cube.py @@ -0,0 +1,137 @@ +""" +MemCube load example using SingleCubeView. + +Demonstrates: +1. Initialize server and create SingleCubeView +2. Load memories from dump via graph_store.import_graph() +3. Display loaded memories +4. Search loaded memories (semantic search) + +Requirements: + - MemOS service environment (.env configured) + - Neo4j graph database (set NEO4J_BACKEND=neo4j in .env) + +Note on Embeddings: + The sample data (examples/data/mem_cube_tree) uses: bge-m3 model, 1024 dimensions. + For semantic search to work correctly, your environment must use the same + embedding model and dimension. If different, search results may be inaccurate. +""" + +import json +import os + +from memos.api.handlers import init_server +from memos.api.product_models import APISearchRequest +from memos.log import get_logger +from memos.multi_mem_cube.single_cube import SingleCubeView + + +logger = get_logger(__name__) + +EXAMPLE_CUBE_ID = "example_dump_cube" +EXAMPLE_USER_ID = "example_user" + +# ============================================================================= +# Step 1: Initialize server +# ============================================================================= +print("=" * 60) +print("Step 1: Initialize server") +print("=" * 60) + +components = init_server() +print("✓ Server initialized") + +# ============================================================================= +# Step 2: Create SingleCubeView +# ============================================================================= +print("\n" + "=" * 60) +print(f"Step 2: Create SingleCubeView (cube_id={EXAMPLE_CUBE_ID})") +print("=" * 60) + +naive = components["naive_mem_cube"] +view = SingleCubeView( + cube_id=EXAMPLE_CUBE_ID, + naive_mem_cube=naive, + mem_reader=components["mem_reader"], + mem_scheduler=components["mem_scheduler"], + logger=logger, + searcher=components["searcher"], + feedback_server=components["feedback_server"], +) +print("✓ SingleCubeView created") + +# ============================================================================= +# Step 3: Load memories from dump +# ============================================================================= +print("\n" + "=" * 60) +print("Step 3: Load memories from dump") +print("=" * 60) + +load_dir = "examples/data/mem_cube_tree" +memory_file = os.path.join(load_dir, "textual_memory.json") + +if not os.path.exists(memory_file): + print(f"❌ File not found: {memory_file}") + print(" Run dump_cube.py first to create data!") + exit(1) + +with open(memory_file, encoding="utf-8") as f: + json_data = json.load(f) + +# Import graph data into graph_store +text_mem = naive.text_mem +text_mem.graph_store.import_graph(json_data, user_name=EXAMPLE_CUBE_ID) + +nodes = json_data.get("nodes", []) +edges = json_data.get("edges", []) +print(f"✓ Imported {len(nodes)} nodes, {len(edges)} edges") + +# ============================================================================= +# Step 4: Display loaded memories +# ============================================================================= +print("\n" + "=" * 60) +print("Step 4: Display loaded memories") +print("=" * 60) + +print(f"\nLoaded {len(nodes)} memories:") +for i, node in enumerate(nodes, 1): + metadata = node.get("metadata", {}) + memory_text = node.get("memory", "N/A") + mem_type = metadata.get("memory_type", "unknown") + print(f"\n [{i}] Type: {mem_type}") + print(f" Content: {memory_text[:70]}...") + +# ============================================================================= +# Step 5: Search loaded memories +# ============================================================================= +print("\n" + "=" * 60) +print("Step 5: Search loaded memories") +print("=" * 60) + +query = "test memory dump persistence demonstration" +print(f'Query: "{query}"') + +search_result = view.search_memories( + APISearchRequest( + user_id=EXAMPLE_USER_ID, + readable_cube_ids=[EXAMPLE_CUBE_ID], + query=query, + ) +) + +text_mem_results = search_result.get("text_mem", []) +memories = [] +for group in text_mem_results: + memories.extend(group.get("memories", [])) + +print(f"\n✓ Found {len(memories)} relevant memories:") +for i, mem in enumerate(memories[:3], 1): + content = mem.get("metadata", {}).get("memory", "N/A")[:70] + print(f" [{i}] {content}...") + +# ============================================================================= +# Done +# ============================================================================= +print("\n" + "=" * 60) +print("✅ Example completed!") +print("=" * 60) From 82a9477e4c7a873bb62f8f03e908a2bb15167f9c Mon Sep 17 00:00:00 2001 From: Travis Tang Date: Wed, 14 Jan 2026 14:50:01 +0800 Subject: [PATCH 32/47] fix:examples update for core memories (#863) * fix bugs: try to fix bugs in _submit_web_logs * fix bugs: try to address bugs * fix bugs * refactor: modify examples * revise add operation and fix an unbelievable bug * address the bug issues * the doc file has a format problem which has been fixed in this commit * add a range of new feats for the add operation * address the incompatible issue of local scheduler * feat(scheduler): optimize redis queue consumer group management - Proactively ensure consumer groups exist in '_refresh_stream_keys' for newly discovered streams. - Remove redundant consumer group checks in '_read_new_messages_batch' to improve read performance. - Clean up 'seen_streams' cache when streams are deleted to ensure correct group recreation. - This change reduces unnecessary Redis calls during high-frequency polling. * fix(tests): resolve AttributeError in SimpleStructMemReader tests - Import 'parse_json_result' from 'memos.mem_reader.utils' instead of accessing it as an instance attribute. - Fixes 'AttributeError: 'SimpleStructMemReader' object has no attribute 'parse_json_result'' in 'test_parse_json_result_success' and 'test_parse_json_result_failure'. - Remove incorrect mock assignment of 'parse_json_result' in 'test_process_chat_data'. * fix(mem_reader): pass info dict to add_before_search for correct user_id usage - Update 'add_before_search' signature in 'SimpleStructMemReader' to accept 'info' dict. - Pass 'info' (containing 'user_id' and 'session_id') to 'self.searcher.search' instead of using empty strings. - Add 'test_add_before_search' to 'TestSimpleStructMemReader' to verify the fix and ensure 'searcher.search' receives the correct 'info'. - This ensures that memory searches are scoped to the correct user and session. * refactor add_before_search from mem_reader to SingleCubeView * address bugs * fix: fix the qsize bug of task queue, and accept change from hotfix/scheduler * fix: address some issues to run old scheduler example and kv cache example * fix: address the issue of Top-level import of unavailable module 'torch' * fix: resolve linting errors and make optional dependencies lazy loaded - Fix ambiguous characters and commented-out code in examples/mem_scheduler/quick_start_examples.py - Fix nested if statements in src/memos/mem_os/core.py - Move torch and transformers imports to method scope in src/memos/llms/hf.py to support optional dependencies - Update tests/llms/test_hf.py to patch transformers module directly * refactor: revise the rewrite prompt to make it better * refactor: update examples * refactor: update examples for scheduler * fix bugs: address the unsupported xautoclaim command when redis version larger than 6.2.0 via adding a new feature of manul auto claim with the combination of xpending + xclaim * refactor: review settings * refactor: adjust examples to make it run better for code debugging * refactor: review slow add apis to get a better performance on Halumen * fix bugs: address the issue when set user_redis_queue to false, the status_tracker is still using * refactor: allow the code to run without rabbitmq * refactor: create a _parse_pending_entry for redis queue * refactor: add a try/catch for status_tracker * fix: revise examples of textual memories to run normally * fix:address the issues in existing examples of core memories * refactor: remove deprecated scheduler examples, and revise half examples * refactor: address all issues in examples --- examples/core_memories/kv_cache_memory.py | 186 +++++++---- .../core_memories/vllm_kv_cache_memory.py | 2 +- examples/mem_scheduler/api_w_scheduler.py | 154 +++++---- .../mem_scheduler/debug_text_mem_replace.py | 109 ------ examples/mem_scheduler/memos_w_scheduler.py | 258 ++++++--------- .../memos_w_scheduler_for_test.py | 88 ----- .../mem_scheduler/quick_start_examples.py | 312 ------------------ examples/mem_scheduler/rabbitmq_example.py | 60 ---- examples/mem_scheduler/redis_example.py | 4 +- ..._for_async_tasks.py => run_async_tasks.py} | 0 examples/mem_scheduler/show_redis_status.py | 33 +- examples/mem_scheduler/task_fair_schedule.py | 87 ----- src/memos/api/config.py | 2 +- src/memos/api/start_api.py | 2 +- .../task_schedule_modules/redis_queue.py | 35 +- 15 files changed, 352 insertions(+), 980 deletions(-) delete mode 100644 examples/mem_scheduler/debug_text_mem_replace.py delete mode 100644 examples/mem_scheduler/memos_w_scheduler_for_test.py delete mode 100644 examples/mem_scheduler/quick_start_examples.py delete mode 100644 examples/mem_scheduler/rabbitmq_example.py rename examples/mem_scheduler/{scheduler_for_async_tasks.py => run_async_tasks.py} (100%) delete mode 100644 examples/mem_scheduler/task_fair_schedule.py diff --git a/examples/core_memories/kv_cache_memory.py b/examples/core_memories/kv_cache_memory.py index dbe3ac4d7..470ad56a7 100644 --- a/examples/core_memories/kv_cache_memory.py +++ b/examples/core_memories/kv_cache_memory.py @@ -1,68 +1,132 @@ +import json + +from transformers import DynamicCache + from memos.configs.memory import MemoryConfigFactory +from memos.memories.activation.item import KVCacheItem from memos.memories.factory import MemoryFactory -# ===== Example: Use factory and HFLLM to build and manage KVCacheMemory ===== +def get_cache_info(cache): + if not cache: + return None + + num_layers = 0 + total_size_bytes = 0 + + if hasattr(cache, "layers"): + num_layers = len(cache.layers) + for layer in cache.layers: + if hasattr(layer, "key_cache") and layer.key_cache is not None: + total_size_bytes += layer.key_cache.nelement() * layer.key_cache.element_size() + if hasattr(layer, "value_cache") and layer.value_cache is not None: + total_size_bytes += layer.value_cache.nelement() * layer.value_cache.element_size() + + if hasattr(layer, "keys") and layer.keys is not None: + total_size_bytes += layer.keys.nelement() * layer.keys.element_size() + if hasattr(layer, "values") and layer.values is not None: + total_size_bytes += layer.values.nelement() * layer.values.element_size() + + elif hasattr(cache, "key_cache") and hasattr(cache, "value_cache"): + num_layers = len(cache.key_cache) + for k, v in zip(cache.key_cache, cache.value_cache, strict=False): + if k is not None: + total_size_bytes += k.nelement() * k.element_size() + if v is not None: + total_size_bytes += v.nelement() * v.element_size() + + return { + "num_layers": num_layers, + "size_bytes": total_size_bytes, + "size_mb": f"{total_size_bytes / (1024 * 1024):.2f} MB", + } + + +def serialize_item(obj): + if isinstance(obj, list): + return [serialize_item(x) for x in obj] + + if isinstance(obj, KVCacheItem): + return { + "id": obj.id, + "metadata": obj.metadata, + "records": obj.records.model_dump() + if hasattr(obj.records, "model_dump") + else obj.records, + "memory": get_cache_info(obj.memory), + } + + if isinstance(obj, DynamicCache): + return get_cache_info(obj) -# 1. Create config for KVCacheMemory (using HuggingFace backend) -config = MemoryConfigFactory( - backend="kv_cache", - config={ - "extractor_llm": { - "backend": "huggingface", - "config": { - "model_name_or_path": "Qwen/Qwen3-0.6B", # Use a valid HuggingFace model name - "max_tokens": 32, - "add_generation_prompt": True, - "remove_think_prefix": True, + return str(obj) + + +if __name__ == "__main__": + # ===== Example: Use factory and HFLLM to build and manage KVCacheMemory ===== + + # 1. Create config for KVCacheMemory (using HuggingFace backend) + config = MemoryConfigFactory( + backend="kv_cache", + config={ + "extractor_llm": { + "backend": "huggingface", + "config": { + "model_name_or_path": "Qwen/Qwen3-0.6B", # Use a valid HuggingFace model name + "max_tokens": 32, + "add_generation_prompt": True, + "remove_think_prefix": True, + }, }, }, - }, -) - -# 2. Instantiate KVCacheMemory using the factory -kv_mem = MemoryFactory.from_config(config) - -# 3. Extract a KVCacheItem (DynamicCache) from a prompt (uses HFLLM.build_kv_cache internally) -prompt = [ - {"role": "user", "content": "What is MemOS?"}, - {"role": "assistant", "content": "MemOS is a memory operating system for LLMs."}, -] -print("===== Extract KVCacheItem =====") -cache_item = kv_mem.extract(prompt) -print(cache_item) -print() - -# 4. Add the extracted KVCacheItem -print("===== Add KVCacheItem =====") -kv_mem.add([cache_item]) -print(kv_mem.get_all()) -print() - -# 5. Get by id -print("===== Get KVCacheItem by id =====") -retrieved = kv_mem.get(cache_item.id) -print(retrieved) -print() - -# 6. Merge caches (simulate with two items) -print("===== Merge DynamicCache =====") -item2 = kv_mem.extract([{"role": "user", "content": "Tell me a joke."}]) -kv_mem.add([item2]) -merged_cache = kv_mem.get_cache([cache_item.id, item2.id]) -print(merged_cache) -print() - -# 7. Delete one -print("===== Delete one KVCacheItem =====") -kv_mem.delete([cache_item.id]) -print(kv_mem.get_all()) -print() - -# 8. Dump and load -print("===== Dump and Load KVCacheMemory =====") -kv_mem.dump("tmp/kv_mem") -print("Memory dumped to 'tmp/kv_mem'.") -kv_mem.delete_all() -kv_mem.load("tmp/kv_mem") -print("Memory loaded from 'tmp/kv_mem':", kv_mem.get_all()) + ) + + # 2. Instantiate KVCacheMemory using the factory + kv_mem = MemoryFactory.from_config(config) + + # 3. Extract a KVCacheItem (DynamicCache) from a prompt (uses HFLLM.build_kv_cache internally) + prompt = [ + {"role": "user", "content": "What is MemOS?"}, + {"role": "assistant", "content": "MemOS is a memory operating system for LLMs."}, + ] + print("===== Extract KVCacheItem =====") + cache_item = kv_mem.extract(prompt) + print(json.dumps(serialize_item(cache_item), indent=2, default=str)) + print() + + # 4. Add the extracted KVCacheItem + print("===== Add KVCacheItem =====") + kv_mem.add([cache_item]) + print(json.dumps(serialize_item(kv_mem.get_all()), indent=2, default=str)) + print() + + # 5. Get by id + print("===== Get KVCacheItem by id =====") + retrieved = kv_mem.get(cache_item.id) + print(json.dumps(serialize_item(retrieved), indent=2, default=str)) + print() + + # 6. Merge caches (simulate with two items) + print("===== Merge DynamicCache =====") + item2 = kv_mem.extract([{"role": "user", "content": "Tell me a joke."}]) + kv_mem.add([item2]) + merged_cache = kv_mem.get_cache([cache_item.id, item2.id]) + print(json.dumps(serialize_item(merged_cache), indent=2, default=str)) + print() + + # 7. Delete one + print("===== Delete one KVCacheItem =====") + kv_mem.delete([cache_item.id]) + print(json.dumps(serialize_item(kv_mem.get_all()), indent=2, default=str)) + print() + + # 8. Dump and load + print("===== Dump and Load KVCacheMemory =====") + kv_mem.dump("tmp/kv_mem") + print("Memory dumped to 'tmp/kv_mem'.") + kv_mem.delete_all() + kv_mem.load("tmp/kv_mem") + print( + "Memory loaded from 'tmp/kv_mem':", + json.dumps(serialize_item(kv_mem.get_all()), indent=2, default=str), + ) diff --git a/examples/core_memories/vllm_kv_cache_memory.py b/examples/core_memories/vllm_kv_cache_memory.py index 65ae64911..7122200f6 100644 --- a/examples/core_memories/vllm_kv_cache_memory.py +++ b/examples/core_memories/vllm_kv_cache_memory.py @@ -20,7 +20,7 @@ def main(): "extractor_llm": { "backend": "vllm", "config": { - "model_name_or_path": "/mnt/afs/models/hf_models/Qwen2.5-7B", + "model_name_or_path": "Qwen/Qwen3-0.6B", "api_base": "http://localhost:8088/v1", "temperature": 0.7, "max_tokens": 1024, diff --git a/examples/mem_scheduler/api_w_scheduler.py b/examples/mem_scheduler/api_w_scheduler.py index 871dd0258..ba3d64bf1 100644 --- a/examples/mem_scheduler/api_w_scheduler.py +++ b/examples/mem_scheduler/api_w_scheduler.py @@ -1,85 +1,103 @@ +import sys + +from pathlib import Path from time import sleep -from memos.api.handlers.scheduler_handler import ( + +FILE_PATH = Path(__file__).absolute() +BASE_DIR = FILE_PATH.parent.parent.parent +sys.path.insert(0, str(BASE_DIR)) # Enable execution from any working directory + +from memos.api.handlers.scheduler_handler import ( # noqa: E402 handle_scheduler_status, handle_scheduler_wait, ) -from memos.api.routers.server_router import mem_scheduler, status_tracker -from memos.mem_scheduler.schemas.message_schemas import ScheduleMessageItem - - -# Debug: Print scheduler configuration -print("=== Scheduler Configuration Debug ===") -print(f"Scheduler type: {type(mem_scheduler).__name__}") -print(f"Config: {mem_scheduler.config}") -print(f"use_redis_queue: {mem_scheduler.use_redis_queue}") -print(f"Queue type: {type(mem_scheduler.memos_message_queue).__name__}") -print(f"Queue maxsize: {getattr(mem_scheduler.memos_message_queue, 'maxsize', 'N/A')}") -print("=====================================\n") - -queue = mem_scheduler.memos_message_queue -queue.clear() - - -# 1. Define a handler function -def my_test_handler(messages: list[ScheduleMessageItem]): - print(f"My test handler received {len(messages)} messages:") - for msg in messages: - print(f" my_test_handler - {msg.item_id}: {msg.content}") - user_status_running = handle_scheduler_status( - user_id=msg.user_id, status_tracker=status_tracker - ) - print("[Monitor] Status after submit:", user_status_running) +from memos.api.routers.server_router import mem_scheduler, status_tracker # noqa: E402 +from memos.mem_scheduler.schemas.message_schemas import ScheduleMessageItem # noqa: E402 -# 2. Register the handler TEST_HANDLER_LABEL = "test_handler" TEST_USER_ID = "test_user" -mem_scheduler.register_handlers({TEST_HANDLER_LABEL: my_test_handler}) - -# 2.1 Monitor global scheduler status before submitting tasks -global_status_before = handle_scheduler_status(user_id=TEST_USER_ID, status_tracker=status_tracker) -print("[Monitor] Global status before submit:", global_status_before) - -# 3. Create messages -messages_to_send = [ - ScheduleMessageItem( - item_id=f"test_item_{i}", - user_id=TEST_USER_ID, - mem_cube_id="test_mem_cube", - label=TEST_HANDLER_LABEL, - content=f"This is test message {i}", +USER_MEM_CUBE = "test_mem_cube" + + +def run_with_scheduler_api(): + # Debug: Print scheduler configuration + print("=== Scheduler Configuration Debug ===") + print(f"Scheduler type: {type(mem_scheduler).__name__}") + print(f"Config: {mem_scheduler.config}") + print(f"use_redis_queue: {mem_scheduler.use_redis_queue}") + print(f"Queue type: {type(mem_scheduler.memos_message_queue).__name__}") + print(f"Queue maxsize: {getattr(mem_scheduler.memos_message_queue, 'maxsize', 'N/A')}") + print("=====================================\n") + + queue = mem_scheduler.memos_message_queue + queue.clear() + + # 1. Define a handler function + def my_test_handler(messages: list[ScheduleMessageItem]): + print(f"My test handler received {len(messages)} messages:") + for msg in messages: + print(f" my_test_handler - {msg.item_id}: {msg.content}") + user_status_running = handle_scheduler_status( + user_id=msg.user_id, status_tracker=status_tracker + ) + print("[Monitor] Status after submit:", user_status_running) + + # 2. Register the handler + mem_scheduler.register_handlers({TEST_HANDLER_LABEL: my_test_handler}) + + # 2.1 Monitor global scheduler status before submitting tasks + global_status_before = handle_scheduler_status( + user_id=TEST_USER_ID, status_tracker=status_tracker ) - for i in range(5) -] + print("[Monitor] Global status before submit:", global_status_before) + + # 3. Create messages + messages_to_send = [ + ScheduleMessageItem( + item_id=f"test_item_{i}", + user_id=TEST_USER_ID, + mem_cube_id="test_mem_cube", + label=TEST_HANDLER_LABEL, + content=f"This is test message {i}", + ) + for i in range(5) + ] -# 5. Submit messages -for mes in messages_to_send: - print(f"Submitting message {mes.item_id} to the scheduler...") - mem_scheduler.submit_messages([mes]) - sleep(1) + # 5. Submit messages + for mes in messages_to_send: + print(f"Submitting message {mes.item_id} to the scheduler...") + mem_scheduler.submit_messages([mes]) + sleep(1) -# 5.1 Monitor status for specific mem_cube while running -USER_MEM_CUBE = "test_mem_cube" + # 5.1 Monitor status for specific mem_cube while running + # 6. Wait for messages to be processed (limited to 100 checks) -# 6. Wait for messages to be processed (limited to 100 checks) + user_status_running = handle_scheduler_status( + user_id=TEST_USER_ID, status_tracker=status_tracker + ) + print(f"[Monitor] Status for {USER_MEM_CUBE} after submit:", user_status_running) + + # 6.1 Wait until idle for specific mem_cube via handler + wait_result = handle_scheduler_wait( + user_name=TEST_USER_ID, + status_tracker=status_tracker, + timeout_seconds=120.0, + poll_interval=0.5, + ) + print(f"[Monitor] Wait result for {USER_MEM_CUBE}:", wait_result) -user_status_running = handle_scheduler_status(user_id=TEST_USER_ID, status_tracker=status_tracker) -print(f"[Monitor] Status for {USER_MEM_CUBE} after submit:", user_status_running) + # 6.2 Monitor global scheduler status after processing + global_status_after = handle_scheduler_status( + user_id=TEST_USER_ID, status_tracker=status_tracker + ) + print("[Monitor] Global status after processing:", global_status_after) -# 6.1 Wait until idle for specific mem_cube via handler -wait_result = handle_scheduler_wait( - user_name=TEST_USER_ID, - status_tracker=status_tracker, - timeout_seconds=120.0, - poll_interval=0.5, -) -print(f"[Monitor] Wait result for {USER_MEM_CUBE}:", wait_result) + # 7. Stop the scheduler + print("Stopping the scheduler...") + mem_scheduler.stop() -# 6.2 Monitor global scheduler status after processing -global_status_after = handle_scheduler_status(user_id=TEST_USER_ID, status_tracker=status_tracker) -print("[Monitor] Global status after processing:", global_status_after) -# 7. Stop the scheduler -print("Stopping the scheduler...") -mem_scheduler.stop() +if __name__ == "__main__": + run_with_scheduler_api() diff --git a/examples/mem_scheduler/debug_text_mem_replace.py b/examples/mem_scheduler/debug_text_mem_replace.py deleted file mode 100644 index a5de8e572..000000000 --- a/examples/mem_scheduler/debug_text_mem_replace.py +++ /dev/null @@ -1,109 +0,0 @@ -import json -import shutil -import sys - -from pathlib import Path - -from memos_w_scheduler_for_test import init_task - -from memos.configs.mem_cube import GeneralMemCubeConfig -from memos.configs.mem_os import MOSConfig -from memos.configs.mem_scheduler import AuthConfig -from memos.log import get_logger -from memos.mem_cube.general import GeneralMemCube -from memos.mem_scheduler.analyzer.mos_for_test_scheduler import MOSForTestScheduler - - -FILE_PATH = Path(__file__).absolute() -BASE_DIR = FILE_PATH.parent.parent.parent -sys.path.insert(0, str(BASE_DIR)) - -# Enable execution from any working directory - -logger = get_logger(__name__) - -if __name__ == "__main__": - # set up data - conversations, questions = init_task() - - # set configs - mos_config = MOSConfig.from_yaml_file( - f"{BASE_DIR}/examples/data/config/mem_scheduler/memos_config_w_optimized_scheduler.yaml" - ) - - mem_cube_config = GeneralMemCubeConfig.from_yaml_file( - f"{BASE_DIR}/examples/data/config/mem_scheduler/mem_cube_config_neo4j.yaml" - ) - - # default local graphdb uri - if AuthConfig.default_config_exists(): - auth_config = AuthConfig.from_local_config() - - mos_config.mem_reader.config.llm.config.api_key = auth_config.openai.api_key - mos_config.mem_reader.config.llm.config.api_base = auth_config.openai.base_url - - mem_cube_config.text_mem.config.graph_db.config.uri = auth_config.graph_db.uri - mem_cube_config.text_mem.config.graph_db.config.user = auth_config.graph_db.user - mem_cube_config.text_mem.config.graph_db.config.password = auth_config.graph_db.password - mem_cube_config.text_mem.config.graph_db.config.db_name = auth_config.graph_db.db_name - mem_cube_config.text_mem.config.graph_db.config.auto_create = ( - auth_config.graph_db.auto_create - ) - - # Initialization - mos = MOSForTestScheduler(mos_config) - - user_id = "user_1" - mos.create_user(user_id) - - mem_cube_id = "mem_cube_5" - mem_cube_name_or_path = f"{BASE_DIR}/outputs/mem_scheduler/{user_id}/{mem_cube_id}" - - if Path(mem_cube_name_or_path).exists(): - shutil.rmtree(mem_cube_name_or_path) - print(f"{mem_cube_name_or_path} is not empty, and has been removed.") - - mem_cube = GeneralMemCube(mem_cube_config) - mem_cube.dump(mem_cube_name_or_path) - mos.register_mem_cube( - mem_cube_name_or_path=mem_cube_name_or_path, mem_cube_id=mem_cube_id, user_id=user_id - ) - - mos.add(conversations, user_id=user_id, mem_cube_id=mem_cube_id) - - # Add interfering conversations - file_path = Path(f"{BASE_DIR}/examples/data/mem_scheduler/scene_data.json") - scene_data = json.load(file_path.open("r", encoding="utf-8")) - mos.add(scene_data[0], user_id=user_id, mem_cube_id=mem_cube_id) - mos.add(scene_data[1], user_id=user_id, mem_cube_id=mem_cube_id) - - # Test the replace_working_memory functionality - print("\n--- Testing replace_working_memory ---") - - # Get current working memories - text_mem_base = mem_cube.text_mem - if text_mem_base is not None: - working_memories_before = text_mem_base.get_working_memory() - print(f"Working memories before replacement: {len(working_memories_before)}") - - # Create filtered memories (simulate what the scheduler would do) - # Keep only memories related to Max - filtered_memories = [working_memories_before[1], working_memories_before[4]] - - text_mem_base.replace_working_memory(memories=filtered_memories) - - # Check working memory after replacement - working_memories_after = text_mem_base.get_working_memory() - print(f"Working memories after replacement: {len(working_memories_after)}") - - if len(working_memories_after) == len(filtered_memories): - print("✅ SUCCESS: Working memory count matches filtered memories") - else: - print( - f"❌ FAILED: Expected {len(filtered_memories)}, got {len(working_memories_after)}" - ) - - else: - print("❌ text_mem is None - not properly initialized") - - mos.mem_scheduler.stop() diff --git a/examples/mem_scheduler/memos_w_scheduler.py b/examples/mem_scheduler/memos_w_scheduler.py index ef7d853df..55e966b5a 100644 --- a/examples/mem_scheduler/memos_w_scheduler.py +++ b/examples/mem_scheduler/memos_w_scheduler.py @@ -1,32 +1,36 @@ -import re -import shutil +import asyncio +import json +import os import sys +import time -from datetime import datetime from pathlib import Path -from memos.configs.mem_cube import GeneralMemCubeConfig -from memos.configs.mem_os import MOSConfig -from memos.configs.mem_scheduler import AuthConfig -from memos.log import get_logger -from memos.mem_cube.general import GeneralMemCube -from memos.mem_os.main import MOS -from memos.mem_scheduler.schemas.message_schemas import ScheduleLogForWebItem -from memos.mem_scheduler.schemas.task_schemas import ( - ADD_TASK_LABEL, - ANSWER_TASK_LABEL, - MEM_ARCHIVE_TASK_LABEL, - MEM_ORGANIZE_TASK_LABEL, - MEM_UPDATE_TASK_LABEL, - QUERY_TASK_LABEL, -) -from memos.mem_scheduler.utils.filter_utils import transform_name_to_key - +# Setup paths before imports that depend on them FILE_PATH = Path(__file__).absolute() BASE_DIR = FILE_PATH.parent.parent.parent sys.path.insert(0, str(BASE_DIR)) # Enable execution from any working directory +# Set environment variables before importing server_router to ensure components are initialized correctly +os.environ["ENABLE_CHAT_API"] = "true" + +from memos.api.product_models import APIADDRequest, ChatPlaygroundRequest # noqa: E402 + +# Import from server_router for initialization +from memos.api.routers.server_router import ( # noqa: E402 + add_handler, + chat_stream_playground, + mem_scheduler, +) +from memos.log import get_logger # noqa: E402 +from memos.mem_scheduler.schemas.message_schemas import ScheduleMessageItem # noqa: E402 +from memos.mem_scheduler.schemas.task_schemas import ( # noqa: E402 + MEM_UPDATE_TASK_LABEL, + QUERY_TASK_LABEL, +) + + logger = get_logger(__name__) @@ -73,150 +77,106 @@ def init_task(): return conversations, questions -def _truncate_with_rules(text: str) -> str: - has_cjk = bool(re.search(r"[\u4e00-\u9fff]", text)) - limit = 32 if has_cjk else 64 - normalized = text.strip().replace("\n", " ") - if len(normalized) <= limit: - return normalized - return normalized[:limit] + "..." - - -def _format_title(ts: datetime, title_text: str) -> str: - return f"{ts.astimezone().strftime('%H:%M:%S')} {title_text}" - - -def _cube_display_from(mem_cube_id: str) -> str: - if "public" in (mem_cube_id or "").lower(): - return "PublicMemCube" - return "UserMemCube" - - -_TYPE_SHORT = { - "LongTermMemory": "LTM", - "UserMemory": "User", - "WorkingMemory": "Working", - "ActivationMemory": "Activation", - "ParameterMemory": "Parameter", - "TextMemory": "Text", - "UserInput": "Input", - "NotApplicable": "NA", -} - - -def _format_entry(item: ScheduleLogForWebItem) -> tuple[str, str]: - cube_display = getattr(item, "memcube_name", None) or _cube_display_from(item.mem_cube_id) - label = item.label - content = item.log_content or "" - memcube_content = getattr(item, "memcube_log_content", None) or [] - memory_len = getattr(item, "memory_len", None) or len(memcube_content) or 1 - - def _first_content() -> str: - if memcube_content: - return memcube_content[0].get("content", "") or content - return content - - if label in ("addMessage", QUERY_TASK_LABEL, ANSWER_TASK_LABEL): - target_cube = cube_display.replace("MemCube", "") - title = _format_title(item.timestamp, f"addMessages to {target_cube} MemCube") - return title, _truncate_with_rules(_first_content()) - - if label in ("addMemory", ADD_TASK_LABEL): - title = _format_title(item.timestamp, f"{cube_display} added {memory_len} memories") - return title, _truncate_with_rules(_first_content()) - - if label in ("updateMemory", MEM_UPDATE_TASK_LABEL): - title = _format_title(item.timestamp, f"{cube_display} updated {memory_len} memories") - return title, _truncate_with_rules(_first_content()) - - if label in ("archiveMemory", MEM_ARCHIVE_TASK_LABEL): - title = _format_title(item.timestamp, f"{cube_display} archived {memory_len} memories") - return title, _truncate_with_rules(_first_content()) - - if label in ("mergeMemory", MEM_ORGANIZE_TASK_LABEL): - title = _format_title(item.timestamp, f"{cube_display} merged {memory_len} memories") - merged = [c for c in memcube_content if c.get("type") == "merged"] - post = [c for c in memcube_content if c.get("type") == "postMerge"] - parts = [] - if merged: - parts.append("Merged: " + " | ".join(c.get("content", "") for c in merged)) - if post: - parts.append("Result: " + " | ".join(c.get("content", "") for c in post)) - detail = " ".join(parts) if parts else _first_content() - return title, _truncate_with_rules(detail) - - if label == "scheduleMemory": - title = _format_title(item.timestamp, f"{cube_display} scheduled {memory_len} memories") - if memcube_content: - return title, _truncate_with_rules(memcube_content[0].get("content", "")) - key = transform_name_to_key(content) - from_short = _TYPE_SHORT.get(item.from_memory_type, item.from_memory_type) - to_short = _TYPE_SHORT.get(item.to_memory_type, item.to_memory_type) - return title, _truncate_with_rules(f"[{from_short}→{to_short}] {key}: {content}") - - title = _format_title(item.timestamp, f"{cube_display} event") - return title, _truncate_with_rules(_first_content()) - - -def run_with_scheduler_init(): - print("==== run_with_automatic_scheduler_init ====") - conversations, questions = init_task() - - # set configs - mos_config = MOSConfig.from_yaml_file( - f"{BASE_DIR}/examples/data/config/mem_scheduler/memos_config_w_optimized_scheduler.yaml" - ) - - mem_cube_config = GeneralMemCubeConfig.from_yaml_file( - f"{BASE_DIR}/examples/data/config/mem_scheduler/mem_cube_config_neo4j.yaml" - ) - - # default local graphdb uri - if AuthConfig.default_config_exists(): - auth_config = AuthConfig.from_local_config() +working_memories = [] + + +# Define custom query handler function +def custom_query_handler(messages: list[ScheduleMessageItem]): + for msg in messages: + # Print user input content + print(f"\n[scheduler] User input query: {msg.content}") + # Manually construct a new message with MEM_UPDATE label to trigger memory update + new_msg = msg.model_copy(update={"label": MEM_UPDATE_TASK_LABEL}) + # Submit the message to the scheduler for processing + mem_scheduler.submit_messages([new_msg]) + + +# Define custom memory update handler function +def custom_mem_update_handler(messages: list[ScheduleMessageItem]): + global working_memories + search_args = {} + top_k = 2 + for msg in messages: + # Search for memories relevant to the current content in text memory (return top_k=2) + results = mem_scheduler.retriever.search( + query=msg.content, + user_id=msg.user_id, + mem_cube_id=msg.mem_cube_id, + mem_cube=mem_scheduler.current_mem_cube, + top_k=top_k, + method=mem_scheduler.search_method, + search_args=search_args, + ) + working_memories.extend(results) + working_memories = working_memories[-5:] + for mem in results: + print(f"\n[scheduler] Retrieved memory: {mem.memory}") - mos_config.mem_reader.config.llm.config.api_key = auth_config.openai.api_key - mos_config.mem_reader.config.llm.config.api_base = auth_config.openai.base_url - mem_cube_config.text_mem.config.graph_db.config.uri = auth_config.graph_db.uri - mem_cube_config.text_mem.config.graph_db.config.user = auth_config.graph_db.user - mem_cube_config.text_mem.config.graph_db.config.password = auth_config.graph_db.password - mem_cube_config.text_mem.config.graph_db.config.db_name = auth_config.graph_db.db_name - mem_cube_config.text_mem.config.graph_db.config.auto_create = ( - auth_config.graph_db.auto_create - ) +async def run_with_scheduler(): + print("==== run_with_automatic_scheduler_init ====") + conversations, questions = init_task() - # Initialization - mos = MOS(mos_config) + # Initialization using server_router components + # Configs are loaded via environment variables in init_server() user_id = "user_1" - mos.create_user(user_id) - mem_cube_id = "mem_cube_5" - mem_cube_name_or_path = f"{BASE_DIR}/outputs/mem_scheduler/{user_id}/{mem_cube_id}" - if Path(mem_cube_name_or_path).exists(): - shutil.rmtree(mem_cube_name_or_path) - print(f"{mem_cube_name_or_path} is not empty, and has been removed.") + print(f"Adding conversations for user {user_id}...") - mem_cube = GeneralMemCube(mem_cube_config) - mem_cube.dump(mem_cube_name_or_path) - mos.register_mem_cube( - mem_cube_name_or_path=mem_cube_name_or_path, mem_cube_id=mem_cube_id, user_id=user_id + # Use add_handler to add memories + add_req = APIADDRequest( + user_id=user_id, + writable_cube_ids=[mem_cube_id], + messages=conversations, + async_mode="sync", # Use sync mode for immediate addition in this example ) - - mos.add(conversations, user_id=user_id, mem_cube_id=mem_cube_id) - mos.mem_scheduler.current_mem_cube = mem_cube + add_handler.handle_add_memories(add_req) for item in questions: print("===== Chat Start =====") query = item["question"] print(f"Query:\n {query}\n") - response = mos.chat(query=query, user_id=user_id) - print(f"Answer:\n {response}\n") - mos.mem_scheduler.stop() + # Use chat_handler to chat + chat_req = ChatPlaygroundRequest( + user_id=user_id, + query=query, + readable_cube_ids=[mem_cube_id], + writable_cube_ids=[mem_cube_id], + ) + response = chat_stream_playground(chat_req) + + answer = "" + buffer = "" + async for chunk in response.body_iterator: + if isinstance(chunk, bytes): + chunk = chunk.decode("utf-8") + buffer += chunk + while "\n\n" in buffer: + msg, buffer = buffer.split("\n\n", 1) + for line in msg.split("\n"): + if line.startswith("data: "): + json_str = line[6:] + try: + data = json.loads(json_str) + if data.get("type") == "text": + answer += data["data"] + except json.JSONDecodeError: + pass + print(f"\nAnswer: {answer}") if __name__ == "__main__": - run_with_scheduler_init() + mem_scheduler.register_handlers( + { + QUERY_TASK_LABEL: custom_query_handler, # Query task + MEM_UPDATE_TASK_LABEL: custom_mem_update_handler, # Memory update task + } + ) + + asyncio.run(run_with_scheduler()) + + time.sleep(20) + mem_scheduler.stop() diff --git a/examples/mem_scheduler/memos_w_scheduler_for_test.py b/examples/mem_scheduler/memos_w_scheduler_for_test.py deleted file mode 100644 index 2e135f127..000000000 --- a/examples/mem_scheduler/memos_w_scheduler_for_test.py +++ /dev/null @@ -1,88 +0,0 @@ -import json -import shutil -import sys - -from pathlib import Path - -from memos_w_scheduler import init_task - -from memos.configs.mem_cube import GeneralMemCubeConfig -from memos.configs.mem_os import MOSConfig -from memos.configs.mem_scheduler import AuthConfig -from memos.log import get_logger -from memos.mem_cube.general import GeneralMemCube -from memos.mem_scheduler.analyzer.mos_for_test_scheduler import MOSForTestScheduler - - -FILE_PATH = Path(__file__).absolute() -BASE_DIR = FILE_PATH.parent.parent.parent -sys.path.insert(0, str(BASE_DIR)) - -# Enable execution from any working directory - -logger = get_logger(__name__) - -if __name__ == "__main__": - # set up data - conversations, questions = init_task() - - # set configs - mos_config = MOSConfig.from_yaml_file( - f"{BASE_DIR}/examples/data/config/mem_scheduler/memos_config_w_optimized_scheduler.yaml" - ) - - mem_cube_config = GeneralMemCubeConfig.from_yaml_file( - f"{BASE_DIR}/examples/data/config/mem_scheduler/mem_cube_config_neo4j.yaml" - ) - - # default local graphdb uri - if AuthConfig.default_config_exists(): - auth_config = AuthConfig.from_local_config() - - mos_config.mem_reader.config.llm.config.api_key = auth_config.openai.api_key - mos_config.mem_reader.config.llm.config.api_base = auth_config.openai.base_url - - mem_cube_config.text_mem.config.graph_db.config.uri = auth_config.graph_db.uri - mem_cube_config.text_mem.config.graph_db.config.user = auth_config.graph_db.user - mem_cube_config.text_mem.config.graph_db.config.password = auth_config.graph_db.password - mem_cube_config.text_mem.config.graph_db.config.db_name = auth_config.graph_db.db_name - mem_cube_config.text_mem.config.graph_db.config.auto_create = ( - auth_config.graph_db.auto_create - ) - - # Initialization - mos = MOSForTestScheduler(mos_config) - - user_id = "user_1" - mos.create_user(user_id) - - mem_cube_id = "mem_cube_5" - mem_cube_name_or_path = f"{BASE_DIR}/outputs/mem_scheduler/{user_id}/{mem_cube_id}" - - if Path(mem_cube_name_or_path).exists(): - shutil.rmtree(mem_cube_name_or_path) - print(f"{mem_cube_name_or_path} is not empty, and has been removed.") - - mem_cube = GeneralMemCube(mem_cube_config) - mem_cube.dump(mem_cube_name_or_path) - mos.register_mem_cube( - mem_cube_name_or_path=mem_cube_name_or_path, mem_cube_id=mem_cube_id, user_id=user_id - ) - mos.mem_scheduler.current_mem_cube = mem_cube - - mos.add(conversations, user_id=user_id, mem_cube_id=mem_cube_id) - - # Add interfering conversations - file_path = Path(f"{BASE_DIR}/examples/data/mem_scheduler/scene_data.json") - scene_data = json.load(file_path.open("r", encoding="utf-8")) - mos.add(scene_data[0], user_id=user_id, mem_cube_id=mem_cube_id) - mos.add(scene_data[1], user_id=user_id, mem_cube_id=mem_cube_id) - - for item in questions: - print("===== Chat Start =====") - query = item["question"] - print(f"Query:\n {query}\n") - response = mos.chat(query=query, user_id=user_id) - print(f"Answer:\n {response}\n") - - mos.mem_scheduler.stop() diff --git a/examples/mem_scheduler/quick_start_examples.py b/examples/mem_scheduler/quick_start_examples.py deleted file mode 100644 index 724663be6..000000000 --- a/examples/mem_scheduler/quick_start_examples.py +++ /dev/null @@ -1,312 +0,0 @@ -import json -import shutil -import sys -import uuid - -from pathlib import Path - -from transformers import DynamicCache - -from memos.configs.mem_cube import GeneralMemCubeConfig -from memos.configs.mem_os import MOSConfig -from memos.configs.memory import MemoryConfigFactory -from memos.mem_cube.general import GeneralMemCube -from memos.mem_os.main import MOS -from memos.mem_scheduler.schemas.message_schemas import ScheduleMessageItem -from memos.mem_scheduler.schemas.task_schemas import ( - ANSWER_TASK_LABEL, - MEM_UPDATE_TASK_LABEL, - QUERY_TASK_LABEL, -) -from memos.mem_scheduler.utils.db_utils import get_utc_now -from memos.mem_scheduler.utils.misc_utils import parse_yaml -from memos.memories.activation.item import KVCacheItem -from memos.memories.factory import MemoryFactory - - -FILE_PATH = Path(__file__).absolute() -BASE_DIR = FILE_PATH.parent.parent.parent -sys.path.insert(0, str(BASE_DIR)) # Enable execution from any working directory - - -def get_cache_info(cache): - if not cache: - return None - - num_layers = 0 - total_size_bytes = 0 - - if hasattr(cache, "layers"): - num_layers = len(cache.layers) - for layer in cache.layers: - if hasattr(layer, "key_cache") and layer.key_cache is not None: - total_size_bytes += layer.key_cache.nelement() * layer.key_cache.element_size() - if hasattr(layer, "value_cache") and layer.value_cache is not None: - total_size_bytes += layer.value_cache.nelement() * layer.value_cache.element_size() - - if hasattr(layer, "keys") and layer.keys is not None: - total_size_bytes += layer.keys.nelement() * layer.keys.element_size() - if hasattr(layer, "values") and layer.values is not None: - total_size_bytes += layer.values.nelement() * layer.values.element_size() - - elif hasattr(cache, "key_cache") and hasattr(cache, "value_cache"): - num_layers = len(cache.key_cache) - for k, v in zip(cache.key_cache, cache.value_cache, strict=False): - if k is not None: - total_size_bytes += k.nelement() * k.element_size() - if v is not None: - total_size_bytes += v.nelement() * v.element_size() - - return { - "num_layers": num_layers, - "size_bytes": total_size_bytes, - "size_mb": f"{total_size_bytes / (1024 * 1024):.2f} MB", - } - - -def serialize_item(obj): - if isinstance(obj, list): - return [serialize_item(x) for x in obj] - - if isinstance(obj, KVCacheItem): - return { - "id": obj.id, - "metadata": obj.metadata, - "records": obj.records.model_dump() - if hasattr(obj.records, "model_dump") - else obj.records, - "memory": get_cache_info(obj.memory), - } - - if isinstance(obj, DynamicCache): - return get_cache_info(obj) - - return str(obj) - - -def kv_cache_only(): - # 为 KVCacheMemory(HuggingFace 后端)创建配置 - config = MemoryConfigFactory( - backend="kv_cache", - config={ - "extractor_llm": { - "backend": "huggingface", - "config": { - "model_name_or_path": "Qwen/Qwen3-0.6B", - "max_tokens": 32, - "add_generation_prompt": True, - "remove_think_prefix": True, - }, - }, - }, - ) - - # 实例化 KVCacheMemory - kv_mem = MemoryFactory.from_config(config) - - # 提取一个 KVCacheItem(DynamicCache) - prompt = [ - {"role": "user", "content": "What is MemOS?"}, - {"role": "assistant", "content": "MemOS is a memory operating system for LLMs."}, - ] - print("===== Extract KVCacheItem =====") - cache_item = kv_mem.extract(prompt) - print(json.dumps(serialize_item(cache_item), indent=2, default=str)) - - # 将缓存添加到内存中 - kv_mem.add([cache_item]) - print("All caches:") - print(json.dumps(serialize_item(kv_mem.get_all()), indent=2, default=str)) - - # 通过 ID 获取 - retrieved = kv_mem.get(cache_item.id) - print("Retrieved:") - print(json.dumps(serialize_item(retrieved), indent=2, default=str)) - - # 合并缓存 - item2 = kv_mem.extract([{"role": "user", "content": "Tell me a joke."}]) - kv_mem.add([item2]) - merged = kv_mem.get_cache([cache_item.id, item2.id]) - print("Merged cache:") - print(json.dumps(serialize_item(merged), indent=2, default=str)) - - # 删除其中一个 - kv_mem.delete([cache_item.id]) - print("After delete:") - print(json.dumps(serialize_item(kv_mem.get_all()), indent=2, default=str)) - - # 导出和加载缓存 - kv_mem.dump("tmp/kv_mem") - print("Dumped to tmp/kv_mem") - kv_mem.delete_all() - kv_mem.load("tmp/kv_mem") - print("Loaded caches:") - print(json.dumps(serialize_item(kv_mem.get_all()), indent=2, default=str)) - - -def run_scheduler_example(): - # 使用 MemScheduler 加载主 MOS(Memory-Oriented System)配置文件 - config = parse_yaml( - f"{BASE_DIR}/examples/data/config/mem_scheduler/memos_config_w_scheduler.yaml" - ) - # 将解析出的配置字典传入 MOSConfig 构造器, 构建配置对象 - mos_config = MOSConfig(**config) - # 使用配置对象初始化 MOS 系统实例 - mos = MOS(mos_config) - - # 生成一个唯一的动态用户 ID(使用 UUID4) - user_id = str(uuid.uuid4()) - # 在 MOS 系统中为该用户创建账户 - mos.create_user(user_id=user_id) - - # 从 YAML 文件加载 MemCube(记忆立方体)的通用配置 - config = GeneralMemCubeConfig.from_yaml_file( - f"{BASE_DIR}/examples/data/config/mem_scheduler/mem_cube_config.yaml" - ) - # 定义 MemCube 的唯一标识符 - mem_cube_id = "mem_cube_5" - # 定义 MemCube 的本地存储路径(路径中包含用户 ID 和 MemCube ID) - mem_cube_name_or_path = f"{BASE_DIR}/outputs/mem_scheduler/{user_id}/{mem_cube_id}" - - # 如果该路径已存在, 则先删除旧目录 - if Path(mem_cube_name_or_path).exists(): - shutil.rmtree(mem_cube_name_or_path) - print(f"{mem_cube_name_or_path} 目录非空，已被删除。") - - # 根据加载的配置创建一个新的 MemCube 实例 - mem_cube = GeneralMemCube(config) - # 将该 MemCube 实例序列化并保存到指定路径 - mem_cube.dump(mem_cube_name_or_path) - - # 在 MOS 系统中为当前用户注册这个 MemCube - mos.register_mem_cube( - mem_cube_name_or_path=mem_cube_name_or_path, mem_cube_id=mem_cube_id, user_id=user_id - ) - - # 定义一个辅助函数, 用于获取缓存(如 KV Cache)的内存信息 - def get_cache_info(cache): - # 如果缓存为空, 则直接返回 None - if not cache: - return None - - num_layers = 0 # 记录缓存的层数 - total_size_bytes = 0 # 记录总字节数 - - # 情况一: 缓存结构包含 layers 属性(如 HuggingFace 的缓存格式) - if hasattr(cache, "layers"): - num_layers = len(cache.layers) - for layer in cache.layers: - # 统计 key_cache 的内存占用(如果存在) - if hasattr(layer, "key_cache") and layer.key_cache is not None: - total_size_bytes += layer.key_cache.nelement() * layer.key_cache.element_size() - # 统计 value_cache 的内存占用(如果存在) - if hasattr(layer, "value_cache") and layer.value_cache is not None: - total_size_bytes += ( - layer.value_cache.nelement() * layer.value_cache.element_size() - ) - - # 兼容其他可能的缓存命名方式(如 keys/values) - if hasattr(layer, "keys") and layer.keys is not None: - total_size_bytes += layer.keys.nelement() * layer.keys.element_size() - if hasattr(layer, "values") and layer.values is not None: - total_size_bytes += layer.values.nelement() * layer.values.element_size() - - # 情况二: 缓存结构直接包含 key_cache 和 value_cache 列表(如某些自定义格式) - elif hasattr(cache, "key_cache") and hasattr(cache, "value_cache"): - num_layers = len(cache.key_cache) - for k, v in zip(cache.key_cache, cache.value_cache, strict=False): - if k is not None: - total_size_bytes += k.nelement() * k.element_size() - if v is not None: - total_size_bytes += v.nelement() * v.element_size() - - # 返回结构化的缓存信息, 包括层数, 字节数和以 MB 为单位的可读格式 - return { - "num_layers": num_layers, - "size_bytes": total_size_bytes, - "size_mb": f"{total_size_bytes / (1024 * 1024):.2f} MB", - } - - # 定义自定义的查询(query)处理函数 - def custom_query_handler(messages: list[ScheduleMessageItem]): - for msg in messages: - # 打印用户输入内容 - print(f"\n[scheduler] 用户输入了查询：{msg.content}") - # 手动构造一个带有 MEM_UPDATE 标签的新消息, 用于触发记忆更新 - new_msg = msg.model_copy(update={"label": MEM_UPDATE_TASK_LABEL}) - # 将该消息提交给调度器处理 - mos.mem_scheduler.submit_messages([new_msg]) - - # 定义自定义的回答(answer)处理函数 - def custom_answer_handler(messages: list[ScheduleMessageItem]): - for msg in messages: - # 打印 LLM 的回复内容 - print(f"\n[scheduler] LLM 回复了答案：{msg.content}") - - # 定义自定义的记忆更新(mem_update)处理函数 - def custom_mem_update_handler(messages: list[ScheduleMessageItem]): - for msg in messages: - mem_cube = mos.mem_cubes.get(msg.mem_cube_id) - kv_mem = mem_cube.act_mem - # 如果该 MemCube 配置了文本记忆(TreeTextMemory / NaiveTextMemory) - if mem_cube and mem_cube.text_mem: - # 在文本记忆中搜索与当前内容相关的记忆(返回 top_k=3 条) - results = mem_cube.text_mem.search(msg.content, top_k=3) - for mem in results: - print(f"\n[scheduler] 检索到的记忆：{mem.memory}") - print("\n[scheduler] 转换为激活记忆......") - # 从文本记忆中提取对应的 KV 缓存项 - cache_item = kv_mem.extract(mem.memory) - # 附加元信息 - cache_item.records.text_memories = [mem.memory] - cache_item.records.timestamp = get_utc_now() - # 将该缓存项添加到激活记忆中 - kv_mem.add([cache_item]) - print("\n[scheduler] 完成！") - - # 将上述三个自定义处理器注册到调度器的分发器中, 分别对应不同任务标签 - mos.mem_scheduler.dispatcher.register_handlers( - { - QUERY_TASK_LABEL: custom_query_handler, # 查询任务 - ANSWER_TASK_LABEL: custom_answer_handler, # 回答任务 - MEM_UPDATE_TASK_LABEL: custom_mem_update_handler, # 记忆更新任务 - } - ) - - # 初始添加两条测试消息(用户和助手的对话)到系统中 - messages = [ - {"role": "user", "content": "I like playing football."}, - {"role": "assistant", "content": "I like playing football too."}, - ] - mos.add(messages, user_id=user_id, mem_cube_id=mem_cube_id) - - # 进入聊天循环: 展示 TreeTextMemory 的记忆节点结构 + KV Cache 的状态 - while True: - # 获取用户输入并去除首尾空格 - user_input = input("👤 [You] ").strip() - print() - # 调用 MOS 系统进行聊天响应 - response = mos.chat(user_input, user_id=user_id) - # 获取该用户当前 MemCube 中的所有记忆内容 - retrieved_memories = mos.get_all(mem_cube_id=mem_cube_id, user_id=user_id) - - # 打印助手的回复 - print(f"🤖 [Assistant] {response}") - - # 获取文本记忆部分 - TreeTextMemory - memories = retrieved_memories["text_mem"][0]["memories"] - for mem in memories: - print(f"[文本记忆] {mem.memory}") - - # 获取对应的 MemCube 和其激活记忆(KV Cache) - mem_cube = mos.mem_scheduler.mem_cube - kv_mem = mem_cube.act_mem - # 遍历所有激活记忆项, 打印其缓存信息和记录 - for cache_item in kv_mem.get_all(): - print(f"[激活记忆] {get_cache_info(cache_item.memory)} （记录：{cache_item.records}）") - - -if __name__ == "__main__": - kv_cache_only() - - run_scheduler_example() diff --git a/examples/mem_scheduler/rabbitmq_example.py b/examples/mem_scheduler/rabbitmq_example.py deleted file mode 100644 index 5e40eaad5..000000000 --- a/examples/mem_scheduler/rabbitmq_example.py +++ /dev/null @@ -1,60 +0,0 @@ -import threading -import time - -from memos.configs.mem_scheduler import AuthConfig -from memos.mem_scheduler.webservice_modules.rabbitmq_service import RabbitMQSchedulerModule - - -def publish_message(rabbitmq_module, message): - """Function to publish a message.""" - rabbitmq_module.rabbitmq_publish_message(message) - print(f"Published message: {message}\n") - - -def main(): - # Initialize RabbitMQ module - rabbitmq_module = RabbitMQSchedulerModule() - rabbitmq_module.rabbit_queue_name = "test" - - # Initialize from configuration dictionary - if not AuthConfig.default_config_exists(): - print("Please set configs for rabbitmq.") - return - else: - rabbitmq_module.initialize_rabbitmq(config=AuthConfig.from_local_config().rabbitmq) - - try: - rabbitmq_module.wait_for_connection_ready() - - # === Publish some test messages === - # List to hold thread references - threads = [] - - # Publish some test messages using multiple threads - for i in range(3): - message = {"type": "test", "data": f"Message {i}", "timestamp": time.time()} - thread = threading.Thread(target=publish_message, args=(rabbitmq_module, message)) - thread.start() - threads.append(thread) - - # Start consumer - rabbitmq_module.rabbitmq_start_consuming() - - # Join threads to ensure all messages are published before proceeding - for thread in threads: - thread.join() - - except KeyboardInterrupt: - print("\nProgram interrupted by user") - - finally: - # Give some time for cleanup - time.sleep(3) - - # Close connections - rabbitmq_module.rabbitmq_close() - print("RabbitMQ connection closed") - - -if __name__ == "__main__": - main() diff --git a/examples/mem_scheduler/redis_example.py b/examples/mem_scheduler/redis_example.py index be6f20bed..9f7ca4139 100644 --- a/examples/mem_scheduler/redis_example.py +++ b/examples/mem_scheduler/redis_example.py @@ -1,5 +1,5 @@ -import asyncio import sys +import time from datetime import datetime from pathlib import Path @@ -64,7 +64,7 @@ def service_run(): print( f"Added: {res}", ) - asyncio.sleep(0.5) + time.sleep(0.5) mem_scheduler.redis_stop_listening() diff --git a/examples/mem_scheduler/scheduler_for_async_tasks.py b/examples/mem_scheduler/run_async_tasks.py similarity index 100% rename from examples/mem_scheduler/scheduler_for_async_tasks.py rename to examples/mem_scheduler/run_async_tasks.py diff --git a/examples/mem_scheduler/show_redis_status.py b/examples/mem_scheduler/show_redis_status.py index 04e79ca97..d88e86655 100644 --- a/examples/mem_scheduler/show_redis_status.py +++ b/examples/mem_scheduler/show_redis_status.py @@ -7,50 +7,46 @@ queue = mem_scheduler.memos_message_queue.memos_message_queue -def fetch_status(queue: SchedulerRedisQueue) -> dict[str, dict[str, int]]: +def fetch_status( + queue: SchedulerRedisQueue, stream_key_prefix: str | None = None +) -> dict[str, dict[str, int]]: """Fetch and print per-user Redis queue status using built-in API. - Returns a dict mapping user_id -> {"pending": int, "remaining": int}. + Returns a dict mapping user_id -> {"remaining": int}. """ # This method will also print a summary and per-user counts. - return queue.show_task_status() + return queue.show_task_status(stream_key_prefix=stream_key_prefix) def print_diff(prev: dict[str, dict[str, int]], curr: dict[str, dict[str, int]]) -> None: """Print aggregated totals and per-user changes compared to previous snapshot.""" ts = time.strftime("%Y-%m-%d %H:%M:%S") - tot_p_prev = sum(v.get("pending", 0) for v in prev.values()) if prev else 0 tot_r_prev = sum(v.get("remaining", 0) for v in prev.values()) if prev else 0 - tot_p_curr = sum(v.get("pending", 0) for v in curr.values()) tot_r_curr = sum(v.get("remaining", 0) for v in curr.values()) - dp_tot = tot_p_curr - tot_p_prev dr_tot = tot_r_curr - tot_r_prev - print(f"[{ts}] Total pending={tot_p_curr} ({dp_tot:+d}), remaining={tot_r_curr} ({dr_tot:+d})") + print(f"[{ts}] Total remaining={tot_r_curr} ({dr_tot:+d})") # Print per-user deltas (current counts are already printed by show_task_status) all_uids = sorted(set(prev.keys()) | set(curr.keys())) for uid in all_uids: - p_prev = prev.get(uid, {}).get("pending", 0) r_prev = prev.get(uid, {}).get("remaining", 0) - p_curr = curr.get(uid, {}).get("pending", 0) r_curr = curr.get(uid, {}).get("remaining", 0) - dp = p_curr - p_prev dr = r_curr - r_prev # Only print when there is any change to reduce noise - if dp != 0 or dr != 0: - print(f" Δ {uid}: pending={dp:+d}, remaining={dr:+d}") + if dr != 0: + print(f" Δ {uid}: remaining={dr:+d}") # Note: queue.show_task_status() handles printing per-user counts internally. -def main(interval_sec: float = 5.0) -> None: +def main(interval_sec: float = 5.0, stream_key_prefix: str | None = None) -> None: prev: dict[str, dict[str, int]] = {} while True: try: - curr = fetch_status(queue) + curr = fetch_status(queue, stream_key_prefix=stream_key_prefix) print_diff(prev, curr) print(f"stream_cache ({len(queue._stream_keys_cache)}): {queue._stream_keys_cache}") prev = curr @@ -64,4 +60,11 @@ def main(interval_sec: float = 5.0) -> None: if __name__ == "__main__": - main() + import argparse + + parser = argparse.ArgumentParser() + parser.add_argument("--interval", type=float, default=1.0) + parser.add_argument("--prefix", type=str, default=None) + args = parser.parse_args() + + main(interval_sec=args.interval, stream_key_prefix=args.prefix) diff --git a/examples/mem_scheduler/task_fair_schedule.py b/examples/mem_scheduler/task_fair_schedule.py deleted file mode 100644 index 8b02b1931..000000000 --- a/examples/mem_scheduler/task_fair_schedule.py +++ /dev/null @@ -1,87 +0,0 @@ -import sys - -from collections import defaultdict -from pathlib import Path - -from memos.api.routers.server_router import mem_scheduler -from memos.mem_scheduler.schemas.message_schemas import ScheduleMessageItem - - -FILE_PATH = Path(__file__).absolute() -BASE_DIR = FILE_PATH.parent.parent.parent -sys.path.insert(0, str(BASE_DIR)) - - -def make_message(user_id: str, mem_cube_id: str, label: str, idx: int | str) -> ScheduleMessageItem: - return ScheduleMessageItem( - item_id=f"{user_id}:{mem_cube_id}:{label}:{idx}", - user_id=user_id, - mem_cube_id=mem_cube_id, - label=label, - content=f"msg-{idx} for {user_id}/{mem_cube_id}/{label}", - ) - - -def seed_messages_for_test_fairness(queue, combos, per_stream): - # send overwhelm message by one user - (u, c, label) = combos[0] - task_target = 100 - print(f"{u}:{c}:{label} submit {task_target} messages") - for i in range(task_target): - msg = make_message(u, c, label, f"overwhelm_{i}") - queue.submit_messages(msg) - - for u, c, label in combos: - print(f"{u}:{c}:{label} submit {per_stream} messages") - for i in range(per_stream): - msg = make_message(u, c, label, i) - queue.submit_messages(msg) - print("======= seed_messages Done ===========") - - -def count_by_stream(messages): - counts = defaultdict(int) - for m in messages: - key = f"{m.user_id}:{m.mem_cube_id}:{m.label}" - counts[key] += 1 - return counts - - -def run_fair_redis_schedule(batch_size: int = 3): - print("=== Redis Fairness Demo ===") - print(f"use_redis_queue: {mem_scheduler.use_redis_queue}") - mem_scheduler.consume_batch = batch_size - queue = mem_scheduler.memos_message_queue - - # Isolate and clear queue - queue.clear() - - # Define multiple streams: (user_id, mem_cube_id, task_label) - combos = [ - ("u1", "u1", "labelX"), - ("u1", "u1", "labelY"), - ("u2", "u2", "labelX"), - ("u2", "u2", "labelY"), - ] - per_stream = 5 - - # Seed messages evenly across streams - seed_messages_for_test_fairness(queue, combos, per_stream) - - # Compute target batch size (fair split across streams) - print(f"Request batch_size={batch_size} for {len(combos)} streams") - - for _ in range(len(combos)): - # Fetch one brokered pack - msgs = queue.get_messages(batch_size=batch_size) - print(f"Fetched {len(msgs)} messages in first pack") - - # Check fairness: counts per stream - counts = count_by_stream(msgs) - for k in sorted(counts): - print(f"{k}: {counts[k]}") - - -if __name__ == "__main__": - # task 1 fair redis schedule - run_fair_redis_schedule() diff --git a/src/memos/api/config.py b/src/memos/api/config.py index daf9b6cfe..204b0961c 100644 --- a/src/memos/api/config.py +++ b/src/memos/api/config.py @@ -23,7 +23,7 @@ # Load environment variables -load_dotenv() +load_dotenv(override=True) logger = logging.getLogger(__name__) diff --git a/src/memos/api/start_api.py b/src/memos/api/start_api.py index cbcdf6ce2..24a36f017 100644 --- a/src/memos/api/start_api.py +++ b/src/memos/api/start_api.py @@ -20,7 +20,7 @@ logger = logging.getLogger(__name__) # Load environment variables -load_dotenv() +load_dotenv(override=True) T = TypeVar("T") diff --git a/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py b/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py index 1c9683542..d570dccdd 100644 --- a/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py +++ b/src/memos/mem_scheduler/task_schedule_modules/redis_queue.py @@ -983,34 +983,21 @@ def qsize(self) -> dict: logger.error(f"Failed to get Redis queue size: {e}", stack_info=True) return {} - def show_task_status(self) -> dict[str, dict[str, int]]: - stream_keys = self.get_stream_keys(stream_key_prefix=self.stream_key_prefix) + def show_task_status(self, stream_key_prefix: str | None = None) -> dict[str, dict[str, int]]: + effective_prefix = ( + stream_key_prefix if stream_key_prefix is not None else self.stream_key_prefix + ) + stream_keys = self.get_stream_keys(stream_key_prefix=effective_prefix) if not stream_keys: - logger.info("No Redis streams found for the configured prefix") + logger.info(f"No Redis streams found for the configured prefix: {effective_prefix}") return {} - consumer_group = self.consumer_group or "scheduler_group" - grouped: dict[str, dict[str, int]] = {} for sk in stream_keys: uid = sk if uid not in grouped: - grouped[uid] = {"pending": 0, "remaining": 0} - - # Pending count via XPENDING - pending_count = 0 - try: - pending_info = self._redis_conn.xpending(sk, consumer_group) - # redis-py may return a tuple-like [count, ...] - if pending_info: - try: - pending_count = int(pending_info[0]) - except Exception: - # Fallback if structure differs - pending_count = int(getattr(pending_info, "count", 0) or 0) - except Exception as e: - logger.debug(f"XPENDING failed for '{sk}': {e}") + grouped[uid] = {"remaining": 0} # Remaining count via XLEN remaining_count = 0 @@ -1019,20 +1006,16 @@ def show_task_status(self) -> dict[str, dict[str, int]]: except Exception as e: logger.debug(f"XLEN failed for '{sk}': {e}") - grouped[uid]["pending"] += pending_count grouped[uid]["remaining"] += remaining_count # Pretty-print summary try: - total_pending = sum(v.get("pending", 0) for v in grouped.values()) total_remaining = sum(v.get("remaining", 0) for v in grouped.values()) - header = f"Task Queue Status by user_id | pending={total_pending}, remaining={total_remaining}" + header = f"Task Queue Status by user_id | remaining={total_remaining}" print(header) for uid in sorted(grouped.keys()): counts = grouped[uid] - print( - f"- {uid}: pending={counts.get('pending', 0)}, remaining={counts.get('remaining', 0)}" - ) + print(f"- {uid}: remaining={counts.get('remaining', 0)}") except Exception: # Printing is best-effort; return grouped regardless pass From 78ca96c2d2f9f3a2c73e7e9ff2979601c6f6a5b7 Mon Sep 17 00:00:00 2001 From: Dubberman <48425266+whipser030@users.noreply.github.com> Date: Thu, 15 Jan 2026 20:40:12 +0800 Subject: [PATCH 33/47] fix:feedback mute pref (#876) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * feedback mute pref * mute pref feedback --------- Co-authored-by: 黑布林 <11641432+heiheiyouyou@user.noreply.gitee.com> --- src/memos/mem_feedback/feedback.py | 14 +++++++++----- src/memos/mem_feedback/simple_feedback.py | 2 ++ 2 files changed, 11 insertions(+), 5 deletions(-) diff --git a/src/memos/mem_feedback/feedback.py b/src/memos/mem_feedback/feedback.py index 15d7c336a..da3324572 100644 --- a/src/memos/mem_feedback/feedback.py +++ b/src/memos/mem_feedback/feedback.py @@ -95,6 +95,7 @@ def __init__(self, config: MemFeedbackConfig): self.searcher: Searcher = None self.reranker = None self.pref_mem: SimplePreferenceTextMemory = None + self.pref_feedback: bool = False self.DB_IDX_READY = False @require_python_package( @@ -629,11 +630,14 @@ def _retrieve(self, query: str, info=None, top_k=20, user_name=None): ) retrieved_mems = [item[0] for item in retrieved_mems if float(item[1]) > 0.01] - pref_info = {} - if "user_id" in info: - pref_info = {"user_id": info["user_id"]} - retrieved_prefs = self.pref_mem.search(query, top_k, pref_info) - return retrieved_mems + retrieved_prefs + if self.pref_feedback: + pref_info = {} + if "user_id" in info: + pref_info = {"user_id": info["user_id"]} + retrieved_prefs = self.pref_mem.search(query, top_k, pref_info) + return retrieved_mems + retrieved_prefs + else: + return retrieved_mems def _vec_query(self, new_memories_embedding: list[float], user_name=None): """Vector retrieval query""" diff --git a/src/memos/mem_feedback/simple_feedback.py b/src/memos/mem_feedback/simple_feedback.py index e32f939c7..2ac0a0a39 100644 --- a/src/memos/mem_feedback/simple_feedback.py +++ b/src/memos/mem_feedback/simple_feedback.py @@ -25,6 +25,7 @@ def __init__( searcher: Searcher, reranker: BaseReranker, pref_mem: SimplePreferenceTextMemory, + pref_feedback: bool = False, ): self.llm = llm self.embedder = embedder @@ -36,3 +37,4 @@ def __init__( self.pref_mem = pref_mem self.reranker = reranker self.DB_IDX_READY = False + self.pref_feedback = pref_feedback From 51a98ebc3017d28a5118eae1b33a2b8d8fa8a63f Mon Sep 17 00:00:00 2001 From: Wenqiang Wei <46308778+endxxxx@users.noreply.github.com> Date: Fri, 16 Jan 2026 14:22:16 +0800 Subject: [PATCH 34/47] =?UTF-8?q?examples=20update=20from=20tree=5Ftextual?= =?UTF-8?q?=5Fmemories=20and=20preference=5Ftextual=5Fmem=E2=80=A6=20(#872?= =?UTF-8?q?)?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit examples update from tree_textual_memories and preference_textual_memories --- examples/core_memories/pref_textual_memory.py | 192 ++++++++++++++++++ examples/core_memories/tree_textual_memory.py | 28 +++ examples/data/config/preference_config.json | 53 +++++ .../config/tree_config_shared_database.json | 3 +- 4 files changed, 275 insertions(+), 1 deletion(-) create mode 100644 examples/core_memories/pref_textual_memory.py create mode 100644 examples/data/config/preference_config.json diff --git a/examples/core_memories/pref_textual_memory.py b/examples/core_memories/pref_textual_memory.py new file mode 100644 index 000000000..ca9d471b9 --- /dev/null +++ b/examples/core_memories/pref_textual_memory.py @@ -0,0 +1,192 @@ +import time + +from memos import log +from memos.configs.memory import PreferenceTextMemoryConfig +from memos.memories.textual.preference import PreferenceTextMemory + + +logger = log.get_logger(__name__) + +preference_config = PreferenceTextMemoryConfig.from_json_file( + "examples/data/config/preference_config.json" +) +my_preference_textual_memory = PreferenceTextMemory(preference_config) +my_preference_textual_memory.delete_all() + + +scene_data = [ + [ + {"role": "user", "chat_time": "3 May 2025", "content": "I’m feeling a bit down today."}, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "I’m sorry to hear that. Do you want to talk about what’s been going on?", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "It’s just been a tough couple of days, you know? Everything feels a bit overwhelming, and I just can’t seem to shake it off.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "It sounds like you're going through a lot right now. Sometimes it helps to talk things out. Is there something specific that's been weighing on you, or is it more of a general feeling?", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "It’s a mix, I guess. Work’s been really stressful, and on top of that, I’ve been feeling kinda disconnected from the people around me.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "That can be really draining, especially when you’re feeling isolated on top of the stress. Do you think there’s something from your past that’s contributing to how you’re feeling now? Sometimes our emotions are tied to older experiences.", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "Yeah, now that you mention it… I’ve been thinking a lot about my childhood lately. I didn’t have the easiest upbringing. My parents were always busy, and I often felt like I had to figure things out on my own. I remember one winter, I got really sick with a high fever. My parents were both working, and I didn’t want to bother them. I just lay in bed, crying by myself, not knowing what to do.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "That must have been very lonely. Growing up without that support can really make you feel like you have to handle everything on your own. How do you think that experience has affected you now?", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "Yeah, it was really lonely. I remember spending a lot of time doing things on my own, like drawing, because it was my only way to escape. I used to draw animals, and I created my own little world on paper. It was peaceful in a way, just me and my imagination, with no outside distractions.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "Drawing sounds like a beautiful way to express yourself and find some peace in that solitude. It must have been a very quiet and private world for you. Do you think that sense of loneliness from back then has shaped how you connect with others today?", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "I think it has. I’ve always found it hard to let others in. I feel like I have to handle everything on my own. If I rely on someone else, I feel vulnerable, and I start to feel that loneliness again.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "It sounds like this was a protective mechanism that helped you cope with your feelings of loneliness back then. But as you’ve grown, it seems like this pattern might not be serving you as well anymore. Have you thought about trying to break this cycle, or finding new ways to connect with others?", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "I’ve thought about it, though it’s hard. But I also know I can’t keep going like this forever. Maybe it’s time to seek some help.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "It’s a big step, but a positive one. Exploring your emotions and past experiences could really help you understand how they’ve shaped your present. Therapy could be a great place to start, as it would help you connect with both yourself and others. Would you be open to trying it?", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "I’m open to trying. Thank you for encouraging me. It feels like it might be a good starting point for me.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "I’m really glad to hear that. Taking that first step is always difficult, but you’ve made an important decision. If you need help finding the right therapist, or just want to talk, I’m here for you.", + }, + ], + [ + { + "role": "user", + "chat_time": "3 May 2025", + "content": "This week I’ve been feeling a bit off, especially when playing tennis. My body just doesn’t feel right.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "It sounds like you've been having some physical discomfort lately. Where specifically are you feeling unwell? Is there something particular about tennis that's been difficult?", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "I just feel a bit fatigued, and every time I play tennis, my movements feel off. I used to play pretty well, but lately, I’ve been feeling weak and my movements aren’t as coordinated as they used to be.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "Physical discomfort can definitely affect performance, especially in a sport like tennis that requires quick reactions and coordination. Have you noticed anything specific that might be causing these changes? Could it be overtraining, or is there another physical issue making you feel off?", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "I think it might be due to stress and lack of sleep recently. I just feel drained all the time. Plus, I’ve been frustrated with my tennis performance, which makes me feel even worse, like I’m stuck in a vicious cycle.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "Stress and poor sleep quality can definitely affect your physical performance, especially in sports. When you’re also feeling down about your performance, it’s easy to fall into a negative cycle. Have you tried anything to relieve some of the stress, or to improve your sleep?", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "I’ve tried some relaxation techniques, like deep breathing and simple meditation, but it doesn’t seem to help much. I still can’t focus during tennis, and I feel like my mind is distracted by other things.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "Relaxation techniques like deep breathing and meditation can help reduce stress, but sometimes we need a more structured approach to improve both our physical and mental state. For example, you might want to focus on specific aspects of your tennis training, or adjust your rest and recovery time. Have you thought about setting smaller goals for yourself? Like focusing on a specific tennis move each day, rather than expecting perfection right away? That might help you gradually regain confidence.", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "That’s a good idea. I think I’ve been expecting too much from myself, which just makes me more anxious. Maybe I can start with small practice sessions and gradually find my rhythm again.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "Exactly! Setting small and clear goals will help reduce pressure and give you a sense of accomplishment. And don’t forget that rest is just as important—taking time to recover will help you feel better physically and mentally. Both physical and mental recovery are key to improving your performance and health.", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "Thanks, I feel like I need to rethink a few things. Maybe I really need to be kinder to myself and take things step by step.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "You’re on the right track. Rethinking things and giving yourself space and patience is so important. You’ve already taken the first step, now just keep moving forward, one step at a time. If you need anything, I’m always here to help.", + }, + ], +] + +memories = my_preference_textual_memory.get_memory( + scene_data, type="chat", info={"user_id": "1234", "session_id": "2222"} +) + +added_ids = my_preference_textual_memory.add(memories) + +time.sleep(10) + +init_time = time.time() +# search preference memories +results = my_preference_textual_memory.search("Talk about childhood story of the user", top_k=10) + +for i, r in enumerate(results): + r = r.to_dict() + print(f"{i}'th similar result is: " + str(r["memory"])) +print(f"Successfully search {len(results)} memories in {round(time.time() - init_time)}s") + +# get all preference memories +all_preference_memories = my_preference_textual_memory.get_all() +for key, value in all_preference_memories.items(): + for i, m in enumerate(value): + print(f"{i}'th {key} memory is: " + str(m.memory)) + +# use filter to get all implicit preference memories +all_implicit_memories = my_preference_textual_memory.get_memory_by_filter( + {"preference_type": "implicit_preference"} +) +for i, m in enumerate(all_implicit_memories[0]): + print(f"{i}'th filtered memory is: " + str(m.memory)) + +# dump preference memories +dumped_memories_dir = "tmp/my_preference_textual_memory" +my_preference_textual_memory.dump(dumped_memories_dir) diff --git a/examples/core_memories/tree_textual_memory.py b/examples/core_memories/tree_textual_memory.py index d2e197e5b..641335495 100644 --- a/examples/core_memories/tree_textual_memory.py +++ b/examples/core_memories/tree_textual_memory.py @@ -3,6 +3,7 @@ from memos import log from memos.configs.mem_reader import SimpleStructMemReaderConfig from memos.configs.memory import TreeTextMemoryConfig +from memos.mem_reader.multi_modal_struct import MultiModalStructMemReader from memos.mem_reader.simple_struct import SimpleStructMemReader from memos.memories.textual.tree import TreeTextMemory @@ -240,6 +241,33 @@ top_k=30, info={"query": "Tell me about what memos consist of?", "user_id": "111", "session": "2234"}, ) + +for i, r in enumerate(results): + r = r.to_dict() + print(f"{i}'th similar result is: " + str(r["memory"])) +print(f"Successfully search {len(results)} memories") + +logger.info("start multi-modal memory search example...") + +multi_modal_reader = MultiModalStructMemReader(reader_config) +doc_paths = ["examples/data/one_page_example.pdf"] +multi_modal_memory = multi_modal_reader.get_memory( + doc_paths, "doc", info={"user_id": "1111", "session_id": "2222"} +) + +for m_list in multi_modal_memory: + added_ids = my_tree_textual_memory.add(m_list) + my_tree_textual_memory.memory_manager.wait_reorganizer() + +results = my_tree_textual_memory.search( + "Give me one poem from Tagore's 'Stray birds'", + top_k=30, + info={ + "query": "Give me one poem from Tagore's 'Stray birds'", + "user_id": "111", + "session": "2234", + }, +) for i, r in enumerate(results): r = r.to_dict() print(f"{i}'th similar result is: " + str(r["memory"])) diff --git a/examples/data/config/preference_config.json b/examples/data/config/preference_config.json new file mode 100644 index 000000000..4db7475a0 --- /dev/null +++ b/examples/data/config/preference_config.json @@ -0,0 +1,53 @@ +{ + "extractor_llm": { + "backend": "ollama", + "config": { + "model_name_or_path": "qwen3:0.6b", + "temperature": 0.0, + "remove_think_prefix": true, + "max_tokens": 8192 + } + }, + "vector_db": { + "backend": "milvus", + "config": { + "collection_name": [ + "explicit_preference", + "implicit_preference" + ], + "vector_dimension": 768, + "distance_metric": "cosine", + "uri": "./milvus_demo.db" + } + }, + "embedder": { + "backend": "ollama", + "config": { + "model_name_or_path": "nomic-embed-text:latest" + } + }, + "reranker": { + "backend": "cosine_local", + "config": { + "level_weights": { + "topic": 1.0, + "concept": 1.0, + "fact": 1.0 + }, + "level_field": "background" + } + }, + "extractor": { + "backend": "naive", + "config": {} + }, + "adder": { + "backend": "naive", + "config": {} + }, + "retriever": { + "backend": "naive", + "config": {} + }, + "memory_filename": "preference_textual_memories.json" +} diff --git a/examples/data/config/tree_config_shared_database.json b/examples/data/config/tree_config_shared_database.json index 914f3c725..889a4a592 100644 --- a/examples/data/config/tree_config_shared_database.json +++ b/examples/data/config/tree_config_shared_database.json @@ -36,5 +36,6 @@ "embedding_dimension": 768 } }, - "reorganize": true + "reorganize": true, + "memory_filename": "tree_textual_memories.json" } From a90d256bdc5a0a8923ed27b239666181fb96229e Mon Sep 17 00:00:00 2001 From: novaleolin <15062791135@163.com> Date: Fri, 16 Jan 2026 14:27:06 +0800 Subject: [PATCH 35/47] feat(examples): update basic modules examples and configs (#856) * feat(examples): update basic modules examples and configs * feat: update MCP examples and internet search * docs: api reference --------- Co-authored-by: nova Co-authored-by: CaralHsi --- docs/openapi.json | 3596 +++++++++++++---- .../textual_memory_internet_search_example.py | 307 +- .../tree_textual_memory_recall.py | 203 +- ...textual_memory_relation_reason_detector.py | 272 +- .../tree_textual_memory_task_goal_parser.py | 205 +- .../config/simple_struct_reader_config.json | 22 +- .../config/tree_config_shared_database.json | 58 +- examples/mem_mcp/simple_fastmcp_client.py | 69 +- examples/mem_mcp/simple_fastmcp_serve.py | 77 +- src/memos/api/mcp_serve.py | 80 +- src/memos/cli.py | 2 +- tests/test_openapi_sync.py | 2 +- 12 files changed, 3870 insertions(+), 1023 deletions(-) diff --git a/docs/openapi.json b/docs/openapi.json index 46d715147..d9ef710b5 100644 --- a/docs/openapi.json +++ b/docs/openapi.json @@ -1,21 +1,24 @@ { "openapi": "3.1.0", "info": { - "title": "MemOS REST APIs", - "description": "A REST API for managing and searching memories using MemOS.", - "version": "1.0.0" + "title": "MemOS Server REST APIs", + "description": "A REST API for managing multiple users with MemOS Server.", + "version": "1.0.1" }, "paths": { - "/configure": { + "/product/search": { "post": { - "summary": "Configure MemOS", - "description": "Set MemOS configuration.", - "operationId": "set_config_configure_post", + "tags": [ + "Server API" + ], + "summary": "Search memories", + "description": "Search memories for a specific user.\n\nThis endpoint uses the class-based SearchHandler for better code organization.", + "operationId": "search_memories_product_search_post", "requestBody": { "content": { "application/json": { "schema": { - "$ref": "#/components/schemas/MOSConfig" + "$ref": "#/components/schemas/APISearchRequest" } } }, @@ -27,7 +30,7 @@ "content": { "application/json": { "schema": { - "$ref": "#/components/schemas/ConfigResponse" + "$ref": "#/components/schemas/SearchResponse" } } } @@ -45,33 +48,19 @@ } } }, - "/users": { - "get": { - "summary": "List all users", - "description": "List all active users.", - "operationId": "list_users_users_get", - "responses": { - "200": { - "description": "Successful Response", - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/UserListResponse" - } - } - } - } - } - }, + "/product/add": { "post": { - "summary": "Create a new user", - "description": "Create a new user.", - "operationId": "create_user_users_post", + "tags": [ + "Server API" + ], + "summary": "Add memories", + "description": "Add memories for a specific user.\n\nThis endpoint uses the class-based AddHandler for better code organization.", + "operationId": "add_memories_product_add_post", "requestBody": { "content": { "application/json": { "schema": { - "$ref": "#/components/schemas/UserCreate" + "$ref": "#/components/schemas/APIADDRequest" } } }, @@ -83,7 +72,7 @@ "content": { "application/json": { "schema": { - "$ref": "#/components/schemas/UserResponse" + "$ref": "#/components/schemas/MemoryResponse" } } } @@ -101,57 +90,21 @@ } } }, - "/users/me": { + "/product/scheduler/allstatus": { "get": { - "summary": "Get current user info", - "description": "Get current user information including accessible cubes.", - "operationId": "get_user_info_users_me_get", - "responses": { - "200": { - "description": "Successful Response", - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/UserResponse" - } - } - } - } - } - } - }, - "/mem_cubes": { - "post": { - "summary": "Register a MemCube", - "description": "Register a new MemCube.", - "operationId": "register_mem_cube_mem_cubes_post", - "requestBody": { - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/MemCubeRegister" - } - } - }, - "required": true - }, + "tags": [ + "Server API" + ], + "summary": "Get detailed scheduler status", + "description": "Get detailed scheduler status including running tasks and queue metrics.", + "operationId": "scheduler_allstatus_product_scheduler_allstatus_get", "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": { - "$ref": "#/components/schemas/SimpleResponse" - } - } - } - }, - "422": { - "description": "Validation Error", - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/HTTPValidationError" + "$ref": "#/components/schemas/AllStatusResponse" } } } @@ -159,23 +112,28 @@ } } }, - "/mem_cubes/{mem_cube_id}": { - "delete": { - "summary": "Unregister a MemCube", - "description": "Unregister a MemCube.", - "operationId": "unregister_mem_cube_mem_cubes__mem_cube_id__delete", + "/product/scheduler/status": { + "get": { + "tags": [ + "Server API" + ], + "summary": "Get scheduler running status", + "description": "Get scheduler running status.", + "operationId": "scheduler_status_product_scheduler_status_get", "parameters": [ { - "name": "mem_cube_id", - "in": "path", + "name": "user_id", + "in": "query", "required": true, "schema": { "type": "string", - "title": "Mem Cube Id" - } + "description": "User ID", + "title": "User Id" + }, + "description": "User ID" }, { - "name": "user_id", + "name": "task_id", "in": "query", "required": false, "schema": { @@ -187,8 +145,10 @@ "type": "null" } ], - "title": "User Id" - } + "description": "Optional Task ID to query a specific task", + "title": "Task Id" + }, + "description": "Optional Task ID to query a specific task" } ], "responses": { @@ -197,7 +157,7 @@ "content": { "application/json": { "schema": { - "$ref": "#/components/schemas/SimpleResponse" + "$ref": "#/components/schemas/StatusResponse" } } } @@ -215,39 +175,34 @@ } } }, - "/mem_cubes/{cube_id}/share": { - "post": { - "summary": "Share a cube with another user", - "description": "Share a cube with another user.", - "operationId": "share_cube_mem_cubes__cube_id__share_post", + "/product/scheduler/task_queue_status": { + "get": { + "tags": [ + "Server API" + ], + "summary": "Get scheduler task queue status", + "description": "Get scheduler task queue backlog/pending status for a user.", + "operationId": "scheduler_task_queue_status_product_scheduler_task_queue_status_get", "parameters": [ { - "name": "cube_id", - "in": "path", + "name": "user_id", + "in": "query", "required": true, "schema": { "type": "string", - "title": "Cube Id" - } + "description": "User ID whose queue status is requested", + "title": "User Id" + }, + "description": "User ID whose queue status is requested" } ], - "requestBody": { - "required": true, - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/CubeShare" - } - } - } - }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": { - "$ref": "#/components/schemas/SimpleResponse" + "$ref": "#/components/schemas/TaskQueueResponse" } } } @@ -265,79 +220,42 @@ } } }, - "/memories": { + "/product/scheduler/wait": { "post": { - "summary": "Create memories", - "description": "Store new memories in a MemCube.", - "operationId": "add_memory_memories_post", - "requestBody": { - "required": true, - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/MemoryCreate" - } - } - } - }, - "responses": { - "200": { - "description": "Successful Response", - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/SimpleResponse" - } - } + "tags": [ + "Server API" + ], + "summary": "Wait until scheduler is idle for a specific user", + "description": "Wait until scheduler is idle for a specific user.", + "operationId": "scheduler_wait_product_scheduler_wait_post", + "parameters": [ + { + "name": "user_name", + "in": "query", + "required": true, + "schema": { + "type": "string", + "title": "User Name" } }, - "422": { - "description": "Validation Error", - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/HTTPValidationError" - } - } - } - } - } - }, - "get": { - "summary": "Get all memories", - "description": "Retrieve all memories from a MemCube.", - "operationId": "get_all_memories_memories_get", - "parameters": [ { - "name": "mem_cube_id", + "name": "timeout_seconds", "in": "query", "required": false, "schema": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "title": "Mem Cube Id" + "type": "number", + "default": 120.0, + "title": "Timeout Seconds" } }, { - "name": "user_id", + "name": "poll_interval", "in": "query", "required": false, "schema": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "title": "User Id" + "type": "number", + "default": 0.5, + "title": "Poll Interval" } } ], @@ -346,9 +264,7 @@ "description": "Successful Response", "content": { "application/json": { - "schema": { - "$ref": "#/components/schemas/MemoryResponse" - } + "schema": {} } } }, @@ -365,44 +281,42 @@ } } }, - "/memories/{mem_cube_id}/{memory_id}": { + "/product/scheduler/wait/stream": { "get": { - "summary": "Get a memory", - "description": "Retrieve a specific memory by ID from a MemCube.", - "operationId": "get_memory_memories__mem_cube_id___memory_id__get", + "tags": [ + "Server API" + ], + "summary": "Stream scheduler progress for a user", + "description": "Stream scheduler progress via Server-Sent Events (SSE).", + "operationId": "scheduler_wait_stream_product_scheduler_wait_stream_get", "parameters": [ { - "name": "mem_cube_id", - "in": "path", + "name": "user_name", + "in": "query", "required": true, "schema": { "type": "string", - "title": "Mem Cube Id" + "title": "User Name" } }, { - "name": "memory_id", - "in": "path", - "required": true, + "name": "timeout_seconds", + "in": "query", + "required": false, "schema": { - "type": "string", - "title": "Memory Id" + "type": "number", + "default": 120.0, + "title": "Timeout Seconds" } }, { - "name": "user_id", + "name": "poll_interval", "in": "query", "required": false, "schema": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "title": "User Id" + "type": "number", + "default": 0.5, + "title": "Poll Interval" } } ], @@ -411,9 +325,7 @@ "description": "Successful Response", "content": { "application/json": { - "schema": { - "$ref": "#/components/schemas/MemoryResponse" - } + "schema": {} } } }, @@ -428,67 +340,32 @@ } } } - }, - "put": { - "summary": "Update a memory", - "description": "Update an existing memory in a MemCube.", - "operationId": "update_memory_memories__mem_cube_id___memory_id__put", - "parameters": [ - { - "name": "mem_cube_id", - "in": "path", - "required": true, - "schema": { - "type": "string", - "title": "Mem Cube Id" - } - }, - { - "name": "memory_id", - "in": "path", - "required": true, - "schema": { - "type": "string", - "title": "Memory Id" - } - }, - { - "name": "user_id", - "in": "query", - "required": false, - "schema": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "title": "User Id" - } - } + } + }, + "/product/chat/complete": { + "post": { + "tags": [ + "Server API" ], + "summary": "Chat with MemOS (Complete Response)", + "description": "Chat with MemOS for a specific user. Returns complete response (non-streaming).\n\nThis endpoint uses the class-based ChatHandler.", + "operationId": "chat_complete_product_chat_complete_post", "requestBody": { - "required": true, "content": { "application/json": { "schema": { - "type": "object", - "additionalProperties": true, - "title": "Updated Memory" + "$ref": "#/components/schemas/APIChatCompleteRequest" } } - } + }, + "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { - "schema": { - "$ref": "#/components/schemas/SimpleResponse" - } + "schema": {} } } }, @@ -503,55 +380,32 @@ } } } - }, - "delete": { - "summary": "Delete a memory", - "description": "Delete a specific memory from a MemCube.", - "operationId": "delete_memory_memories__mem_cube_id___memory_id__delete", - "parameters": [ - { - "name": "mem_cube_id", - "in": "path", - "required": true, - "schema": { - "type": "string", - "title": "Mem Cube Id" - } - }, - { - "name": "memory_id", - "in": "path", - "required": true, - "schema": { - "type": "string", - "title": "Memory Id" + } + }, + "/product/chat/stream": { + "post": { + "tags": [ + "Server API" + ], + "summary": "Chat with MemOS", + "description": "Chat with MemOS for a specific user. Returns SSE stream.\n\nThis endpoint uses the class-based ChatHandler which internally\ncomposes SearchHandler and AddHandler for a clean architecture.", + "operationId": "chat_stream_product_chat_stream_post", + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/ChatRequest" + } } }, - { - "name": "user_id", - "in": "query", - "required": false, - "schema": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "title": "User Id" - } - } - ], + "required": true + }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { - "schema": { - "$ref": "#/components/schemas/SimpleResponse" - } + "schema": {} } } }, @@ -568,16 +422,19 @@ } } }, - "/search": { + "/product/chat/stream/playground": { "post": { - "summary": "Search memories", - "description": "Search for memories across MemCubes.", - "operationId": "search_memories_search_post", + "tags": [ + "Server API" + ], + "summary": "Chat with MemOS playground", + "description": "Chat with MemOS for a specific user. Returns SSE stream.\n\nThis endpoint uses the class-based ChatHandler which internally\ncomposes SearchHandler and AddHandler for a clean architecture.", + "operationId": "chat_stream_playground_product_chat_stream_playground_post", "requestBody": { "content": { "application/json": { "schema": { - "$ref": "#/components/schemas/SearchRequest" + "$ref": "#/components/schemas/ChatPlaygroundRequest" } } }, @@ -588,8 +445,131 @@ "description": "Successful Response", "content": { "application/json": { - "schema": { - "$ref": "#/components/schemas/SearchResponse" + "schema": {} + } + } + }, + "422": { + "description": "Validation Error", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" + } + } + } + } + } + } + }, + "/product/suggestions": { + "post": { + "tags": [ + "Server API" + ], + "summary": "Get suggestion queries", + "description": "Get suggestion queries for a specific user with language preference.", + "operationId": "get_suggestion_queries_product_suggestions_post", + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/SuggestionRequest" + } + } + }, + "required": true + }, + "responses": { + "200": { + "description": "Successful Response", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/SuggestionResponse" + } + } + } + }, + "422": { + "description": "Validation Error", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" + } + } + } + } + } + } + }, + "/product/get_all": { + "post": { + "tags": [ + "Server API" + ], + "summary": "Get all memories for user", + "description": "Get all memories or subgraph for a specific user.\n\nIf search_query is provided, returns a subgraph based on the query.\nOtherwise, returns all memories of the specified type.", + "operationId": "get_all_memories_product_get_all_post", + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/GetMemoryPlaygroundRequest" + } + } + }, + "required": true + }, + "responses": { + "200": { + "description": "Successful Response", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/MemoryResponse" + } + } + } + }, + "422": { + "description": "Validation Error", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" + } + } + } + } + } + } + }, + "/product/get_memory": { + "post": { + "tags": [ + "Server API" + ], + "summary": "Get memories for user", + "operationId": "get_memories_product_get_memory_post", + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/GetMemoryRequest" + } + } + }, + "required": true + }, + "responses": { + "200": { + "description": "Successful Response", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/GetMemoryResponse" } } } @@ -607,107 +587,2013 @@ } } }, - "/memories/{mem_cube_id}": { - "delete": { - "summary": "Delete all memories", - "description": "Delete all memories from a MemCube.", - "operationId": "delete_all_memories_memories__mem_cube_id__delete", + "/product/get_memory/{memory_id}": { + "get": { + "tags": [ + "Server API" + ], + "summary": "Get memory by id", + "operationId": "get_memory_by_id_product_get_memory__memory_id__get", "parameters": [ { - "name": "mem_cube_id", + "name": "memory_id", "in": "path", "required": true, "schema": { "type": "string", - "title": "Mem Cube Id" + "title": "Memory Id" + } + } + ], + "responses": { + "200": { + "description": "Successful Response", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/GetMemoryResponse" + } + } } }, - { - "name": "user_id", - "in": "query", - "required": false, - "schema": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" + "422": { + "description": "Validation Error", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" } - ], - "title": "User Id" + } + } + } + } + } + }, + "/product/delete_memory": { + "post": { + "tags": [ + "Server API" + ], + "summary": "Delete memories for user", + "operationId": "delete_memories_product_delete_memory_post", + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/DeleteMemoryRequest" + } + } + }, + "required": true + }, + "responses": { + "200": { + "description": "Successful Response", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/DeleteMemoryResponse" + } + } + } + }, + "422": { + "description": "Validation Error", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" + } + } + } + } + } + } + }, + "/product/feedback": { + "post": { + "tags": [ + "Server API" + ], + "summary": "Feedback memories", + "description": "Feedback memories for a specific user.\n\nThis endpoint uses the class-based FeedbackHandler for better code organization.", + "operationId": "feedback_memories_product_feedback_post", + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/APIFeedbackRequest" + } + } + }, + "required": true + }, + "responses": { + "200": { + "description": "Successful Response", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/MemoryResponse" + } + } + } + }, + "422": { + "description": "Validation Error", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" + } + } + } + } + } + } + }, + "/product/get_user_names_by_memory_ids": { + "post": { + "tags": [ + "Server API" + ], + "summary": "Get user names by memory ids", + "description": "Get user names by memory ids.", + "operationId": "get_user_names_by_memory_ids_product_get_user_names_by_memory_ids_post", + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/GetUserNamesByMemoryIdsRequest" + } + } + }, + "required": true + }, + "responses": { + "200": { + "description": "Successful Response", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/GetUserNamesByMemoryIdsResponse" + } + } + } + }, + "422": { + "description": "Validation Error", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" + } + } } } + } + } + }, + "/product/exist_mem_cube_id": { + "post": { + "tags": [ + "Server API" ], + "summary": "Check if mem cube id exists", + "description": "Check if mem cube id exists.", + "operationId": "exist_mem_cube_id_product_exist_mem_cube_id_post", + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/ExistMemCubeIdRequest" + } + } + }, + "required": true + }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": { - "$ref": "#/components/schemas/SimpleResponse" + "$ref": "#/components/schemas/ExistMemCubeIdResponse" } } - } + } + }, + "422": { + "description": "Validation Error", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" + } + } + } + } + } + } + } + }, + "components": { + "schemas": { + "APIADDRequest": { + "properties": { + "user_id": { + "type": "string", + "title": "User Id", + "description": "User ID" + }, + "session_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Session Id", + "description": "Session ID. If not provided, a default session will be used." + }, + "task_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Task Id", + "description": "Task ID for monitering async tasks" + }, + "writable_cube_ids": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Writable Cube Ids", + "description": "List of cube IDs user can write for multi-cube add" + }, + "async_mode": { + "type": "string", + "enum": [ + "async", + "sync" + ], + "title": "Async Mode", + "description": "Whether to add memory in async mode. Use 'async' to enqueue background add (non-blocking), or 'sync' to add memories in the current call. Default: 'async'.", + "default": "async" + }, + "mode": { + "anyOf": [ + { + "type": "string", + "enum": [ + "fast", + "fine" + ] + }, + { + "type": "null" + } + ], + "title": "Mode", + "description": "(Internal) Add mode used only when async_mode='sync'. If set to 'fast', the handler will use a fast add pipeline. Ignored when async_mode='async'." + }, + "custom_tags": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Custom Tags", + "description": "Custom tags for this add request, e.g. ['Travel', 'family']. These tags can be used as filters in search." + }, + "info": { + "anyOf": [ + { + "additionalProperties": true, + "type": "object" + }, + { + "type": "null" + } + ], + "title": "Info", + "description": "Additional metadata for the add request. All keys can be used as filters in search. Example: {'agent_id': 'xxxxxx', 'app_id': 'xxxx', 'source_type': 'web', 'source_url': 'https://www.baidu.com', 'source_content': '西湖是杭州最著名的景点'}." + }, + "messages": { + "anyOf": [ + { + "type": "string" + }, + { + "items": { + "anyOf": [ + { + "$ref": "#/components/schemas/ChatCompletionSystemMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionUserMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionAssistantMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionToolMessageParam" + } + ] + }, + "type": "array" + }, + { + "items": { + "anyOf": [ + { + "$ref": "#/components/schemas/ChatCompletionContentPartTextParam" + }, + { + "$ref": "#/components/schemas/File" + } + ] + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Messages", + "description": "List of messages to store. Supports: - system / user / assistant messages with 'content' and 'chat_time'; - tool messages including: * tool_description (name, description, parameters), * tool_input (call_id, name, argument), * raw tool messages where content is str or list[str], * tool_output with structured output items (input_text / input_image / input_file, etc.). Also supports pure input items when there is no dialog." + }, + "chat_history": { + "anyOf": [ + { + "items": { + "anyOf": [ + { + "$ref": "#/components/schemas/ChatCompletionSystemMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionUserMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionAssistantMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionToolMessageParam" + } + ] + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Chat History", + "description": "Historical chat messages used internally by algorithms. If None, internal stored history will be used; if provided (even an empty list), this value will be used as-is." + }, + "is_feedback": { + "type": "boolean", + "title": "Is Feedback", + "description": "Whether this request represents user feedback. Default: False.", + "default": false + }, + "mem_cube_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Mem Cube Id", + "description": "(Deprecated) Target cube ID for this add request (optional for developer API)." + }, + "memory_content": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Memory Content", + "description": "(Deprecated) Plain memory content to store. Prefer using `messages`." + }, + "doc_path": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Doc Path", + "description": "(Deprecated / internal) Path to document to store." + }, + "source": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Source", + "description": "(Deprecated) Simple source tag of the memory. Prefer using `info.source_type` / `info.source_url`." + }, + "operation": { + "anyOf": [ + { + "items": { + "$ref": "#/components/schemas/PermissionDict" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Operation", + "description": "(Internal) Operation definitions for multi-cube write permissions." + } + }, + "type": "object", + "title": "APIADDRequest", + "description": "Request model for creating memories." + }, + "APIChatCompleteRequest": { + "properties": { + "user_id": { + "type": "string", + "title": "User Id", + "description": "User ID" + }, + "query": { + "type": "string", + "title": "Query", + "description": "Chat query message" + }, + "readable_cube_ids": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Readable Cube Ids", + "description": "List of cube IDs user can read for multi-cube chat" + }, + "writable_cube_ids": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Writable Cube Ids", + "description": "List of cube IDs user can write for multi-cube chat" + }, + "history": { + "anyOf": [ + { + "items": { + "anyOf": [ + { + "$ref": "#/components/schemas/ChatCompletionSystemMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionUserMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionAssistantMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionToolMessageParam" + } + ] + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "History", + "description": "Chat history" + }, + "mode": { + "$ref": "#/components/schemas/SearchMode", + "description": "search mode: fast, fine, or mixture", + "default": "fast" + }, + "system_prompt": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "System Prompt", + "description": "Base system prompt to use for chat" + }, + "top_k": { + "type": "integer", + "title": "Top K", + "description": "Number of results to return", + "default": 10 + }, + "session_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Session Id", + "description": "Session ID for soft-filtering memories" + }, + "include_preference": { + "type": "boolean", + "title": "Include Preference", + "description": "Whether to handle preference memory", + "default": true + }, + "pref_top_k": { + "type": "integer", + "title": "Pref Top K", + "description": "Number of preference results to return", + "default": 6 + }, + "model_name_or_path": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Model Name Or Path", + "description": "Model name to use for chat" + }, + "max_tokens": { + "anyOf": [ + { + "type": "integer" + }, + { + "type": "null" + } + ], + "title": "Max Tokens", + "description": "Max tokens to generate" + }, + "temperature": { + "anyOf": [ + { + "type": "number" + }, + { + "type": "null" + } + ], + "title": "Temperature", + "description": "Temperature for sampling" + }, + "top_p": { + "anyOf": [ + { + "type": "number" + }, + { + "type": "null" + } + ], + "title": "Top P", + "description": "Top-p (nucleus) sampling parameter" + }, + "add_message_on_answer": { + "type": "boolean", + "title": "Add Message On Answer", + "description": "Add dialogs to memory after chat", + "default": true + }, + "filter": { + "anyOf": [ + { + "additionalProperties": true, + "type": "object" + }, + { + "type": "null" + } + ], + "title": "Filter", + "description": "\n Filter for the memory, example:\n {\n \"`and` or `or`\": [\n {\"id\": \"uuid-xxx\"},\n {\"created_at\": {\"gt\": \"2024-01-01\"}},\n ]\n }\n " + }, + "internet_search": { + "type": "boolean", + "title": "Internet Search", + "description": "Whether to use internet search", + "default": false + }, + "threshold": { + "type": "number", + "title": "Threshold", + "description": "Threshold for filtering references", + "default": 0.5 + }, + "mem_cube_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Mem Cube Id", + "description": "Cube ID to use for chat" + }, + "moscube": { + "type": "boolean", + "title": "Moscube", + "description": "(Deprecated) Whether to use legacy MemOSCube pipeline", + "default": false + } + }, + "type": "object", + "required": [ + "user_id", + "query" + ], + "title": "APIChatCompleteRequest", + "description": "Request model for chat operations." + }, + "APIFeedbackRequest": { + "properties": { + "user_id": { + "type": "string", + "title": "User Id", + "description": "User ID" + }, + "session_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Session Id", + "description": "Session ID for soft-filtering memories", + "default": "default_session" + }, + "task_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Task Id", + "description": "Task ID for monitering async tasks" + }, + "history": { + "anyOf": [ + { + "items": { + "anyOf": [ + { + "$ref": "#/components/schemas/ChatCompletionSystemMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionUserMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionAssistantMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionToolMessageParam" + } + ] + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "History", + "description": "Chat history" + }, + "retrieved_memory_ids": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Retrieved Memory Ids", + "description": "Retrieved memory ids at last turn" + }, + "feedback_content": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Feedback Content", + "description": "Feedback content to process" + }, + "feedback_time": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Feedback Time", + "description": "Feedback time" + }, + "writable_cube_ids": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Writable Cube Ids", + "description": "List of cube IDs user can write for multi-cube add" + }, + "async_mode": { + "type": "string", + "enum": [ + "sync", + "async" + ], + "title": "Async Mode", + "description": "feedback mode: sync or async", + "default": "async" + }, + "corrected_answer": { + "type": "boolean", + "title": "Corrected Answer", + "description": "Whether need return corrected answer", + "default": false + }, + "info": { + "anyOf": [ + { + "additionalProperties": true, + "type": "object" + }, + { + "type": "null" + } + ], + "title": "Info", + "description": "Additional metadata for the add request. All keys can be used as filters in search. Example: {'agent_id': 'xxxxxx', 'app_id': 'xxxx', 'source_type': 'web', 'source_url': 'https://www.baidu.com', 'source_content': 'West Lake is the most famous scenic spot in Hangzhou'}." + }, + "mem_cube_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Mem Cube Id", + "description": "(Deprecated) Single cube ID to search in. Prefer `readable_cube_ids` for multi-cube search." + } + }, + "type": "object", + "required": [ + "user_id", + "history", + "feedback_content" + ], + "title": "APIFeedbackRequest", + "description": "Request model for processing feedback info." + }, + "APISearchRequest": { + "properties": { + "query": { + "type": "string", + "title": "Query", + "description": "User search query" + }, + "user_id": { + "type": "string", + "title": "User Id", + "description": "User ID" + }, + "readable_cube_ids": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Readable Cube Ids", + "description": "List of cube IDs that are readable for this request. Required for algorithm-facing API; optional for developer-facing API." + }, + "mode": { + "$ref": "#/components/schemas/SearchMode", + "description": "Search mode: fast, fine, or mixture.", + "default": "fast" + }, + "session_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Session Id", + "description": "Session ID used as a soft signal to prioritize more relevant memories. Only used for weighting, not as a hard filter." + }, + "top_k": { + "type": "integer", + "minimum": 1.0, + "title": "Top K", + "description": "Number of textual memories to retrieve (top-K). Default: 10.", + "default": 10 + }, + "dedup": { + "anyOf": [ + { + "type": "string", + "enum": [ + "no", + "sim" + ] + }, + { + "type": "null" + } + ], + "title": "Dedup", + "description": "Optional dedup option for textual memories. Use 'no' for no dedup, 'sim' for similarity dedup. If None, default exact-text dedup is applied." + }, + "pref_top_k": { + "type": "integer", + "minimum": 0.0, + "title": "Pref Top K", + "description": "Number of preference memories to retrieve (top-K). Default: 6.", + "default": 6 + }, + "include_preference": { + "type": "boolean", + "title": "Include Preference", + "description": "Whether to retrieve preference memories along with general memories. If enabled, the system will automatically recall user preferences relevant to the query. Default: True.", + "default": true + }, + "search_tool_memory": { + "type": "boolean", + "title": "Search Tool Memory", + "description": "Whether to retrieve tool memories along with general memories. If enabled, the system will automatically recall tool memories relevant to the query. Default: True.", + "default": true + }, + "tool_mem_top_k": { + "type": "integer", + "minimum": 0.0, + "title": "Tool Mem Top K", + "description": "Number of tool memories to retrieve (top-K). Default: 6.", + "default": 6 + }, + "filter": { + "anyOf": [ + { + "additionalProperties": true, + "type": "object" + }, + { + "type": "null" + } + ], + "title": "Filter", + "description": "\n Filter for the memory, example:\n {\n \"`and` or `or`\": [\n {\"id\": \"uuid-xxx\"},\n {\"created_at\": {\"gt\": \"2024-01-01\"}},\n ]\n }\n " + }, + "internet_search": { + "type": "boolean", + "title": "Internet Search", + "description": "Whether to enable internet search in addition to memory search. Primarily used by internal algorithms. Default: False.", + "default": false + }, + "threshold": { + "anyOf": [ + { + "type": "number" + }, + { + "type": "null" + } + ], + "title": "Threshold", + "description": "Internal similarity threshold for searching plaintext memories. If None, default thresholds will be applied." + }, + "search_memory_type": { + "type": "string", + "title": "Search Memory Type", + "description": "Type of memory to search: All, WorkingMemory, LongTermMemory, UserMemory, OuterMemory, ToolSchemaMemory, ToolTrajectoryMemory", + "default": "All" + }, + "chat_history": { + "anyOf": [ + { + "items": { + "anyOf": [ + { + "$ref": "#/components/schemas/ChatCompletionSystemMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionUserMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionAssistantMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionToolMessageParam" + } + ] + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Chat History", + "description": "Historical chat messages used internally by algorithms. If None, internal stored history may be used; if provided (even an empty list), this value will be used as-is." + }, + "mem_cube_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Mem Cube Id", + "description": "(Deprecated) Single cube ID to search in. Prefer `readable_cube_ids` for multi-cube search." + }, + "moscube": { + "type": "boolean", + "title": "Moscube", + "description": "(Deprecated / internal) Whether to use legacy MemOSCube path.", + "default": false + }, + "operation": { + "anyOf": [ + { + "items": { + "$ref": "#/components/schemas/PermissionDict" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Operation", + "description": "(Internal) Operation definitions for multi-cube read permissions." + }, + "source": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Source", + "description": "Source of the search query [plugin will router diff search]" + } + }, + "type": "object", + "required": [ + "query", + "user_id" + ], + "title": "APISearchRequest", + "description": "Request model for searching memories." + }, + "AllStatusResponse": { + "properties": { + "code": { + "type": "integer", + "title": "Code", + "description": "Response status code", + "default": 200 + }, + "message": { + "type": "string", + "title": "Message", + "default": "Scheduler status summary retrieved successfully" + }, + "data": { + "anyOf": [ + { + "$ref": "#/components/schemas/AllStatusResponseData" + }, + { + "type": "null" + } + ], + "description": "Response data" + } + }, + "type": "object", + "title": "AllStatusResponse", + "description": "Response model for full scheduler status operations." + }, + "AllStatusResponseData": { + "properties": { + "scheduler_summary": { + "$ref": "#/components/schemas/TaskSummary", + "description": "Aggregated status for scheduler-managed tasks" + }, + "all_tasks_summary": { + "$ref": "#/components/schemas/TaskSummary", + "description": "Aggregated status for all tracked tasks" + } + }, + "type": "object", + "required": [ + "scheduler_summary", + "all_tasks_summary" + ], + "title": "AllStatusResponseData", + "description": "Aggregated scheduler status metrics." + }, + "Audio": { + "properties": { + "id": { + "type": "string", + "title": "Id" + } + }, + "type": "object", + "required": [ + "id" + ], + "title": "Audio" + }, + "ChatCompletionAssistantMessageParam": { + "properties": { + "role": { + "type": "string", + "const": "assistant", + "title": "Role" + }, + "audio": { + "anyOf": [ + { + "$ref": "#/components/schemas/Audio" + }, + { + "type": "null" + } + ] + }, + "content": { + "anyOf": [ + { + "type": "string" + }, + { + "items": { + "anyOf": [ + { + "$ref": "#/components/schemas/ChatCompletionContentPartTextParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionContentPartRefusalParam" + } + ] + }, + "type": "array" + }, + { + "$ref": "#/components/schemas/ChatCompletionContentPartTextParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionContentPartRefusalParam" + }, + { + "type": "null" + } + ], + "title": "Content" + }, + "refusal": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Refusal" + }, + "tool_calls": { + "anyOf": [ + { + "items": { + "anyOf": [ + { + "$ref": "#/components/schemas/ChatCompletionMessageFunctionToolCallParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionMessageCustomToolCallParam" + } + ] + }, + "type": "array" + }, + { + "$ref": "#/components/schemas/ChatCompletionMessageFunctionToolCallParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionMessageCustomToolCallParam" + } + ], + "title": "Tool Calls" + }, + "chat_time": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Chat Time" + }, + "message_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Message Id" + } + }, + "type": "object", + "required": [ + "role" + ], + "title": "ChatCompletionAssistantMessageParam" + }, + "ChatCompletionContentPartImageParam": { + "properties": { + "image_url": { + "$ref": "#/components/schemas/ImageURL" + }, + "type": { + "type": "string", + "const": "image_url", + "title": "Type" + } + }, + "type": "object", + "required": [ + "image_url", + "type" + ], + "title": "ChatCompletionContentPartImageParam" + }, + "ChatCompletionContentPartInputAudioParam": { + "properties": { + "input_audio": { + "$ref": "#/components/schemas/InputAudio" + }, + "type": { + "type": "string", + "const": "input_audio", + "title": "Type" + } + }, + "type": "object", + "required": [ + "input_audio", + "type" + ], + "title": "ChatCompletionContentPartInputAudioParam" + }, + "ChatCompletionContentPartRefusalParam": { + "properties": { + "refusal": { + "type": "string", + "title": "Refusal" + }, + "type": { + "type": "string", + "const": "refusal", + "title": "Type" + } + }, + "type": "object", + "required": [ + "refusal", + "type" + ], + "title": "ChatCompletionContentPartRefusalParam" + }, + "ChatCompletionContentPartTextParam": { + "properties": { + "text": { + "type": "string", + "title": "Text" + }, + "type": { + "type": "string", + "const": "text", + "title": "Type" + } + }, + "type": "object", + "required": [ + "text", + "type" + ], + "title": "ChatCompletionContentPartTextParam" + }, + "ChatCompletionMessageCustomToolCallParam": { + "properties": { + "id": { + "type": "string", + "title": "Id" + }, + "custom": { + "$ref": "#/components/schemas/Custom" + }, + "type": { + "type": "string", + "const": "custom", + "title": "Type" + } + }, + "type": "object", + "required": [ + "id", + "custom", + "type" + ], + "title": "ChatCompletionMessageCustomToolCallParam" + }, + "ChatCompletionMessageFunctionToolCallParam": { + "properties": { + "id": { + "type": "string", + "title": "Id" + }, + "function": { + "$ref": "#/components/schemas/Function" + }, + "type": { + "type": "string", + "const": "function", + "title": "Type" + } + }, + "type": "object", + "required": [ + "id", + "function", + "type" + ], + "title": "ChatCompletionMessageFunctionToolCallParam" + }, + "ChatCompletionSystemMessageParam": { + "properties": { + "content": { + "anyOf": [ + { + "type": "string" + }, + { + "items": { + "$ref": "#/components/schemas/ChatCompletionContentPartTextParam" + }, + "type": "array" + }, + { + "$ref": "#/components/schemas/ChatCompletionContentPartTextParam" + } + ], + "title": "Content" + }, + "role": { + "type": "string", + "const": "system", + "title": "Role" + }, + "name": { + "type": "string", + "title": "Name" + }, + "chat_time": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Chat Time" + }, + "message_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Message Id" + } + }, + "type": "object", + "required": [ + "content", + "role" + ], + "title": "ChatCompletionSystemMessageParam" + }, + "ChatCompletionToolMessageParam": { + "properties": { + "content": { + "anyOf": [ + { + "type": "string" + }, + { + "items": { + "anyOf": [ + { + "$ref": "#/components/schemas/ChatCompletionContentPartTextParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionContentPartImageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionContentPartInputAudioParam" + }, + { + "$ref": "#/components/schemas/File" + } + ] + }, + "type": "array" + }, + { + "$ref": "#/components/schemas/ChatCompletionContentPartTextParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionContentPartImageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionContentPartInputAudioParam" + }, + { + "$ref": "#/components/schemas/File" + } + ], + "title": "Content" + }, + "role": { + "type": "string", + "const": "tool", + "title": "Role" + }, + "tool_call_id": { + "type": "string", + "title": "Tool Call Id" + }, + "chat_time": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Chat Time" + }, + "message_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Message Id" + } + }, + "type": "object", + "required": [ + "content", + "role", + "tool_call_id" + ], + "title": "ChatCompletionToolMessageParam" + }, + "ChatCompletionUserMessageParam": { + "properties": { + "content": { + "anyOf": [ + { + "type": "string" + }, + { + "items": { + "anyOf": [ + { + "$ref": "#/components/schemas/ChatCompletionContentPartTextParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionContentPartImageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionContentPartInputAudioParam" + }, + { + "$ref": "#/components/schemas/File" + } + ] + }, + "type": "array" + }, + { + "$ref": "#/components/schemas/ChatCompletionContentPartTextParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionContentPartImageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionContentPartInputAudioParam" + }, + { + "$ref": "#/components/schemas/File" + } + ], + "title": "Content" + }, + "role": { + "type": "string", + "const": "user", + "title": "Role" + }, + "name": { + "type": "string", + "title": "Name" + }, + "chat_time": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Chat Time" + }, + "message_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Message Id" + } + }, + "type": "object", + "required": [ + "content", + "role" + ], + "title": "ChatCompletionUserMessageParam" + }, + "ChatPlaygroundRequest": { + "properties": { + "user_id": { + "type": "string", + "title": "User Id", + "description": "User ID" + }, + "query": { + "type": "string", + "title": "Query", + "description": "Chat query message" + }, + "readable_cube_ids": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Readable Cube Ids", + "description": "List of cube IDs user can read for multi-cube chat" + }, + "writable_cube_ids": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Writable Cube Ids", + "description": "List of cube IDs user can write for multi-cube chat" + }, + "history": { + "anyOf": [ + { + "items": { + "anyOf": [ + { + "$ref": "#/components/schemas/ChatCompletionSystemMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionUserMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionAssistantMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionToolMessageParam" + } + ] + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "History", + "description": "Chat history" + }, + "mode": { + "$ref": "#/components/schemas/SearchMode", + "description": "search mode: fast, fine, or mixture", + "default": "fast" + }, + "system_prompt": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "System Prompt", + "description": "Base system prompt to use for chat" + }, + "top_k": { + "type": "integer", + "title": "Top K", + "description": "Number of results to return", + "default": 10 + }, + "session_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Session Id", + "description": "Session ID for soft-filtering memories" + }, + "include_preference": { + "type": "boolean", + "title": "Include Preference", + "description": "Whether to handle preference memory", + "default": true + }, + "pref_top_k": { + "type": "integer", + "title": "Pref Top K", + "description": "Number of preference results to return", + "default": 6 + }, + "model_name_or_path": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Model Name Or Path", + "description": "Model name to use for chat" + }, + "max_tokens": { + "anyOf": [ + { + "type": "integer" + }, + { + "type": "null" + } + ], + "title": "Max Tokens", + "description": "Max tokens to generate" + }, + "temperature": { + "anyOf": [ + { + "type": "number" + }, + { + "type": "null" + } + ], + "title": "Temperature", + "description": "Temperature for sampling" + }, + "top_p": { + "anyOf": [ + { + "type": "number" + }, + { + "type": "null" + } + ], + "title": "Top P", + "description": "Top-p (nucleus) sampling parameter" + }, + "add_message_on_answer": { + "type": "boolean", + "title": "Add Message On Answer", + "description": "Add dialogs to memory after chat", + "default": true + }, + "filter": { + "anyOf": [ + { + "additionalProperties": true, + "type": "object" + }, + { + "type": "null" + } + ], + "title": "Filter", + "description": "\n Filter for the memory, example:\n {\n \"`and` or `or`\": [\n {\"id\": \"uuid-xxx\"},\n {\"created_at\": {\"gt\": \"2024-01-01\"}},\n ]\n }\n " + }, + "internet_search": { + "type": "boolean", + "title": "Internet Search", + "description": "Whether to use internet search", + "default": false + }, + "threshold": { + "type": "number", + "title": "Threshold", + "description": "Threshold for filtering references", + "default": 0.5 + }, + "moscube": { + "type": "boolean", + "title": "Moscube", + "description": "(Deprecated) Whether to use legacy MemOSCube pipeline.", + "default": false + }, + "mem_cube_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Mem Cube Id", + "description": "(Deprecated) Single cube ID to use for chat. Prefer `readable_cube_ids` / `writable_cube_ids` for multi-cube chat." + }, + "beginner_guide_step": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Beginner Guide Step", + "description": "Whether to use beginner guide, option: [first, second]" + } + }, + "type": "object", + "required": [ + "user_id", + "query" + ], + "title": "ChatPlaygroundRequest", + "description": "Request model for chat operations in playground." + }, + "ChatRequest": { + "properties": { + "user_id": { + "type": "string", + "title": "User Id", + "description": "User ID" + }, + "query": { + "type": "string", + "title": "Query", + "description": "Chat query message" + }, + "readable_cube_ids": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Readable Cube Ids", + "description": "List of cube IDs user can read for multi-cube chat" + }, + "writable_cube_ids": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Writable Cube Ids", + "description": "List of cube IDs user can write for multi-cube chat" + }, + "history": { + "anyOf": [ + { + "items": { + "anyOf": [ + { + "$ref": "#/components/schemas/ChatCompletionSystemMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionUserMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionAssistantMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionToolMessageParam" + } + ] + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "History", + "description": "Chat history" + }, + "mode": { + "$ref": "#/components/schemas/SearchMode", + "description": "search mode: fast, fine, or mixture", + "default": "fast" + }, + "system_prompt": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "System Prompt", + "description": "Base system prompt to use for chat" + }, + "top_k": { + "type": "integer", + "title": "Top K", + "description": "Number of results to return", + "default": 10 + }, + "session_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Session Id", + "description": "Session ID for soft-filtering memories" + }, + "include_preference": { + "type": "boolean", + "title": "Include Preference", + "description": "Whether to handle preference memory", + "default": true + }, + "pref_top_k": { + "type": "integer", + "title": "Pref Top K", + "description": "Number of preference results to return", + "default": 6 + }, + "model_name_or_path": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Model Name Or Path", + "description": "Model name to use for chat" + }, + "max_tokens": { + "anyOf": [ + { + "type": "integer" + }, + { + "type": "null" + } + ], + "title": "Max Tokens", + "description": "Max tokens to generate" }, - "422": { - "description": "Validation Error", - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/HTTPValidationError" - } - } - } - } - } - } - }, - "/chat": { - "post": { - "summary": "Chat with MemOS", - "description": "Chat with the MemOS system.", - "operationId": "chat_chat_post", - "requestBody": { - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/ChatRequest" + "temperature": { + "anyOf": [ + { + "type": "number" + }, + { + "type": "null" } - } + ], + "title": "Temperature", + "description": "Temperature for sampling" }, - "required": true - }, - "responses": { - "200": { - "description": "Successful Response", - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/ChatResponse" - } + "top_p": { + "anyOf": [ + { + "type": "number" + }, + { + "type": "null" } - } + ], + "title": "Top P", + "description": "Top-p (nucleus) sampling parameter" }, - "422": { - "description": "Validation Error", - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/HTTPValidationError" - } + "add_message_on_answer": { + "type": "boolean", + "title": "Add Message On Answer", + "description": "Add dialogs to memory after chat", + "default": true + }, + "filter": { + "anyOf": [ + { + "additionalProperties": true, + "type": "object" + }, + { + "type": "null" } - } - } - } - } - } - }, - "components": { - "schemas": { - "ChatRequest": { - "properties": { - "user_id": { + ], + "title": "Filter", + "description": "\n Filter for the memory, example:\n {\n \"`and` or `or`\": [\n {\"id\": \"uuid-xxx\"},\n {\"created_at\": {\"gt\": \"2024-01-01\"}},\n ]\n }\n " + }, + "internet_search": { + "type": "boolean", + "title": "Internet Search", + "description": "Whether to use internet search", + "default": false + }, + "threshold": { + "type": "number", + "title": "Threshold", + "description": "Threshold for filtering references", + "default": 0.5 + }, + "moscube": { + "type": "boolean", + "title": "Moscube", + "description": "(Deprecated) Whether to use legacy MemOSCube pipeline.", + "default": false + }, + "mem_cube_id": { "anyOf": [ { "type": "string" @@ -716,42 +2602,112 @@ "type": "null" } ], - "title": "User Id", - "description": "User ID for the request", - "example": "user123" + "title": "Mem Cube Id", + "description": "(Deprecated) Single cube ID to use for chat. Prefer `readable_cube_ids` / `writable_cube_ids` for multi-cube chat." + } + }, + "type": "object", + "required": [ + "user_id", + "query" + ], + "title": "ChatRequest", + "description": "Request model for chat operations.\n\nThis model is used as the algorithm-facing chat interface, while also\nremaining backward compatible with older developer-facing APIs." + }, + "Custom": { + "properties": { + "input": { + "type": "string", + "title": "Input" }, - "query": { + "name": { "type": "string", - "title": "Query", - "description": "Chat query message.", - "example": "What is the latest update?" + "title": "Name" } }, "type": "object", "required": [ - "query" + "input", + "name" ], - "title": "ChatRequest" + "title": "Custom" + }, + "DeleteMemoryRequest": { + "properties": { + "writable_cube_ids": { + "items": { + "type": "string" + }, + "type": "array", + "title": "Writable Cube Ids", + "description": "Writable cube IDs" + }, + "memory_ids": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "Memory Ids", + "description": "Memory IDs" + }, + "file_ids": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "title": "File Ids", + "description": "File IDs" + }, + "filter": { + "anyOf": [ + { + "additionalProperties": true, + "type": "object" + }, + { + "type": "null" + } + ], + "title": "Filter", + "description": "Filter for the memory" + } + }, + "type": "object", + "title": "DeleteMemoryRequest", + "description": "Request model for deleting memories." }, - "ChatResponse": { + "DeleteMemoryResponse": { "properties": { "code": { "type": "integer", "title": "Code", "description": "Response status code", - "default": 200, - "example": 200 + "default": 200 }, "message": { "type": "string", "title": "Message", - "description": "Response message", - "example": "Operation successful" + "description": "Response message" }, "data": { "anyOf": [ { - "type": "string" + "additionalProperties": true, + "type": "object" }, { "type": "null" @@ -765,26 +2721,49 @@ "required": [ "message" ], - "title": "ChatResponse", - "description": "Response model for chat operations." + "title": "DeleteMemoryResponse", + "description": "Response model for deleting memories." + }, + "ExistMemCubeIdRequest": { + "properties": { + "mem_cube_id": { + "type": "string", + "title": "Mem Cube Id", + "description": "Mem cube ID" + } + }, + "type": "object", + "required": [ + "mem_cube_id" + ], + "title": "ExistMemCubeIdRequest", + "description": "Request model for checking if mem cube id exists." }, - "ConfigResponse": { + "ExistMemCubeIdResponse": { "properties": { "code": { "type": "integer", "title": "Code", "description": "Response status code", - "default": 200, - "example": 200 + "default": 200 }, "message": { "type": "string", "title": "Message", - "description": "Response message", - "example": "Operation successful" + "description": "Response message" }, "data": { - "type": "null", + "anyOf": [ + { + "additionalProperties": { + "type": "boolean" + }, + "type": "object" + }, + { + "type": "null" + } + ], "title": "Data", "description": "Response data" } @@ -793,247 +2772,124 @@ "required": [ "message" ], - "title": "ConfigResponse", - "description": "Response model for configuration endpoint." + "title": "ExistMemCubeIdResponse", + "description": "Response model for checking if mem cube id exists." }, - "CubeShare": { + "File": { "properties": { - "user_id": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "title": "User Id", - "description": "User ID for the request", - "example": "user123" + "file": { + "$ref": "#/components/schemas/FileFile" }, - "target_user_id": { + "type": { "type": "string", - "title": "Target User Id", - "description": "Target user ID to share with", - "example": "user456" + "const": "file", + "title": "Type" } }, "type": "object", "required": [ - "target_user_id" + "file", + "type" ], - "title": "CubeShare" + "title": "File" }, - "HTTPValidationError": { + "FileFile": { "properties": { - "detail": { - "items": { - "$ref": "#/components/schemas/ValidationError" - }, - "type": "array", - "title": "Detail" + "file_data": { + "type": "string", + "title": "File Data" + }, + "file_id": { + "type": "string", + "title": "File Id" + }, + "filename": { + "type": "string", + "title": "Filename" } }, "type": "object", - "title": "HTTPValidationError" + "title": "FileFile" }, - "LLMConfigFactory": { + "Function": { "properties": { - "model_schema": { + "arguments": { "type": "string", - "title": "Model Schema", - "description": "Schema for configuration. This value will be automatically set.", - "default": "NOT_SET" + "title": "Arguments" }, - "backend": { + "name": { "type": "string", - "title": "Backend", - "description": "Backend for LLM" - }, - "config": { - "additionalProperties": true, - "type": "object", - "title": "Config", - "description": "Configuration for the LLM backend" + "title": "Name" } }, - "additionalProperties": false, "type": "object", "required": [ - "backend", - "config" + "arguments", + "name" ], - "title": "LLMConfigFactory", - "description": "Factory class for creating LLM configurations." + "title": "Function" }, - "MOSConfig": { + "GetMemoryPlaygroundRequest": { "properties": { - "model_schema": { - "type": "string", - "title": "Model Schema", - "description": "Schema for configuration. This value will be automatically set.", - "default": "NOT_SET" - }, "user_id": { "type": "string", "title": "User Id", - "description": "User ID for the MOS. This is used to distinguish between different users' memories.", - "default": "root" + "description": "User ID" }, - "session_id": { + "memory_type": { "type": "string", - "title": "Session Id", - "description": "Session ID for the MOS. This is used to distinguish between different dialogue", - "default": "8dcdbd62-c231-4678-a3ae-0946b7d9ce14" - }, - "chat_model": { - "$ref": "#/components/schemas/LLMConfigFactory", - "description": "LLM configuration for the chat model in the MOS" - }, - "mem_reader": { - "$ref": "#/components/schemas/MemReaderConfigFactory", - "description": "MemReader configuration for the MOS" - }, - "mem_scheduler": { - "anyOf": [ - { - "$ref": "#/components/schemas/SchedulerConfigFactory" - }, - { - "type": "null" - } + "enum": [ + "text_mem", + "act_mem", + "param_mem", + "para_mem" ], - "description": "Memory scheduler configuration for managing memory operations" - }, - "user_manager": { - "$ref": "#/components/schemas/UserManagerConfigFactory", - "description": "User manager configuration for database operations" - }, - "max_turns_window": { - "type": "integer", - "title": "Max Turns Window", - "description": "Maximum number of turns to keep in the conversation history", - "default": 15 - }, - "top_k": { - "type": "integer", - "title": "Top K", - "description": "Maximum number of memories to retrieve for each query", - "default": 5 + "title": "Memory Type", + "description": "Memory type" }, - "enable_textual_memory": { - "type": "boolean", - "title": "Enable Textual Memory", - "description": "Enable textual memory for the MemChat", - "default": true - }, - "enable_activation_memory": { - "type": "boolean", - "title": "Enable Activation Memory", - "description": "Enable activation memory for the MemChat", - "default": false - }, - "enable_parametric_memory": { - "type": "boolean", - "title": "Enable Parametric Memory", - "description": "Enable parametric memory for the MemChat", - "default": false - }, - "enable_preference_memory": { - "type": "boolean", - "title": "Enable Preference Memory", - "description": "Enable preference memory for the MemChat", - "default": false - }, - "enable_mem_scheduler": { - "type": "boolean", - "title": "Enable Mem Scheduler", - "description": "Enable memory scheduler for automated memory management", - "default": false - }, - "PRO_MODE": { - "type": "boolean", - "title": "Pro Mode", - "description": "Enable PRO mode for complex query decomposition", - "default": false - } - }, - "additionalProperties": false, - "type": "object", - "title": "MOSConfig" - }, - "MemCubeRegister": { - "properties": { - "user_id": { + "mem_cube_ids": { "anyOf": [ { - "type": "string" + "items": { + "type": "string" + }, + "type": "array" }, { "type": "null" } ], - "title": "User Id", - "description": "User ID for the request", - "example": "user123" - }, - "mem_cube_name_or_path": { - "type": "string", - "title": "Mem Cube Name Or Path", - "description": "Name or path of the MemCube to register.", - "example": "/path/to/cube" + "title": "Mem Cube Ids", + "description": "Cube IDs" }, - "mem_cube_id": { + "search_query": { "anyOf": [ { "type": "string" }, - { - "type": "null" - } - ], - "title": "Mem Cube Id", - "description": "ID for the MemCube", - "example": "cube123" - } - }, - "type": "object", - "required": [ - "mem_cube_name_or_path" - ], - "title": "MemCubeRegister" - }, - "MemReaderConfigFactory": { - "properties": { - "model_schema": { - "type": "string", - "title": "Model Schema", - "description": "Schema for configuration. This value will be automatically set.", - "default": "NOT_SET" - }, - "backend": { - "type": "string", - "title": "Backend", - "description": "Backend for MemReader" - }, - "config": { - "additionalProperties": true, - "type": "object", - "title": "Config", - "description": "Configuration for the MemReader backend" + { + "type": "null" + } + ], + "title": "Search Query", + "description": "Search query" } }, - "additionalProperties": false, "type": "object", "required": [ - "backend", - "config" + "user_id", + "memory_type" ], - "title": "MemReaderConfigFactory", - "description": "Factory class for creating MemReader configurations." + "title": "GetMemoryPlaygroundRequest", + "description": "Request model for getting memories." }, - "MemoryCreate": { + "GetMemoryRequest": { "properties": { + "mem_cube_id": { + "type": "string", + "title": "Mem Cube Id", + "description": "Cube ID" + }, "user_id": { "anyOf": [ { @@ -1044,92 +2900,124 @@ } ], "title": "User Id", - "description": "User ID for the request", - "example": "user123" + "description": "User ID" }, - "messages": { - "anyOf": [ - { - "items": { - "$ref": "#/components/schemas/Message" - }, - "type": "array" - }, - { - "type": "null" - } - ], - "title": "Messages", - "description": "List of messages to store.", - "example": [ - { - "content": "Hello", - "role": "user" - } - ] + "include_preference": { + "type": "boolean", + "title": "Include Preference", + "description": "Whether to handle preference memory", + "default": true }, - "mem_cube_id": { + "page": { "anyOf": [ { - "type": "string" + "type": "integer" }, { "type": "null" } ], - "title": "Mem Cube Id", - "description": "ID of the memory cube", - "example": "cube123" + "title": "Page", + "description": "Page number (starts from 1). If None, exports all data without pagination." }, - "memory_content": { + "page_size": { "anyOf": [ { - "type": "string" + "type": "integer" }, { "type": "null" } ], - "title": "Memory Content", - "description": "Content to store as memory", - "example": "This is a memory content" + "title": "Page Size", + "description": "Number of items per page. If None, exports all data without pagination." + } + }, + "type": "object", + "required": [ + "mem_cube_id" + ], + "title": "GetMemoryRequest", + "description": "Request model for getting memories." + }, + "GetMemoryResponse": { + "properties": { + "code": { + "type": "integer", + "title": "Code", + "description": "Response status code", + "default": 200 }, - "doc_path": { + "message": { + "type": "string", + "title": "Message", + "description": "Response message" + }, + "data": { "anyOf": [ { - "type": "string" + "additionalProperties": true, + "type": "object" }, { "type": "null" } ], - "title": "Doc Path", - "description": "Path to document to store", - "example": "/path/to/document.txt" + "title": "Data", + "description": "Response data" } }, "type": "object", - "title": "MemoryCreate" + "required": [ + "message" + ], + "title": "GetMemoryResponse", + "description": "Response model for getting memories." }, - "MemoryResponse": { + "GetUserNamesByMemoryIdsRequest": { + "properties": { + "memory_ids": { + "items": { + "type": "string" + }, + "type": "array", + "title": "Memory Ids", + "description": "Memory IDs" + } + }, + "type": "object", + "required": [ + "memory_ids" + ], + "title": "GetUserNamesByMemoryIdsRequest", + "description": "Request model for getting user names by memory ids." + }, + "GetUserNamesByMemoryIdsResponse": { "properties": { "code": { "type": "integer", "title": "Code", "description": "Response status code", - "default": 200, - "example": 200 + "default": 200 }, "message": { "type": "string", "title": "Message", - "description": "Response message", - "example": "Operation successful" + "description": "Response message" }, "data": { "anyOf": [ { - "additionalProperties": true, + "additionalProperties": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ] + }, "type": "object" }, { @@ -1144,106 +3032,133 @@ "required": [ "message" ], - "title": "MemoryResponse", - "description": "Response model for memory operations." + "title": "GetUserNamesByMemoryIdsResponse", + "description": "Response model for getting user names by memory ids." }, - "Message": { + "HTTPValidationError": { "properties": { - "role": { + "detail": { + "items": { + "$ref": "#/components/schemas/ValidationError" + }, + "type": "array", + "title": "Detail" + } + }, + "type": "object", + "title": "HTTPValidationError" + }, + "ImageURL": { + "properties": { + "url": { "type": "string", - "title": "Role", - "description": "Role of the message (user or assistant).", - "example": "user" + "title": "Url" }, - "content": { + "detail": { "type": "string", - "title": "Content", - "description": "Message content.", - "example": "Hello, how can I help you?" + "enum": [ + "auto", + "low", + "high" + ], + "title": "Detail" } }, "type": "object", "required": [ - "role", - "content" + "url" ], - "title": "Message" + "title": "ImageURL" }, - "SchedulerConfigFactory": { + "InputAudio": { "properties": { - "model_schema": { + "data": { "type": "string", - "title": "Model Schema", - "description": "Schema for configuration. This value will be automatically set.", - "default": "NOT_SET" + "title": "Data" }, - "backend": { + "format": { "type": "string", - "title": "Backend", - "description": "Backend for scheduler" - }, - "config": { - "additionalProperties": true, - "type": "object", - "title": "Config", - "description": "Configuration for the scheduler backend" + "enum": [ + "wav", + "mp3" + ], + "title": "Format" } }, - "additionalProperties": false, "type": "object", "required": [ - "backend", - "config" + "data", + "format" ], - "title": "SchedulerConfigFactory", - "description": "Factory class for creating scheduler configurations." + "title": "InputAudio" }, - "SearchRequest": { + "MemoryResponse": { "properties": { - "user_id": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "title": "User Id", - "description": "User ID for the request", - "example": "user123" + "code": { + "type": "integer", + "title": "Code", + "description": "Response status code", + "default": 200 }, - "query": { + "message": { "type": "string", - "title": "Query", - "description": "Search query.", - "example": "How to implement a feature?" + "title": "Message", + "description": "Response message" }, - "install_cube_ids": { + "data": { "anyOf": [ { - "items": { - "type": "string" - }, + "items": {}, "type": "array" }, { "type": "null" } ], - "title": "Install Cube Ids", - "description": "List of cube IDs to search in", - "example": [ - "cube123", - "cube456" - ] + "title": "Data", + "description": "Response data" } }, "type": "object", "required": [ - "query" + "message" + ], + "title": "MemoryResponse", + "description": "Response model for memory operations." + }, + "PermissionDict": { + "properties": { + "permissions": { + "items": { + "type": "string", + "enum": [ + "read", + "write", + "delete", + "execute" + ] + }, + "type": "array", + "title": "Permissions" + }, + "mem_cube_id": { + "type": "string", + "title": "Mem Cube Id" + } + }, + "type": "object", + "title": "PermissionDict", + "description": "Typed dictionary for chat message dictionaries." + }, + "SearchMode": { + "type": "string", + "enum": [ + "fast", + "fine", + "mixture" ], - "title": "SearchRequest" + "title": "SearchMode", + "description": "Enumeration for search modes." }, "SearchResponse": { "properties": { @@ -1251,14 +3166,12 @@ "type": "integer", "title": "Code", "description": "Response status code", - "default": 200, - "example": 200 + "default": 200 }, "message": { "type": "string", "title": "Message", - "description": "Response message", - "example": "Operation successful" + "description": "Response message" }, "data": { "anyOf": [ @@ -1281,89 +3194,165 @@ "title": "SearchResponse", "description": "Response model for search operations." }, - "SimpleResponse": { + "StatusResponse": { "properties": { "code": { "type": "integer", "title": "Code", "description": "Response status code", - "default": 200, - "example": 200 + "default": 200 }, "message": { "type": "string", "title": "Message", - "description": "Response message", - "example": "Operation successful" + "default": "Memory get status successfully" }, "data": { - "type": "null", + "anyOf": [ + { + "items": { + "$ref": "#/components/schemas/StatusResponseItem" + }, + "type": "array" + }, + { + "type": "null" + } + ], "title": "Data", "description": "Response data" } }, "type": "object", + "title": "StatusResponse", + "description": "Response model for scheduler status operations." + }, + "StatusResponseItem": { + "properties": { + "task_id": { + "type": "string", + "title": "Task Id", + "description": "The ID of the task" + }, + "status": { + "type": "string", + "enum": [ + "in_progress", + "completed", + "waiting", + "failed", + "cancelled" + ], + "title": "Status", + "description": "The current status of the task" + } + }, + "type": "object", "required": [ - "message" + "task_id", + "status" ], - "title": "SimpleResponse", - "description": "Simple response model for operations without data return." + "title": "StatusResponseItem", + "description": "Individual task status item." }, - "UserCreate": { + "SuggestionRequest": { "properties": { "user_id": { "type": "string", "title": "User Id", - "description": "User ID", - "example": "user123" + "description": "User ID" }, - "user_name": { + "mem_cube_id": { + "type": "string", + "title": "Mem Cube Id", + "description": "Cube ID" + }, + "language": { + "type": "string", + "enum": [ + "zh", + "en" + ], + "title": "Language", + "description": "Language for suggestions", + "default": "zh" + }, + "message": { "anyOf": [ { "type": "string" }, + { + "items": { + "anyOf": [ + { + "$ref": "#/components/schemas/ChatCompletionSystemMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionUserMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionAssistantMessageParam" + }, + { + "$ref": "#/components/schemas/ChatCompletionToolMessageParam" + } + ] + }, + "type": "array" + }, + { + "items": { + "anyOf": [ + { + "$ref": "#/components/schemas/ChatCompletionContentPartTextParam" + }, + { + "$ref": "#/components/schemas/File" + } + ] + }, + "type": "array" + }, { "type": "null" } ], - "title": "User Name", - "description": "Name of the user", - "example": "john_doe" - }, - "role": { - "type": "string", - "title": "Role", - "description": "Role of the user", - "default": "user", - "example": "user" + "title": "Message", + "description": "List of messages to store." } }, "type": "object", "required": [ - "user_id" + "user_id", + "mem_cube_id" ], - "title": "UserCreate" + "title": "SuggestionRequest", + "description": "Request model for getting suggestion queries." }, - "UserListResponse": { + "SuggestionResponse": { "properties": { "code": { "type": "integer", "title": "Code", "description": "Response status code", - "default": 200, - "example": 200 + "default": 200 }, "message": { "type": "string", "title": "Message", - "description": "Response message", - "example": "Operation successful" + "description": "Response message" }, "data": { "anyOf": [ { - "items": {}, - "type": "array" + "additionalProperties": { + "items": { + "type": "string" + }, + "type": "array" + }, + "type": "object" }, { "type": "null" @@ -1377,63 +3366,170 @@ "required": [ "message" ], - "title": "UserListResponse", - "description": "Response model for user list operations." + "title": "SuggestionResponse", + "description": "Response model for suggestion operations." }, - "UserManagerConfigFactory": { + "TaskQueueData": { "properties": { - "backend": { + "user_id": { "type": "string", - "title": "Backend", - "description": "Backend for user manager", - "default": "sqlite" + "title": "User Id", + "description": "User ID the query is scoped to" + }, + "user_name": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "User Name", + "description": "User name if available" + }, + "mem_cube_id": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Mem Cube Id", + "description": "MemCube ID if a single cube is targeted; otherwise None" + }, + "stream_keys": { + "items": { + "type": "string" + }, + "type": "array", + "title": "Stream Keys", + "description": "Matched Redis stream keys for this user" + }, + "users_count": { + "type": "integer", + "title": "Users Count", + "description": "Distinct users currently present in queue streams" + }, + "pending_tasks_count": { + "type": "integer", + "title": "Pending Tasks Count", + "description": "Count of pending (delivered, not acked) tasks" + }, + "remaining_tasks_count": { + "type": "integer", + "title": "Remaining Tasks Count", + "description": "Count of enqueued tasks (xlen)" + }, + "pending_tasks_detail": { + "items": { + "type": "string" + }, + "type": "array", + "title": "Pending Tasks Detail", + "description": "Per-stream pending counts, formatted as '{stream_key}:{count}'" }, - "config": { - "additionalProperties": true, - "type": "object", - "title": "Config", - "description": "Configuration for the user manager backend" + "remaining_tasks_detail": { + "items": { + "type": "string" + }, + "type": "array", + "title": "Remaining Tasks Detail", + "description": "Per-stream remaining counts, formatted as '{stream_key}:{count}'" } }, "type": "object", - "title": "UserManagerConfigFactory", - "description": "Factory for user manager configurations." + "required": [ + "user_id", + "stream_keys", + "users_count", + "pending_tasks_count", + "remaining_tasks_count", + "pending_tasks_detail", + "remaining_tasks_detail" + ], + "title": "TaskQueueData", + "description": "Queue-level metrics for scheduler tasks." }, - "UserResponse": { + "TaskQueueResponse": { "properties": { "code": { "type": "integer", "title": "Code", "description": "Response status code", - "default": 200, - "example": 200 + "default": 200 }, "message": { "type": "string", "title": "Message", - "description": "Response message", - "example": "Operation successful" + "default": "Scheduler task queue status retrieved successfully" }, "data": { "anyOf": [ { - "additionalProperties": true, - "type": "object" + "$ref": "#/components/schemas/TaskQueueData" }, { "type": "null" } ], - "title": "Data", "description": "Response data" } }, "type": "object", - "required": [ - "message" - ], - "title": "UserResponse", - "description": "Response model for user operations." + "title": "TaskQueueResponse", + "description": "Response model for scheduler task queue status." + }, + "TaskSummary": { + "properties": { + "waiting": { + "type": "integer", + "title": "Waiting", + "description": "Number of tasks waiting to run", + "default": 0 + }, + "in_progress": { + "type": "integer", + "title": "In Progress", + "description": "Number of tasks currently running", + "default": 0 + }, + "pending": { + "type": "integer", + "title": "Pending", + "description": "Number of tasks fetched by workers but not yet acknowledged", + "default": 0 + }, + "completed": { + "type": "integer", + "title": "Completed", + "description": "Number of tasks completed", + "default": 0 + }, + "failed": { + "type": "integer", + "title": "Failed", + "description": "Number of tasks failed", + "default": 0 + }, + "cancelled": { + "type": "integer", + "title": "Cancelled", + "description": "Number of tasks cancelled", + "default": 0 + }, + "total": { + "type": "integer", + "title": "Total", + "description": "Total number of tasks counted", + "default": 0 + } + }, + "type": "object", + "title": "TaskSummary", + "description": "Aggregated counts of tasks by status." }, "ValidationError": { "properties": { diff --git a/examples/basic_modules/textual_memory_internet_search_example.py b/examples/basic_modules/textual_memory_internet_search_example.py index f26d3afd8..9007d7e67 100644 --- a/examples/basic_modules/textual_memory_internet_search_example.py +++ b/examples/basic_modules/textual_memory_internet_search_example.py @@ -1,7 +1,49 @@ """ -Example: Using InternetRetrieverFactory with BochaAISearchRetriever +Textual Memory Internet Search Example +======================================= + +This example demonstrates how to use MemOS's InternetRetrieverFactory to search +the web and retrieve relevant information as memory items. + +**What you'll learn:** +- How to initialize an embedder for web content embedding +- How to configure and use BochaAI web search retriever +- How to configure and use Google Custom Search API +- How to chunk and process web content into memory items +- How to retrieve structured information from internet searches + +**Use case:** +When you need to answer questions that require real-time web information +(e.g., "What's in Alibaba's 2024 ESG report?"), this retriever can: +1. Search the web using BochaAI API or Google Custom Search API +2. Fetch and parse web page content +3. Chunk the content into manageable pieces +4. Return structured memory items with embeddings + +**Prerequisites:** +- Valid BochaAI API Key (set in environment variable: BOCHA_API_KEY) +- (Optional) Valid Google API Key and Search Engine ID for Google Custom Search + - GOOGLE_API_KEY: Get from https://console.cloud.google.com/ + - GOOGLE_SEARCH_ENGINE_ID: Get from https://programmablesearchengine.google.com/ +- Embedder service running (e.g., Ollama with nomic-embed-text) +- Internet connection for web searches + +Run this example: + # Basic test with BochaAI + export BOCHA_API_KEY='sk-your-bocha-api-key' + python examples/basic_modules/textual_memory_internet_search_example.py + + # Test with both BochaAI and Google + export BOCHA_API_KEY='sk-your-bocha-api-key' + export GOOGLE_API_KEY='your-google-api-key' + export GOOGLE_SEARCH_ENGINE_ID='your-search-engine-id' + python examples/basic_modules/textual_memory_internet_search_example.py """ +import json +import os + +from memos import log from memos.configs.embedder import EmbedderConfigFactory from memos.configs.internet_retriever import InternetRetrieverConfigFactory from memos.embedders.factory import EmbedderFactory @@ -10,43 +52,258 @@ ) -# ========= 1. Create an embedder ========= -embedder_config = EmbedderConfigFactory.model_validate( - { - "backend": "ollama", # Or "sentence_transformer", etc. - "config": { - "model_name_or_path": "nomic-embed-text:latest", - }, - } -) +logger = log.get_logger(__name__) + +# ============================================================================ +# Step 0: Setup - Load configuration files +# ============================================================================ +print("=" * 80) +print("Textual Memory Internet Search Example") +print("=" * 80) + +current_dir = os.path.dirname(os.path.abspath(__file__)) +config_dir = os.path.join(current_dir, "../data/config") + +# Load the shared tree-text memory configuration +config_path = os.path.join(config_dir, "tree_config_shared_database.json") +with open(config_path) as f: + config_data = json.load(f) + +print(f"\n✓ Loaded configuration from: {config_path}") + +# ============================================================================ +# Step 1: Initialize Embedder +# ============================================================================ +print("\n[Step 1] Initializing embedder for web content...") + +# The embedder will convert web content into vector embeddings +embedder_config = EmbedderConfigFactory.model_validate(config_data["embedder"]) embedder = EmbedderFactory.from_config(embedder_config) -# ========= 2. Create retriever config for BochaAI ========= +print(f"✓ Embedder initialized: {embedder_config.backend}") + +# ============================================================================ +# Step 2: Configure Internet Retriever (BochaAI) +# ============================================================================ +print("\n[Step 2] Configuring internet retriever...") + +# Load the simple_struct reader configuration +reader_config_path = os.path.join(config_dir, "simple_struct_reader_config.json") +with open(reader_config_path) as f: + reader_config_data = json.load(f) + +print(f"✓ Loaded reader configuration from: {reader_config_path}") + +# NOTE: You need to set your BochaAI API key here or in environment variable +# For this example, we'll read from environment variable +bocha_api_key = os.environ.get("BOCHA_API_KEY", "sk-your-bocha-api-key-here") + +if bocha_api_key == "sk-your-bocha-api-key-here": + print("⚠️ Warning: Using placeholder API key. Set BOCHA_API_KEY environment variable.") + retriever_config = InternetRetrieverConfigFactory.model_validate( { "backend": "bocha", "config": { - "api_key": "sk-xxx", # Your BochaAI API Key - "max_results": 5, - "reader": { # Reader config for chunking web content + "api_key": bocha_api_key, + "max_results": 5, # Maximum number of search results to retrieve + "reader": { + # The reader chunks web content into memory items "backend": "simple_struct", - "config": { # your simple struct reader config - }, + "config": reader_config_data, # Use loaded configuration }, }, } ) -# ========= 3. Build retriever instance via factory ========= +print(f"✓ Retriever configured: {retriever_config.backend}") +print(f" Max results per search: {retriever_config.config.max_results}") + +# ============================================================================ +# Step 3: Create Retriever Instance +# ============================================================================ +print("\n[Step 3] Creating internet retriever instance...") + retriever = InternetRetrieverFactory.from_config(retriever_config, embedder) -# ========= 4. Run BochaAI Web Search ========= -print("=== Scenario 1: Web Search (BochaAI) ===") -query_web = "Alibaba 2024 ESG report" -results_web = retriever.retrieve_from_internet(query_web) +print("✓ Retriever initialized and ready") + +# ============================================================================ +# Step 4: Perform Web Search +# ============================================================================ +print("\n[Step 4] Performing web search...") + +# Define the search query +query = "Alibaba 2024 ESG report" +print(f" 🔍 Query: '{query}'") +print(" ⏳ Searching the web and processing results...\n") + +# Execute the search +# This will: +# 1. Search using BochaAI API +# 2. Fetch web page content +# 3. Parse and chunk the content +# 4. Generate embeddings for each chunk +# 5. Return as TextualMemoryItem objects +results = retriever.retrieve_from_internet(query) + +print("✓ Search completed!") +print(f"✓ Retrieved {len(results)} memory items from web search\n") + +# ============================================================================ +# Step 5: Display Results +# ============================================================================ +print("=" * 80) +print("WEB SEARCH RESULTS") +print("=" * 80) + +if not results: + print("\n❌ No results found.") + print(" This might indicate:") + print(" - Invalid or missing BochaAI API key") + print(" - Network connectivity issues") + print(" - The query returned no relevant web pages") + print(" - The web content couldn't be parsed") +else: + for idx, item in enumerate(results, 1): + print(f"\n[Result #{idx}]") + print("-" * 80) + + # Display the memory content (truncated for readability) + content = item.memory + if len(content) > 300: + print(f"Content: {content[:300]}...") + print(f" (... {len(content) - 300} more characters)") + else: + print(f"Content: {content}") + + # Display metadata if available + if hasattr(item, "metadata") and item.metadata: + metadata = item.metadata + if hasattr(metadata, "sources") and metadata.sources: + print(f"Source: {metadata.sources[0] if metadata.sources else 'N/A'}") + + print() + +print("=" * 80) +print("Example completed successfully!") +print("=" * 80) +print("\n💡 Next steps:") +print(" - Set your BochaAI API key in environment variable: export BOCHA_API_KEY='sk-...'") +print(" - Try different search queries to test various topics") +print(" - Adjust max_results in config to control number of results") +print(" - Use the retrieved memory items in your retrieval pipeline") +print(" - Combine internet search with local memory retrieval for hybrid systems\n") + +print("\n⚠️ Note:") +print(" If you see 'No results found', make sure:") +print(" 1. Your BochaAI API key is valid and set correctly") +print(" 2. You have internet connectivity") +print(" 3. The embedder service is running\n") + +# ============================================================================ +# Step 6: Test Google Custom Search API (Optional) +# ============================================================================ +print("\n" + "=" * 80) +print("GOOGLE CUSTOM SEARCH API TEST") +print("=" * 80) + +# NOTE: You need to set your Google API key and Search Engine ID +# Get these from: https://developers.google.com/custom-search/v1/overview +google_api_key = os.environ.get("GOOGLE_API_KEY", "") +google_search_engine_id = os.environ.get("GOOGLE_SEARCH_ENGINE_ID", "") + +if google_api_key and google_search_engine_id: + print("\n[Step 6.1] Configuring Google Custom Search retriever...") + + google_retriever_config = InternetRetrieverConfigFactory.model_validate( + { + "backend": "google", + "config": { + "api_key": google_api_key, + "search_engine_id": google_search_engine_id, + "max_results": 5, # Maximum number of search results to retrieve + "num_per_request": 5, # Number of results per API request (max 10 for Google) + }, + } + ) + + print("✓ Google retriever configured") + print(f" Max results: {google_retriever_config.config.max_results}") + + print("\n[Step 6.2] Creating Google retriever instance...") + google_retriever = InternetRetrieverFactory.from_config(google_retriever_config, embedder) + print("✓ Google retriever initialized") + + print("\n[Step 6.3] Performing Google web search...") + google_query = "Python best practices 2024" + print(f" 🔍 Query: '{google_query}'") + print(" ⏳ Searching via Google Custom Search API...\n") + + google_results = google_retriever.retrieve_from_internet(google_query) + + print("✓ Google search completed!") + print(f"✓ Retrieved {len(google_results)} memory items from Google search\n") + + # Display Google search results + print("=" * 80) + print("GOOGLE SEARCH RESULTS") + print("=" * 80) + + if not google_results: + print("\n❌ No results found from Google.") + print(" This might indicate:") + print(" - Invalid Google API key or Search Engine ID") + print(" - API quota exceeded") + print(" - Network connectivity issues") + else: + for idx, item in enumerate(google_results, 1): + print(f"\n[Google Result #{idx}]") + print("-" * 80) + + # Display the memory content (truncated for readability) + content = item.memory + if len(content) > 300: + print(f"Content: {content[:300]}...") + print(f" (... {len(content) - 300} more characters)") + else: + print(f"Content: {content}") + + # Display metadata if available + if hasattr(item, "metadata") and item.metadata: + metadata = item.metadata + if hasattr(metadata, "sources") and metadata.sources: + print(f"Source: {metadata.sources[0] if metadata.sources else 'N/A'}") + + print() -print(f"Retrieved {len(results_web)} memory items.") -for idx, item in enumerate(results_web, 1): - print(f"[{idx}] {item.memory[:500]}...") # preview first 100 chars + print("=" * 80) + print("Google Search Test completed!") + print("=" * 80) +else: + print("\n⏭️ Skipping Google Custom Search API test") + print(" To enable this test, set the following environment variables:") + print(" - GOOGLE_API_KEY: Your Google API key") + print(" - GOOGLE_SEARCH_ENGINE_ID: Your Google Custom Search Engine ID (cx parameter)") + print("\n Get your credentials from:") + print(" https://developers.google.com/custom-search/v1/overview") -print("==" * 20) +print("\n" + "=" * 80) +print("ALL TESTS COMPLETED") +print("=" * 80) +print("\n💡 Summary:") +print(" ✓ Tested BochaAI web search retriever") +if google_api_key and google_search_engine_id: + print(" ✓ Tested Google Custom Search API") +else: + print(" ⏭️ Skipped Google Custom Search API (credentials not set)") +print("\n💡 Quick Start:") +print(" # Set BochaAI API key") +print(" export BOCHA_API_KEY='sk-your-bocha-api-key'") +print(" ") +print(" # Set Google Custom Search credentials (optional)") +print(" export GOOGLE_API_KEY='your-google-api-key'") +print(" export GOOGLE_SEARCH_ENGINE_ID='your-search-engine-id'") +print(" ") +print(" # Run the example") +print(" python examples/basic_modules/textual_memory_internet_search_example.py\n") diff --git a/examples/basic_modules/tree_textual_memory_recall.py b/examples/basic_modules/tree_textual_memory_recall.py index 935513784..10831cbeb 100644 --- a/examples/basic_modules/tree_textual_memory_recall.py +++ b/examples/basic_modules/tree_textual_memory_recall.py @@ -1,26 +1,152 @@ +""" +Tree Textual Memory Recall Example +=================================== + +This example demonstrates how to use MemOS's GraphMemoryRetriever to recall memories +from a shared graph database. + +**What you'll learn:** +- How to load embedder and graph database configurations +- How to insert memories into the graph store with embeddings +- How to build a ParsedTaskGoal to guide retrieval +- How to retrieve relevant memories using hybrid search + +**Use case:** +You have stored various long-term memories about a user (e.g., "Caroline") +in a graph database, and now you want to answer a natural language question +by retrieving the most relevant memories. + +Run this example: + python examples/basic_modules/tree_textual_memory_recall.py +""" + +import json +import os + from memos import log from memos.configs.embedder import EmbedderConfigFactory from memos.configs.graph_db import GraphDBConfigFactory from memos.embedders.factory import EmbedderFactory from memos.graph_dbs.factory import GraphStoreFactory -from memos.memories.textual.item import TextualMemoryItem +from memos.memories.textual.item import TextualMemoryItem, TreeNodeTextualMemoryMetadata from memos.memories.textual.tree_text_memory.retrieve.recall import GraphMemoryRetriever from memos.memories.textual.tree_text_memory.retrieve.retrieval_mid_structs import ParsedTaskGoal logger = log.get_logger(__name__) -embedder_config = EmbedderConfigFactory.model_validate( - { - "backend": "ollama", - "config": { - "model_name_or_path": "nomic-embed-text:latest", - }, - } -) +# ============================================================================ +# Step 0: Setup - Load configuration files +# ============================================================================ +print("=" * 70) +print("Tree Textual Memory Recall Example") +print("=" * 70) + +current_dir = os.path.dirname(os.path.abspath(__file__)) +config_dir = os.path.join(current_dir, "../data/config") + +# Load the shared tree-text memory configuration +# This config includes both embedder settings and graph database settings +config_path = os.path.join(config_dir, "tree_config_shared_database.json") +with open(config_path) as f: + config_data = json.load(f) + +print(f"\n✓ Loaded configuration from: {config_path}") + +# ============================================================================ +# Step 1: Initialize Embedder +# ============================================================================ +# The embedder converts text into vector embeddings for semantic search +embedder_config = EmbedderConfigFactory.model_validate(config_data["embedder"]) embedder = EmbedderFactory.from_config(embedder_config) -# Step 1: Prepare a mock ParsedTaskGoal +print(f"✓ Initialized embedder: {embedder_config.backend}") + +# ============================================================================ +# Step 2: Initialize Graph Store +# ============================================================================ +# The graph store persists memories and supports both graph queries and vector search +graph_config = GraphDBConfigFactory(**config_data["graph_db"]) +graph_store = GraphStoreFactory.from_config(graph_config) + +print(f"✓ Initialized graph store: {graph_config.backend}") + +# ============================================================================ +# Step 3: Clean up old mock data (optional) +# ============================================================================ +# If you're running this example multiple times, clean up previous test data +# to avoid duplicates. This is optional in production. +print("\nCleaning up old mock data...") +try: + if hasattr(graph_store, "delete_node_by_prams"): + graph_store.delete_node_by_prams(filter={"key": "LGBTQ support group"}) + graph_store.delete_node_by_prams(filter={"key": "LGBTQ community"}) + print("✓ Old mock data cleaned") + else: + print("⚠ Graph store doesn't support delete_node_by_prams, skipping cleanup") +except Exception as exc: + print(f"⚠ Cleanup warning: {exc}") + +# ============================================================================ +# Step 4: Insert mock memories into the graph store +# ============================================================================ +# In a real application, these would be memories extracted from user conversations +# or documents. Here we use a few hardcoded examples about "Caroline". +print("\nInserting mock memories...") + +mock_memories = [ + { + "memory": "Caroline joined the LGBTQ support group in 2023.", + "tags": ["LGBTQ", "support group"], + "key": "LGBTQ support group", + }, + { + "memory": "Caroline has been an active member of the LGBTQ community since college.", + "tags": ["LGBTQ", "community"], + "key": "LGBTQ community", + }, + { + "memory": "She attended the weekly LGBTQ support group meetings every Friday.", + "tags": ["LGBTQ", "support group", "meetings"], + "key": "LGBTQ support group", + }, +] + +for idx, mem_data in enumerate(mock_memories, 1): + # Generate embedding for this memory + mem_embedding = embedder.embed([mem_data["memory"]])[0] + + # Create a TextualMemoryItem with metadata + item = TextualMemoryItem( + memory=mem_data["memory"], + metadata=TreeNodeTextualMemoryMetadata( + memory_type="LongTermMemory", # Can be ShortTermMemory, LongTermMemory, etc. + key=mem_data["key"], + tags=mem_data["tags"], + embedding=mem_embedding, + sources=[], + ), + ) + + # Add the memory node to the graph store + graph_store.add_node(item.id, item.memory, item.metadata.model_dump()) + print(f" [{idx}/{len(mock_memories)}] Added: {mem_data['memory'][:60]}...") + +print("✓ Mock memories inserted successfully") + +# ============================================================================ +# Step 5: Define a query and retrieval goal +# ============================================================================ +# This is the natural language question we want to answer +query = "When did Caroline go to the LGBTQ support group?" +print(f"\n{'=' * 70}") +print(f"Query: {query}") +print(f"{'=' * 70}") + +# ParsedTaskGoal provides hints to guide the retrieval process: +# - memories: semantic descriptions of what we're looking for +# - keys: specific keywords to match +# - tags: categorical tags to filter by parsed_goal = ParsedTaskGoal( memories=[ "Caroline's participation in the LGBTQ community", @@ -34,37 +160,46 @@ tags=["LGBTQ", "support group"], ) -# Step 2: Initialize graph store -graph_config = GraphDBConfigFactory( - backend="neo4j", - config={ - "uri": "bolt://localhost:7687", - "user": "neo4j", - "password": "12345678", - "db_name": "caroline", - "auto_create": True, - }, -) -graph_store = GraphStoreFactory.from_config(graph_config) +# ============================================================================ +# Step 6: Perform hybrid retrieval +# ============================================================================ +# The retriever uses both semantic similarity (embeddings) and graph structure +# to find the most relevant memories +print("\nPerforming hybrid retrieval...") -# Step 6: Create embedding for query -query = "When did Caroline go to the LGBTQ support group?" query_embedding = embedder.embed([query])[0] - -# Step 7: Init memory retriever retriever = GraphMemoryRetriever(graph_store=graph_store, embedder=embedder) -# Step 8: Run hybrid retrieval retrieved_items: list[TextualMemoryItem] = retriever.retrieve( query=query, parsed_goal=parsed_goal, - top_k=10, - memory_scope="LongTermMemory", + top_k=10, # Maximum number of memories to retrieve + memory_scope="LongTermMemory", # Filter by memory type query_embedding=[query_embedding], ) -# Step 9: Print retrieved memory items -print("\n=== Retrieved Memory Items ===") -for item in retrieved_items: - print(f"ID: {item.id}") - print(f"Memory: {item.memory}") +print(f"✓ Retrieved {len(retrieved_items)} memories") + +# ============================================================================ +# Step 7: Display results +# ============================================================================ +print(f"\n{'=' * 70}") +print("Retrieved Memory Items:") +print(f"{'=' * 70}\n") + +if not retrieved_items: + print("❌ No memories retrieved.") + print(" This might indicate:") + print(" - The mock data wasn't inserted correctly") + print(" - The query doesn't match any stored memories") + print(" - The retrieval parameters are too restrictive") +else: + for idx, item in enumerate(retrieved_items, 1): + print(f"[{idx}] ID: {item.id}") + print(f" Memory: {item.memory}") + print(f" Tags: {item.metadata.tags if hasattr(item.metadata, 'tags') else 'N/A'}") + print() + +print(f"{'=' * 70}") +print("Example completed successfully!") +print(f"{'=' * 70}\n") diff --git a/examples/basic_modules/tree_textual_memory_relation_reason_detector.py b/examples/basic_modules/tree_textual_memory_relation_reason_detector.py index 72e4deb60..dd6bca67f 100644 --- a/examples/basic_modules/tree_textual_memory_relation_reason_detector.py +++ b/examples/basic_modules/tree_textual_memory_relation_reason_detector.py @@ -1,3 +1,31 @@ +""" +Tree Textual Memory Relation & Reasoning Detector Example +========================================================== + +This example demonstrates how to use MemOS's RelationAndReasoningDetector to +automatically discover relationships between memories and infer new knowledge. + +**What you'll learn:** +- How to initialize embedder, graph store, and LLM for relation detection +- How to create mock memory nodes with rich metadata +- How to detect pairwise relations between memory nodes (e.g., causal, temporal) +- How to infer new facts through multi-hop reasoning chains +- How to generate aggregate concepts from related memories +- How to identify sequential patterns (FOLLOWS relationships) + +**Use case:** +You have stored multiple facts about a user (e.g., "Caroline's work stress", +"joining support group", "improved mental health"). This detector can: +1. Find causal links: "Work stress" → "Joining support group" → "Better mental health" +2. Infer new facts: "Support groups help reduce work-related stress" +3. Build aggregate concepts: "Caroline's stress management journey" + +Run this example: + python examples/basic_modules/tree_textual_memory_relation_reason_detector.py +""" + +import json +import os import uuid from memos import log @@ -16,52 +44,79 @@ logger = log.get_logger(__name__) -# === Step 1: Initialize embedder === -embedder_config = EmbedderConfigFactory.model_validate( - { - "backend": "ollama", - "config": { - "model_name_or_path": "nomic-embed-text:latest", - }, - } -) +# ============================================================================ +# Step 0: Setup - Load configuration files +# ============================================================================ +print("=" * 80) +print("Tree Textual Memory Relation & Reasoning Detector Example") +print("=" * 80) +print("\nThis example will:") +print(" 1. Create a set of related memories about Caroline") +print(" 2. Detect causal and temporal relationships between them") +print(" 3. Infer new knowledge through reasoning chains") +print(" 4. Generate aggregate concepts") +print("=" * 80) + +current_dir = os.path.dirname(os.path.abspath(__file__)) +config_dir = os.path.join(current_dir, "../data/config") + +# Load the shared tree-text memory configuration +# This includes embedder, graph DB, and LLM configurations +config_path = os.path.join(config_dir, "tree_config_shared_database.json") +with open(config_path) as f: + config_data = json.load(f) + +print(f"\n✓ Loaded configuration from: {config_path}") + +# ============================================================================ +# Step 1: Initialize Embedder +# ============================================================================ +print("\n[Step 1] Initializing embedder...") + +embedder_config = EmbedderConfigFactory.model_validate(config_data["embedder"]) embedder = EmbedderFactory.from_config(embedder_config) -# === Step 2: Initialize Neo4j GraphStore === -graph_config = GraphDBConfigFactory( - backend="neo4j", - config={ - "uri": "bolt://localhost:7687", - "user": "neo4j", - "password": "12345678", - "db_name": "lucy4", - "auto_create": True, - }, -) +print(f"✓ Embedder initialized: {embedder_config.backend}") + +# ============================================================================ +# Step 2: Initialize Graph Store +# ============================================================================ +print("\n[Step 2] Initializing graph database...") + +# Load graph database configuration from the config file +graph_config = GraphDBConfigFactory(**config_data["graph_db"]) graph_store = GraphStoreFactory.from_config(graph_config) -# === Step 3: Initialize LLM for pairwise relation detection === -# Step 1: Load LLM config and instantiate -config = LLMConfigFactory.model_validate( - { - "backend": "ollama", - "config": { - "model_name_or_path": "qwen3:0.6b", - "temperature": 0.7, - "max_tokens": 1024, - }, - } -) -llm = LLMFactory.from_config(config) +print(f"✓ Graph store initialized: {graph_config.backend}") +print(f" Connected to: {graph_config.config.get('uri', 'N/A')}") +print(f" Database: {graph_config.config.get('db_name', 'N/A')}") + +# ============================================================================ +# Step 3: Initialize LLM +# ============================================================================ +print("\n[Step 3] Initializing LLM for relation detection...") -# === Step 4: Create a mock GraphDBNode to test relation detection === +# The LLM analyzes pairs of memories to detect semantic relationships +# (e.g., "causes", "leads to", "happens before", etc.) +# We use the extractor_llm from the config file +llm_config = LLMConfigFactory.model_validate(config_data["extractor_llm"]) +llm = LLMFactory.from_config(llm_config) +print(f"✓ LLM initialized: {llm_config.backend}") + +# ============================================================================ +# Step 4: Create Mock Memory Nodes +# ============================================================================ +print("\n[Step 4] Creating mock memory nodes...") +print(" Building a scenario about Caroline's stress and support journey...\n") + +# Node A: Caroline's work stress node_a = GraphDBNode( id=str(uuid.uuid4()), memory="Caroline faced increased workload stress during the project deadline.", metadata=TreeNodeTextualMemoryMetadata( memory_type="LongTermMemory", - embedding=[0.1] * 10, + embedding=[0.1] * 10, # Placeholder embedding (real one will be generated) key="Workload stress", tags=["stress", "workload"], type="fact", @@ -70,7 +125,7 @@ updated_at="2024-06-28T09:00:00Z", ), ) - +# Node B: Improved mental health after joining support group node_b = GraphDBNode( id=str(uuid.uuid4()), memory="After joining the support group, Caroline reported improved mental health.", @@ -85,7 +140,9 @@ updated_at="2024-07-10T12:00:00Z", ), ) +print(" ✓ Node B: Improved mental health") +# Node C: General research about support groups node_c = GraphDBNode( id=str(uuid.uuid4()), memory="Peer support groups are effective in reducing stress for LGBTQ individuals.", @@ -100,8 +157,9 @@ updated_at="2024-06-29T14:00:00Z", ), ) +print(" ✓ Node C: Support group benefits") -# === D: Work pressure ➜ stress === +# Node D: Work pressure → stress (causal chain element) node_d = GraphDBNode( id=str(uuid.uuid4()), memory="Excessive work pressure increases stress levels among employees.", @@ -116,8 +174,9 @@ updated_at="2024-06-15T08:00:00Z", ), ) +print(" ✓ Node D: Work pressure → stress") -# === E: Stress ➜ poor sleep === +# Node E: Stress → poor sleep (causal chain element) node_e = GraphDBNode( id=str(uuid.uuid4()), memory="High stress levels often result in poor sleep quality.", @@ -132,8 +191,9 @@ updated_at="2024-06-18T10:00:00Z", ), ) +print(" ✓ Node E: Stress → poor sleep") -# === F: Poor sleep ➜ low performance === +# Node F: Poor sleep → low performance (causal chain element) node_f = GraphDBNode( id=str(uuid.uuid4()), memory="Employees with poor sleep show reduced work performance.", @@ -148,7 +208,10 @@ updated_at="2024-06-20T12:00:00Z", ), ) +print(" ✓ Node F: Poor sleep → low performance") +# Main Node: The central fact we want to analyze +# This node will be used as the "anchor" to find related memories node = GraphDBNode( id="a88db9ce-3c77-4e83-8d61-aa9ef95c957e", memory="Caroline joined an LGBTQ support group to cope with work-related stress.", @@ -156,7 +219,7 @@ memory_type="LongTermMemory", embedding=embedder.embed( ["Caroline joined an LGBTQ support group to cope with work-related stress."] - )[0], + )[0], # Generate real embedding for the main node key="Caroline LGBTQ stress", tags=["LGBTQ", "support group", "stress"], type="fact", @@ -165,49 +228,122 @@ updated_at="2024-07-01T10:00:00Z", ), ) +print(" ✓ Main Node: Caroline's support group action\n") +# ============================================================================ +# Step 5: Insert Nodes into Graph Store +# ============================================================================ +print("[Step 5] Inserting all nodes into graph database...") -for n in [node, node_a, node_b, node_c, node_d, node_e, node_f]: +all_nodes = [node, node_a, node_b, node_c, node_d, node_e, node_f] +for n in all_nodes: graph_store.add_node(n.id, n.memory, n.metadata.dict()) +print(f"✓ Successfully inserted {len(all_nodes)} memory nodes into the graph\n") + +# ============================================================================ +# Step 6: Initialize Relation & Reasoning Detector +# ============================================================================ +print("[Step 6] Initializing RelationAndReasoningDetector...") -# === Step 5: Initialize RelationDetector and run detection === relation_detector = RelationAndReasoningDetector( - graph_store=graph_store, llm=llm, embedder=embedder + graph_store=graph_store, + llm=llm, + embedder=embedder, ) +print("✓ Detector initialized and ready\n") + +# ============================================================================ +# Step 7: Run Relation Detection & Reasoning +# ============================================================================ +print("[Step 7] Running relation detection and reasoning...") +print(f" Analyzing relationships for: '{node.memory[:60]}...'\n") + +# This will: +# 1. Find semantically similar nodes using embeddings +# 2. Detect pairwise relations (causal, temporal, etc.) using LLM +# 3. Infer new facts through multi-hop reasoning +# 4. Generate aggregate concepts +# 5. Identify sequential patterns results = relation_detector.process_node( node=node, - exclude_ids=[node.id], # Exclude self when searching for neighbors - top_k=5, + exclude_ids=[node.id], # Don't compare the node with itself + top_k=5, # Consider top 5 most similar nodes ) -# === Step 6: Print detected relations === -print("\n=== Detected Global Relations ===") +print("✓ Analysis complete!\n") + +# ============================================================================ +# Step 8: Display Results +# ============================================================================ +print("=" * 80) +print("ANALYSIS RESULTS") +print("=" * 80) + +# Display detected pairwise relations +print("\n📊 [1] Detected Pairwise Relations") +print("-" * 80) +if results["relations"]: + for idx, rel in enumerate(results["relations"], 1): + print(f"\n Relation #{idx}:") + print(f" Source: {rel['source_id'][:8]}...") + print(f" Target: {rel['target_id'][:8]}...") + print(f" Type: {rel['relation_type']}") +else: + print(" ❌ No pairwise relations detected") + print(" Try adjusting similarity threshold or adding more related nodes") +# Display inferred new facts +print("\n\n💡 [2] Inferred New Facts (through reasoning)") +print("-" * 80) +if results["inferred_nodes"]: + for idx, inferred_node in enumerate(results["inferred_nodes"], 1): + print(f"\n Inferred Fact #{idx}:") + print(f" 💬 {inferred_node.memory}") + print(f" 📌 Sources: {inferred_node.metadata.sources}") + print(f" 🏷️ Key: {inferred_node.metadata.key}") +else: + print(" ℹ️ No new facts inferred") + print(" This is normal if relations are simple or insufficient for reasoning") -# === Step 6: Pretty-print detected results === -print("\n=== Detected Pairwise Relations ===") -for rel in results["relations"]: - print(f" Source ID: {rel['source_id']}") - print(f" Target ID: {rel['target_id']}") - print(f" Relation Type: {rel['relation_type']}") - print("------") +# Display sequence links (temporal ordering) +print("\n\n⏱️ [3] Sequence Links (FOLLOWS relationships)") +print("-" * 80) +if results["sequence_links"]: + for idx, link in enumerate(results["sequence_links"], 1): + print(f" {idx}. {link['from_id'][:8]}... → {link['to_id'][:8]}...") +else: + print(" ℹ️ No sequential patterns detected") -print("\n=== Inferred Nodes ===") -for node in results["inferred_nodes"]: - print(f" New Fact: {node.memory}") - print(f" Sources: {node.metadata.sources}") - print("------") +# Display aggregate concepts +print("\n\n🎯 [4] Aggregate Concepts") +print("-" * 80) +if results["aggregate_nodes"]: + for idx, agg in enumerate(results["aggregate_nodes"], 1): + print(f"\n Concept #{idx}:") + print(f" 📖 {agg.memory}") + print(f" 🔑 Key: {agg.metadata.key}") + print(f" 📎 Aggregates from: {agg.metadata.sources}") +else: + print(" ℹ️ No aggregate concepts generated") + print(" Aggregates are created when multiple related memories share themes") -print("\n=== Sequence Links (FOLLOWS) ===") -for link in results["sequence_links"]: - print(f" From: {link['from_id']} -> To: {link['to_id']}") - print("------") +print("\n" + "=" * 80) +print("Example completed successfully!") +print("=" * 80) +print("\n💡 Next steps:") +print(" - Modify the mock memories to test different scenarios") +print(" - Adjust top_k parameter to control how many neighbors are considered") +print(" - Experiment with different LLM models for relation detection") +print(" - Check the Neo4j database to visualize the created graph\n") print("\n=== Aggregate Concepts ===") -for agg in results["aggregate_nodes"]: - print(f" Concept Key: {agg.metadata.key}") - print(f" Concept Memory: {agg.memory}") - print(f" Sources: {agg.metadata.sources}") - print("------") +if not results["aggregate_nodes"]: + print("No aggregate concepts generated.") +else: + for agg in results["aggregate_nodes"]: + print(f" Concept Key: {agg.metadata.key}") + print(f" Concept Memory: {agg.memory}") + print(f" Sources: {agg.metadata.sources}") + print("------") diff --git a/examples/basic_modules/tree_textual_memory_task_goal_parser.py b/examples/basic_modules/tree_textual_memory_task_goal_parser.py index c36d47cf1..11c2c8087 100644 --- a/examples/basic_modules/tree_textual_memory_task_goal_parser.py +++ b/examples/basic_modules/tree_textual_memory_task_goal_parser.py @@ -1,52 +1,185 @@ +""" +Tree Textual Memory Task Goal Parser Example +============================================= + +This example demonstrates how to use MemOS's TaskGoalParser to parse natural +language queries into structured retrieval goals. + +**What you'll learn:** +- How to initialize an LLM for task parsing +- How to parse a natural language query into structured components +- The difference between "fast" and "fine" parsing modes +- How the parser extracts memories, keys, tags, and goal types + +**Use case:** +When a user asks "When did Caroline go to the LGBTQ support group?", you need to: +1. Extract semantic descriptions (memories to look for) +2. Identify key phrases and keywords +3. Determine relevant tags for filtering +4. Classify the goal type (retrieval, update, etc.) + +The TaskGoalParser does this automatically using an LLM. + +Run this example: + python examples/basic_modules/tree_textual_memory_task_goal_parser.py +""" + +import json +import os import time +from memos import log from memos.configs.llm import LLMConfigFactory from memos.llms.factory import LLMFactory from memos.memories.textual.tree_text_memory.retrieve.task_goal_parser import TaskGoalParser -# Step 1: Load LLM config and instantiate -config = LLMConfigFactory.model_validate( - { - "backend": "ollama", - "config": { - "model_name_or_path": "qwen3:0.6b", - "temperature": 0.7, - "max_tokens": 1024, - "remove_think_prefix": True, - }, - } -) -llm = LLMFactory.from_config(config) +logger = log.get_logger(__name__) + +# ============================================================================ +# Step 0: Setup - Load configuration files +# ============================================================================ +print("=" * 80) +print("Tree Textual Memory Task Goal Parser Example") +print("=" * 80) + +current_dir = os.path.dirname(os.path.abspath(__file__)) +config_dir = os.path.join(current_dir, "../data/config") + +# Load the shared tree-text memory configuration +config_path = os.path.join(config_dir, "tree_config_shared_database.json") +with open(config_path) as f: + config_data = json.load(f) + +print(f"\n✓ Loaded configuration from: {config_path}") + +# ============================================================================ +# Step 1: Initialize LLM for Task Parsing +# ============================================================================ +print("\n[Step 1] Initializing LLM for task goal parsing...") + +# The LLM will analyze the natural language query and extract structured information +# We use the extractor_llm from the config file +llm_config = LLMConfigFactory.model_validate(config_data["extractor_llm"]) +llm = LLMFactory.from_config(llm_config) + +print(f"✓ LLM initialized: {llm_config.backend}") -# Task input +# ============================================================================ +# Step 2: Define a natural language task/query +# ============================================================================ +# This is the user's question that needs to be parsed task = "When did Caroline go to the LGBTQ support group?" -parser = TaskGoalParser(llm, mode="fast") +print("\n[Step 2] Task to parse:") +print(f" 📝 '{task}'") +print() -time_init = time.time() -# Parse task goal -result = parser.parse(task) +# ============================================================================ +# Step 3: Parse using FAST mode +# ============================================================================ +print("[Step 3] Parsing with FAST mode...") +print(" (Fast mode uses a simpler prompt for quick parsing)") -# Print output -print("=== Parsed Result ===") -print("memories:", result.memories) -print("keys:", result.keys) -print("tags:", result.tags) -print("goal_type:", result.goal_type) -print("time:", time.time() - time_init) +parser = TaskGoalParser(llm) -parser = TaskGoalParser(llm, mode="fine") +time_start = time.time() +result_fast = parser.parse(task, mode="fast") +time_fast = time.time() - time_start -time_init = time.time() +print(f"✓ Fast mode parsing completed in {time_fast:.3f}s\n") -# Parse task goal -result = parser.parse(task) +# Display fast mode results +print("=" * 80) +print("FAST MODE RESULTS") +print("=" * 80) +print("\n📋 Memories (semantic descriptions):") +if result_fast.memories: + for idx, mem in enumerate(result_fast.memories, 1): + print(f" {idx}. {mem}") +else: + print(" (None extracted)") + +print("\n🔑 Keys (important keywords):") +if result_fast.keys: + for idx, key in enumerate(result_fast.keys, 1): + print(f" {idx}. {key}") +else: + print(" (None extracted)") + +print("\n🏷️ Tags (categorical labels):") +if result_fast.tags: + print(f" {', '.join(result_fast.tags)}") +else: + print(" (None extracted)") + +print(f"\n🎯 Goal Type: {result_fast.goal_type}") +print(f"⏱️ Processing Time: {time_fast:.3f}s") + +# ============================================================================ +# Step 4: Parse using FINE mode +# ============================================================================ +print(f"\n{'=' * 80}") +print("[Step 4] Parsing with FINE mode...") +print(" (Fine mode uses more detailed prompts for better accuracy)") + +time_start = time.time() +result_fine = parser.parse(task, mode="fine") +time_fine = time.time() - time_start + +print(f"✓ Fine mode parsing completed in {time_fine:.3f}s\n") + +# Display fine mode results +print("=" * 80) +print("FINE MODE RESULTS") +print("=" * 80) +print("\n📋 Memories (semantic descriptions):") +if result_fine.memories: + for idx, mem in enumerate(result_fine.memories, 1): + print(f" {idx}. {mem}") +else: + print(" (None extracted)") + +print("\n🔑 Keys (important keywords):") +if result_fine.keys: + for idx, key in enumerate(result_fine.keys, 1): + print(f" {idx}. {key}") +else: + print(" (None extracted)") + +print("\n🏷️ Tags (categorical labels):") +if result_fine.tags: + print(f" {', '.join(result_fine.tags)}") +else: + print(" (None extracted)") + +print(f"\n🎯 Goal Type: {result_fine.goal_type}") +print(f"⏱️ Processing Time: {time_fine:.3f}s") + +# ============================================================================ +# Step 5: Compare Results +# ============================================================================ +print(f"\n{'=' * 80}") +print("COMPARISON") +print("=" * 80) +print("\nSpeed:") +print(f" Fast mode: {time_fast:.3f}s") +print(f" Fine mode: {time_fine:.3f}s") +print(f" Difference: {abs(time_fast - time_fine):.3f}s") + +print("\nExtracted Components:") +print( + f" Fast mode: {len(result_fast.memories)} memories, {len(result_fast.keys)} keys, {len(result_fast.tags)} tags" +) +print( + f" Fine mode: {len(result_fine.memories)} memories, {len(result_fine.keys)} keys, {len(result_fine.tags)} tags" +) -# Print output -print("=== Parsed Result ===") -print("memories:", result.memories) -print("keys:", result.keys) -print("tags:", result.tags) -print("goal_type:", result.goal_type) -print("time:", time.time() - time_init) +print(f"\n{'=' * 80}") +print("Example completed successfully!") +print("=" * 80) +print("\n💡 Next steps:") +print(" - Try different queries to see how the parser handles various inputs") +print(" - Use the parsed result as input for GraphMemoryRetriever") +print(" - Experiment with 'fast' vs 'fine' mode based on your accuracy/speed needs") +print(" - The parsed ParsedTaskGoal can be passed directly to retrieval functions\n") diff --git a/examples/data/config/simple_struct_reader_config.json b/examples/data/config/simple_struct_reader_config.json index 8a27de457..abfcdfa92 100644 --- a/examples/data/config/simple_struct_reader_config.json +++ b/examples/data/config/simple_struct_reader_config.json @@ -1,24 +1,30 @@ { "llm": { - "backend": "ollama", + "backend": "openai", "config": { - "model_name_or_path": "qwen3:0.6b", - "temperature": 0.0, - "remove_think_prefix": true, - "max_tokens": 8192 + "model_name_or_path": "gpt-4o-mini", + "temperature": 0.8, + "max_tokens": 1024, + "top_p": 0.9, + "top_k": 50, + "api_key": "sk-xxx", + "api_base": "http://" } }, "embedder": { - "backend": "ollama", + "backend": "universal_api", "config": { - "model_name_or_path": "nomic-embed-text:latest" + "provider": "openai", + "api_key": "EMPTY", + "model_name_or_path": "bge-m3", + "base_url": "http://" } }, "chunker": { "backend": "sentence", "config": { "tokenizer_or_token_counter": "gpt2", - "chunk_size": 512, + "chunk_size": 2048, "chunk_overlap": 128, "min_sentences_per_chunk": 1 } diff --git a/examples/data/config/tree_config_shared_database.json b/examples/data/config/tree_config_shared_database.json index 889a4a592..a0a9bc3a3 100644 --- a/examples/data/config/tree_config_shared_database.json +++ b/examples/data/config/tree_config_shared_database.json @@ -1,41 +1,63 @@ { "extractor_llm": { - "backend": "ollama", + "backend": "openai", "config": { - "model_name_or_path": "qwen3:0.6b", - "temperature": 0.0, - "remove_think_prefix": true, - "max_tokens": 8192 + "model_name_or_path": "gpt-4o", + "temperature": 0.8, + "max_tokens": 1024, + "top_p": 0.9, + "top_k": 50, + "api_key": "sk-xxx", + "api_base": "http://" } }, "dispatcher_llm": { - "backend": "ollama", + "backend": "openai", "config": { - "model_name_or_path": "qwen3:0.6b", - "temperature": 0.0, - "remove_think_prefix": true, - "max_tokens": 8192 + "model_name_or_path": "gpt-4o", + "temperature": 0.8, + "max_tokens": 1024, + "top_p": 0.9, + "top_k": 50, + "api_key": "sk-xxx", + "api_base": "http://" } }, "embedder": { - "backend": "ollama", + "backend": "universal_api", "config": { - "model_name_or_path": "nomic-embed-text:latest" + "provider": "openai", + "api_key": "EMPTY", + "model_name_or_path": "bge-m3", + "base_url": "http://" + } + }, + "reranker": { + "backend": "http_bge", + "config": { + "url": "http://", + "model": "bge-reranker-v2-m3", + "timeout": 10 } }, "graph_db": { "backend": "neo4j", "config": { - "uri": "bolt://localhost:7687", + "uri": "neo4j://127.0.0.1:7687", "user": "neo4j", "password": "12345678", - "db_name": "shared-tree-textual-memory", - "user_name": "alice", + "db_name": "neo4j", + "user_name": "xxx", "auto_create": true, - "use_multi_db": false, - "embedding_dimension": 768 + "use_multi_db": true, + "embedding_dimension": 1024 } }, - "reorganize": true, + "reorganize": false, + "memory_size": { + "WorkingMemory": 200, + "LongTermMemory": 20000, + "UserMemory": 30000 + } "memory_filename": "tree_textual_memories.json" } diff --git a/examples/mem_mcp/simple_fastmcp_client.py b/examples/mem_mcp/simple_fastmcp_client.py index 1981e3066..e5c186b3b 100644 --- a/examples/mem_mcp/simple_fastmcp_client.py +++ b/examples/mem_mcp/simple_fastmcp_client.py @@ -12,66 +12,43 @@ async def main(): print("Working FastMCP Client") print("=" * 40) - async with Client("http://127.0.0.1:8000/mcp") as client: - print("Connected to MOS MCP server!") + # Connect to MCP server via HTTP + # FastMCP HTTP endpoint is at /mcp (not /mcp/v1) + async with Client("http://localhost:8002/mcp") as client: + print("Connected to MCP server") - print("Available tools:") - tools = await client.list_tools() - for tool in tools: - print("**" * 20) - print(f" - {tool.name}: {tool.description}") + print("\nTesting tool calls via Server API...") - print("Available resources:") - resources = await client.list_resources() - for resource in resources: - print(f" - {resource.uri}: {resource.description}") + # Note: 'create_user' and 'get_user_info' are not supported by the Server API. + # We assume the user already exists or the Server API handles it implicitly. + # Using a demo user ID. + user_id = "fastmcp_demo_user" - print("Testing tool calls...") - - print(" Getting user info...") - result = await client.call_tool("get_user_info", {}) - print(f" Result: {result.content[0].text}") - - print(" Creating user...") - result = await client.call_tool( - "create_user", - {"user_id": "fastmcp_user", "role": "USER", "user_name": "FastMCP Test User"}, - ) - print(f"Result: {result.content[0].text}") - - print(" register cube...") + print("\n 1. Adding memory...") result = await client.call_tool( - "register_cube", - { - "cube_name_or_path": "cube_default_user", - "user_id": "fastmcp_user", - "cube_id": "fastmcp_user", + "add_memory", + arguments={ + "memory_content": "MemOS is a great tool for memory management.", + "user_id": user_id, }, ) print(f" Result: {result}") - print(" Adding memory...") + print("\n 2. Searching memories...") result = await client.call_tool( - "add_memory", - { - "memory_content": "This is a test memory from FastMCP client.", - "cube_id": "fastmcp_user", - "user_id": "fastmcp_user", - }, + "search_memories", + arguments={"query": "MemOS", "user_id": user_id}, ) - print(f" Result: {result.content[0].text}") + print(f" Result: {result}") - print(" Searching memories...") + print("\n 3. Chatting...") result = await client.call_tool( - "search_memories", {"query": "test memory", "user_id": "fastmcp_user"} + "chat", + arguments={"query": "What is MemOS?", "user_id": user_id}, ) - print(f" Result: {result.content[0].text[:200]}...") + print(f" Result: {result}") - print(" Testing chat...") - result = await client.call_tool( - "chat", {"query": "Hello! Tell me about yourself.", "user_id": "fastmcp_user"} - ) - print(f" Result: {result.content[0].text[:200]}...") + print("\n✓ All tests completed!") if __name__ == "__main__": diff --git a/examples/mem_mcp/simple_fastmcp_serve.py b/examples/mem_mcp/simple_fastmcp_serve.py index 78c05cd05..55ad4d84d 100644 --- a/examples/mem_mcp/simple_fastmcp_serve.py +++ b/examples/mem_mcp/simple_fastmcp_serve.py @@ -1,18 +1,67 @@ import argparse +import json import os -from memos.api.mcp_serve import MOSMCPStdioServer +import requests +from dotenv import load_dotenv +from fastmcp import FastMCP + + +load_dotenv() + +# Configuration +# This points to the Server API base URL (e.g., started via server_api.py) +API_BASE_URL = os.getenv("MEMOS_API_BASE_URL", "http://localhost:8001/product") + +# Create MCP Server +mcp = FastMCP("MemOS MCP via Server API") -if __name__ == "__main__": - import argparse - from dotenv import load_dotenv +@mcp.tool() +def add_memory(memory_content: str, user_id: str, cube_id: str | None = None): + """Add memory using the Server API.""" + payload = { + "user_id": user_id, + "messages": memory_content, + "writable_cube_ids": [cube_id] if cube_id else None, + } + try: + resp = requests.post(f"{API_BASE_URL}/add", json=payload) + resp.raise_for_status() + return resp.json()["message"] + except Exception as e: + return f"Error: {e}" - load_dotenv() +@mcp.tool() +def search_memories(query: str, user_id: str, cube_ids: str | None = None): + """Search memories using the Server API.""" + payload = {"query": query, "user_id": user_id, "readable_cube_ids": cube_ids} + try: + resp = requests.post(f"{API_BASE_URL}/search", json=payload) + resp.raise_for_status() + # The Server API search response structure matches product API mostly + return json.dumps(resp.json()["data"], ensure_ascii=False) + except Exception as e: + return f"Error: {e}" + + +@mcp.tool() +def chat(query: str, user_id: str): + """Chat using the Server API.""" + payload = {"query": query, "user_id": user_id} + try: + resp = requests.post(f"{API_BASE_URL}/chat/complete", json=payload) + resp.raise_for_status() + return resp.json()["data"]["response"] + except Exception as e: + return f"Error: {e}" + + +if __name__ == "__main__": # Parse command line arguments - parser = argparse.ArgumentParser(description="MOS MCP Server") + parser = argparse.ArgumentParser(description="MOS MCP Server via API") parser.add_argument( "--transport", choices=["stdio", "http", "sse"], @@ -24,14 +73,8 @@ args = parser.parse_args() - # Set environment variables - os.environ["OPENAI_API_BASE"] = os.getenv("OPENAI_API_BASE") - os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY") - os.environ["MOS_TEXT_MEM_TYPE"] = "tree_text" # "tree_text" need set neo4j - os.environ["NEO4J_URI"] = os.getenv("NEO4J_URI") - os.environ["NEO4J_USER"] = os.getenv("NEO4J_USER") - os.environ["NEO4J_PASSWORD"] = os.getenv("NEO4J_PASSWORD") - - # Create and run MCP server - server = MOSMCPStdioServer() - server.run(transport=args.transport, host=args.host, port=args.port) + # For stdio transport, don't pass host and port + if args.transport == "stdio": + mcp.run(transport=args.transport) + else: + mcp.run(transport=args.transport, host=args.host, port=args.port) diff --git a/src/memos/api/mcp_serve.py b/src/memos/api/mcp_serve.py index 838c2a76a..ce2e41390 100644 --- a/src/memos/api/mcp_serve.py +++ b/src/memos/api/mcp_serve.py @@ -61,6 +61,19 @@ def load_default_config(user_id="default_user"): "SCHEDULER_TOP_N": "scheduler_top_n", } + # Fields that should always be kept as strings (not converted to numbers) + string_only_fields = { + "openai_api_key", + "openai_api_base", + "neo4j_uri", + "neo4j_user", + "neo4j_password", + "neo4j_db_name", + "text_mem_type", + "model_name", + "embedder_model", + } + kwargs = {"user_id": user_id} for env_key, param_key in env_mapping.items(): val = os.getenv(env_key) @@ -74,6 +87,9 @@ def load_default_config(user_id="default_user"): # Handle boolean conversions if val.lower() in ("true", "false"): kwargs[param_key] = val.lower() == "true" + # Keep certain fields as strings + elif param_key in string_only_fields: + kwargs[param_key] = val else: # Try numeric conversions (int first, then float) try: @@ -93,6 +109,10 @@ def load_default_config(user_id="default_user"): openai_api_base = kwargs.pop("openai_api_base", "https://api.openai.com/v1") text_mem_type = kwargs.pop("text_mem_type", "tree_text") + # Ensure embedder_model has a default value if not set + if "embedder_model" not in kwargs: + kwargs["embedder_model"] = os.getenv("EMBEDDER_MODEL", "nomic-embed-text:latest") + config, cube = get_default( openai_api_key=openai_api_key, openai_api_base=openai_api_base, @@ -110,6 +130,21 @@ def __init__(self): self.mos_core.register_mem_cube(cube) self._setup_tools() + +class MOSMCPServer: + """MCP Server that accepts an existing MOS instance.""" + + def __init__(self, mos_instance: MOS | None = None): + self.mcp = FastMCP("MOS Memory System") + if mos_instance is None: + # Fall back to creating from default config + config, cube = load_default_config() + self.mos_core = MOS(config=config) + self.mos_core.register_mem_cube(cube) + else: + self.mos_core = mos_instance + self._setup_tools() + def _setup_tools(self): """Setup MCP tools""" @@ -133,7 +168,10 @@ async def chat(query: str, user_id: str | None = None) -> str: response = self.mos_core.chat(query, user_id) return response except Exception as e: - return f"Chat error: {e!s}" + import traceback + + error_details = traceback.format_exc() + return f"Chat error: {e!s}\nTraceback:\n{error_details}" @self.mcp.tool() async def create_user( @@ -261,7 +299,10 @@ async def search_memories( result = self.mos_core.search(query, user_id, cube_ids) return result except Exception as e: - return {"error": str(e)} + import traceback + + error_details = traceback.format_exc() + return {"error": str(e), "traceback": error_details} @self.mcp.tool() async def add_memory( @@ -527,23 +568,24 @@ async def control_memory_scheduler(action: str) -> str: except Exception as e: return f"Error controlling memory scheduler: {e!s}" - def run(self, transport: str = "stdio", **kwargs): - """Run MCP server with specified transport""" - if transport == "stdio": - # Run stdio mode (default for local usage) - self.mcp.run(transport="stdio") - elif transport == "http": - # Run HTTP mode - host = kwargs.get("host", "localhost") - port = kwargs.get("port", 8000) - asyncio.run(self.mcp.run_http_async(host=host, port=port)) - elif transport == "sse": - # Run SSE mode (deprecated but still supported) - host = kwargs.get("host", "localhost") - port = kwargs.get("port", 8000) - self.mcp.run(transport="sse", host=host, port=port) - else: - raise ValueError(f"Unsupported transport: {transport}") + +def _run_mcp(self, transport: str = "stdio", **kwargs): + if transport == "stdio": + self.mcp.run(transport="stdio") + elif transport == "http": + host = kwargs.get("host", "localhost") + port = kwargs.get("port", 8000) + asyncio.run(self.mcp.run_http_async(host=host, port=port)) + elif transport == "sse": + host = kwargs.get("host", "localhost") + port = kwargs.get("port", 8000) + self.mcp.run(transport="sse", host=host, port=port) + else: + raise ValueError(f"Unsupported transport: {transport}") + + +MOSMCPStdioServer.run = _run_mcp +MOSMCPServer.run = _run_mcp # Usage example diff --git a/src/memos/cli.py b/src/memos/cli.py index fb3475ff3..092f2d276 100644 --- a/src/memos/cli.py +++ b/src/memos/cli.py @@ -13,7 +13,7 @@ def export_openapi(output: str) -> bool: """Export OpenAPI schema to JSON file.""" - from memos.api.start_api import app + from memos.api.server_api import app # Create directory if it doesn't exist if os.path.dirname(output): diff --git a/tests/test_openapi_sync.py b/tests/test_openapi_sync.py index 90d44dcf0..48e872d66 100644 --- a/tests/test_openapi_sync.py +++ b/tests/test_openapi_sync.py @@ -2,7 +2,7 @@ from pathlib import Path -from memos.api.start_api import app +from memos.api.server_api import app OPENAPI_JSON_PATH = Path(__file__).parent.parent / "docs" / "openapi.json" From 62ac224cbf167d26c4d4d4c8fd234e74e0cddb42 Mon Sep 17 00:00:00 2001 From: caocuilong <39516215+caocuilong@users.noreply.github.com> Date: Fri, 16 Jan 2026 15:19:09 +0800 Subject: [PATCH 36/47] Examples update (#887) * neo4j_example.py * neo4j_example.py * neo4j_example.py --- examples/basic_modules/neo4j_example.py | 73 +++++++++++++++++++++++++ 1 file changed, 73 insertions(+) diff --git a/examples/basic_modules/neo4j_example.py b/examples/basic_modules/neo4j_example.py index ea68975cc..e1c0df317 100644 --- a/examples/basic_modules/neo4j_example.py +++ b/examples/basic_modules/neo4j_example.py @@ -27,6 +27,23 @@ def embed_memory_item(memory: str) -> list[float]: return embedder.embed([memory])[0] +def get_neo4j_graph(db_name: str = "paper"): + config = GraphDBConfigFactory( + backend="neo4j", + config={ + "uri": "bolt://xxxx:7687", + "user": "neo4j", + "password": "xxxx", + "db_name": db_name, + "auto_create": True, + "embedding_dimension": 3072, + "use_multi_db": True, + }, + ) + graph = GraphStoreFactory.from_config(config) + return graph + + def example_multi_db(db_name: str = "paper"): # Step 1: Build factory config config = GraphDBConfigFactory( @@ -537,6 +554,53 @@ def example_complex_shared_db(db_name: str = "shared-traval-group-complex", comm ) +def example_complex_shared_db_search_filter(db): + embedding = embed_memory_item( + "The reward function combines " + "multiple objectives: coverage " + "maximization, energy consumption " + ) + print(f"get_node:{db.get_node(id='5364c28e-1e4b-485a-b1d5-1ba11bc5bc8b')}") + + filter_id = {"id": "a269f2bf-f4a2-43b9-aa8d-1cb2a2eb4691"} + print(f"==filter_id:{db.search_by_embedding(vector=embedding, filter=filter_id)}") + + filter_and_params = { + "and": [{"id": "a269f2bf-f4a2-43b9-aa8d-1cb2a2eb4691"}, {"source": "file123"}] + } + print( + f"==filter_and_params:{db.search_by_embedding(vector=embedding, filter=filter_and_params)}" + ) + + filter_or_params = {"or": [{"id": "a269f2bf-f4a2-43b9-aa8d-1cb2a2eb4691"}, {"id": "xxxxxxxx"}]} + print(f"==filter_or_params:{db.search_by_embedding(vector=embedding, filter=filter_or_params)}") + filter_like_params = { + "and": [ + {"memory_type": {"like": "LongTermMemory"}}, + ] + } + print( + f"==filter_like_params:{db.search_by_embedding(vector=embedding, filter=filter_like_params)}" + ) + + """ + cypher_op_map = {"gt": ">", "lt": "<", "gte": ">=", "lte": "<="} + """ + filter_lt_params = { + "and": [ + {"created_at": {"gt": "2025-11-29"}}, + ] + } + print(f"==filter_lt_params:{db.search_by_embedding(vector=embedding, filter=filter_lt_params)}") + + +def example_complex_shared_db_delete_memory(db): + print("delete node") + db.delete_node(id="582de45f-8f99-4006-8062-76eea5649d94") + print("delete edge") + db.delete_edge(source_id=1, target_id=2, type="PARENT", user_name="") + + if __name__ == "__main__": print("\n=== Example: Multi-DB ===") example_multi_db(db_name="paper") @@ -544,8 +608,17 @@ def example_complex_shared_db(db_name: str = "shared-traval-group-complex", comm print("\n=== Example: Single-DB ===") example_shared_db(db_name="shared-traval-group") + print("\n=== Example: Single-DB ===") + example_shared_db(db_name="shared-traval-group") + print("\n=== Example: Single-DB-Complex ===") example_complex_shared_db(db_name="shared-traval-group-complex-new") print("\n=== Example: Single-Community-DB-Complex ===") example_complex_shared_db(db_name="paper", community=True) + + print("\n=== Example: Single-DB-Complex searchFilter ===") + db = get_neo4j_graph(db_name="paper") + example_complex_shared_db_search_filter(db) + + example_complex_shared_db_delete_memory(db) From d00a468123a3d09274bcbf7269c50290063c8aac Mon Sep 17 00:00:00 2001 From: HanshuZhou <118414084+zhouhanshu@users.noreply.github.com> Date: Fri, 16 Jan 2026 15:22:07 +0800 Subject: [PATCH 37/47] Examples memfeedback (#885) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * update example of feedback * update example of mem_feedback --------- Co-authored-by: 周函数 --- examples/mem_feedback/example_feedback.py | 248 ++++++++++++++++++++++ 1 file changed, 248 insertions(+) create mode 100644 examples/mem_feedback/example_feedback.py diff --git a/examples/mem_feedback/example_feedback.py b/examples/mem_feedback/example_feedback.py new file mode 100644 index 000000000..8f4446863 --- /dev/null +++ b/examples/mem_feedback/example_feedback.py @@ -0,0 +1,248 @@ +import json +import os +import sys + + +# Add project root to python path to ensure src modules can be imported +sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../../../src"))) + + +def init_components(): + """ + Initialize MemOS core components. + + This function is responsible for building and configuring all basic components required for MemOS operation, including: + 1. LLM (Large Language Model): Model responsible for natural language understanding and generation (e.g., GPT-4o). + 2. Embedder: Responsible for converting text into vector representations for semantic search and similarity calculation. + 3. GraphDB (Neo4j): Graph database for persistent storage of memory nodes and their relationships. + 4. MemoryManager: Memory manager responsible for memory CRUD operations. + 5. MemReader: Memory reader for parsing and processing input text. + 6. Reranker: Reranker for refining the sorting of retrieval results. + 7. Searcher: Searcher that integrates retrieval and reranking logic. + 8. FeedbackServer (SimpleMemFeedback): Feedback service core, responsible for processing user feedback and updating memory. + + Returns: + tuple: (feedback_server, memory_manager, embedder) + """ + # Lazy import to avoid E402 (module level import not at top of file) + from memos.configs.embedder import EmbedderConfigFactory + from memos.configs.graph_db import GraphDBConfigFactory + from memos.configs.llm import LLMConfigFactory + from memos.configs.mem_reader import MemReaderConfigFactory + from memos.configs.reranker import RerankerConfigFactory + from memos.embedders.factory import EmbedderFactory + from memos.graph_dbs.factory import GraphStoreFactory + from memos.llms.factory import LLMFactory + from memos.mem_feedback.simple_feedback import SimpleMemFeedback + from memos.mem_reader.factory import MemReaderFactory + from memos.memories.textual.tree_text_memory.organize.manager import MemoryManager + from memos.memories.textual.tree_text_memory.retrieve.searcher import Searcher + from memos.reranker.factory import RerankerFactory + + print("Initializing MemOS Components...") + + # 1. LLM: Configure Large Language Model, using OpenAI compatible interface + llm_config = LLMConfigFactory.model_validate( + { + "backend": "openai", + "config": { + "model_name_or_path": os.getenv("MOS_CHAT_MODEL", "gpt-4o"), + "temperature": 0.8, + "max_tokens": 1024, + "top_p": 0.9, + "top_k": 50, + "api_key": os.getenv("OPENAI_API_KEY"), + "api_base": os.getenv("OPENAI_API_BASE"), + }, + } + ) + llm = LLMFactory.from_config(llm_config) + + # 2. Embedder: Configure embedding model for generating text vectors + embedder_config = EmbedderConfigFactory.model_validate( + { + "backend": os.getenv("MOS_EMBEDDER_BACKEND", "universal_api"), + "config": { + "provider": "openai", + "api_key": os.getenv("MOS_EMBEDDER_API_KEY", "EMPTY"), + "model_name_or_path": os.getenv("MOS_EMBEDDER_MODEL", "bge-m3"), + "base_url": os.getenv("MOS_EMBEDDER_API_BASE"), + }, + } + ) + embedder = EmbedderFactory.from_config(embedder_config) + + # 3. GraphDB: Configure Neo4j graph database connection + graph_db = GraphStoreFactory.from_config( + GraphDBConfigFactory.model_validate( + { + "backend": "neo4j", + "config": { + "uri": os.getenv("NEO4J_URI", "neo4j://127.0.0.1:7687"), + "user": os.getenv("NEO4J_USER", "neo4j"), + "password": os.getenv("NEO4J_PASSWORD", "12345678"), + "db_name": os.getenv("NEO4J_DB_NAME", "neo4j"), + "user_name": "zhs", + "auto_create": True, + "use_multi_db": False, + "embedding_dimension": int(os.getenv("EMBEDDING_DIMENSION", "1024")), + }, + } + ) + ) + + # Clear test data for specific user to ensure a clean environment for each run + graph_db.clear(user_name="cube_id_001_0115") + + # 4. MemoryManager: Core memory management, coordinating storage and retrieval + memory_manager = MemoryManager(graph_db, embedder, llm, is_reorganize=False) + + # 5. MemReader: Configure memory reader, including chunking strategy + mem_reader = MemReaderFactory.from_config( + MemReaderConfigFactory.model_validate( + { + "backend": "simple_struct", + "config": { + "llm": llm_config.model_dump(), + "embedder": embedder_config.model_dump(), + "chunker": { + "backend": "sentence", + "config": { + "tokenizer_or_token_counter": "gpt2", + "chunk_size": 512, + "chunk_overlap": 128, + "min_sentences_per_chunk": 1, + }, + }, + }, + } + ) + ) + + # 6. Reranker: Configure reranker to improve retrieval relevance + mem_reranker = RerankerFactory.from_config( + RerankerConfigFactory.model_validate( + { + "backend": os.getenv("MOS_RERANKER_BACKEND", "cosine_local"), + "config": { + "level_weights": {"topic": 1.0, "concept": 1.0, "fact": 1.0}, + "level_field": "background", + }, + } + ) + ) + + # 7. Searcher: Comprehensive searcher + searcher = Searcher(llm, graph_db, embedder, mem_reranker) + + # 8. Feedback Server: Initialize feedback service, the core of this example + feedback_server = SimpleMemFeedback( + llm=llm, + embedder=embedder, + graph_store=graph_db, + memory_manager=memory_manager, + mem_reader=mem_reader, + searcher=searcher, + reranker=mem_reranker, + pref_mem=None, + ) + + return feedback_server, memory_manager, embedder + + +def main(): + """ + Main program flow: + 1. Initialize components. + 2. Simulate a conversation scenario and existing (possibly incorrect) memory. + 3. Receive user feedback (correct memory). + 4. Process feedback and update memory store. + 5. Display processing results. + """ + # Load dotenv in main to avoid affecting module import order + from dotenv import load_dotenv + + load_dotenv() + + # Lazy import to avoid E402 + from memos.mem_feedback.utils import make_mem_item + + feedback_server, memory_manager, embedder = init_components() + print("-" * 50) + print("Initialization Done. Processing Feedback...") + print("-" * 50) + + # 1. Simulate Chat History + # Simulate a conversation between user and assistant, where the assistant's response contains a statement about user preferences. + history = [ + {"role": "user", "content": "我喜欢什么水果,不喜欢什么水果"}, + {"role": "assistant", "content": "你喜欢苹果,不喜欢香蕉"}, + ] + + # 2. Simulate Initial Memory + # We manually add a memory to the database, representing what the system currently believes to be a "fact". + # This memory content is "你喜欢苹果,不喜欢香蕉", which we will later correct via feedback. + mem_text = "你喜欢苹果,不喜欢香蕉" + memory_manager.add( + [ + make_mem_item( + mem_text, + user_id="user_id_001", + user_name="cube_id_001_0115", + session_id="session_id", + tags=["fact"], + key="food_preference", + sources=[{"type": "chat"}], + background="init from chat history", + embedding=embedder.embed([mem_text])[ + 0 + ], # Generate embedding for subsequent retrieval + info={ + "user_id": "user_id_001", + "user_name": "cube_id_001_0115", + "session_id": "session_id", + }, + ) + ], + user_name="cube_id_001_0115", + mode="sync", + ) + + # 3. Feedback Input + # The user points out the previous memory is incorrect and provides the correct information. + feedback_content = "错了,实际上我喜欢的是山竹" + + print("\nChat History:") + print(json.dumps(history, ensure_ascii=False, indent=2)) + print("\nFeedback Input:") + print(feedback_content) + + # 4. Process Feedback + # Core step: Call feedback_server to process user correction information. + # The system analyzes feedback content, retrieves relevant memories, and generates update operations (e.g., add, modify, or archive old memories). + res = feedback_server.process_feedback( + user_id="user_id_001", + user_name="cube_id_001_0115", + session_id="session_id", + chat_history=history, + feedback_content=feedback_content, + feedback_time="", + async_mode="sync", + corrected_answer="", + task_id="task_id", + info={}, + ) + + # 5. Feedback Result + print("\n" + "=" * 50) + print("Feedback Result") + print("=" * 50) + + """ + Print feedback processing results, including added or updated memory operations (add/update) + """ + print(json.dumps(res, ensure_ascii=False, indent=4, default=str)) + + +if __name__ == "__main__": + main() From d25d32739f1879dbf344cec1d7401826e8dc9d09 Mon Sep 17 00:00:00 2001 From: HanshuZhou <118414084+zhouhanshu@users.noreply.github.com> Date: Fri, 16 Jan 2026 16:51:29 +0800 Subject: [PATCH 38/47] fix:examples update for mem_reader (#866) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * fix:examples update for mem_reader * update readme of the examples of mem_reader --------- Co-authored-by: 周函数 --- examples/mem_reader/README.md | 90 ++ examples/mem_reader/builders.py | 78 ++ .../compare_simple_vs_multimodal.py | 461 -------- .../mem_reader/multimodal_struct_reader.py | 1042 ----------------- examples/mem_reader/parser/__init__.py | 1 - examples/mem_reader/parser/config_utils.py | 132 --- .../parser/example_assistant_parser.py | 94 -- .../parser/example_file_content_parser.py | 132 --- .../parser/example_multi_modal_parser.py | 400 ------- .../parser/example_string_parser.py | 66 -- .../parser/example_system_parser.py | 158 --- .../parser/example_text_content_parser.py | 72 -- .../mem_reader/parser/example_tool_parser.py | 101 -- .../mem_reader/parser/example_user_parser.py | 135 --- examples/mem_reader/parser/print_utils.py | 11 - examples/mem_reader/parser_demos/__init__.py | 0 examples/mem_reader/parser_demos/_base.py | 76 ++ .../mem_reader/parser_demos/demo_assistant.py | 44 + .../parser_demos/demo_file_content.py | 68 ++ .../mem_reader/parser_demos/demo_image.py | 87 ++ .../parser_demos/demo_multi_modal.py | 346 ++++++ .../mem_reader/parser_demos/demo_string.py | 30 + .../mem_reader/parser_demos/demo_system.py | 41 + .../parser_demos/demo_text_content.py | 40 + examples/mem_reader/parser_demos/demo_tool.py | 28 + examples/mem_reader/parser_demos/demo_user.py | 43 + examples/mem_reader/runners/__init__.py | 0 examples/mem_reader/runners/run_multimodal.py | 139 +++ examples/mem_reader/runners/run_simple.py | 113 ++ examples/mem_reader/samples.py | 773 ++++++++++++ examples/mem_reader/settings.py | 107 ++ examples/mem_reader/simple_struct_reader.py | 831 ------------- examples/mem_reader/utils.py | 84 ++ 33 files changed, 2187 insertions(+), 3636 deletions(-) create mode 100644 examples/mem_reader/README.md create mode 100644 examples/mem_reader/builders.py delete mode 100644 examples/mem_reader/compare_simple_vs_multimodal.py delete mode 100644 examples/mem_reader/multimodal_struct_reader.py delete mode 100644 examples/mem_reader/parser/__init__.py delete mode 100644 examples/mem_reader/parser/config_utils.py delete mode 100644 examples/mem_reader/parser/example_assistant_parser.py delete mode 100644 examples/mem_reader/parser/example_file_content_parser.py delete mode 100644 examples/mem_reader/parser/example_multi_modal_parser.py delete mode 100644 examples/mem_reader/parser/example_string_parser.py delete mode 100644 examples/mem_reader/parser/example_system_parser.py delete mode 100644 examples/mem_reader/parser/example_text_content_parser.py delete mode 100644 examples/mem_reader/parser/example_tool_parser.py delete mode 100644 examples/mem_reader/parser/example_user_parser.py delete mode 100644 examples/mem_reader/parser/print_utils.py create mode 100644 examples/mem_reader/parser_demos/__init__.py create mode 100644 examples/mem_reader/parser_demos/_base.py create mode 100644 examples/mem_reader/parser_demos/demo_assistant.py create mode 100644 examples/mem_reader/parser_demos/demo_file_content.py create mode 100644 examples/mem_reader/parser_demos/demo_image.py create mode 100644 examples/mem_reader/parser_demos/demo_multi_modal.py create mode 100644 examples/mem_reader/parser_demos/demo_string.py create mode 100644 examples/mem_reader/parser_demos/demo_system.py create mode 100644 examples/mem_reader/parser_demos/demo_text_content.py create mode 100644 examples/mem_reader/parser_demos/demo_tool.py create mode 100644 examples/mem_reader/parser_demos/demo_user.py create mode 100644 examples/mem_reader/runners/__init__.py create mode 100644 examples/mem_reader/runners/run_multimodal.py create mode 100644 examples/mem_reader/runners/run_simple.py create mode 100644 examples/mem_reader/samples.py create mode 100644 examples/mem_reader/settings.py delete mode 100644 examples/mem_reader/simple_struct_reader.py create mode 100644 examples/mem_reader/utils.py diff --git a/examples/mem_reader/README.md b/examples/mem_reader/README.md new file mode 100644 index 000000000..3677d0502 --- /dev/null +++ b/examples/mem_reader/README.md @@ -0,0 +1,90 @@ +# MemReader Examples + +This directory contains examples and sample code demonstrating how to use the `MemReader` module in MemOS. `MemReader` is responsible for parsing various types of input data (text, chat history, files, images) into structured memory formats. + +## 📂 Directory Structure + +```text +examples/mem_reader/ +├── builders.py # Factory functions to initialize Reader components +├── parser_demos/ # Demos for individual parser components +│ ├── demo_image.py # Example: Parsing image content +│ ├── demo_string.py # Example: Parsing string content +│ └── ... # Other specific parser demos +├── runners/ # Main execution scripts for running examples +│ ├── run_simple.py # Runner for SimpleStructMemReader +│ └── run_multimodal.py# Runner for MultiModalStructMemReader +├── samples.py # Sample data (chat logs, test cases) +├── settings.py # Configuration management (loads from .env) +└── utils.py # Utility functions (printing, formatting) +``` + +## 🚀 Getting Started + +### 1. Configuration + +Before running the examples, ensure you have configured your environment variables. Copy the `.env.example` file in the project root to `.env` and fill in the necessary API keys. + +The `settings.py` file loads these configurations. Key variables include: +- `OPENAI_API_KEY`: For LLM and Embeddings. +- `MOS_CHAT_MODEL`: Default model for chat (e.g., `gpt-4o`). +- `MOS_EMBEDDER_MODEL`: Model for embeddings. + +### 2. Running Examples + +We provide two main runners to demonstrate different capabilities: + +#### A. Simple Reader (`run_simple.py`) + +Demonstrates the `SimpleStructMemReader`, which is optimized for text-based chat history and documents. + +**Features:** +- **Fast Mode**: Quick parsing without LLM (regex/rule-based). +- **Fine Mode**: Detailed parsing using LLM. +- **Transfer**: Converting Fast memories to Fine memories. +- **Document Parsing**: Reading text files. + +**Usage:** +```bash +python -m examples.mem_reader.runners.run_simple +``` + +#### B. Multimodal Reader (`run_multimodal.py`) + +Demonstrates the `MultiModalStructMemReader`, which handles complex inputs like images, files, and mixed content types. + +**Features:** +- Supports **String**, **Multimodal**, and **Raw** input types. +- Configurable output format (Text/JSON). +- Selectable test cases. + +**Usage:** +```bash +# Run all examples in 'fine' mode +python -m examples.mem_reader.runners.run_multimodal --example all --mode fine + +# Run specific example (e.g., multimodal inputs) +python -m examples.mem_reader.runners.run_multimodal --example multimodal + +# View help for more options +python -m examples.mem_reader.runners.run_multimodal --help +``` + +### 3. Parser Demos + +If you want to understand how specific parsers work internally (e.g., how the system parses a User message vs. an Assistant message), check the `parser_demos/` directory. + +**Usage:** +```bash +python -m examples.mem_reader.parser_demos.demo_user +python -m examples.mem_reader.parser_demos.demo_image +``` + +## 🧩 Key Components + +- **`SimpleStructMemReader`**: Best for standard text-based chat applications. It's lightweight and efficient. +- **`MultiModalStructMemReader`**: Designed for advanced agents that handle images, file attachments, and complex tool interactions. + +## 🛠️ Customization + +You can modify `settings.py` or `builders.py` to change the underlying LLM backend (e.g., switching from OpenAI to Ollama) or adjust chunking strategies. diff --git a/examples/mem_reader/builders.py b/examples/mem_reader/builders.py new file mode 100644 index 000000000..89c39a5de --- /dev/null +++ b/examples/mem_reader/builders.py @@ -0,0 +1,78 @@ +"""Builder functions for initializing MemReader components. + +This module provides factory functions to create configured instances of +LLMs, Embedders, and MemReaders, simplifying the setup process in examples. +""" + +from typing import Any + +from memos.configs.embedder import EmbedderConfigFactory +from memos.configs.llm import LLMConfigFactory +from memos.configs.mem_reader import ( + MultiModalStructMemReaderConfig, + SimpleStructMemReaderConfig, +) +from memos.configs.parser import ParserConfigFactory +from memos.embedders.factory import EmbedderFactory +from memos.llms.factory import LLMFactory +from memos.mem_reader.multi_modal_struct import MultiModalStructMemReader +from memos.mem_reader.simple_struct import SimpleStructMemReader +from memos.parsers.factory import ParserFactory + +from .settings import get_embedder_config, get_llm_config, get_reader_config + + +def build_llm_and_embedder() -> tuple[Any, Any]: + """Initialize and return configured LLM and Embedder instances.""" + llm_config_dict = get_llm_config() + embedder_config_dict = get_embedder_config() + + llm_config = LLMConfigFactory.model_validate(llm_config_dict) + embedder_config = EmbedderConfigFactory.model_validate(embedder_config_dict) + + llm = LLMFactory.from_config(llm_config) + embedder = EmbedderFactory.from_config(embedder_config) + + return embedder, llm + + +def build_file_parser() -> Any: + """Initialize and return a configured file parser (MarkItDown). + + Returns: + Configured parser instance or None if initialization fails. + """ + try: + parser_config = ParserConfigFactory.model_validate( + { + "backend": "markitdown", + "config": {}, + } + ) + return ParserFactory.from_config(parser_config) + except Exception as e: + print(f"⚠️ Warning: Could not initialize file parser: {e}") + return None + + +def build_simple_reader() -> SimpleStructMemReader: + """Initialize and return a configured SimpleStructMemReader. + + Returns: + Configured SimpleStructMemReader instance. + """ + config_dict = get_reader_config() + # Simple reader doesn't need file parser + config = SimpleStructMemReaderConfig(**config_dict) + return SimpleStructMemReader(config) + + +def build_multimodal_reader() -> MultiModalStructMemReader: + """Initialize and return a configured MultiModalStructMemReader. + + Returns: + Configured MultiModalStructMemReader instance. + """ + config_dict = get_reader_config() + config = MultiModalStructMemReaderConfig(**config_dict) + return MultiModalStructMemReader(config) diff --git a/examples/mem_reader/compare_simple_vs_multimodal.py b/examples/mem_reader/compare_simple_vs_multimodal.py deleted file mode 100644 index fa12ac211..000000000 --- a/examples/mem_reader/compare_simple_vs_multimodal.py +++ /dev/null @@ -1,461 +0,0 @@ -"""Compare SimpleStructMemReader and MultiModalStructMemReader outputs. - -This example demonstrates the differences between simple_struct and multi_modal_struct -in both fast and fine modes. -""" - -import os -import sys - -from pathlib import Path - -from dotenv import load_dotenv - -from memos.configs.mem_reader import ( - MultiModalStructMemReaderConfig, - SimpleStructMemReaderConfig, -) -from memos.memories.textual.item import TextualMemoryItem - - -# Add src directory to path -project_root = Path(__file__).parent.parent.parent -src_path = project_root / "src" -if str(src_path) not in sys.path: - sys.path.insert(0, str(src_path)) - -# Load environment variables -load_dotenv() - - -def get_reader_config() -> dict: - """Get reader configuration from environment variables.""" - openai_api_key = os.getenv("OPENAI_API_KEY") - openai_base_url = os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1") - ollama_api_base = os.getenv("OLLAMA_API_BASE", "http://localhost:11434") - - # LLM config - llm_backend = os.getenv("MEM_READER_LLM_BACKEND", "openai") - if llm_backend == "ollama": - llm_config = { - "backend": "ollama", - "config": { - "model_name_or_path": os.getenv("MEM_READER_LLM_MODEL", "qwen3:0.6b"), - "api_base": ollama_api_base, - "temperature": float(os.getenv("MEM_READER_LLM_TEMPERATURE", "0.0")), - "remove_think_prefix": os.getenv( - "MEM_READER_LLM_REMOVE_THINK_PREFIX", "true" - ).lower() - == "true", - "max_tokens": int(os.getenv("MEM_READER_LLM_MAX_TOKENS", "8192")), - }, - } - else: # openai - llm_config = { - "backend": "openai", - "config": { - "model_name_or_path": os.getenv("MEM_READER_LLM_MODEL", "gpt-4o-mini"), - "api_key": openai_api_key or os.getenv("MEMRADER_API_KEY", "EMPTY"), - "api_base": openai_base_url, - "temperature": float(os.getenv("MEM_READER_LLM_TEMPERATURE", "0.5")), - "remove_think_prefix": os.getenv( - "MEM_READER_LLM_REMOVE_THINK_PREFIX", "true" - ).lower() - == "true", - "max_tokens": int(os.getenv("MEM_READER_LLM_MAX_TOKENS", "8192")), - }, - } - - # Embedder config - embedder_backend = os.getenv( - "MEM_READER_EMBEDDER_BACKEND", os.getenv("MOS_EMBEDDER_BACKEND", "ollama") - ) - if embedder_backend == "universal_api": - embedder_config = { - "backend": "universal_api", - "config": { - "provider": os.getenv( - "MEM_READER_EMBEDDER_PROVIDER", - os.getenv("MOS_EMBEDDER_PROVIDER", "openai"), - ), - "api_key": os.getenv( - "MEM_READER_EMBEDDER_API_KEY", - os.getenv("MOS_EMBEDDER_API_KEY", openai_api_key or "sk-xxxx"), - ), - "model_name_or_path": os.getenv( - "MEM_READER_EMBEDDER_MODEL", - os.getenv("MOS_EMBEDDER_MODEL", "text-embedding-3-large"), - ), - "base_url": os.getenv( - "MEM_READER_EMBEDDER_API_BASE", - os.getenv("MOS_EMBEDDER_API_BASE", openai_base_url), - ), - }, - } - else: # ollama - embedder_config = { - "backend": "ollama", - "config": { - "model_name_or_path": os.getenv( - "MEM_READER_EMBEDDER_MODEL", - os.getenv("MOS_EMBEDDER_MODEL", "nomic-embed-text:latest"), - ), - "api_base": ollama_api_base, - }, - } - - return { - "llm": llm_config, - "embedder": embedder_config, - "chunker": { - "backend": "sentence", - "config": { - "tokenizer_or_token_counter": "gpt2", - "chunk_size": 512, - "chunk_overlap": 128, - "min_sentences_per_chunk": 1, - }, - }, - } - - -def print_memory_item(item: TextualMemoryItem, prefix: str = "", max_length: int = 500): - """Print a memory item in a readable format.""" - print(f"{prefix}Memory ID: {item.id}") - print(f"{prefix}Memory Type: {item.metadata.memory_type}") - print(f"{prefix}Tags: {item.metadata.tags}") - memory_preview = ( - item.memory[:max_length] + "..." if len(item.memory) > max_length else item.memory - ) - print(f"{prefix}Memory: {memory_preview}") - print(f"{prefix}Key: {item.metadata.key}") - if item.metadata.background: - bg_preview = ( - item.metadata.background[:max_length] + "..." - if len(item.metadata.background) > max_length - else item.metadata.background - ) - print(f"{prefix}Background: {bg_preview}") - print(f"{prefix}Sources count: {len(item.metadata.sources) if item.metadata.sources else 0}") - print() - - -def compare_readers(): - """Compare SimpleStructMemReader and MultiModalStructMemReader.""" - print("=" * 80) - print("Comparing SimpleStructMemReader vs MultiModalStructMemReader") - print("=" * 80) - print() - - # Test data - simple chat messages - scene_data = [ - [ - {"role": "user", "chat_time": "3 May 2025", "content": "I'm feeling a bit down today."}, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "I'm sorry to hear that. Do you want to talk about what's been going on?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "It's just been a tough couple of days, you know? Everything feels a bit overwhelming, and I just can't seem to shake it off.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "It sounds like you're going through a lot right now. Sometimes it helps to talk things out. Is there something specific that's been weighing on you, or is it more of a general feeling?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "It's a mix, I guess. Work's been really stressful, and on top of that, I've been feeling kinda disconnected from the people around me.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "That can be really draining, especially when you're feeling isolated on top of the stress. Do you think there's something from your past that's contributing to how you're feeling now? Sometimes our emotions are tied to older experiences.", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "Yeah, now that you mention it… I've been thinking a lot about my childhood lately. I didn't have the easiest upbringing. My parents were always busy, and I often felt like I had to figure things out on my own. I remember one winter, I got really sick with a high fever. My parents were both working, and I didn't want to bother them. I just lay in bed, crying by myself, not knowing what to do.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "That must have been very lonely. Growing up without that support can really make you feel like you have to handle everything on your own. How do you think that experience has affected you now?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "Yeah, it was really lonely. I remember spending a lot of time doing things on my own, like drawing, because it was my only way to escape. I used to draw animals, and I created my own little world on paper. It was peaceful in a way, just me and my imagination, with no outside distractions.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "Drawing sounds like a beautiful way to express yourself and find some peace in that solitude. It must have been a very quiet and private world for you. Do you think that sense of loneliness from back then has shaped how you connect with others today?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "I think it has. I've always found it hard to let others in. I feel like I have to handle everything on my own. If I rely on someone else, I feel vulnerable, and I start to feel that loneliness again.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "It sounds like this was a protective mechanism that helped you cope with your feelings of loneliness back then. But as you've grown, it seems like this pattern might not be serving you as well anymore. Have you thought about trying to break this cycle, or finding new ways to connect with others?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "I've thought about it, though it's hard. But I also know I can't keep going like this forever. Maybe it's time to seek some help.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "It's a big step, but a positive one. Exploring your emotions and past experiences could really help you understand how they've shaped your present. Therapy could be a great place to start, as it would help you connect with both yourself and others. Would you be open to trying it?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "I'm open to trying. Thank you for encouraging me. It feels like it might be a good starting point for me.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "I'm really glad to hear that. Taking that first step is always difficult, but you've made an important decision. If you need help finding the right therapist, or just want to talk, I'm here for you.", - }, - ], - [ - { - "role": "user", - "chat_time": "3 May 2025", - "content": "This week I've been feeling a bit off, especially when playing tennis. My body just doesn't feel right.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "It sounds like you've been having some physical discomfort lately. Where specifically are you feeling unwell? Is there something particular about tennis that's been difficult?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "I just feel a bit fatigued, and every time I play tennis, my movements feel off. I used to play pretty well, but lately, I've been feeling weak and my movements aren't as coordinated as they used to be.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "Physical discomfort can definitely affect performance, especially in a sport like tennis that requires quick reactions and coordination. Have you noticed anything specific that might be causing these changes? Could it be overtraining, or is there another physical issue making you feel off?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "I think it might be due to stress and lack of sleep recently. I just feel drained all the time. Plus, I've been frustrated with my tennis performance, which makes me feel even worse, like I'm stuck in a vicious cycle.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "Stress and poor sleep quality can definitely affect your physical performance, especially in sports. When you're also feeling down about your performance, it's easy to fall into a negative cycle. Have you tried anything to relieve some of the stress, or to improve your sleep?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "I've tried some relaxation techniques, like deep breathing and simple meditation, but it doesn't seem to help much. I still can't focus during tennis, and I feel like my mind is distracted by other things.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "Relaxation techniques like deep breathing and meditation can help reduce stress, but sometimes we need a more structured approach to improve both our physical and mental state. For example, you might want to focus on specific aspects of your tennis training, or adjust your rest and recovery time. Have you thought about setting smaller goals for yourself? Like focusing on a specific tennis move each day, rather than expecting perfection right away? That might help you gradually regain confidence.", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "That's a good idea. I think I've been expecting too much from myself, which just makes me more anxious. Maybe I can start with small practice sessions and gradually find my rhythm again.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "Exactly! Setting small and clear goals will help reduce pressure and give you a sense of accomplishment. And don't forget that rest is just as important—taking time to recover will help you feel better physically and mentally. Both physical and mental recovery are key to improving your performance and health.", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "Thanks, I feel like I need to rethink a few things. Maybe I really need to be kinder to myself and take things step by step.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "You're on the right track. Rethinking things and giving yourself space and patience is so important. You've already taken the first step, now just keep moving forward, one step at a time. If you need anything, I'm always here to help.", - }, - ], - [ - { - "role": "user", - "chat_time": "3 May 2025", - "content": "Yesterday at 3 PM I had a meeting with my team about the new project. We discussed the timeline and I'm concerned we won't meet the deadline of December 15th.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "I understand your concern about the project timeline. What specific challenges do you think might prevent your team from meeting the December 15th deadline?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "We have too many requirements to implement in just two weeks. The backend team needs at least until December 10th to finish their part, which leaves almost no time for testing before the deadline.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "That's definitely a tight timeline. Have you considered prioritizing the requirements to focus on the most critical features first? You might also want to discuss with stakeholders about possibly extending the deadline or reducing the scope for this initial release.", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "That's a good point. We have a follow-up meeting scheduled for tomorrow morning at 9:30 AM. I'll suggest we prioritize features and maybe propose pushing the deadline to January 5th next year.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "That sounds like a solid approach. Coming to the meeting with both a prioritization strategy and a specific alternative deadline shows you've thought through the problem carefully. It might also help to bring some data about similar past projects and how long they took to complete, if you have that information available.", - }, - ], - ] - - info = {"user_id": "test_user", "session_id": "test_session"} - - # Get config - config_dict = get_reader_config() - - # Initialize readers - print("Initializing readers...") - simple_config = SimpleStructMemReaderConfig(**config_dict) - multimodal_config = MultiModalStructMemReaderConfig(**config_dict) - - from memos.mem_reader.multi_modal_struct import MultiModalStructMemReader - from memos.mem_reader.simple_struct import SimpleStructMemReader - - simple_reader = SimpleStructMemReader(simple_config) - multimodal_reader = MultiModalStructMemReader(multimodal_config) - print("Readers initialized.\n") - print(f"Using LLM: {config_dict['llm']['backend']}") - print(f"Using Embedder: {config_dict['embedder']['backend']}") - print() - - # Test FAST mode - print("=" * 80) - print("FAST MODE COMPARISON") - print("=" * 80) - print() - - print("-" * 80) - print("SimpleStructMemReader (FAST):") - print("-" * 80) - try: - simple_fast = simple_reader.get_memory(scene_data, "chat", info, mode="fast") - if simple_fast and len(simple_fast) > 0: - for scene_idx, scene_memories in enumerate(simple_fast): - print(f"\nScene {scene_idx + 1}:") - for item_idx, item in enumerate(scene_memories): - print_memory_item(item, prefix=f" [{item_idx + 1}] ") - else: - print(" No memories generated.") - except Exception as e: - print(f" Error: {e}") - import traceback - - traceback.print_exc() - - print("\n" + "-" * 80) - print("MultiModalStructMemReader (FAST):") - print("-" * 80) - try: - multimodal_fast = multimodal_reader.get_memory(scene_data, "chat", info, mode="fast") - if multimodal_fast and len(multimodal_fast) > 0: - for scene_idx, scene_memories in enumerate(multimodal_fast): - print(f"\nScene {scene_idx + 1}:") - for item_idx, item in enumerate(scene_memories): - print_memory_item(item, prefix=f" [{item_idx + 1}] ") - else: - print(" No memories generated.") - except Exception as e: - print(f" Error: {e}") - import traceback - - traceback.print_exc() - - # Test FINE mode - print("\n" + "=" * 80) - print("FINE MODE COMPARISON") - print("=" * 80) - print() - - print("-" * 80) - print("SimpleStructMemReader (FINE):") - print("-" * 80) - try: - simple_fine = simple_reader.get_memory(scene_data, "chat", info, mode="fine") - if simple_fine and len(simple_fine) > 0: - for scene_idx, scene_memories in enumerate(simple_fine): - print(f"\nScene {scene_idx + 1}:") - for item_idx, item in enumerate(scene_memories): - print_memory_item(item, prefix=f" [{item_idx + 1}] ") - else: - print(" No memories generated.") - except Exception as e: - print(f" Error: {e}") - import traceback - - traceback.print_exc() - - print("\n" + "-" * 80) - print("MultiModalStructMemReader (FINE):") - print("-" * 80) - try: - multimodal_fine = multimodal_reader.get_memory(scene_data, "chat", info, mode="fine") - if multimodal_fine and len(multimodal_fine) > 0: - for scene_idx, scene_memories in enumerate(multimodal_fine): - print(f"\nScene {scene_idx + 1}:") - for item_idx, item in enumerate(scene_memories): - print_memory_item(item, prefix=f" [{item_idx + 1}] ") - else: - print(" No memories generated.") - except Exception as e: - print(f" Error: {e}") - import traceback - - traceback.print_exc() - - # Summary comparison - print("\n" + "=" * 80) - print("SUMMARY") - print("=" * 80) - print() - - def count_memories(memories_list): - """Count total memories across all scenes.""" - if not memories_list: - return 0 - return sum(len(scene) for scene in memories_list if scene) - - simple_fast_count = count_memories(simple_fast) if "simple_fast" in locals() else 0 - multimodal_fast_count = count_memories(multimodal_fast) if "multimodal_fast" in locals() else 0 - simple_fine_count = count_memories(simple_fine) if "simple_fine" in locals() else 0 - multimodal_fine_count = count_memories(multimodal_fine) if "multimodal_fine" in locals() else 0 - - print(f"SimpleStructMemReader FAST: {simple_fast_count} memories") - print(f"MultiModalStructMemReader FAST: {multimodal_fast_count} memories") - print(f"SimpleStructMemReader FINE: {simple_fine_count} memories") - print(f"MultiModalStructMemReader FINE: {multimodal_fine_count} memories") - print() - - print("Key Differences:") - print("1. Both readers should produce similar results for simple text messages") - print("2. MultiModalStructMemReader can handle multimodal content (images, files, etc.)") - print("3. FINE mode uses LLM to extract structured memories from aggregated windows") - print("4. FAST mode directly aggregates messages into windows without LLM processing") - - -if __name__ == "__main__": - compare_readers() diff --git a/examples/mem_reader/multimodal_struct_reader.py b/examples/mem_reader/multimodal_struct_reader.py deleted file mode 100644 index 790b13f85..000000000 --- a/examples/mem_reader/multimodal_struct_reader.py +++ /dev/null @@ -1,1042 +0,0 @@ -#!/usr/bin/env python3 -""" -MultiModalStructMemReader Example Script - -This script demonstrates various use cases for MultiModalStructMemReader, -including different message types, modes (fast/fine), and output formats. - -Usage: - python multimodal_struct_reader.py --example all - python multimodal_struct_reader.py --example string_message --mode fast - python multimodal_struct_reader.py --example multimodal --format json -""" - -import argparse -import json -import os -import sys -import time - -from pathlib import Path -from typing import Any - -from dotenv import load_dotenv - -from memos.configs.mem_reader import MultiModalStructMemReaderConfig -from memos.mem_reader.multi_modal_struct import MultiModalStructMemReader -from memos.memories.textual.item import TextualMemoryItem - - -# Add src directory to path -src_path = Path(__file__).parent.parent.parent / "src" -sys.path.insert(0, str(src_path)) - -# Load environment variables -load_dotenv() - - -# ============================================================================ -# Test Case Definitions -# ============================================================================ - - -class TestCase: - """Base class for test cases.""" - - def __init__( - self, - name: str, - description: str, - scene_data: Any, - expected_count: dict[str, int] | None = None, - ): - """ - Initialize a test case. - - Args: - name: Test case name - description: Test case description - scene_data: Scene data to test - expected_count: Expected memory count for each mode (optional) - """ - self.name = name - self.description = description - self.scene_data = scene_data - self.expected_count = expected_count or {} - - def get_info(self) -> dict[str, Any]: - """Get info dict for this test case.""" - return { - "user_id": "test_user", - "session_id": f"session_{self.name}", - "test_case": self.name, - } - - -# String message test cases -STRING_MESSAGE_CASES = [ - TestCase( - name="string_simple", - description="Simple string message", - scene_data=["今天心情不错，喝了咖啡。"], - expected_count={"fast": 1, "fine": 1}, # StringParser returns [] in - # fast mode - ), - TestCase( - name="string_multiple", - description="Multiple string messages", - scene_data=[ - "这是第一条消息。", - "这是第二条消息。", - "这是第三条消息。", - ], - ), -] - -# Standard chat message test cases -CHAT_MESSAGE_CASES = [ - TestCase( - name="chat_simple", - description="Simple chat conversation", - scene_data=[ - [ - { - "role": "user", - "content": "Hello, how are you?", - "chat_time": "2025-01-01T10:00:00Z", - }, - { - "role": "assistant", - "content": "I'm doing well, thank you!", - "chat_time": "2025-01-01T10:00:01Z", - }, - ] - ], - ), - TestCase( - name="chat_with_system", - description="Chat with system message", - scene_data=[ - [ - { - "role": "system", - "content": [{"type": "text", "text": "You are a helpful assistant."}], - "chat_time": "2025-01-01T10:00:00Z", - }, - { - "role": "user", - "content": "What's the weather?", - "chat_time": "2025-01-01T10:00:01Z", - }, - { - "role": "assistant", - "content": "I don't have access to weather data.", - "chat_time": "2025-01-01T10:00:02Z", - }, - ] - ], - ), - TestCase( - name="chat_long_conversation", - description="Long conversation with multiple turns", - scene_data=[ - [ - { - "role": "user", - "chat_time": "3 May 2025", - "content": "I'm feeling a bit down today.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "I'm sorry to hear that. Do you want to talk about what's been going on?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "It's just been a tough couple of days.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "It sounds like you're going through a lot right now.", - }, - ] - ], - ), - TestCase( - name="chat_with_list_content", - description="", - scene_data=[ - [ - { - "role": "user", - "content": [ - { - "type": "text", - "text": "我是测试base64", - }, - { - "type": "file", - "file": { - "file_data": "Hello World", - "filename": "2102b64c-25a2-481c-a940-4325496baf39.txt", - "file_id": "90ee1bcf-5295-4b75-91a4-23fe1f7ab30a", - }, - }, - { - "type": "image_url", - "image_url": { - "url": "https://play-groud-test-1.oss-cn-shanghai.aliyuncs.com/algorithmImages/2025/12/01/ce545319ba6d4d21a0aebcb75337acc3.jpeg" - }, - }, - ], - "message_id": "1995458892790317057", - } - ] - ], - ), -] - -# Tool-related test cases -TOOL_MESSAGE_CASES = [ - TestCase( - name="tool_assistant_with_calls", - description="Assistant message with tool_calls", - scene_data=[ - [ - { - "role": "assistant", - "content": None, - "tool_calls": [ - { - "id": "tool-call-weather-1", - "type": "function", - "function": { - "name": "get_weather", - "arguments": '{"location": "北京"}', - }, - } - ], - "chat_time": "2025-11-24T10:12:00Z", - "message_id": "assistant-with-call-1", - } - ] - ], - ), - TestCase( - name="tool_with_result", - description="Tool call with result message", - scene_data=[ - [ - { - "role": "assistant", - "content": None, - "tool_calls": [ - { - "id": "tool-call-weather-1", - "type": "function", - "function": { - "name": "get_weather", - "arguments": '{"location": "北京"}', - }, - } - ], - "chat_time": "2025-11-24T10:12:00Z", - }, - { - "role": "tool", - "content": "北京今天天气晴朗，温度25°C，湿度60%。", - "tool_call_id": "tool-call-weather-1", - "chat_time": "2025-11-24T10:12:05Z", - }, - ] - ], - ), - TestCase( - name="tool_custom_format", - description="Custom tool format (tool_description, tool_input, tool_output)", - scene_data=[ - [ - { - "type": "tool_description", - "name": "get_weather", - "description": "获取指定地点的当前天气信息", - "parameters": { - "type": "object", - "properties": {"location": {"type": "string", "description": "城市名称"}}, - "required": ["location"], - }, - }, - { - "type": "tool_input", - "call_id": "call_123", - "name": "get_weather", - "argument": {"location": "北京"}, - }, - { - "type": "tool_output", - "call_id": "call_123", - "name": "get_weather", - "output": {"weather": "晴朗", "temperature": 25, "humidity": 60}, - }, - ] - ], - ), -] - -# Multimodal message test cases -MULTIMODAL_MESSAGE_CASES = [ - TestCase( - name="multimodal_text_image", - description="User message with text and image", - scene_data=[ - [ - { - "role": "user", - "content": [ - {"type": "text", "text": "帮我看看这张图片大概是什么内容？"}, - { - "type": "image_url", - "image_url": { - "url": "https://example.com/mountain_lake.jpg", - "detail": "high", - }, - }, - ], - "chat_time": "2025-11-24T10:20:00Z", - "message_id": "mm-img-1", - } - ] - ], - ), - TestCase( - name="multimodal_text_file", - description="User message with text and file", - scene_data=[ - [ - { - "role": "user", - "content": [ - {"type": "text", "text": "请阅读这个PDF，总结里面的要点。"}, - {"type": "file", "file": {"file_id": "file_123", "filename": "report.pdf"}}, - ], - "chat_time": "2025-11-24T10:21:00Z", - "message_id": "mm-file-1", - } - ] - ], - ), - TestCase( - name="oss_text_file", - description="User message with text and file", - scene_data=[ - [ - { - "role": "user", - "content": [ - {"type": "text", "text": "请阅读这个PDF，总结里面的要点。"}, - { - "type": "file", - "file": { - "file_id": "file_123", - "filename": "report.pdf", - "file_data": "@http://139.196.232.20:9090/graph-test/algorithm/2025_11_13/1763043889_1763043782_PM1%E8%BD%A6%E9%97%B4PMT%E9%9D%B4%E5%8E%8B%E8%BE%B9%E5%8E%8B%E5%8E%8B%E5%8A%9B%E6%97%A0%E6%B3%95%E5%BB%BA%E7%AB%8B%E6%95%85%E9%9A%9C%E6%8A%A5%E5%91%8A20240720.md", - }, - }, - ], - "chat_time": "2025-11-24T10:21:00Z", - "message_id": "mm-file-1", - } - ] - ], - ), - TestCase( - name="pure_data_file", - description="User message with text and file", - scene_data=[ - [ - { - "role": "user", - "content": [ - {"type": "text", "text": "请阅读这个PDF，总结里面的要点。"}, - { - "type": "file", - "file": { - "file_id": "file_123", - "filename": "report.pdf", - "file_data": "明文记忆是系统与用户对话、操作等交互中动态习得，以及外部提供的、可显式管理的结构化知识形态，通常以文档、提示模板、图结构或用户规则等形式存在。它具备编辑性、可共享性与治理友好性，适合存储需要频繁修改、可审计或多方协同使用的信息。 在 MemOS 中，明文记忆可用于动态生成推理上下文、个性化偏好注入、多代理协作共享等场景，成为连接人类输入与模型认知的关键桥梁。激活记忆是指模型在推理过程中产生的瞬时性认知状态，包括 KV cache、隐藏层激活、注意力权重等中间张量结构。它通常用于维持上下文连续性、对话一致性与行为风格控制。 MemOS 将激活记忆抽象为可调度资源，支持按需唤醒、延迟卸载与结构变换。例如，某些上下文状态可以被压缩为“半结构化记忆片段”用于未来复用，也可以在任务级别转化为参数化模块，支持短期记忆的长期化演进。这一机制为模型行为一致性、风格保持与状态持续性提供了基础。", - }, - }, - ], - "chat_time": "2025-11-24T10:21:00Z", - "message_id": "mm-file-1", - } - ] - ], - ), - TestCase( - name="local_data_file", - description="User message with text and file", - scene_data=[ - [ - { - "role": "user", - "content": [ - {"type": "text", "text": "请阅读这个PDF，总结里面的要点。"}, - { - "type": "file", - "file": { - "file_id": "file_123", - "filename": "report.pdf", - "file_data": "./my_local_file/report.pdf", - }, - }, - ], - "chat_time": "2025-11-24T10:21:00Z", - "message_id": "mm-file-1", - } - ] - ], - ), - TestCase( - name="internet_file", - description="User message with text and file", - scene_data=[ - [ - { - "role": "user", - "content": [ - {"type": "text", "text": "请阅读这个PDF，总结里面的要点。"}, - { - "type": "file", - "file": { - "file_id": "file_123", - "filename": "report.pdf", - "file_data": "https://upload.wikimedia.org/wikipedia/commons/c/cb/NLC416-16jh004830-88775_%E7%B4%85%E6%A8%93%E5%A4%A2.pdf", - }, - }, - ], - "chat_time": "2025-11-24T10:21:00Z", - "message_id": "mm-file-1", - } - ] - ], - ), - TestCase( - name="multimodal_mixed", - description="Mixed multimodal message (text + file + image)", - scene_data=[ - [ - { - "role": "user", - "content": [ - {"type": "text", "text": "请同时分析这个报告和图表。"}, - { - "type": "file", - "file": {"file_id": "file_789", "filename": "analysis_report.pdf"}, - }, - { - "type": "image_url", - "image_url": {"url": "https://example.com/chart.png", "detail": "auto"}, - }, - ], - "chat_time": "2025-11-24T10:23:00Z", - "message_id": "mixed-1", - } - ] - ], - ), - TestCase( - name="multimodal_audio", - description="Audio-only message", - scene_data=[ - [ - { - "role": "user", - "content": [ - { - "type": "input_audio", - "input_audio": {"data": "base64_encoded_audio_here", "format": "mp3"}, - } - ], - "chat_time": "2025-11-24T10:22:00Z", - "message_id": "audio-1", - } - ] - ], - ), -] - -# Raw input item test cases -RAW_INPUT_CASES = [ - TestCase( - name="raw_text_items", - description="Pure text input items without dialog context", - scene_data=[ - [ - {"type": "text", "text": "这是一段独立的文本输入，没有明确的对话上下文。"}, - {"type": "text", "text": "它依然会被抽取和写入明文记忆。"}, - ] - ], - ), - TestCase( - name="raw_file_item", - description="Pure file input by file_id", - scene_data=[ - [{"type": "file", "file": {"file_id": "file_uploaded_123", "filename": "document.pdf"}}] - ], - ), - # File parameter test cases - covering all combinations - TestCase( - name="file_only_file_id", - description="File with only file_id parameter", - scene_data=[[{"type": "file", "file": {"file_id": "file_only_id_123"}}]], - ), - TestCase( - name="file_only_filename", - description="File with only filename parameter", - scene_data=[[{"type": "file", "file": {"filename": "document_only.pdf"}}]], - ), - TestCase( - name="file_only_file_data_base64", - description="File with only file_data (base64 encoded)", - scene_data=[ - [ - { - "type": "file", - "file": { - "file_data": "data:application/pdf;base64,JVBERi0xLjQKJdPr6eEKMSAwIG9iago8PAovVHlwZSAvQ2F0YWxvZwovUGFnZXMgMiAwIFIKPj4KZW5kb2JqCjIgMCBvYmoKPDwKL1R5cGUgL1BhZ2VzCi9LaWRzIFszIDAgUl0KL0NvdW50IDEKPD4KZW5kb2JqCjMgMCBvYmoKPDwKL1R5cGUgL1BhZ2UKL1BhcmVudCAyIDAgUgovTWVkaWFCb3ggWzAgMCA2MTIgNzkyXQovUmVzb3VyY2VzIDw8Ci9Gb250IDw8Ci9GMSA0IDAgUgo+Pgo+PgovQ29udGVudHMgNSAwIFIKPj4KZW5kb2JqCjQgMCBvYmoKPDwKL1R5cGUgL0ZvbnQKL1N1YnR5cGUgL1R5cGUxCi9CYXNlRm9udCAvSGVsdmV0aWNhCj4+CmVuZG9iag==" - }, - } - ] - ], - ), - TestCase( - name="file_only_file_data_url", - description="File with only file_data (URL)", - scene_data=[ - [ - { - "type": "file", - "file": {"file_data": "https://example.com/documents/report.pdf"}, - } - ] - ], - ), - TestCase( - name="file_only_file_data_text", - description="File with only file_data (plain text content)", - scene_data=[ - [ - { - "type": "file", - "file": { - "file_data": "This is a plain text file content. It contains multiple lines.\nLine 2 of the file.\nLine 3 of the file." - }, - } - ] - ], - ), - TestCase( - name="file_file_data_and_file_id", - description="File with file_data and file_id", - scene_data=[ - [ - { - "type": "file", - "file": { - "file_data": "https://example.com/documents/data.pdf", - "file_id": "file_with_data_123", - }, - } - ] - ], - ), - TestCase( - name="file_file_data_and_filename", - description="File with file_data and filename", - scene_data=[ - [ - { - "type": "file", - "file": { - "file_data": "This is file content with filename.", - "filename": "content_with_name.txt", - }, - } - ] - ], - ), - TestCase( - name="file_file_id_and_filename", - description="File with file_id and filename (existing case)", - scene_data=[ - [{"type": "file", "file": {"file_id": "file_uploaded_123", "filename": "document.pdf"}}] - ], - ), - TestCase( - name="file_all_parameters", - description="File with all parameters (file_data, file_id, filename)", - scene_data=[ - [ - { - "type": "file", - "file": { - "file_data": "https://example.com/documents/complete.pdf", - "file_id": "file_complete_123", - "filename": "complete_document.pdf", - }, - } - ] - ], - ), - TestCase( - name="file_no_parameters", - description="File with no parameters (should return [File: unknown])", - scene_data=[[{"type": "file", "file": {}}]], - ), -] - -# Assistant message test cases -ASSISTANT_MESSAGE_CASES = [ - TestCase( - name="assistant_with_refusal", - description="Assistant message with refusal", - scene_data=[ - [ - { - "role": "assistant", - "content": [{"type": "text", "text": "I can help you with that."}], - "refusal": "I cannot provide information about that topic.", - "chat_time": "2025-11-24T10:30:00Z", - } - ] - ], - ), - TestCase( - name="assistant_with_audio", - description="Assistant message with audio", - scene_data=[ - [ - { - "role": "assistant", - "content": "Here's the audio response.", - "audio": {"id": "audio_response_123"}, - "chat_time": "2025-11-24T10:31:00Z", - } - ] - ], - ), -] - -# All test cases organized by category -TEST_CASES = { - "string": STRING_MESSAGE_CASES, - "chat": CHAT_MESSAGE_CASES, - "tool": TOOL_MESSAGE_CASES, - "multimodal": MULTIMODAL_MESSAGE_CASES, - "raw": RAW_INPUT_CASES, - "assistant": ASSISTANT_MESSAGE_CASES, -} - -# Flattened list of all test cases -ALL_TEST_CASES = {case.name: case for cases in TEST_CASES.values() for case in cases} - - -# ============================================================================ -# Utility Functions -# ============================================================================ - - -def print_textual_memory_item(item: TextualMemoryItem, prefix: str = "", max_length: int = 500): - """Print a memory item in a readable format.""" - print(f"{prefix}Memory ID: {item.id}") - print(f"{prefix}Memory Type: {item.metadata.memory_type}") - if item.metadata.tags: - print(f"{prefix}Tags: {item.metadata.tags}") - memory_preview = ( - item.memory[:max_length] + "..." if len(item.memory) > max_length else item.memory - ) - print(f"{prefix}Memory: {memory_preview}") - if item.metadata.key: - print(f"{prefix}Key: {item.metadata.key}") - if item.metadata.sources: - sources_count = len(item.metadata.sources) if isinstance(item.metadata.sources, list) else 1 - print(f"{prefix}Sources count: {sources_count}") - print() - - -def print_textual_memory_item_json(item: TextualMemoryItem, indent: int = 2): - """Print a memory item as formatted JSON.""" - data = item.to_dict() - if "metadata" in data and "embedding" in data["metadata"]: - embedding = data["metadata"]["embedding"] - if embedding: - data["metadata"]["embedding"] = f"[vector of {len(embedding)} dimensions]" - print(json.dumps(data, indent=indent, ensure_ascii=False)) - - -def get_reader_config() -> dict[str, Any]: - """ - Get reader configuration from environment variables. - - Returns: - Configuration dictionary for MultiModalStructMemReaderConfig - """ - openai_api_key = os.getenv("OPENAI_API_KEY") - openai_base_url = os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1") - ollama_api_base = os.getenv("OLLAMA_API_BASE", "http://localhost:11434") - - # Get LLM backend and config - llm_backend = os.getenv("MEM_READER_LLM_BACKEND", "openai") - if llm_backend == "ollama": - llm_config = { - "backend": "ollama", - "config": { - "model_name_or_path": os.getenv("MEM_READER_LLM_MODEL", "qwen3:0.6b"), - "api_base": ollama_api_base, - "temperature": float(os.getenv("MEM_READER_LLM_TEMPERATURE", "0.0")), - "remove_think_prefix": os.getenv( - "MEM_READER_LLM_REMOVE_THINK_PREFIX", "true" - ).lower() - == "true", - "max_tokens": int(os.getenv("MEM_READER_LLM_MAX_TOKENS", "8192")), - }, - } - else: # openai - llm_config = { - "backend": "openai", - "config": { - "model_name_or_path": os.getenv("MEM_READER_LLM_MODEL", "gpt-4o-mini"), - "api_key": openai_api_key or os.getenv("MEMRADER_API_KEY", "EMPTY"), - "api_base": openai_base_url, - "temperature": float(os.getenv("MEM_READER_LLM_TEMPERATURE", "0.5")), - "remove_think_prefix": os.getenv( - "MEM_READER_LLM_REMOVE_THINK_PREFIX", "true" - ).lower() - == "true", - "max_tokens": int(os.getenv("MEM_READER_LLM_MAX_TOKENS", "8192")), - }, - } - - # Get embedder backend and config - embedder_backend = os.getenv( - "MEM_READER_EMBEDDER_BACKEND", os.getenv("MOS_EMBEDDER_BACKEND", "ollama") - ) - if embedder_backend == "universal_api": - embedder_config = { - "backend": "universal_api", - "config": { - "provider": os.getenv( - "MEM_READER_EMBEDDER_PROVIDER", os.getenv("MOS_EMBEDDER_PROVIDER", "openai") - ), - "api_key": os.getenv( - "MEM_READER_EMBEDDER_API_KEY", - os.getenv("MOS_EMBEDDER_API_KEY", openai_api_key or "sk-xxxx"), - ), - "model_name_or_path": os.getenv( - "MEM_READER_EMBEDDER_MODEL", - os.getenv("MOS_EMBEDDER_MODEL", "text-embedding-3-large"), - ), - "base_url": os.getenv( - "MEM_READER_EMBEDDER_API_BASE", - os.getenv("MOS_EMBEDDER_API_BASE", openai_base_url), - ), - }, - } - else: # ollama - embedder_config = { - "backend": "ollama", - "config": { - "model_name_or_path": os.getenv( - "MEM_READER_EMBEDDER_MODEL", - os.getenv("MOS_EMBEDDER_MODEL", "nomic-embed-text:latest"), - ), - "api_base": ollama_api_base, - }, - } - - # Get direct markdown hostnames from environment variable - direct_markdown_hostnames = None - env_hostnames = os.getenv("FILE_PARSER_DIRECT_MARKDOWN_HOSTNAMES", "139.196.232.20") - if env_hostnames: - direct_markdown_hostnames = [h.strip() for h in env_hostnames.split(",") if h.strip()] - - return { - "llm": llm_config, - "embedder": embedder_config, - "chunker": { - "backend": "sentence", - "config": { - "tokenizer_or_token_counter": "gpt2", - "chunk_size": 512, - "chunk_overlap": 128, - "min_sentences_per_chunk": 1, - }, - }, - "direct_markdown_hostnames": direct_markdown_hostnames, - } - - -def count_memories(memory_results: list[list[TextualMemoryItem]]) -> int: - """Count total number of memory items across all scenes.""" - return sum(len(mem_list) for mem_list in memory_results) - - -# ============================================================================ -# Main Functions -# ============================================================================ - - -def run_test_case( - test_case: TestCase, reader: MultiModalStructMemReader, mode: str = "fast", format: str = "text" -): - """ - Run a single test case. - - Args: - test_case: Test case to run - reader: MultiModalStructMemReader instance - mode: Processing mode ("fast" or "fine") - format: Output format ("text" or "json") - """ - print(f"\n{'=' * 80}") - print(f"Test Case: {test_case.name}") - print(f"Description: {test_case.description}") - print(f"Mode: {mode.upper()}") - print(f"{'=' * 80}\n") - - info = test_case.get_info() - start_time = time.time() - - try: - memory_results = reader.get_memory(test_case.scene_data, type="chat", info=info, mode=mode) - elapsed_time = time.time() - start_time - - total_count = count_memories(memory_results) - print(f"✅ Completed in {elapsed_time:.2f}s") - print(f"📊 Generated {total_count} memory items across {len(memory_results)} scenes\n") - - # Check expected count if provided - if test_case.expected_count and mode in test_case.expected_count: - expected = test_case.expected_count[mode] - if total_count == expected: - print(f"✅ Expected count matches: {expected}") - else: - print(f"⚠️ Expected {expected}, got {total_count}") - - # Print sample results - print("\nSample Results:") - print("-" * 80) - for scene_idx, mem_list in enumerate(memory_results[:3]): # Show first 3 scenes - if not mem_list: - continue - print(f"\nScene {scene_idx + 1}:") - for item_idx, item in enumerate(mem_list[:2]): # Show first 2 items per scene - print(f"\n [Item {item_idx + 1}]") - if format == "json": - print_textual_memory_item_json(item, indent=4) - else: - print_textual_memory_item(item, prefix=" ", max_length=300) - - except Exception as e: - print(f"❌ Error: {e}") - import traceback - - traceback.print_exc() - - -def run_all_test_cases(reader: MultiModalStructMemReader, mode: str = "fast", format: str = "text"): - """Run all test cases.""" - print(f"\n{'=' * 80}") - print(f"Running All Test Cases (Mode: {mode.upper()})") - print(f"{'=' * 80}\n") - - total_cases = len(ALL_TEST_CASES) - for idx, (name, test_case) in enumerate(ALL_TEST_CASES.items(), 1): - print(f"\n[{idx}/{total_cases}] Running: {name}") - run_test_case(test_case, reader, mode=mode, format=format) - - -def run_category( - category: str, reader: MultiModalStructMemReader, mode: str = "fast", format: str = "text" -): - """Run all test cases in a category.""" - if category not in TEST_CASES: - print(f"❌ Unknown category: {category}") - print(f"Available categories: {', '.join(TEST_CASES.keys())}") - return - - cases = TEST_CASES[category] - print(f"\n{'=' * 80}") - print(f"Running Category: {category.upper()} ({len(cases)} test cases)") - print(f"Mode: {mode.upper()}") - print(f"{'=' * 80}\n") - - for idx, test_case in enumerate(cases, 1): - print(f"\n[{idx}/{len(cases)}] {test_case.name}") - run_test_case(test_case, reader, mode=mode, format=format) - - -def compare_modes(test_case: TestCase, reader: MultiModalStructMemReader, format: str = "text"): - """Compare fast and fine modes for a test case.""" - print(f"\n{'=' * 80}") - print(f"Comparing Fast vs Fine Mode: {test_case.name}") - print(f"{'=' * 80}\n") - - info = test_case.get_info() - - # Fast mode - print("⚡ FAST Mode:") - print("-" * 80) - start_time = time.time() - fast_results = reader.get_memory(test_case.scene_data, type="chat", info=info, mode="fast") - fast_time = time.time() - start_time - fast_count = count_memories(fast_results) - print(f"Time: {fast_time:.2f}s, Items: {fast_count}") - - # Fine mode - print("\n🔄 FINE Mode:") - print("-" * 80) - start_time = time.time() - fine_results = reader.get_memory(test_case.scene_data, type="chat", info=info, mode="fine") - fine_time = time.time() - start_time - fine_count = count_memories(fine_results) - print(f"Time: {fine_time:.2f}s, Items: {fine_count}") - - # Comparison - print("\n📈 Comparison:") - print(f" Fast: {fast_time:.2f}s, {fast_count} items") - print(f" Fine: {fine_time:.2f}s, {fine_count} items") - if fast_time > 0: - print(f" Speed: {fine_time / fast_time:.1f}x difference") - - # Show samples - if format == "text": - print("\n--- Fast Mode Sample (first item) ---") - if fast_results and fast_results[0]: - print_textual_memory_item(fast_results[0][0], prefix=" ", max_length=300) - - print("\n--- Fine Mode Sample (first item) ---") - if fine_results and fine_results[0]: - print_textual_memory_item(fine_results[0][0], prefix=" ", max_length=300) - - -def list_test_cases(): - """List all available test cases.""" - print("\n" + "=" * 80) - print("Available Test Cases") - print("=" * 80 + "\n") - - for category, cases in TEST_CASES.items(): - print(f"📁 {category.upper()} ({len(cases)} cases):") - for case in cases: - print(f" • {case.name}: {case.description}") - print() - - -def main(): - """Main entry point.""" - parser = argparse.ArgumentParser( - description="Test MultiModalStructMemReader with various use cases", - formatter_class=argparse.RawDescriptionHelpFormatter, - epilog=""" -Examples: - # Run all test cases in fast mode - python multimodal_struct_reader.py --example all --mode fast - - # Run a specific test case - python multimodal_struct_reader.py --example chat_simple --mode fine - - # Run a category of test cases - python multimodal_struct_reader.py --example multimodal --mode fast - - # Compare fast vs fine mode - python multimodal_struct_reader.py --example chat_simple --compare - - # List all available test cases - python multimodal_struct_reader.py --list - - # Output in JSON format - python multimodal_struct_reader.py --example chat_simple --format json - """, - ) - - parser.add_argument( - "--example", - type=str, - default="oss_text_file", - help="Test case name, category name, or 'all' to run all cases (default: all)", - ) - parser.add_argument( - "--mode", - choices=["fast", "fine"], - default="fine", - help="Processing mode: fast (quick) or fine (with LLM) (default: fast)", - ) - parser.add_argument( - "--format", - choices=["text", "json"], - default="text", - help="Output format: text (readable) or json (structured) (default: text)", - ) - parser.add_argument( - "--compare", - action="store_true", - help="Compare fast and fine modes (only works with specific test case)", - ) - parser.add_argument( - "--list", - action="store_true", - help="List all available test cases and exit", - ) - parser.add_argument( - "--max-memory-length", - type=int, - default=500, - help="Maximum length of memory content to display (default: 500)", - ) - - args = parser.parse_args() - - # List test cases and exit - if args.list: - list_test_cases() - return - - # Initialize reader - print("Initializing MultiModalStructMemReader...") - try: - config_dict = get_reader_config() - reader_config = MultiModalStructMemReaderConfig.model_validate(config_dict) - reader = MultiModalStructMemReader(reader_config) - print("✅ Reader initialized\n") - except Exception as e: - print(f"❌ Failed to initialize reader: {e}") - import traceback - - traceback.print_exc() - return - - # Run test cases - if args.example == "all": - run_all_test_cases(reader, mode=args.mode, format=args.format) - elif args.example in ALL_TEST_CASES: - test_case = ALL_TEST_CASES[args.example] - if args.compare: - compare_modes(test_case, reader, format=args.format) - else: - run_test_case(test_case, reader, mode=args.mode, format=args.format) - elif args.example in TEST_CASES: - run_category(args.example, reader, mode=args.mode, format=args.format) - else: - print(f"❌ Unknown test case or category: {args.example}") - print("\nAvailable options:") - print(" Categories:", ", ".join(TEST_CASES.keys())) - print(" Test cases:", ", ".join(ALL_TEST_CASES.keys())) - print("\nUse --list to see all available test cases") - - -if __name__ == "__main__": - main() diff --git a/examples/mem_reader/parser/__init__.py b/examples/mem_reader/parser/__init__.py deleted file mode 100644 index 3a947ae89..000000000 --- a/examples/mem_reader/parser/__init__.py +++ /dev/null @@ -1 +0,0 @@ -"""Parser examples for different message types.""" diff --git a/examples/mem_reader/parser/config_utils.py b/examples/mem_reader/parser/config_utils.py deleted file mode 100644 index 225b8b5b4..000000000 --- a/examples/mem_reader/parser/config_utils.py +++ /dev/null @@ -1,132 +0,0 @@ -"""Shared configuration utilities for parser examples. - -This module provides configuration functions that match the configuration -logic in examples/mem_reader/multimodal_struct_reader.py. -""" - -import os - -from typing import Any - -from memos.configs.embedder import EmbedderConfigFactory -from memos.configs.llm import LLMConfigFactory -from memos.embedders.factory import EmbedderFactory -from memos.llms.factory import LLMFactory - - -def get_reader_config() -> dict[str, Any]: - """ - Get reader configuration from environment variables. - - Returns a dictionary that can be used to create MultiModalStructMemReaderConfig. - Matches the configuration logic in examples/mem_reader/multimodal_struct_reader.py. - - Returns: - Configuration dictionary with llm, embedder, and chunker configs - """ - openai_api_key = os.getenv("OPENAI_API_KEY") - openai_base_url = os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1") - ollama_api_base = os.getenv("OLLAMA_API_BASE", "http://localhost:11434") - - # Get LLM backend and config - llm_backend = os.getenv("MEM_READER_LLM_BACKEND", "openai") - if llm_backend == "ollama": - llm_config = { - "backend": "ollama", - "config": { - "model_name_or_path": os.getenv("MEM_READER_LLM_MODEL", "qwen3:0.6b"), - "api_base": ollama_api_base, - "temperature": float(os.getenv("MEM_READER_LLM_TEMPERATURE", "0.0")), - "remove_think_prefix": os.getenv( - "MEM_READER_LLM_REMOVE_THINK_PREFIX", "true" - ).lower() - == "true", - "max_tokens": int(os.getenv("MEM_READER_LLM_MAX_TOKENS", "8192")), - }, - } - else: # openai - llm_config = { - "backend": "openai", - "config": { - "model_name_or_path": os.getenv("MEM_READER_LLM_MODEL", "gpt-4o-mini"), - "api_key": openai_api_key or os.getenv("MEMRADER_API_KEY", "EMPTY"), - "api_base": openai_base_url, - "temperature": float(os.getenv("MEM_READER_LLM_TEMPERATURE", "0.5")), - "remove_think_prefix": os.getenv( - "MEM_READER_LLM_REMOVE_THINK_PREFIX", "true" - ).lower() - == "true", - "max_tokens": int(os.getenv("MEM_READER_LLM_MAX_TOKENS", "8192")), - }, - } - - # Get embedder backend and config - embedder_backend = os.getenv( - "MEM_READER_EMBEDDER_BACKEND", os.getenv("MOS_EMBEDDER_BACKEND", "ollama") - ) - if embedder_backend == "universal_api": - embedder_config = { - "backend": "universal_api", - "config": { - "provider": os.getenv( - "MEM_READER_EMBEDDER_PROVIDER", os.getenv("MOS_EMBEDDER_PROVIDER", "openai") - ), - "api_key": os.getenv( - "MEM_READER_EMBEDDER_API_KEY", - os.getenv("MOS_EMBEDDER_API_KEY", openai_api_key or "sk-xxxx"), - ), - "model_name_or_path": os.getenv( - "MEM_READER_EMBEDDER_MODEL", - os.getenv("MOS_EMBEDDER_MODEL", "text-embedding-3-large"), - ), - "base_url": os.getenv( - "MEM_READER_EMBEDDER_API_BASE", - os.getenv("MOS_EMBEDDER_API_BASE", openai_base_url), - ), - }, - } - else: # ollama - embedder_config = { - "backend": "ollama", - "config": { - "model_name_or_path": os.getenv( - "MEM_READER_EMBEDDER_MODEL", - os.getenv("MOS_EMBEDDER_MODEL", "nomic-embed-text:latest"), - ), - "api_base": ollama_api_base, - }, - } - - return { - "llm": llm_config, - "embedder": embedder_config, - "chunker": { - "backend": "sentence", - "config": { - "tokenizer_or_token_counter": "gpt2", - "chunk_size": 512, - "chunk_overlap": 128, - "min_sentences_per_chunk": 1, - }, - }, - } - - -def init_embedder_and_llm(): - """ - Initialize embedder and LLM from environment variables. - - Returns: - Tuple of (embedder, llm) instances - """ - config_dict = get_reader_config() - - # Initialize embedder - embedder_config = EmbedderConfigFactory.model_validate(config_dict["embedder"]) - embedder = EmbedderFactory.from_config(embedder_config) - - # Initialize LLM - llm_config = LLMConfigFactory.model_validate(config_dict["llm"]) - llm = LLMFactory.from_config(llm_config) - - return embedder, llm diff --git a/examples/mem_reader/parser/example_assistant_parser.py b/examples/mem_reader/parser/example_assistant_parser.py deleted file mode 100644 index a77f04a68..000000000 --- a/examples/mem_reader/parser/example_assistant_parser.py +++ /dev/null @@ -1,94 +0,0 @@ -"""Example demonstrating AssistantParser usage. - -AssistantParser handles assistant messages in chat conversations. -""" - -import sys - -from pathlib import Path - -from dotenv import load_dotenv - -from memos.mem_reader.read_multi_modal.assistant_parser import AssistantParser - - -# Handle imports for both script and module usage -try: - from .config_utils import init_embedder_and_llm -except ImportError: - # When running as script, add parent directory to path - sys.path.insert(0, str(Path(__file__).parent)) - from config_utils import init_embedder_and_llm - -# Load environment variables -load_dotenv() - - -def main(): - """Demonstrate AssistantParser usage.""" - print("=== AssistantParser Example ===\n") - - # 1. Initialize embedder and LLM (using shared config) - embedder, llm = init_embedder_and_llm() - - # 3. Create AssistantParser - parser = AssistantParser(embedder=embedder, llm=llm) - - # 4. Example assistant messages - assistant_messages = [ - { - "role": "assistant", - "content": "I'm sorry to hear that you're feeling down. Would you like to talk about what's been going on?", - "chat_time": "2025-01-15T10:00:30", - "message_id": "msg_001", - }, - { - "role": "assistant", - "content": "Based on the document you provided, I can see several key points: 1) The project timeline, 2) Budget considerations, and 3) Resource allocation.", - "chat_time": "2025-01-15T10:05:30", - "message_id": "msg_002", - }, - { - "role": "assistant", - "content": "Here's a Python solution for your problem:\n```python\ndef solve_problem():\n return 'solution'\n```", - "chat_time": "2025-01-15T10:10:30", - "message_id": "msg_003", - }, - ] - - print("📝 Processing assistant messages:\n") - for i, message in enumerate(assistant_messages, 1): - print(f"Assistant Message {i}:") - print(f" Content: {message['content'][:60]}...") - - # Create source from assistant message - info = {"user_id": "user1", "session_id": "session1"} - source = parser.create_source(message, info) - - print(" ✅ Created SourceMessage:") - print(f" - Type: {source.type}") - print(f" - Role: {source.role}") - print(f" - Content: {source.content[:60]}...") - print(f" - Chat Time: {source.chat_time}") - print(f" - Message ID: {source.message_id}") - print() - - # Parse in fast mode - memory_items = parser.parse_fast(message, info) - print(f" 📊 Fast mode generated {len(memory_items)} memory item(s)") - if memory_items: - print(f" - Memory: {memory_items[0].memory[:60]}...") - print(f" - Memory Type: {memory_items[0].metadata.memory_type}") - print(f" - Tags: {memory_items[0].metadata.tags}") - print() - - # Rebuild assistant message from source - rebuilt = parser.rebuild_from_source(source) - print(f" 🔄 Rebuilt message: role={rebuilt['role']}, content={rebuilt['content'][:40]}...") - print() - - print("✅ AssistantParser example completed!") - - -if __name__ == "__main__": - main() diff --git a/examples/mem_reader/parser/example_file_content_parser.py b/examples/mem_reader/parser/example_file_content_parser.py deleted file mode 100644 index 06071a70c..000000000 --- a/examples/mem_reader/parser/example_file_content_parser.py +++ /dev/null @@ -1,132 +0,0 @@ -"""Example demonstrating FileContentParser usage. - -FileContentParser handles file content parts in multimodal messages (RawMessageList). -""" - -import sys - -from pathlib import Path - -from dotenv import load_dotenv - -from memos.configs.parser import ParserConfigFactory -from memos.mem_reader.read_multi_modal.file_content_parser import FileContentParser -from memos.parsers.factory import ParserFactory - - -# Handle imports for both script and module usage -try: - from .config_utils import init_embedder_and_llm -except ImportError: - # When running as script, add parent directory to path - sys.path.insert(0, str(Path(__file__).parent)) - from config_utils import init_embedder_and_llm - -# Load environment variables -load_dotenv() - - -def main(): - """Demonstrate FileContentParser usage.""" - print("=== FileContentParser Example ===\n") - - # 1. Initialize embedder and LLM (using shared config) - embedder, llm = init_embedder_and_llm() - - # 3. Initialize parser for file content parsing (optional) - try: - parser_config = ParserConfigFactory.model_validate( - { - "backend": "markitdown", - "config": {}, - } - ) - file_parser = ParserFactory.from_config(parser_config) - except Exception as e: - print(f"⚠️ Warning: Could not initialize file parser: {e}") - print(" FileContentParser will work without a parser, but file parsing will be limited.") - file_parser = None - - # 4. Create FileContentParser - parser = FileContentParser(embedder=embedder, llm=llm, parser=file_parser) - - # 5. Example file content parts - file_content_parts = [ - { - "type": "file", - "file": { - "filename": "document.pdf", - "file_id": "file_123", - "file_data": "This is the content extracted from the PDF file...", - }, - }, - { - "type": "file", - "file": { - "filename": "report.docx", - "file_id": "file_456", - "file_data": "Report content: Analysis of Q4 performance...", - }, - }, - { - "type": "file", - "file": { - "filename": "data.csv", - "file_id": "file_789", - "path": "/path/to/data.csv", # Alternative: using path instead of file_data - }, - }, - ] - - print("📝 Processing file content parts:\n") - for i, part in enumerate(file_content_parts, 1): - print(f"File Content Part {i}:") - file_info = part.get("file", {}) - print(f" Filename: {file_info.get('filename', 'unknown')}") - print(f" File ID: {file_info.get('file_id', 'N/A')}") - - # Create source from file content part - info = {"user_id": "user1", "session_id": "session1"} - source = parser.create_source(part, info) - - print(" ✅ Created SourceMessage:") - print(f" - Type: {source.type}") - print(f" - Doc Path: {source.doc_path}") - if source.content: - print(f" - Content: {source.content[:60]}...") - if hasattr(source, "original_part") and source.original_part: - print(" - Has original_part: Yes") - print() - - # Rebuild file content part from source - rebuilt = parser.rebuild_from_source(source) - print(" 🔄 Rebuilt part:") - print(f" - Type: {rebuilt['type']}") - print(f" - Filename: {rebuilt['file'].get('filename', 'N/A')}") - print() - - # 6. Example with actual file path (if parser is available) - if file_parser: - print("📄 Testing file parsing with actual file path:\n") - # Note: This is just an example - actual file parsing would require a real file - example_file_part = { - "type": "file", - "file": { - "filename": "example.txt", - "path": "examples/mem_reader/text1.txt", # Using existing test file - }, - } - - try: - source = parser.create_source(example_file_part, info) - print(f" ✅ Created SourceMessage for file: {source.doc_path}") - # The parser would parse the file content if the file exists - except Exception as e: - print(f" ⚠️ File parsing note: {e}") - print() - - print("✅ FileContentParser example completed!") - - -if __name__ == "__main__": - main() diff --git a/examples/mem_reader/parser/example_multi_modal_parser.py b/examples/mem_reader/parser/example_multi_modal_parser.py deleted file mode 100644 index 3638d8d5e..000000000 --- a/examples/mem_reader/parser/example_multi_modal_parser.py +++ /dev/null @@ -1,400 +0,0 @@ -"""Example demonstrating MultiModalParser parser selection. - -This example verifies that different input types correctly return -the corresponding parser instances. - -MessagesType Definition (from src/memos/types/general_types.py): - MessagesType = str | MessageList | RawMessageList - - Where: - - str: Simple string messages - - MessageList: list[ChatCompletionMessageParam] - ChatCompletionMessageParam = ( - ChatCompletionSystemMessageParam | - ChatCompletionUserMessageParam | - ChatCompletionAssistantMessageParam | - ChatCompletionToolMessageParam - ) - - RawMessageList: list[RawMessageDict] - RawMessageDict = ChatCompletionContentPartTextParam | File - - Note: User/Assistant messages can have multimodal content (list of parts): - - {"type": "text", "text": "..."} - - {"type": "file", "file": {...}} - - {"type": "image_url", "image_url": {...}} - - {"type": "input_audio", "input_audio": {...}} -""" - -import sys - -from pathlib import Path - -from dotenv import load_dotenv - -from memos.mem_reader.read_multi_modal.multi_modal_parser import MultiModalParser - - -# Add src directory to path for imports -project_root = Path(__file__).parent.parent.parent.parent -src_path = project_root / "src" -if str(src_path) not in sys.path: - sys.path.insert(0, str(src_path)) - - -# Handle imports for both script and module usage -try: - from .config_utils import init_embedder_and_llm -except ImportError: - # When running as script, add parent directory to path - sys.path.insert(0, str(Path(__file__).parent)) - from config_utils import init_embedder_and_llm - -# Load environment variables -load_dotenv() - - -def parser_selection(): - """Test that different input types return the correct parser.""" - print("=== MultiModalParser Parser Selection Test ===\n") - - # 1. Initialize embedder and LLM - embedder, llm = init_embedder_and_llm() - - # 2. Create MultiModalParser - parser = MultiModalParser(embedder=embedder, llm=llm) - - # 3. Test cases: different input types - test_cases = [ - # String input -> StringParser - { - "name": "String input", - "message": "This is a simple string message", - "expected_parser_type": "StringParser", - }, - # RawMessageList: text type -> TextContentParser - { - "name": "Text content part (RawMessageList)", - "message": {"type": "text", "text": "This is a text content part"}, - "expected_parser_type": "TextContentParser", - }, - # RawMessageList: file type -> FileContentParser - { - "name": "File content part (RawMessageList)", - "message": { - "type": "file", - "file": { - "filename": "example.pdf", - "file_data": "File content here", - }, - }, - "expected_parser_type": "FileContentParser", - }, - # RawMessageList: image_url type -> None (type_parsers uses "image" key, not "image_url") - { - "name": "Image content part (RawMessageList - image_url type)", - "message": { - "type": "image_url", - "image_url": { - "url": "https://example.com/image.jpg", - "detail": "auto", - }, - }, - "expected_parser_type": None, # type_parsers has "image" key, but message has "image_url" type - "should_return_none": True, - }, - # RawMessageList: input_audio type -> None (type_parsers uses "audio" key, not "input_audio") - { - "name": "Audio content part (RawMessageList - input_audio type)", - "message": { - "type": "input_audio", - "input_audio": { - "data": "base64_encoded_audio_data", - "format": "mp3", - }, - }, - "expected_parser_type": None, # type_parsers has "audio" key, but message has "input_audio" type - "should_return_none": True, - }, - # MessageList: system role -> SystemParser - { - "name": "System message", - "message": { - "role": "system", - "content": "You are a helpful assistant.", - }, - "expected_parser_type": "SystemParser", - }, - # MessageList: user role -> UserParser - { - "name": "User message (simple)", - "message": { - "role": "user", - "content": "Hello, how are you?", - }, - "expected_parser_type": "UserParser", - }, - # MessageList: user role with multimodal content -> UserParser - { - "name": "User message (multimodal with text and file)", - "message": { - "role": "user", - "content": [ - {"type": "text", "text": "What's in this image?"}, - {"type": "file", "file": {"filename": "image.jpg", "file_data": ""}}, - ], - }, - "expected_parser_type": "UserParser", - }, - # MessageList: user role with image_url content -> UserParser - { - "name": "User message (with image_url)", - "message": { - "role": "user", - "content": [ - {"type": "text", "text": "What's in this image?"}, - { - "type": "image_url", - "image_url": {"url": "https://example.com/image.jpg"}, - }, - ], - }, - "expected_parser_type": "UserParser", - }, - # MessageList: user role with input_audio content -> UserParser - { - "name": "User message (with input_audio)", - "message": { - "role": "user", - "content": [ - {"type": "text", "text": "Listen to this audio"}, - { - "type": "input_audio", - "input_audio": {"data": "base64_data", "format": "wav"}, - }, - ], - }, - "expected_parser_type": "UserParser", - }, - # MessageList: assistant role -> AssistantParser - { - "name": "Assistant message (simple)", - "message": { - "role": "assistant", - "content": "I'm doing well, thank you!", - }, - "expected_parser_type": "AssistantParser", - }, - # MessageList: assistant role with tool_calls -> AssistantParser - { - "name": "Assistant message (with tool_calls)", - "message": { - "role": "assistant", - "content": None, - "tool_calls": [ - { - "id": "call_123", - "type": "function", - "function": { - "name": "get_weather", - "arguments": '{"location": "Beijing"}', - }, - } - ], - }, - "expected_parser_type": "AssistantParser", - }, - # MessageList: tool role -> ToolParser - { - "name": "Tool message", - "message": { - "role": "tool", - "content": "Tool execution result", - "tool_call_id": "call_123", - }, - "expected_parser_type": "ToolParser", - }, - ] - - print("Testing parser selection for different input types:\n") - all_passed = True - - for i, test_case in enumerate(test_cases, 1): - message = test_case["message"] - expected_type = test_case.get("expected_parser_type") - test_name = test_case["name"] - should_return_none = test_case.get("should_return_none", False) - - # Get parser using internal method - selected_parser = parser._get_parser(message) - - # Handle cases where None is expected - if should_return_none or expected_type is None: - if selected_parser is None: - print(f"✅ Test {i}: {test_name}") - print(" Expected: None (parser not implemented yet or not found)") - print(" Got: None") - if expected_type: - print(f" Note: {expected_type} is not yet implemented") - else: - print(f"⚠️ Test {i}: {test_name}") - print(" Expected: None") - print(f" Got: {type(selected_parser).__name__}") - print(" Note: Parser found but may not be fully implemented") - print() - continue - - # Check if parser was found - if selected_parser is None: - print(f"❌ Test {i}: {test_name}") - print(f" Expected: {expected_type}") - print(" Got: None (parser not found)") - print(f" Message: {message}\n") - all_passed = False - continue - - # Get actual parser type name - actual_type = type(selected_parser).__name__ - - # Verify parser type - if actual_type == expected_type: - print(f"✅ Test {i}: {test_name}") - print(f" Expected: {expected_type}") - print(f" Got: {actual_type}") - print(f" Parser instance: {selected_parser}") - else: - print(f"❌ Test {i}: {test_name}") - print(f" Expected: {expected_type}") - print(f" Got: {actual_type}") - print(f" Message: {message}") - all_passed = False - print() - - # Test edge cases - print("\n=== Testing Edge Cases ===\n") - - edge_cases = [ - { - "name": "Unknown message type (not dict, not str)", - "message": 12345, - "should_return_none": True, - }, - { - "name": "Dict without type or role", - "message": {"content": "Some content"}, - "should_return_none": True, - }, - { - "name": "Unknown type in RawMessageList", - "message": {"type": "unknown_type", "data": "some data"}, - "should_return_none": True, - }, - { - "name": "Unknown role in MessageList", - "message": {"role": "unknown_role", "content": "some content"}, - "should_return_none": True, - }, - { - "name": "List of messages (MessageList - not handled by _get_parser)", - "message": [ - {"role": "user", "content": "Message 1"}, - {"role": "assistant", "content": "Message 2"}, - ], - "should_return_none": True, # Lists are handled in parse(), not _get_parser() - }, - { - "name": "List of RawMessageList items (not handled by _get_parser)", - "message": [ - {"type": "text", "text": "Text content 1"}, - {"type": "file", "file": {"filename": "doc.pdf", "file_data": ""}}, - ], - "should_return_none": True, # Lists are handled in parse(), not _get_parser() - }, - ] - - for i, test_case in enumerate(edge_cases, 1): - message = test_case["message"] - should_return_none = test_case["should_return_none"] - test_name = test_case["name"] - - selected_parser = parser._get_parser(message) - - if should_return_none: - if selected_parser is None: - print(f"✅ Edge Case {i}: {test_name}") - print(" Correctly returned None") - else: - print(f"❌ Edge Case {i}: {test_name}") - print(" Expected: None") - print(f" Got: {type(selected_parser).__name__}") - all_passed = False - else: - if selected_parser is not None: - print(f"✅ Edge Case {i}: {test_name}") - print(f" Got parser: {type(selected_parser).__name__}") - else: - print(f"❌ Edge Case {i}: {test_name}") - print(" Expected: Parser") - print(" Got: None") - all_passed = False - print() - - # Summary - print("=" * 60) - if all_passed: - print("✅ All tests passed! Parser selection is working correctly.") - else: - print("❌ Some tests failed. Please check the output above.") - print("=" * 60) - - -def parser_instances(): - """Test that parser instances are correctly initialized.""" - print("\n=== Parser Instance Verification ===\n") - - embedder, llm = init_embedder_and_llm() - parser = MultiModalParser(embedder=embedder, llm=llm) - - # Verify all parser instances are initialized - parsers_to_check = { - "string_parser": "StringParser", - "system_parser": "SystemParser", - "user_parser": "UserParser", - "assistant_parser": "AssistantParser", - "tool_parser": "ToolParser", - "text_content_parser": "TextContentParser", - "file_content_parser": "FileContentParser", - } - - print("Checking parser instance initialization:\n") - all_initialized = True - - for attr_name, expected_type in parsers_to_check.items(): - parser_instance = getattr(parser, attr_name, None) - if parser_instance is None: - print(f"❌ {attr_name}: Not initialized") - all_initialized = False - else: - actual_type = type(parser_instance).__name__ - if actual_type == expected_type: - print(f"✅ {attr_name}: {actual_type}") - else: - print(f"❌ {attr_name}: Expected {expected_type}, got {actual_type}") - all_initialized = False - - print() - if all_initialized: - print("✅ All parser instances are correctly initialized!") - else: - print("❌ Some parser instances are missing or incorrect.") - print() - - -def main(): - """Run all tests.""" - parser_selection() - parser_instances() - print("\n✅ MultiModalParser example completed!") - - -if __name__ == "__main__": - main() diff --git a/examples/mem_reader/parser/example_string_parser.py b/examples/mem_reader/parser/example_string_parser.py deleted file mode 100644 index 3ec658a0e..000000000 --- a/examples/mem_reader/parser/example_string_parser.py +++ /dev/null @@ -1,66 +0,0 @@ -"""Example demonstrating StringParser usage. - -StringParser handles simple string messages that need to be converted to memory items. -""" - -import sys - -from pathlib import Path - -from dotenv import load_dotenv - -from memos.mem_reader.read_multi_modal.string_parser import StringParser - - -# Handle imports for both script and module usage -try: - from .config_utils import init_embedder_and_llm -except ImportError: - # When running as script, add parent directory to path - sys.path.insert(0, str(Path(__file__).parent)) - from config_utils import init_embedder_and_llm - -# Load environment variables -load_dotenv() - - -def main(): - """Demonstrate StringParser usage.""" - print("=== StringParser Example ===\n") - - # 1. Initialize embedder and LLM (using shared config) - embedder, llm = init_embedder_and_llm() - - # 3. Create StringParser - parser = StringParser(embedder=embedder, llm=llm) - - # 4. Example string messages - string_messages = [ - "This is a simple text message that needs to be parsed.", - "Another string message for processing.", - "StringParser handles plain text strings and converts them to SourceMessage objects.", - ] - - print("📝 Processing string messages:\n") - for i, message in enumerate(string_messages, 1): - print(f"Message {i}: {message[:50]}...") - - # Create source from string - info = {"user_id": "user1", "session_id": "session1"} - source = parser.create_source(message, info) - - print(" ✅ Created SourceMessage:") - print(f" - Type: {source.type}") - print(f" - Content: {source.content[:50]}...") - print() - - # Rebuild string from source - rebuilt = parser.rebuild_from_source(source) - print(f" 🔄 Rebuilt string: {rebuilt[:50]}...") - print() - - print("✅ StringParser example completed!") - - -if __name__ == "__main__": - main() diff --git a/examples/mem_reader/parser/example_system_parser.py b/examples/mem_reader/parser/example_system_parser.py deleted file mode 100644 index bc684a32b..000000000 --- a/examples/mem_reader/parser/example_system_parser.py +++ /dev/null @@ -1,158 +0,0 @@ -"""Example demonstrating SystemParser usage. - -SystemParser handles system messages in chat conversations. -Note: System messages support multimodal content, but only text parts are allowed -(not file, image_url, or input_audio like user messages). -""" - -import sys - -from pathlib import Path - -from dotenv import load_dotenv - - -try: - from .print_utils import pretty_print_dict -except ImportError: - # Fallback if print_utils is not available - def pretty_print_dict(d): - import json - - print(json.dumps(d, indent=2, ensure_ascii=False)) - - -from memos.mem_reader.read_multi_modal.system_parser import SystemParser - - -# Handle imports for both script and module usage -try: - from .config_utils import init_embedder_and_llm -except ImportError: - # When running as script, add parent directory to path - sys.path.insert(0, str(Path(__file__).parent)) - from config_utils import init_embedder_and_llm - -# Load environment variables -load_dotenv() - - -def main(): - """Demonstrate SystemParser usage.""" - print("=== SystemParser Example ===\n") - - # 1. Initialize embedder and LLM (using shared config) - embedder, llm = init_embedder_and_llm() - - # 3. Create SystemParser - parser = SystemParser(embedder=embedder, llm=llm) - - # 4. Example system messages (simple text) - simple_system_message = { - "role": "system", - "content": "You are a helpful assistant that provides clear and concise answers.", - "chat_time": "2025-01-15T10:00:00", - "message_id": "msg_001", - } - - print("📝 Example 1: Simple text system message\n") - pretty_print_dict(simple_system_message) - - info = {"user_id": "user1", "session_id": "session1"} - source = parser.create_source(simple_system_message, info) - - print(" ✅ Created SourceMessage:") - print(f" - Type: {source.type}") - print(f" - Role: {source.role}") - print(f" - Content: {source.content[:60]}...") - print(f" - Chat Time: {source.chat_time}") - print(f" - Message ID: {source.message_id}") - print() - - # Parse in fast mode - memory_items = parser.parse_fast(simple_system_message, info) - print(f" 📊 Fast mode generated {len(memory_items)} memory item(s)") - if memory_items: - print(f" - Memory: {memory_items[0].memory[:60]}...") - print(f" - Memory Type: {memory_items[0].metadata.memory_type}") - print(f" - Tags: {memory_items[0].metadata.tags}") - print() - - # 5. Example multimodal system message (multiple text parts) - # Note: System messages only support text parts, not file/image/audio - multimodal_system_message = { - "role": "system", - "content": [ - {"type": "text", "text": "You are a helpful assistant."}, - {"type": "text", "text": "Always provide clear and concise answers."}, - {"type": "text", "text": "If you don't know something, say so."}, - ], - "chat_time": "2025-01-15T10:05:00", - "message_id": "msg_002", - } - - print("📝 Example 2: Multimodal system message (multiple text parts)\n") - pretty_print_dict(multimodal_system_message) - print(f"Message contains {len(multimodal_system_message['content'])} text parts") - - sources = parser.create_source(multimodal_system_message, info) - if isinstance(sources, list): - print(f" ✅ Created {len(sources)} SourceMessage(s):") - for i, src in enumerate(sources, 1): - print(f" [{i}] Type: {src.type}, Role: {src.role}") - print(f" Content: {src.content[:50]}...") - else: - print(f" ✅ Created SourceMessage: Type={sources.type}") - print() - - # Parse in fast mode - memory_items = parser.parse_fast(multimodal_system_message, info) - print(f" 📊 Fast mode generated {len(memory_items)} memory item(s)") - if memory_items: - print(f" - Memory: {memory_items[0].memory[:60]}...") - print(f" - Memory Type: {memory_items[0].metadata.memory_type}") - print(f" - Tags: {memory_items[0].metadata.tags}") - # Show sources from memory item - if memory_items[0].metadata.sources: - print(f" - Sources: {len(memory_items[0].metadata.sources)} SourceMessage(s)") - print() - - # 6. Example with structured system instructions - structured_system_message = { - "role": "system", - "content": [ - { - "type": "text", - "text": "You are a coding assistant specialized in Python programming.", - }, - {"type": "text", "text": "Always write clean, well-documented code."}, - {"type": "text", "text": "Explain your reasoning when providing solutions."}, - ], - "chat_time": "2025-01-15T10:10:00", - "message_id": "msg_003", - } - - print("📝 Example 3: Structured system instructions (multiple text parts)\n") - pretty_print_dict(structured_system_message) - - sources = parser.create_source(structured_system_message, info) - if isinstance(sources, list): - print(f" ✅ Created {len(sources)} SourceMessage(s):") - for i, src in enumerate(sources, 1): - print(f" [{i}] Type: {src.type}, Role: {src.role}") - print(f" Content: {src.content[:50]}...") - print() - - # Rebuild examples - print("🔄 Rebuilding messages from sources:\n") - if isinstance(sources, list) and sources: - rebuilt = parser.rebuild_from_source(sources[0]) - else: - rebuilt = parser.rebuild_from_source(source) - if rebuilt: - pretty_print_dict(rebuilt) - print("✅ SystemParser example completed!") - - -if __name__ == "__main__": - main() diff --git a/examples/mem_reader/parser/example_text_content_parser.py b/examples/mem_reader/parser/example_text_content_parser.py deleted file mode 100644 index 1eb64d033..000000000 --- a/examples/mem_reader/parser/example_text_content_parser.py +++ /dev/null @@ -1,72 +0,0 @@ -"""Example demonstrating TextContentParser usage. - -TextContentParser handles text content parts in multimodal messages (RawMessageList). -""" - -import sys - -from pathlib import Path - -from dotenv import load_dotenv - -from memos.mem_reader.read_multi_modal.text_content_parser import TextContentParser - - -# Handle imports for both script and module usage -try: - from .config_utils import init_embedder_and_llm -except ImportError: - # When running as script, add parent directory to path - sys.path.insert(0, str(Path(__file__).parent)) - from config_utils import init_embedder_and_llm - -# Load environment variables -load_dotenv() - - -def main(): - """Demonstrate TextContentParser usage.""" - print("=== TextContentParser Example ===\n") - - # 1. Initialize embedder and LLM (using shared config) - embedder, llm = init_embedder_and_llm() - - # 3. Create TextContentParser - parser = TextContentParser(embedder=embedder, llm=llm) - - # 4. Example text content parts - text_content_parts = [ - {"type": "text", "text": "This is a simple text content part."}, - {"type": "text", "text": "TextContentParser handles text parts in multimodal messages."}, - { - "type": "text", - "text": "This parser is used when processing RawMessageList items that contain text content.", - }, - ] - - print("📝 Processing text content parts:\n") - for i, part in enumerate(text_content_parts, 1): - print(f"Text Content Part {i}:") - print(f" Text: {part['text'][:60]}...") - - # Create source from text content part - info = {"user_id": "user1", "session_id": "session1"} - source = parser.create_source(part, info) - - print(" ✅ Created SourceMessage:") - print(f" - Type: {source.type}") - print(f" - Content: {source.content[:60]}...") - if hasattr(source, "original_part") and source.original_part: - print(" - Has original_part: Yes") - print() - - # Rebuild text content part from source - rebuilt = parser.rebuild_from_source(source) - print(f" 🔄 Rebuilt part: type={rebuilt['type']}, text={rebuilt['text'][:40]}...") - print() - - print("✅ TextContentParser example completed!") - - -if __name__ == "__main__": - main() diff --git a/examples/mem_reader/parser/example_tool_parser.py b/examples/mem_reader/parser/example_tool_parser.py deleted file mode 100644 index bf3f4e333..000000000 --- a/examples/mem_reader/parser/example_tool_parser.py +++ /dev/null @@ -1,101 +0,0 @@ -"""Example demonstrating ToolParser usage. - -ToolParser handles tool/function call messages in chat conversations. -""" - -import sys - -from pathlib import Path - -from dotenv import load_dotenv - -from memos.mem_reader.read_multi_modal.tool_parser import ToolParser - - -# Handle imports for both script and module usage -try: - from .config_utils import init_embedder_and_llm -except ImportError: - # When running as script, add parent directory to path - sys.path.insert(0, str(Path(__file__).parent)) - from config_utils import init_embedder_and_llm - -# Load environment variables -load_dotenv() - - -def main(): - """Demonstrate ToolParser usage.""" - print("=== ToolParser Example ===\n") - - # 1. Initialize embedder and LLM (using shared config) - embedder, llm = init_embedder_and_llm() - - # 3. Create ToolParser - parser = ToolParser(embedder=embedder, llm=llm) - - # 4. Example tool messages - tool_messages = [ - { - "role": "tool", - "content": '{"result": "Weather in New York: 72°F, sunny"}', - "tool_call_id": "call_abc123", - "chat_time": "2025-01-15T10:00:30", - "message_id": "msg_001", - }, - { - "role": "tool", - "content": '{"status": "success", "data": {"items": [1, 2, 3]}}', - "tool_call_id": "call_def456", - "chat_time": "2025-01-15T10:05:30", - "message_id": "msg_002", - }, - { - "role": "tool", - "content": "Database query executed successfully. Retrieved 5 records.", - "tool_call_id": "call_ghi789", - "chat_time": "2025-01-15T10:10:30", - "message_id": "msg_003", - }, - ] - - print("📝 Processing tool messages:\n") - for i, message in enumerate(tool_messages, 1): - print(f"Tool Message {i}:") - print(f" Content: {message['content'][:60]}...") - print(f" Tool Call ID: {message['tool_call_id']}") - - # Create source from tool message - info = {"user_id": "user1", "session_id": "session1"} - source = parser.create_source(message, info) - - print(" ✅ Created SourceMessage:") - print(f" - Type: {source.type}") - print(f" - Role: {source.role}") - print(f" - Content: {source.content[:60]}...") - print(f" - Chat Time: {source.chat_time}") - print(f" - Message ID: {source.message_id}") - print() - - # Parse in fast mode - memory_items = parser.parse_fast(message, info) - print(f" 📊 Fast mode generated {len(memory_items)} memory item(s)") - if memory_items: - print(f" - Memory: {memory_items[0].memory[:60]}...") - print(f" - Memory Type: {memory_items[0].metadata.memory_type}") - print(f" - Tags: {memory_items[0].metadata.tags}") - print() - - # Rebuild tool message from source - rebuilt = parser.rebuild_from_source(source) - print(" 🔄 Rebuilt message:") - print(f" - Role: {rebuilt['role']}") - print(f" - Tool Call ID: {rebuilt.get('tool_call_id', 'N/A')}") - print(f" - Content: {rebuilt['content'][:40]}...") - print() - - print("✅ ToolParser example completed!") - - -if __name__ == "__main__": - main() diff --git a/examples/mem_reader/parser/example_user_parser.py b/examples/mem_reader/parser/example_user_parser.py deleted file mode 100644 index 78a75b94f..000000000 --- a/examples/mem_reader/parser/example_user_parser.py +++ /dev/null @@ -1,135 +0,0 @@ -"""Example demonstrating UserParser usage. - -UserParser handles user messages, including multimodal messages with text, files, images, etc. -""" - -import sys - -from pathlib import Path - -from dotenv import load_dotenv -from print_utils import pretty_print_dict - -from memos.mem_reader.read_multi_modal.user_parser import UserParser - - -# Handle imports for both script and module usage -try: - from .config_utils import init_embedder_and_llm -except ImportError: - # When running as script, add parent directory to path - sys.path.insert(0, str(Path(__file__).parent)) - from config_utils import init_embedder_and_llm - -# Load environment variables -load_dotenv() - - -def main(): - """Demonstrate UserParser usage.""" - print("=== UserParser Example ===\n") - - # 1. Initialize embedder and LLM (using shared config) - embedder, llm = init_embedder_and_llm() - - # 3. Create UserParser - parser = UserParser(embedder=embedder, llm=llm) - - # 4. Example user messages (simple text) - simple_user_message = { - "role": "user", - "content": "I'm feeling a bit down today. Can you help me?", - "chat_time": "2025-01-15T10:00:00", - "message_id": "msg_001", - } - - print("📝 Example 1: Simple text user message\n") - pretty_print_dict(simple_user_message) - - info = {"user_id": "user1", "session_id": "session1"} - # Parse in fast mode - memory_items = parser.parse_fast(simple_user_message, info) - print(f" 📊 Fast mode generated {len(memory_items)} memory item(s)") - if memory_items: - print(f" - Memory: {memory_items[0].memory[:60]}...") - print(f" - Memory Type: {memory_items[0].metadata.memory_type}") - print() - - # 5. Example multimodal user message (text + file) - multimodal_user_message = { - "role": "user", - "content": [ - {"type": "text", "text": "Please analyze this document:"}, - { - "type": "file", - "file": { - "filename": "report.pdf", - "file_id": "file_123", - "file_data": "This is the content of the PDF file...", - }, - }, - ], - "chat_time": "2025-01-15T10:05:00", - "message_id": "msg_002", - } - - print("📝 Example 2: Multimodal user message (text + file)\n") - pretty_print_dict(multimodal_user_message) - print(f"Message contains {len(multimodal_user_message['content'])} parts") - - # Parse in fast mode - memory_items = parser.parse_fast(multimodal_user_message, info) - print(f" 📊 Fast mode generated {len(memory_items)} memory item(s)") - for memory_item in memory_items: - sources = memory_item.metadata.sources - print(f" ✅ Created {len(sources)} SourceMessage(s):") - for i, src in enumerate(sources, 1): - print(f" [{i}] Type: {src.type}, Role: {src.role}") - if src.type == "text": - print(f" Content: {src.content[:50]}...") - elif src.type == "file": - print(f" Doc Path: {src.doc_path}") - print() - - # 6. Example with image_url (future support) - image_user_message = { - "role": "user", - "content": [ - {"type": "text", "text": "What's in this image?"}, - { - "type": "image_url", - "image_url": {"url": "https://example.com/image.jpg"}, - }, - ], - "chat_time": "2025-01-15T10:10:00", - "message_id": "msg_003", - } - print("📝 Example 3: User message with image\n") - print(f"Message contains {len(image_user_message['content'])} parts") - pretty_print_dict(image_user_message) - - # Parse in fast mode - memory_items = parser.parse_fast(image_user_message, info) - print(f" 📊 Fast mode generated {len(memory_items)} memory item(s)") - for memory_item in memory_items: - sources = memory_item.metadata.sources - print(f" ✅ Created {len(sources)} SourceMessage(s):") - for i, src in enumerate(sources, 1): - print(f" [{i}] Type: {src.type}, Role: {src.role}") - if src.type == "text": - print(f" Content: {src.content[:50]}...") - elif src.type == "file": - print(f" Doc Path: {src.doc_path}") - elif src.type == "image": - print(f" Image Path: {src.image_path}") - - # Rebuild examples - print("🔄 Rebuilding messages from sources:\n") - rebuilt_simple = parser.rebuild_from_source(sources[1]) - if rebuilt_simple: - pretty_print_dict(rebuilt_simple) - print("✅ UserParser example completed!") - - -if __name__ == "__main__": - main() diff --git a/examples/mem_reader/parser/print_utils.py b/examples/mem_reader/parser/print_utils.py deleted file mode 100644 index 5eba1fa76..000000000 --- a/examples/mem_reader/parser/print_utils.py +++ /dev/null @@ -1,11 +0,0 @@ -import pprint - - -def pretty_print_dict(d: dict): - text = pprint.pformat(d, indent=2, width=120) - border = "═" * (max(len(line) for line in text.split("\n")) + 4) - - print(f"╔{border}╗") - for line in text.split("\n"): - print(f"║ {line.ljust(len(border) - 2)} ║") - print(f"╚{border}╝") diff --git a/examples/mem_reader/parser_demos/__init__.py b/examples/mem_reader/parser_demos/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/examples/mem_reader/parser_demos/_base.py b/examples/mem_reader/parser_demos/_base.py new file mode 100644 index 000000000..883578a21 --- /dev/null +++ b/examples/mem_reader/parser_demos/_base.py @@ -0,0 +1,76 @@ +"""Base class and utilities for parser demos.""" + +from typing import Any + +from examples.mem_reader.builders import build_llm_and_embedder +from examples.mem_reader.utils import pretty_print_dict +from memos.memories.textual.item import SourceMessage + + +class BaseParserDemo: + """Base class for all parser demos.""" + + def __init__(self): + print(f"\n🚀 Initializing {self.__class__.__name__}...") + self.embedder, self.llm = build_llm_and_embedder() + self.parser = self.create_parser() + print("✅ Initialization complete.\n") + + def create_parser(self): + """Create and return the specific parser instance.""" + raise NotImplementedError + + def run(self): + """Run the main demo logic.""" + raise NotImplementedError + + def demo_source_creation( + self, message: Any, info: dict, **kwargs + ) -> SourceMessage | list[SourceMessage]: + """Demonstrate creating a SourceMessage from raw input.""" + print(f"📝 Creating SourceMessage from: {str(message)[:100]}...") + source = self.parser.create_source(message, info, **kwargs) + + if isinstance(source, list): + print(f" ✅ Created {len(source)} SourceMessage(s)") + for i, s in enumerate(source): + print(f" [{i}] Type: {s.type}, Role: {getattr(s, 'role', 'N/A')}") + else: + print(" ✅ Created SourceMessage:") + print(f" - Type: {source.type}") + if hasattr(source, "role"): + print(f" - Role: {source.role}") + if source.content: + print(f" - Content: {str(source.content)[:60]}...") + + return source + + def demo_rebuild(self, source: SourceMessage | list[SourceMessage]): + """Demonstrate rebuilding raw message from SourceMessage.""" + print("\n🔄 Rebuilding message from source...") + + # Handle list of sources (take first one for demo if it's a list) + src_to_rebuild = source[0] if isinstance(source, list) else source + + rebuilt = self.parser.rebuild_from_source(src_to_rebuild) + print(" ✅ Rebuilt result:") + if isinstance(rebuilt, dict): + pretty_print_dict(rebuilt) + else: + print(f" {rebuilt}") + + def demo_parse_fast(self, message: Any, info: dict): + """Demonstrate fast parsing (if supported).""" + if not hasattr(self.parser, "parse_fast"): + return + + print("\n⚡️ Running parse_fast...") + try: + memory_items = self.parser.parse_fast(message, info) + print(f" 📊 Generated {len(memory_items)} memory item(s)") + if memory_items: + item = memory_items[0] + print(f" - Memory: {item.memory[:60]}...") + print(f" - Type: {item.metadata.memory_type}") + except Exception as e: + print(f" ⚠️ parse_fast not applicable or failed: {e}") diff --git a/examples/mem_reader/parser_demos/demo_assistant.py b/examples/mem_reader/parser_demos/demo_assistant.py new file mode 100644 index 000000000..7c6a0a1e8 --- /dev/null +++ b/examples/mem_reader/parser_demos/demo_assistant.py @@ -0,0 +1,44 @@ +"""Demo for AssistantParser.""" + +from examples.mem_reader.samples import ASSISTANT_MESSAGE_CASES +from memos.mem_reader.read_multi_modal.assistant_parser import AssistantParser + +from ._base import BaseParserDemo + + +class AssistantParserDemo(BaseParserDemo): + def create_parser(self): + parser = AssistantParser(embedder=self.embedder, llm=self.llm) + + # Workaround: AssistantParser.rebuild_from_source is empty in src. + # Patch it to return content for demo visualization, aligning with legacy behavior. + original_rebuild = parser.rebuild_from_source + + def patched_rebuild(source): + if source.role == "assistant": + # Only handling simple text content as per legacy example scope + return { + "role": "assistant", + "content": source.content, + } + return original_rebuild(source) + + parser.rebuild_from_source = patched_rebuild + return parser + + def run(self): + print("=== AssistantParser Demo ===") + + info = {"user_id": "user1", "session_id": "session1"} + + for case in ASSISTANT_MESSAGE_CASES: + print(f"\n--- Case: {case.description} ---") + for msg in case.scene_data: + source = self.demo_source_creation(msg, info) + self.demo_rebuild(source) + self.demo_parse_fast(msg, info) + + +if __name__ == "__main__": + demo = AssistantParserDemo() + demo.run() diff --git a/examples/mem_reader/parser_demos/demo_file_content.py b/examples/mem_reader/parser_demos/demo_file_content.py new file mode 100644 index 000000000..f0d11b15f --- /dev/null +++ b/examples/mem_reader/parser_demos/demo_file_content.py @@ -0,0 +1,68 @@ +"""Demo for FileContentParser.""" + +from examples.mem_reader.builders import build_file_parser +from examples.mem_reader.samples import FILE_CONTENT_PARTS, FILE_CONTENT_REAL_FILE_PART +from memos.mem_reader.read_multi_modal.file_content_parser import FileContentParser + +from ._base import BaseParserDemo + + +class FileContentParserDemo(BaseParserDemo): + def create_parser(self): + # Initialize the underlying file parser (MarkItDown) + file_parser_impl = build_file_parser() + + return FileContentParser( + embedder=self.embedder, + llm=self.llm, + parser=file_parser_impl, + ) + + def run(self): + print("=== FileContentParser Demo ===") + + info = {"user_id": "user1", "session_id": "session1"} + + print("📝 Processing file content parts:\n") + for i, part in enumerate(FILE_CONTENT_PARTS, 1): + print(f"File Content Part {i}:") + file_info = part.get("file", {}) + print(f" Filename: {file_info.get('filename', 'unknown')}") + print(f" File ID: {file_info.get('file_id', 'N/A')}") + + # Create source from file content part + source = self.parser.create_source(part, info) + + print(" ✅ Created SourceMessage:") + print(f" - Type: {source.type}") + print(f" - Doc Path: {source.doc_path}") + if source.content: + print(f" - Content: {source.content[:60]}...") + if hasattr(source, "original_part") and source.original_part: + print(" - Has original_part: Yes") + print() + + # Rebuild file content part from source + rebuilt = self.parser.rebuild_from_source(source) + print(" 🔄 Rebuilt part:") + print(f" - Type: {rebuilt.get('type')}") + print(f" - Filename: {rebuilt.get('file', {}).get('filename', 'N/A')}") + + print() + + # 6. Example with actual file path (if parser is available) + if getattr(self.parser, "parser", None): + print("📄 Testing file parsing with actual file path:\n") + + try: + source = self.parser.create_source(FILE_CONTENT_REAL_FILE_PART, info) + print(f" ✅ Created SourceMessage for file: {source.doc_path}") + # The parser would parse the file content if the file exists + except Exception as e: + print(f" ⚠️ File parsing note: {e}") + print() + + +if __name__ == "__main__": + demo = FileContentParserDemo() + demo.run() diff --git a/examples/mem_reader/parser_demos/demo_image.py b/examples/mem_reader/parser_demos/demo_image.py new file mode 100644 index 000000000..a3ff3b334 --- /dev/null +++ b/examples/mem_reader/parser_demos/demo_image.py @@ -0,0 +1,87 @@ +"""Demo for ImageParser.""" + +import base64 +import copy + +from pathlib import Path + +from examples.mem_reader.samples import IMAGE_MESSAGE_CASES +from memos.mem_reader.read_multi_modal.image_parser import ImageParser + +from ._base import BaseParserDemo + + +class ImageParserDemo(BaseParserDemo): + def create_parser(self): + return ImageParser(embedder=self.embedder, llm=self.llm) + + def run(self): + print("🚀 Initializing ImageParserDemo...") + print("✅ Initialization complete.") + print("=== ImageParser Demo ===\n") + + info = {"user_id": "user1", "session_id": "session1"} + + test_cases = copy.deepcopy(IMAGE_MESSAGE_CASES) + + # Add Local Image (Base64) if exists + local_img_path = Path(__file__).parent.parent / "test_image.png" + if local_img_path.exists(): + with open(local_img_path, "rb") as f: + b64_data = base64.b64encode(f.read()).decode("utf-8") + test_cases.append( + { + "type": "image_url", + "image_url": { + "url": f"data:image/png;base64,{b64_data}", + "detail": "auto", + }, + "_note": "Local Image (Base64)", + } + ) + + for i, msg in enumerate(test_cases, 1): + print(f"--- Case {i}: Image URL message ---") + + # 1. Create SourceMessage + print(f"📝 Creating SourceMessage from: {msg}") + source = self.parser.create_source(msg, info) + print(" ✅ Created SourceMessage:") + print(f" - Type: {source.type}") + print(f" - URL: {getattr(source, 'url', 'N/A')}") + + # 2. Rebuild from Source + print("🔄 Rebuilding message from source...") + rebuilt = self.parser.rebuild_from_source(source) + print(f" ✅ Rebuilt result: {rebuilt}") + + # 3. Fast Parse (Expected Empty) + print("⚡️ Running parse_fast (expecting empty)...") + fast_results = self.parser.parse_fast(msg, info) + if not fast_results: + print(" ✅ Got empty list as expected (images require fine mode).") + else: + print(f" ⚠️ Unexpected fast results: {len(fast_results)} items") + + # 4. Fine Parse (Vision Model) + print("🧠 Running parse_fine (Vision Model)...") + # Note: This might fail if the configured LLM doesn't support vision or if the URL is unreachable + try: + fine_results = self.parser.parse_fine(msg, info) + if not fine_results: + print( + " ⚠️ No memories generated (LLM might not support vision or image inaccessible)." + ) + else: + print(f" 📊 Generated {len(fine_results)} memory item(s):") + for item in fine_results: + print(f" - Memory: {item.memory[:100]}...") + except Exception as e: + print(f" ❌ Error during fine parsing: {e}") + + print() + + +if __name__ == "__main__": + demo = ImageParserDemo() + demo.run() diff --git a/examples/mem_reader/parser_demos/demo_multi_modal.py b/examples/mem_reader/parser_demos/demo_multi_modal.py new file mode 100644 index 000000000..3302ef073 --- /dev/null +++ b/examples/mem_reader/parser_demos/demo_multi_modal.py @@ -0,0 +1,346 @@ +"""Demo for MultiModalParser.""" + +from examples.mem_reader.builders import build_file_parser +from memos.mem_reader.read_multi_modal.multi_modal_parser import MultiModalParser + +from ._base import BaseParserDemo + + +class MultiModalParserDemo(BaseParserDemo): + def create_parser(self): + file_parser = build_file_parser() + return MultiModalParser(embedder=self.embedder, llm=self.llm, parser=file_parser) + + def run(self): + self.parser_selection() + self.parser_instances() + print("\n✅ MultiModalParser example completed!") + + def parser_selection(self): + """Test that different input types return the correct parser.""" + print("=== MultiModalParser Parser Selection Test ===\n") + + # Test cases: different input types + test_cases = [ + # String input -> StringParser + { + "name": "String input", + "message": "This is a simple string message", + "expected_parser_type": "StringParser", + }, + # RawMessageList: text type -> TextContentParser + { + "name": "Text content part (RawMessageList)", + "message": {"type": "text", "text": "This is a text content part"}, + "expected_parser_type": "TextContentParser", + }, + # RawMessageList: file type -> FileContentParser + { + "name": "File content part (RawMessageList)", + "message": { + "type": "file", + "file": { + "filename": "example.pdf", + "file_data": "File content here", + }, + }, + "expected_parser_type": "FileContentParser", + }, + # RawMessageList: image_url type -> ImageParser + { + "name": "Image content part (RawMessageList - image_url type)", + "message": { + "type": "image_url", + "image_url": { + "url": "https://example.com/image.jpg", + "detail": "auto", + }, + }, + "expected_parser_type": "ImageParser", + }, + # RawMessageList: input_audio type -> None (type_parsers uses "audio" key, not "input_audio") + { + "name": "Audio content part (RawMessageList - input_audio type)", + "message": { + "type": "input_audio", + "input_audio": { + "data": "base64_encoded_audio_data", + "format": "mp3", + }, + }, + "expected_parser_type": None, # type_parsers has "audio" key, but message has "input_audio" type + "should_return_none": True, + }, + # MessageList: system role -> SystemParser + { + "name": "System message", + "message": { + "role": "system", + "content": "You are a helpful assistant.", + }, + "expected_parser_type": "SystemParser", + }, + # MessageList: user role -> UserParser + { + "name": "User message (simple)", + "message": { + "role": "user", + "content": "Hello, how are you?", + }, + "expected_parser_type": "UserParser", + }, + # MessageList: user role with multimodal content -> UserParser + { + "name": "User message (multimodal with text and file)", + "message": { + "role": "user", + "content": [ + {"type": "text", "text": "What's in this image?"}, + {"type": "file", "file": {"filename": "image.jpg", "file_data": ""}}, + ], + }, + "expected_parser_type": "UserParser", + }, + # MessageList: user role with image_url content -> UserParser + { + "name": "User message (with image_url)", + "message": { + "role": "user", + "content": [ + {"type": "text", "text": "What's in this image?"}, + { + "type": "image_url", + "image_url": {"url": "https://example.com/image.jpg"}, + }, + ], + }, + "expected_parser_type": "UserParser", + }, + # MessageList: user role with input_audio content -> UserParser + { + "name": "User message (with input_audio)", + "message": { + "role": "user", + "content": [ + {"type": "text", "text": "Listen to this audio"}, + { + "type": "input_audio", + "input_audio": {"data": "base64_data", "format": "wav"}, + }, + ], + }, + "expected_parser_type": "UserParser", + }, + # MessageList: assistant role -> AssistantParser + { + "name": "Assistant message (simple)", + "message": { + "role": "assistant", + "content": "I'm doing well, thank you!", + }, + "expected_parser_type": "AssistantParser", + }, + # MessageList: assistant role with tool_calls -> AssistantParser + { + "name": "Assistant message (with tool_calls)", + "message": { + "role": "assistant", + "content": None, + "tool_calls": [ + { + "id": "call_123", + "type": "function", + "function": { + "name": "get_weather", + "arguments": '{"location": "Beijing"}', + }, + } + ], + }, + "expected_parser_type": "AssistantParser", + }, + # MessageList: tool role -> ToolParser + { + "name": "Tool message", + "message": { + "role": "tool", + "content": "Tool execution result", + "tool_call_id": "call_123", + }, + "expected_parser_type": "ToolParser", + }, + ] + + print("Testing parser selection for different input types:\n") + all_passed = True + + for i, test_case in enumerate(test_cases, 1): + message = test_case["message"] + expected_type = test_case.get("expected_parser_type") + test_name = test_case["name"] + should_return_none = test_case.get("should_return_none", False) + + # Get parser using internal method + selected_parser = self.parser._get_parser(message) + + # Handle cases where None is expected + if should_return_none or expected_type is None: + if selected_parser is None: + print(f"✅ Test {i}: {test_name}") + print(" Expected: None (parser not implemented yet or not found)") + print(" Got: None") + if expected_type: + print(f" Note: {expected_type} is not yet implemented") + else: + print(f"⚠️ Test {i}: {test_name}") + print(" Expected: None") + print(f" Got: {type(selected_parser).__name__}") + print(" Note: Parser found but may not be fully implemented") + print() + continue + + # Check if parser was found + if selected_parser is None: + print(f"❌ Test {i}: {test_name}") + print(f" Expected: {expected_type}") + print(" Got: None (parser not found)") + print(f" Message: {message}\n") + all_passed = False + continue + + # Get actual parser type name + actual_type = type(selected_parser).__name__ + + # Verify parser type + if actual_type == expected_type: + print(f"✅ Test {i}: {test_name}") + print(f" Expected: {expected_type}") + print(f" Got: {actual_type}") + print(f" Parser instance: {selected_parser}") + else: + print(f"❌ Test {i}: {test_name}") + print(f" Expected: {expected_type}") + print(f" Got: {actual_type}") + print(f" Message: {message}") + all_passed = False + print() + + # Test edge cases + print("\n=== Testing Edge Cases ===\n") + + edge_cases = [ + { + "name": "Unknown message type (not dict, not str)", + "message": 12345, + "should_return_none": True, + }, + { + "name": "Dict without type or role", + "message": {"content": "Some content"}, + "should_return_none": True, + }, + { + "name": "Unknown type in RawMessageList", + "message": {"type": "unknown_type", "data": "some data"}, + "should_return_none": True, + }, + { + "name": "Unknown role in MessageList", + "message": {"role": "unknown_role", "content": "some content"}, + "should_return_none": True, + }, + { + "name": "List of messages (MessageList - not handled by _get_parser)", + "message": [ + {"role": "user", "content": "Message 1"}, + {"role": "assistant", "content": "Message 2"}, + ], + "should_return_none": True, # Lists are handled in parse(), not _get_parser() + }, + { + "name": "List of RawMessageList items (not handled by _get_parser)", + "message": [ + {"type": "text", "text": "Text content 1"}, + {"type": "file", "file": {"filename": "doc.pdf", "file_data": ""}}, + ], + "should_return_none": True, # Lists are handled in parse(), not _get_parser() + }, + ] + + for i, test_case in enumerate(edge_cases, 1): + message = test_case["message"] + should_return_none = test_case["should_return_none"] + test_name = test_case["name"] + + selected_parser = self.parser._get_parser(message) + + if should_return_none: + if selected_parser is None: + print(f"✅ Edge Case {i}: {test_name}") + print(" Correctly returned None") + else: + print(f"❌ Edge Case {i}: {test_name}") + print(" Expected: None") + print(f" Got: {type(selected_parser).__name__}") + all_passed = False + else: + if selected_parser is not None: + print(f"✅ Edge Case {i}: {test_name}") + print(f" Got parser: {type(selected_parser).__name__}") + else: + print(f"❌ Edge Case {i}: {test_name}") + print(" Expected: Parser") + print(" Got: None") + all_passed = False + print() + + # Summary + print("=" * 60) + if all_passed: + print("✅ All tests passed! Parser selection is working correctly.") + else: + print("❌ Some tests failed. Please check the output above.") + print("=" * 60) + + def parser_instances(self): + """Test that parser instances are correctly initialized.""" + print("\n=== Parser Instance Verification ===\n") + + # Verify all parser instances are initialized + parsers_to_check = { + "string_parser": "StringParser", + "system_parser": "SystemParser", + "user_parser": "UserParser", + "assistant_parser": "AssistantParser", + "tool_parser": "ToolParser", + "text_content_parser": "TextContentParser", + "file_content_parser": "FileContentParser", + } + + print("Checking parser instance initialization:\n") + all_initialized = True + + for attr_name, expected_type in parsers_to_check.items(): + parser_instance = getattr(self.parser, attr_name, None) + if parser_instance is None: + print(f"❌ {attr_name}: Not initialized") + all_initialized = False + else: + actual_type = type(parser_instance).__name__ + if actual_type == expected_type: + print(f"✅ {attr_name}: {actual_type}") + else: + print(f"❌ {attr_name}: Expected {expected_type}, got {actual_type}") + all_initialized = False + + print() + if all_initialized: + print("✅ All parser instances are correctly initialized!") + else: + print("❌ Some parser instances are missing or incorrect.") + print() + + +if __name__ == "__main__": + demo = MultiModalParserDemo() + demo.run() diff --git a/examples/mem_reader/parser_demos/demo_string.py b/examples/mem_reader/parser_demos/demo_string.py new file mode 100644 index 000000000..e6bf99f83 --- /dev/null +++ b/examples/mem_reader/parser_demos/demo_string.py @@ -0,0 +1,30 @@ +"""Demo for StringParser.""" + +from examples.mem_reader.samples import STRING_MESSAGE_CASES +from memos.mem_reader.read_multi_modal.string_parser import StringParser + +from ._base import BaseParserDemo + + +class StringParserDemo(BaseParserDemo): + def create_parser(self): + return StringParser(embedder=self.embedder, llm=self.llm) + + def run(self): + print("=== StringParser Demo ===") + + info = {"user_id": "user1", "session_id": "session1"} + + for case in STRING_MESSAGE_CASES: + print(f"\n--- Case: {case.description} ---") + print("📝 Processing string messages:\n") + for i, msg in enumerate(case.scene_data, 1): + print(f"Message {i}: {msg[:50]}...") + source = self.demo_source_creation(msg, info) + self.demo_rebuild(source) + print() + + +if __name__ == "__main__": + demo = StringParserDemo() + demo.run() diff --git a/examples/mem_reader/parser_demos/demo_system.py b/examples/mem_reader/parser_demos/demo_system.py new file mode 100644 index 000000000..8655833ef --- /dev/null +++ b/examples/mem_reader/parser_demos/demo_system.py @@ -0,0 +1,41 @@ +"""Demo for SystemParser.""" + +from examples.mem_reader.samples import SYSTEM_MESSAGE_CASES +from memos.mem_reader.read_multi_modal.system_parser import SystemParser + +from ._base import BaseParserDemo + + +class SystemParserDemo(BaseParserDemo): + def create_parser(self): + return SystemParser(embedder=self.embedder, llm=self.llm) + + def run(self): + print("=== SystemParser Demo ===") + + info = {"user_id": "user1", "session_id": "session1"} + + for case in SYSTEM_MESSAGE_CASES: + print(f"\n--- Case: {case.description} ---") + for msg in case.scene_data: + # Workaround: SystemParser in src only supports str/dict content, not list. + # Since we cannot modify src, we flatten list content here. + msg_to_process = msg + if isinstance(msg.get("content"), list): + msg_to_process = msg.copy() + content_list = msg["content"] + merged_text = "".join( + part.get("text", "") + for part in content_list + if isinstance(part, dict) and part.get("type") == "text" + ) + msg_to_process["content"] = merged_text + + source = self.demo_source_creation(msg_to_process, info) + self.demo_rebuild(source) + self.demo_parse_fast(msg_to_process, info) + + +if __name__ == "__main__": + demo = SystemParserDemo() + demo.run() diff --git a/examples/mem_reader/parser_demos/demo_text_content.py b/examples/mem_reader/parser_demos/demo_text_content.py new file mode 100644 index 000000000..4c27c6422 --- /dev/null +++ b/examples/mem_reader/parser_demos/demo_text_content.py @@ -0,0 +1,40 @@ +"""Demo for TextContentParser.""" + +from examples.mem_reader.samples import TEXT_CONTENT_PARTS +from memos.mem_reader.read_multi_modal.text_content_parser import TextContentParser + +from ._base import BaseParserDemo + + +class TextContentParserDemo(BaseParserDemo): + def create_parser(self): + return TextContentParser(embedder=self.embedder, llm=self.llm) + + def run(self): + print("=== TextContentParser Demo ===") + + info = {"user_id": "user1", "session_id": "session1"} + + for i, part in enumerate(TEXT_CONTENT_PARTS, 1): + print(f"\n--- Part {i} ---") + source = self.demo_source_creation(part, info) + + # Legacy example attempts to rebuild and access dict keys directly. + # Since current source returns None, we must handle it safely in the demo. + print("\n🔄 Rebuilding from source...") + rebuilt = self.parser.rebuild_from_source(source) + if rebuilt: + print(" ✅ Rebuilt result:") + if isinstance(rebuilt, dict): + from examples.mem_reader.utils import pretty_print_dict + + pretty_print_dict(rebuilt) + else: + print(f" {rebuilt}") + else: + print(" ⚠️ Rebuilt result is None (not implemented in source)") + + +if __name__ == "__main__": + demo = TextContentParserDemo() + demo.run() diff --git a/examples/mem_reader/parser_demos/demo_tool.py b/examples/mem_reader/parser_demos/demo_tool.py new file mode 100644 index 000000000..991f21751 --- /dev/null +++ b/examples/mem_reader/parser_demos/demo_tool.py @@ -0,0 +1,28 @@ +"""Demo for ToolParser.""" + +from examples.mem_reader.samples import TOOL_MESSAGE_CASES +from memos.mem_reader.read_multi_modal.tool_parser import ToolParser + +from ._base import BaseParserDemo + + +class ToolParserDemo(BaseParserDemo): + def create_parser(self): + return ToolParser(embedder=self.embedder, llm=self.llm) + + def run(self): + print("=== ToolParser Demo ===") + + info = {"user_id": "user1", "session_id": "session1"} + + for case in TOOL_MESSAGE_CASES: + print(f"\n--- Case: {case.description} ---") + for msg in case.scene_data: + source = self.demo_source_creation(msg, info) + self.demo_rebuild(source) + self.demo_parse_fast(msg, info) + + +if __name__ == "__main__": + demo = ToolParserDemo() + demo.run() diff --git a/examples/mem_reader/parser_demos/demo_user.py b/examples/mem_reader/parser_demos/demo_user.py new file mode 100644 index 000000000..16dafcb2d --- /dev/null +++ b/examples/mem_reader/parser_demos/demo_user.py @@ -0,0 +1,43 @@ +"""Demo for UserParser.""" + +from examples.mem_reader.samples import USER_MESSAGE_CASES +from memos.mem_reader.read_multi_modal.user_parser import UserParser + +from ._base import BaseParserDemo + + +class UserParserDemo(BaseParserDemo): + def create_parser(self): + return UserParser(embedder=self.embedder, llm=self.llm) + + def run(self): + print("=== UserParser Demo ===") + + info = {"user_id": "user1", "session_id": "session1"} + + for case in USER_MESSAGE_CASES: + print(f"\n--- Case: {case.description} ---") + for msg in case.scene_data: + sources = self.demo_source_creation(msg, info) + + # Rebuild all sources to show full multimodal support + if isinstance(sources, list): + for i, src in enumerate(sources): + print(f"\n🔄 Rebuilding source part {i + 1} ({src.type})...") + rebuilt = self.parser.rebuild_from_source(src) + print(" ✅ Rebuilt result:") + if isinstance(rebuilt, dict): + from examples.mem_reader.utils import pretty_print_dict + + pretty_print_dict(rebuilt) + else: + print(f" {rebuilt}") + else: + self.demo_rebuild(sources) + + self.demo_parse_fast(msg, info) + + +if __name__ == "__main__": + demo = UserParserDemo() + demo.run() diff --git a/examples/mem_reader/runners/__init__.py b/examples/mem_reader/runners/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/examples/mem_reader/runners/run_multimodal.py b/examples/mem_reader/runners/run_multimodal.py new file mode 100644 index 000000000..e4176e898 --- /dev/null +++ b/examples/mem_reader/runners/run_multimodal.py @@ -0,0 +1,139 @@ +"""Runner for MultiModalStructMemReader.""" + +import argparse +import json +import time +import traceback + +from examples.mem_reader.builders import build_multimodal_reader +from examples.mem_reader.samples import ( + MULTIMODAL_MESSAGE_CASES, + RAW_INPUT_CASES, + STRING_MESSAGE_CASES, +) +from examples.mem_reader.utils import print_memory_item + + +# Map example names to test cases +EXAMPLE_MAP = { + "string_message": STRING_MESSAGE_CASES, + "multimodal": MULTIMODAL_MESSAGE_CASES, + "raw_input": RAW_INPUT_CASES, +} + + +def run_multimodal_reader(): + """Run MultiModalStructMemReader with sample data.""" + parser = argparse.ArgumentParser(description="MultiModalStructMemReader Example") + parser.add_argument( + "--example", + type=str, + default="all", + choices=[*list(EXAMPLE_MAP.keys()), "all"], + help="Example to run", + ) + parser.add_argument( + "--mode", + type=str, + default="fine", + choices=["fast", "fine"], + help="Processing mode (fast/fine)", + ) + parser.add_argument( + "--format", + type=str, + default="text", + choices=["text", "json"], + help="Output format", + ) + + args = parser.parse_args() + + print("🚀 Initializing MultiModalStructMemReader...") + reader = build_multimodal_reader() + print("✅ Initialization complete.") + + # Select test cases + if args.example == "all": + test_cases = [] + for cases in EXAMPLE_MAP.values(): + test_cases.extend(cases) + else: + test_cases = EXAMPLE_MAP[args.example] + + print(f"📋 Running {len(test_cases)} test cases in '{args.mode}' mode...\n") + + results = [] + + for i, case in enumerate(test_cases): + print(f"🔹 Case {i + 1}: {case.name} - {case.description}") + + info = case.get_info() + scene_data = case.scene_data + + # Data structure adaptation logic + # Ensure scene_data is List[List[dict]] if it looks like a single conversation + # Most samples in samples.py are wrapped in [], so they are List[List[dict]]. + # Except STRING_MESSAGE_CASES which are List[str]. + if ( + isinstance(scene_data, list) + and len(scene_data) > 0 + and not isinstance(scene_data[0], list) + and not isinstance(scene_data[0], str) + ): + scene_data = [scene_data] + + try: + start_time = time.time() + + # Determine input type + input_type = "chat" + if case in EXAMPLE_MAP["string_message"]: + input_type = "string" + elif case in EXAMPLE_MAP["raw_input"]: + input_type = "raw" + + memories = reader.get_memory( + scene_data, + type=input_type, + mode=args.mode, + info=info, + ) + duration = time.time() - start_time + + result_entry = { + "case": case.name, + "description": case.description, + "duration_seconds": round(duration, 4), + "memory_count": sum(len(m) for m in memories), + "memories": [], + } + + print( + f" ✅ Processed in {duration:.4f}s. Extracted {result_entry['memory_count']} memories." + ) + + # Flatten memories for display/output + flat_memories = [item for sublist in memories for item in sublist] + + if args.format == "json": + # Convert TextualMemoryItem to dict + result_entry["memories"] = [ + m.to_dict() if hasattr(m, "to_dict") else str(m) for m in flat_memories + ] + results.append(result_entry) + else: + for item in flat_memories: + print_memory_item(item, indent=6) + print() + + except Exception as e: + print(f" ❌ Error: {e}") + traceback.print_exc() + + if args.format == "json": + print(json.dumps(results, indent=2, ensure_ascii=False)) + + +if __name__ == "__main__": + run_multimodal_reader() diff --git a/examples/mem_reader/runners/run_simple.py b/examples/mem_reader/runners/run_simple.py new file mode 100644 index 000000000..21ecd73a9 --- /dev/null +++ b/examples/mem_reader/runners/run_simple.py @@ -0,0 +1,113 @@ +"""Runner for SimpleStructMemReader.""" + +import time + +from examples.mem_reader.samples import SIMPLE_CHAT_SCENE +from examples.mem_reader.settings import get_reader_config +from examples.mem_reader.utils import print_memory_item +from memos.configs.mem_reader import SimpleStructMemReaderConfig +from memos.mem_reader.simple_struct import SimpleStructMemReader + + +def _print_memory_sets(title: str, memories): + """memories: list[list[TextualMemoryItem]]""" + total = sum(len(mem_list) for mem_list in memories) + print(f"\n{title}") + print(f"📊 Total memory items: {total}") + print(f"✅ Extracted {len(memories)} memory sets.") + for i, memory_list in enumerate(memories): + print(f"\n--- Window/Conversation {i + 1} Memories ({len(memory_list)} items) ---") + for item in memory_list: + print_memory_item(item, indent=2) + + +def run_simple_reader(): + """Run SimpleStructMemReader with sample data.""" + print("🚀 Initializing SimpleStructMemReader from JSON config...") + + # Use settings config instead of hardcoded JSON + reader_config = SimpleStructMemReaderConfig(**get_reader_config()) + reader = SimpleStructMemReader(reader_config) + print("✅ Initialization complete.") + + info = {"user_id": "simple_user", "session_id": "simple_session"} + + print("\n📝 Processing Simple Chat Scene...") + # SIMPLE_CHAT_SCENE: list[list[dict]] (multiple conversations) + + try: + # 1) FINE + print("\n🔄 Testing FINE mode (with LLM)...") + t0 = time.time() + fine_memory = reader.get_memory( + SIMPLE_CHAT_SCENE, + type="chat", + info=info, + mode="fine", + ) + fine_time = time.time() - t0 + print(f"⏱️ Fine mode time: {fine_time:.2f}s") + _print_memory_sets("=== FINE Mode Results ===", fine_memory) + + # 2) FAST + print("\n⚡ Testing FAST mode (no LLM)...") + t0 = time.time() + fast_memory = reader.get_memory( + SIMPLE_CHAT_SCENE, + type="chat", + info=info, + mode="fast", + ) + fast_time = time.time() - t0 + print(f"⏱️ Fast mode time: {fast_time:.2f}s") + _print_memory_sets("=== FAST Mode Results ===", fast_memory) + + # 3) Transfer: FAST -> FINE + # fine_transfer_simple_mem expects a flat list[TextualMemoryItem] + print("\n🔁 Transfer FAST memories -> FINE...") + flat_fast_items = [item for mem_list in fast_memory for item in mem_list] + + t0 = time.time() + transferred = reader.fine_transfer_simple_mem(flat_fast_items, type="chat") + transfer_time = time.time() - t0 + + print(f"⏱️ Transfer time: {transfer_time:.2f}s") + _print_memory_sets("=== TRANSFER Results (FAST -> FINE) ===", transferred) + + # 4) Documents (Fine only) + print("\n📄 Processing Documents (Fine Mode Only)...") + doc_paths = [ + "text1.txt", + "text2.txt", + ] + + try: + t0 = time.time() + doc_memory = reader.get_memory( + doc_paths, + type="doc", + info={"user_id": "doc_user", "session_id": "doc_session"}, + mode="fine", + ) + doc_time = time.time() - t0 + print(f"⏱️ Doc fine mode time: {doc_time:.2f}s") + _print_memory_sets("=== DOC Mode Results (FINE) ===", doc_memory) + except Exception as e: + print(f"⚠️ Document processing failed: {e}") + print(" (This is expected if document files don't exist)") + + # 5) Summary (no speedup) + print("\n📈 Summary") + print(f" Fine: {fine_time:.2f}s") + print(f" Fast: {fast_time:.2f}s") + print(f" Transfer: {transfer_time:.2f}s") + + except Exception as e: + print(f"❌ Error during processing: {e}") + import traceback + + traceback.print_exc() + + +if __name__ == "__main__": + run_simple_reader() diff --git a/examples/mem_reader/samples.py b/examples/mem_reader/samples.py new file mode 100644 index 000000000..c29177c58 --- /dev/null +++ b/examples/mem_reader/samples.py @@ -0,0 +1,773 @@ +"""Sample data for MemReader examples. + +This module contains test cases and sample data for various MemReader scenarios, +including simple chat, multimodal messages, file content, and tool usage. +""" + +from dataclasses import dataclass, field +from typing import Any + + +@dataclass +class TestCase: + """Base class for test cases.""" + + name: str + description: str + scene_data: Any + expected_count: dict[str, int] = field(default_factory=dict) + + def get_info(self) -> dict[str, Any]: + """Get info dict for this test case.""" + return { + "user_id": "test_user", + "session_id": f"session_{self.name}", + "test_case": self.name, + } + + +# ============================================================================ +# 1. Simple Chat Samples (for SimpleStructMemReader) +# ============================================================================ + +SIMPLE_CHAT_SCENE = [ + [ + {"role": "user", "chat_time": "3 May 2025", "content": "I'm feeling a bit down today."}, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "I'm sorry to hear that. Do you want to talk about what's been going on?", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "It's just been a tough couple of days, you know? Everything feels a bit overwhelming, and I just can't seem to shake it off.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "It sounds like you're going through a lot right now. Sometimes it helps to talk things out. Is there something specific that's been weighing on you, or is it more of a general feeling?", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "It's a mix, I guess. Work's been really stressful, and on top of that, I've been feeling kinda disconnected from the people around me.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "That can be really draining, especially when you're feeling isolated on top of the stress. Do you think there's something from your past that's contributing to how you're feeling now? Sometimes our emotions are tied to older experiences.", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "Yeah, now that you mention it… I've been thinking a lot about my childhood lately. I didn't have the easiest upbringing. My parents were always busy, and I often felt like I had to figure things out on my own. I remember one winter, I got really sick with a high fever. My parents were both working, and I didn't want to bother them. I just lay in bed, crying by myself, not knowing what to do.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "That must have been very lonely. Growing up without that support can really make you feel like you have to handle everything on your own. How do you think that experience has affected you now?", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "Yeah, it was really lonely. I remember spending a lot of time doing things on my own, like drawing, because it was my only way to escape. I used to draw animals, and I created my own little world on paper. It was peaceful in a way, just me and my imagination, with no outside distractions.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "Drawing sounds like a beautiful way to express yourself and find some peace in that solitude. It must have been a very quiet and private world for you. Do you think that sense of loneliness from back then has shaped how you connect with others today?", + }, + { + "role": "user", + "chat_time": "3 May 2025", + "content": "I think it has. I've always found it hard to let others in. I feel like I have to handle everything on my own. If I rely on someone else, I feel vulnerable, and I start to feel that loneliness again.", + }, + { + "role": "assistant", + "chat_time": "3 May 2025", + "content": "It sounds like this was a protective mechanism that helped you cope with your feelings of loneliness back then. But as you've grown, it seems like this pattern might not be serving you as well anymore. Have you thought about trying to break this cycle, or finding new ways to connect with others?", + }, + ] +] + +# ============================================================================ +# 2. String Message Cases +# ============================================================================ + +STRING_MESSAGE_CASES = [ + TestCase( + name="string_simple", + description="Simple string message", + scene_data=[ + "This is a simple text message that needs to be parsed.", + "Another string message for processing.", + "StringParser handles plain text strings and converts them to SourceMessage objects.", + ], + expected_count={"fast": 1, "fine": 1}, + ), + TestCase( + name="string_multiple", + description="Multiple string messages", + scene_data=[ + "这是第一条消息。", + "这是第二条消息。", + "这是第三条消息。", + ], + ), +] + +# ============================================================================ +# 3. Chat Message Cases (Standard & Multimodal) +# ============================================================================ + +CHAT_MESSAGE_CASES = [ + TestCase( + name="chat_simple", + description="Simple chat conversation", + scene_data=[ + [ + { + "role": "user", + "content": "Hello, how are you? I'm planning to learn Python next week.", + "chat_time": "2025-01-01T10:00:00Z", + "message_id": "chat_simple_u1", + }, + { + "role": "assistant", + "content": "I'm doing well, thank you!", + "chat_time": "2025-01-01T10:00:01Z", + "message_id": "chat_simple_a1", + }, + ] + ], + ), + TestCase( + name="chat_with_system", + description="Chat with system message", + scene_data=[ + [ + { + "role": "system", + "content": "You are a helpful assistant.", + "chat_time": "2025-01-01T10:00:00Z", + "message_id": "chat_sys_s1", + }, + { + "role": "user", + "content": "What's the weather?", + "chat_time": "2025-01-01T10:00:01Z", + "message_id": "chat_sys_u1", + }, + { + "role": "assistant", + "content": "I don't have access to weather data.", + "chat_time": "2025-01-01T10:00:02Z", + "message_id": "chat_sys_a1", + }, + ] + ], + ), + TestCase( + name="chat_multimodal_complex", + description="Complex multimodal chat with text, file, and image", + scene_data=[ + [ + { + "role": "user", + "content": [ + {"type": "text", "text": "我是测试base64"}, + { + "type": "file", + "file": { + "file_data": "Hello World", + "filename": "example.txt", + "file_id": "file_123", + }, + }, + { + "type": "image_url", + "image_url": { + "url": "https://statics.memtensor.com.cn/memos/memos-banner.gif", + "detail": "auto", + }, + }, + ], + "chat_time": "2025-01-01T10:00:03Z", + "message_id": "chat_mm_u1", + } + ] + ], + ), +] + + +# ============================================================================ +# 4. Tool Message Cases +# ============================================================================ + +TOOL_MESSAGE_CASES = [ + TestCase( + name="tool_weather", + description="Weather tool result", + scene_data=[ + { + "role": "user", + "content": "I'm planning a hiking trip to New York this weekend, can you check the weather?", + "chat_time": "2025-01-15T10:00:00", + "message_id": "msg_000", + }, + { + "role": "tool", + "content": '{"result": "Weather in New York: 72°F, sunny"}', + "tool_call_id": "call_abc123", + "chat_time": "2025-01-15T10:00:30", + "message_id": "msg_001", + }, + ], + ), + TestCase( + name="tool_data", + description="Data API result", + scene_data=[ + { + "role": "user", + "content": "Please retrieve my saved reading list items.", + "chat_time": "2025-01-15T10:05:00", + "message_id": "msg_000_2", + }, + { + "role": "tool", + "content": '{"status": "success", "data": {"items": ["The Great Gatsby", "1984", "Python Crash Course"]}}', + "tool_call_id": "call_def456", + "chat_time": "2025-01-15T10:05:30", + "message_id": "msg_002", + }, + ], + ), + TestCase( + name="tool_db", + description="Database query result", + scene_data=[ + { + "role": "user", + "content": "Did I complete the registration for the upcoming workshop?", + "chat_time": "2025-01-15T10:10:00", + "message_id": "msg_000_3", + }, + { + "role": "tool", + "content": "Database query executed successfully. Found registration record for user_id=123: status=confirmed.", + "tool_call_id": "call_ghi789", + "chat_time": "2025-01-15T10:10:30", + "message_id": "msg_003", + }, + ], + ), +] + +# ============================================================================ +# 5. File Content Samples (for FileContentParser Demo) +# ============================================================================ + +FILE_CONTENT_PARTS = [ + { + "type": "file", + "file": { + "filename": "document.pdf", + "file_id": "file_123", + "file_data": "This is the content extracted from the PDF file...", + }, + }, + { + "type": "file", + "file": { + "filename": "report.docx", + "file_id": "file_456", + "file_data": "Report content: Analysis of Q4 performance...", + }, + }, + { + "type": "file", + "file": { + "filename": "data.csv", + "file_id": "file_789", + "path": "/path/to/data.csv", + }, + }, +] + +FILE_CONTENT_REAL_FILE_PART = { + "type": "file", + "file": { + "filename": "example.txt", + "path": "examples/mem_reader/text1.txt", + }, +} + +# ============================================================================ +# 6. Text Content Samples (for TextContentParser Demo) +# ============================================================================ + +TEXT_CONTENT_PARTS = [ + {"type": "text", "text": "This is a simple text content part."}, + {"type": "text", "text": "TextContentParser handles text parts in multimodal messages."}, +] + +# ============================================================================ +# 7. System Message Samples (for SystemParser Demo) +# ============================================================================ + +SYSTEM_MESSAGE_CASES = [ + TestCase( + name="system_simple", + description="Simple text system message", + scene_data=[ + { + "role": "system", + "content": "You are a helpful assistant that provides clear and concise answers.", + "chat_time": "2025-01-15T10:00:00", + "message_id": "msg_001", + } + ], + ), + TestCase( + name="system_multimodal", + description="Multimodal system message (multiple text parts)", + scene_data=[ + { + "role": "system", + "content": [ + {"type": "text", "text": "You are a helpful assistant."}, + {"type": "text", "text": "Always provide clear and concise answers."}, + {"type": "text", "text": "If you don't know something, say so."}, + ], + "chat_time": "2025-01-15T10:05:00", + "message_id": "msg_002", + } + ], + ), + TestCase( + name="system_structured", + description="Structured system instructions (multiple text parts)", + scene_data=[ + { + "role": "system", + "content": [ + { + "type": "text", + "text": "You are a coding assistant specialized in Python programming.", + }, + {"type": "text", "text": "Always write clean, well-documented code."}, + {"type": "text", "text": "Explain your reasoning when providing solutions."}, + ], + "chat_time": "2025-01-15T10:10:00", + "message_id": "msg_003", + } + ], + ), +] + +# ============================================================================ +# 8. User Message Samples (for UserParser Demo) +# ============================================================================ + +USER_MESSAGE_CASES = [ + TestCase( + name="user_simple", + description="Simple text user message", + scene_data=[ + { + "role": "user", + "content": "I'm feeling a bit down today. Can you help me?", + "chat_time": "2025-01-15T10:00:00", + "message_id": "msg_001", + } + ], + ), + TestCase( + name="user_multimodal", + description="Multimodal user message (text + file)", + scene_data=[ + { + "role": "user", + "content": [ + {"type": "text", "text": "Please analyze this document:"}, + { + "type": "file", + "file": { + "filename": "report.pdf", + "file_id": "file_123", + "file_data": "This is the content of the PDF file...", + }, + }, + ], + "chat_time": "2025-01-15T10:05:00", + "message_id": "msg_002", + } + ], + ), + TestCase( + name="user_image", + description="User message with image", + scene_data=[ + { + "role": "user", + "content": [ + {"type": "text", "text": "What's in this image?"}, + {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}, + ], + "chat_time": "2025-01-15T10:10:00", + "message_id": "msg_003", + } + ], + ), +] + +# ============================================================================ +# 9. Assistant Message Samples (for AssistantParser Demo) +# ============================================================================ + +ASSISTANT_MESSAGE_CASES = [ + TestCase( + name="assistant_simple", + description="Simple support message", + scene_data=[ + { + "role": "assistant", + "content": "I'm sorry to hear that you're feeling down. Would you like to talk about what's been going on?", + "chat_time": "2025-01-15T10:00:30", + "message_id": "msg_001", + } + ], + ), + TestCase( + name="assistant_analysis", + description="Document analysis response", + scene_data=[ + { + "role": "assistant", + "content": "Based on the document you provided, I can see several key points: 1) The project timeline, 2) Budget considerations, and 3) Resource allocation.", + "chat_time": "2025-01-15T10:05:30", + "message_id": "msg_002", + } + ], + ), + TestCase( + name="assistant_code", + description="Code solution", + scene_data=[ + { + "role": "assistant", + "content": "Here's a Python solution for your problem:\n```python\ndef solve_problem():\n return 'solution'\n```", + "chat_time": "2025-01-15T10:10:30", + "message_id": "msg_003", + } + ], + ), +] + +# ============================================================================ +# 10. Image Samples (for ImageParser Demo) +# ============================================================================ + +IMAGE_MESSAGE_CASES = [ + { + "type": "image_url", + "image_url": { + "url": "https://statics.memtensor.com.cn/memos/memos-banner.gif", + "detail": "auto", + }, + "_note": "Real Image (MemOS Banner)", + }, + { + "type": "image", + "image_url": "https://example.com/image2.png", + "_note": "Dummy Image (Negative Test)", + }, +] + +# ============================================================================ +# 11. Multimodal Message Cases (from Legacy) +# ============================================================================ + +MULTIMODAL_MESSAGE_CASES = [ + TestCase( + name="multimodal_text_image", + description="User message with text and image", + scene_data=[ + [ + { + "role": "user", + "content": [ + {"type": "text", "text": "帮我看看这张图片大概是什么内容？"}, + { + "type": "image_url", + "image_url": { + "url": "https://example.com/mountain_lake.jpg", + "detail": "high", + }, + }, + ], + "chat_time": "2025-11-24T10:20:00Z", + "message_id": "mm-img-1", + } + ] + ], + ), + TestCase( + name="multimodal_text_file", + description="User message with text and file", + scene_data=[ + [ + { + "role": "user", + "content": [ + {"type": "text", "text": "请阅读这个PDF，总结里面的要点。"}, + {"type": "file", "file": {"file_id": "file_123", "filename": "report.pdf"}}, + ], + "chat_time": "2025-11-24T10:21:00Z", + "message_id": "mm-file-1", + } + ] + ], + ), + TestCase( + name="oss_text_file", + description="User message with text and file", + scene_data=[ + [ + { + "role": "user", + "content": [ + {"type": "text", "text": "请阅读这个PDF，总结里面的要点。"}, + { + "type": "file", + "file": { + "file_id": "file_123", + "filename": "report.pdf", + "file_data": "@http://139.196.232.20:9090/graph-test/algorithm/2025_11_13/1763043889_1763043782_PM1%E8%BD%A6%E9%97%B4PMT%E9%9D%B4%E5%8E%8B%E8%BE%B9%E5%8E%8B%E5%8E%8B%E5%8A%9B%E6%97%A0%E6%B3%95%E5%BB%BA%E7%AB%8B%E6%95%85%E9%9A%9C%E6%8A%A5%E5%91%8A20240720.md", + }, + }, + ], + "chat_time": "2025-11-24T10:21:00Z", + "message_id": "mm-file-1", + } + ] + ], + ), + TestCase( + name="pure_data_file", + description="User message with text and file", + scene_data=[ + [ + { + "role": "user", + "content": [ + {"type": "text", "text": "请阅读这个PDF，总结里面的要点。"}, + { + "type": "file", + "file": { + "file_id": "file_123", + "filename": "report.pdf", + "file_data": "明文记忆是系统与用户对话、操作等交互中动态习得，以及外部提供的、可显式管理的结构化知识形态，通常以文档、提示模板、图结构或用户规则等形式存在。它具备编辑性、可共享性与治理友好性，适合存储需要频繁修改、可审计或多方协同使用的信息。 在 MemOS 中，明文记忆可用于动态生成推理上下文、个性化偏好注入、多代理协作共享等场景，成为连接人类输入与模型认知的关键桥梁。激活记忆是指模型在推理过程中产生的瞬时性认知状态，包括 KV cache、隐藏层激活、注意力权重等中间张量结构。它通常用于维持上下文连续性、对话一致性与行为风格控制。 MemOS 将激活记忆抽象为可调度资源，支持按需唤醒、延迟卸载与结构变换。例如，某些上下文状态可以被压缩为“半结构化记忆片段”用于未来复用，也可以在任务级别转化为参数化模块，支持短期记忆的长期化演进。这一机制为模型行为一致性、风格保持与状态持续性提供了基础。", + }, + }, + ], + "chat_time": "2025-11-24T10:21:00Z", + "message_id": "mm-file-1", + } + ] + ], + ), + TestCase( + name="local_data_file", + description="User message with text and file", + scene_data=[ + [ + { + "role": "user", + "content": [ + {"type": "text", "text": "请阅读这个PDF，总结里面的要点。"}, + { + "type": "file", + "file": { + "file_id": "file_123", + "filename": "report.pdf", + "file_data": "./my_local_file/report.pdf", + }, + }, + ], + "chat_time": "2025-11-24T10:21:00Z", + "message_id": "mm-file-1", + } + ] + ], + ), + TestCase( + name="internet_file", + description="User message with text and file", + scene_data=[ + [ + { + "role": "user", + "content": [ + {"type": "text", "text": "请阅读这个PDF，总结里面的要点。"}, + { + "type": "file", + "file": { + "file_id": "file_123", + "filename": "report.pdf", + "file_data": "https://upload.wikimedia.org/wikipedia/commons/c/cb/NLC416-16jh004830-88775_%E7%B4%85%E6%A8%93%E5%A4%A2.pdf", + }, + }, + ], + "chat_time": "2025-11-24T10:21:00Z", + "message_id": "mm-file-1", + } + ] + ], + ), + TestCase( + name="multimodal_mixed", + description="Mixed multimodal message (text + file + image)", + scene_data=[ + [ + { + "role": "user", + "content": [ + {"type": "text", "text": "请同时分析这个报告和图表。"}, + { + "type": "file", + "file": {"file_id": "file_789", "filename": "analysis_report.pdf"}, + }, + { + "type": "image_url", + "image_url": {"url": "https://example.com/chart.png", "detail": "auto"}, + }, + ], + "chat_time": "2025-11-24T10:23:00Z", + "message_id": "mixed-1", + } + ] + ], + ), + TestCase( + name="multimodal_audio", + description="Audio-only message", + scene_data=[ + [ + { + "role": "user", + "content": [ + { + "type": "input_audio", + "input_audio": {"data": "base64_encoded_audio_here", "format": "mp3"}, + } + ], + "chat_time": "2025-11-24T10:22:00Z", + "message_id": "audio-1", + } + ] + ], + ), +] + +# ============================================================================ +# 12. Raw Input Cases (from Legacy) +# ============================================================================ + +RAW_INPUT_CASES = [ + TestCase( + name="raw_text_items", + description="Pure text input items without dialog context", + scene_data=[ + [ + {"type": "text", "text": "这是一段独立的文本输入，没有明确的对话上下文。"}, + {"type": "text", "text": "它依然会被抽取和写入明文记忆。"}, + ] + ], + ), + TestCase( + name="raw_file_item", + description="Pure file input by file_id", + scene_data=[ + [{"type": "file", "file": {"file_id": "file_uploaded_123", "filename": "document.pdf"}}] + ], + ), + TestCase( + name="file_only_file_id", + description="File with only file_id parameter", + scene_data=[[{"type": "file", "file": {"file_id": "file_only_id_123"}}]], + ), + TestCase( + name="file_only_filename", + description="File with only filename parameter", + scene_data=[[{"type": "file", "file": {"filename": "document_only.pdf"}}]], + ), + TestCase( + name="file_only_file_data_base64", + description="File with only file_data (base64 encoded)", + scene_data=[ + [ + { + "type": "file", + "file": { + "file_data": "data:application/pdf;base64,JVBERi0xLjQKJdPr6eEKMSAwIG9iago8PAovVHlwZSAvQ2F0YWxvZwovUGFnZXMgMiAwIFIKPj4KZW5kb2JqCjIgMCBvYmoKPDwKL1R5cGUgL1BhZ2VzCi9LaWRzIFszIDAgUl0KL0NvdW50IDEKPD4KZW5kb2JqCjMgMCBvYmoKPDwKL1R5cGUgL1BhZ2UKL1BhcmVudCAyIDAgUgovTWVkaWFCb3ggWzAgMCA2MTIgNzkyXQovUmVzb3VyY2VzIDw8Ci9Gb250IDw8Ci9GMSA0IDAgUgo+Pgo+PgovQ29udGVudHMgNSAwIFIKPj4KZW5kb2JqCjQgMCBvYmoKPDwKL1R5cGUgL0ZvbnQKL1N1YnR5cGUgL1R5cGUxCi9CYXNlRm9udCAvSGVsdmV0aWNhCj4+CmVuZG9iag==" + }, + } + ] + ], + ), + TestCase( + name="file_only_file_data_url", + description="File with only file_data (URL)", + scene_data=[ + [{"type": "file", "file": {"file_data": "https://example.com/documents/report.pdf"}}] + ], + ), + TestCase( + name="file_only_file_data_text", + description="File with only file_data (plain text content)", + scene_data=[ + [ + { + "type": "file", + "file": { + "file_data": "This is a plain text file content. It contains multiple lines.\nLine 2 of the file.\nLine 3 of the file." + }, + } + ] + ], + ), + TestCase( + name="file_file_data_and_file_id", + description="File with file_data and file_id", + scene_data=[ + [ + { + "type": "file", + "file": { + "file_data": "https://example.com/documents/data.pdf", + "file_id": "file_with_data_123", + }, + } + ] + ], + ), + TestCase( + name="file_file_data_and_filename", + description="File with file_data and filename", + scene_data=[ + [ + { + "type": "file", + "file": { + "file_data": "This is file content with filename.", + "filename": "content_file.txt", + }, + } + ] + ], + ), +] diff --git a/examples/mem_reader/settings.py b/examples/mem_reader/settings.py new file mode 100644 index 000000000..0623a91de --- /dev/null +++ b/examples/mem_reader/settings.py @@ -0,0 +1,107 @@ +"""Configuration settings for MemReader examples. + +This module handles environment variables and default configurations for +LLMs, Embedders, and Chunkers used in the examples. +""" + +import os + +from typing import Any + +from dotenv import load_dotenv + + +# Load environment variables from .env file +load_dotenv() + + +def get_llm_config() -> dict[str, Any]: + """Get LLM configuration from environment variables.""" + openai_api_key = os.getenv("OPENAI_API_KEY") + openai_base_url = os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1") + ollama_api_base = os.getenv("OLLAMA_API_BASE", "http://localhost:11434") + + # Use MEMRADER_ variables from .env as primary source + reader_model = os.getenv("MEMRADER_MODEL", os.getenv("MOS_CHAT_MODEL", "gpt-4o-mini")) + reader_api_key = os.getenv("MEMRADER_API_KEY", openai_api_key) + reader_api_base = os.getenv("MEMRADER_API_BASE", openai_base_url) + + # Check for specific MemReader backend override, otherwise assume openai if keys present + llm_backend = os.getenv("MEMRADER_LLM_BACKEND", "openai") + + if llm_backend == "ollama": + return { + "backend": "ollama", + "config": { + "model_name_or_path": reader_model, + "api_base": ollama_api_base, + "temperature": float(os.getenv("MEMRADER_TEMPERATURE", "0.0")), + "remove_think_prefix": os.getenv("MEMRADER_REMOVE_THINK_PREFIX", "true").lower() + == "true", + "max_tokens": int(os.getenv("MEMRADER_MAX_TOKENS", "8192")), + }, + } + else: # openai + return { + "backend": "openai", + "config": { + "model_name_or_path": reader_model, + "api_key": reader_api_key or "EMPTY", + "api_base": reader_api_base, + "temperature": float(os.getenv("MEMRADER_TEMPERATURE", "0.5")), + "remove_think_prefix": os.getenv("MEMRADER_REMOVE_THINK_PREFIX", "true").lower() + == "true", + "max_tokens": int(os.getenv("MEMRADER_MAX_TOKENS", "8192")), + }, + } + + +def get_embedder_config() -> dict[str, Any]: + """Get Embedder configuration from environment variables.""" + openai_api_key = os.getenv("OPENAI_API_KEY") + openai_base_url = os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1") + ollama_api_base = os.getenv("OLLAMA_API_BASE", "http://localhost:11434") + + # .env uses MOS_EMBEDDER_BACKEND + embedder_backend = os.getenv("MOS_EMBEDDER_BACKEND", "ollama") + + if embedder_backend == "universal_api": + return { + "backend": "universal_api", + "config": { + "provider": os.getenv("MOS_EMBEDDER_PROVIDER", "openai"), + "api_key": os.getenv("MOS_EMBEDDER_API_KEY", openai_api_key or "sk-xxxx"), + "model_name_or_path": os.getenv("MOS_EMBEDDER_MODEL", "text-embedding-3-large"), + "base_url": os.getenv("MOS_EMBEDDER_API_BASE", openai_base_url), + }, + } + else: # ollama + return { + "backend": "ollama", + "config": { + "model_name_or_path": os.getenv("MOS_EMBEDDER_MODEL", "nomic-embed-text:latest"), + "api_base": ollama_api_base, + }, + } + + +def get_chunker_config() -> dict[str, Any]: + """Get Chunker configuration from environment variables.""" + return { + "backend": "sentence", + "config": { + "tokenizer_or_token_counter": "gpt2", + "chunk_size": 512, + "chunk_overlap": 128, + "min_sentences_per_chunk": 1, + }, + } + + +def get_reader_config() -> dict[str, Any]: + """Get full reader configuration.""" + return { + "llm": get_llm_config(), + "embedder": get_embedder_config(), + "chunker": get_chunker_config(), + } diff --git a/examples/mem_reader/simple_struct_reader.py b/examples/mem_reader/simple_struct_reader.py deleted file mode 100644 index 72dc5fd05..000000000 --- a/examples/mem_reader/simple_struct_reader.py +++ /dev/null @@ -1,831 +0,0 @@ -import argparse -import json -import os -import time - -from typing import Any - -from dotenv import load_dotenv - -from memos.configs.mem_reader import SimpleStructMemReaderConfig -from memos.mem_reader.simple_struct import SimpleStructMemReader -from memos.memories.textual.item import ( - SourceMessage, - TextualMemoryItem, - TreeNodeTextualMemoryMetadata, -) - - -# Load environment variables from .env file -load_dotenv() - - -def print_textual_memory_item( - item: TextualMemoryItem, max_memory_length: int = 200, indent: int = 0 -): - """ - Print a TextualMemoryItem in a structured format. - - Args: - item: The TextualMemoryItem to print - max_memory_length: Maximum length of memory content to display - indent: Number of spaces for indentation - """ - indent_str = " " * indent - print(f"{indent_str}{'=' * 80}") - print(f"{indent_str}TextualMemoryItem") - print(f"{indent_str}{'=' * 80}") - print(f"{indent_str}ID: {item.id}") - print( - f"{indent_str}Memory: {item.memory[:max_memory_length]}{'...' if len(item.memory) > max_memory_length else ''}" - ) - print(f"{indent_str}Memory Length: {len(item.memory)} characters") - - # Print metadata - if hasattr(item.metadata, "user_id"): - print(f"{indent_str}User ID: {item.metadata.user_id}") - if hasattr(item.metadata, "session_id"): - print(f"{indent_str}Session ID: {item.metadata.session_id}") - if hasattr(item.metadata, "memory_type"): - print(f"{indent_str}Memory Type: {item.metadata.memory_type}") - if hasattr(item.metadata, "type"): - print(f"{indent_str}Type: {item.metadata.type}") - if hasattr(item.metadata, "key") and item.metadata.key: - print(f"{indent_str}Key: {item.metadata.key}") - if hasattr(item.metadata, "tags") and item.metadata.tags: - print(f"{indent_str}Tags: {', '.join(item.metadata.tags)}") - if hasattr(item.metadata, "confidence"): - print(f"{indent_str}Confidence: {item.metadata.confidence}") - if hasattr(item.metadata, "status"): - print(f"{indent_str}Status: {item.metadata.status}") - if hasattr(item.metadata, "background") and item.metadata.background: - bg_preview = ( - item.metadata.background[:100] + "..." - if len(item.metadata.background) > 100 - else item.metadata.background - ) - print(f"{indent_str}Background: {bg_preview}") - if hasattr(item.metadata, "sources") and item.metadata.sources: - print(f"{indent_str}Sources ({len(item.metadata.sources)}):") - for i, source in enumerate(item.metadata.sources): - source_info = [] - if hasattr(source, "type"): - source_info.append(f"type={source.type}") - if hasattr(source, "role"): - source_info.append(f"role={source.role}") - if hasattr(source, "doc_path"): - source_info.append(f"doc_path={source.doc_path}") - if hasattr(source, "chat_time"): - source_info.append(f"chat_time={source.chat_time}") - if hasattr(source, "index") and source.index is not None: - source_info.append(f"index={source.index}") - print(f"{indent_str} [{i + 1}] {', '.join(source_info)}") - if hasattr(item.metadata, "created_at"): - print(f"{indent_str}Created At: {item.metadata.created_at}") - if hasattr(item.metadata, "updated_at"): - print(f"{indent_str}Updated At: {item.metadata.updated_at}") - if hasattr(item.metadata, "embedding") and item.metadata.embedding: - print(f"{indent_str}Embedding: [vector of {len(item.metadata.embedding)} dimensions]") - print(f"{indent_str}{'=' * 80}\n") - - -def print_textual_memory_item_json(item: TextualMemoryItem, indent: int = 2): - """ - Print a TextualMemoryItem as formatted JSON. - - Args: - item: The TextualMemoryItem to print - indent: JSON indentation level - """ - # Convert to dict and exclude embedding for readability - data = item.to_dict() - if "metadata" in data and "embedding" in data["metadata"]: - embedding = data["metadata"]["embedding"] - if embedding: - data["metadata"]["embedding"] = f"[vector of {len(embedding)} dimensions]" - - print(json.dumps(data, indent=indent, ensure_ascii=False)) - - -def get_reader_config() -> dict[str, Any]: - """ - Get reader configuration from environment variables. - - Returns a dictionary that can be used to create SimpleStructMemReaderConfig. - Similar to APIConfig.get_reader_config() in server_router_api.py. - - Returns: - Configuration dictionary for SimpleStructMemReaderConfig - """ - openai_api_key = os.getenv("OPENAI_API_KEY") - openai_base_url = os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1") - ollama_api_base = os.getenv("OLLAMA_API_BASE", "http://localhost:11434") - - # Get LLM backend and config - llm_backend = os.getenv("MEM_READER_LLM_BACKEND", "openai") - if llm_backend == "ollama": - llm_config = { - "backend": "ollama", - "config": { - "model_name_or_path": os.getenv("MEM_READER_LLM_MODEL", "qwen3:0.6b"), - "api_base": ollama_api_base, - "temperature": float(os.getenv("MEM_READER_LLM_TEMPERATURE", "0.0")), - "remove_think_prefix": os.getenv( - "MEM_READER_LLM_REMOVE_THINK_PREFIX", "true" - ).lower() - == "true", - "max_tokens": int(os.getenv("MEM_READER_LLM_MAX_TOKENS", "8192")), - }, - } - else: # openai - llm_config = { - "backend": "openai", - "config": { - "model_name_or_path": os.getenv("MEM_READER_LLM_MODEL", "gpt-4o-mini"), - "api_key": openai_api_key or os.getenv("MEMRADER_API_KEY", "EMPTY"), - "api_base": openai_base_url, - "temperature": float(os.getenv("MEM_READER_LLM_TEMPERATURE", "0.5")), - "remove_think_prefix": os.getenv( - "MEM_READER_LLM_REMOVE_THINK_PREFIX", "true" - ).lower() - == "true", - "max_tokens": int(os.getenv("MEM_READER_LLM_MAX_TOKENS", "8192")), - }, - } - - # Get embedder backend and config - embedder_backend = os.getenv( - "MEM_READER_EMBEDDER_BACKEND", os.getenv("MOS_EMBEDDER_BACKEND", "ollama") - ) - if embedder_backend == "universal_api": - embedder_config = { - "backend": "universal_api", - "config": { - "provider": os.getenv( - "MEM_READER_EMBEDDER_PROVIDER", os.getenv("MOS_EMBEDDER_PROVIDER", "openai") - ), - "api_key": os.getenv( - "MEM_READER_EMBEDDER_API_KEY", - os.getenv("MOS_EMBEDDER_API_KEY", openai_api_key or "sk-xxxx"), - ), - "model_name_or_path": os.getenv( - "MEM_READER_EMBEDDER_MODEL", - os.getenv("MOS_EMBEDDER_MODEL", "text-embedding-3-large"), - ), - "base_url": os.getenv( - "MEM_READER_EMBEDDER_API_BASE", - os.getenv("MOS_EMBEDDER_API_BASE", openai_base_url), - ), - }, - } - else: # ollama - embedder_config = { - "backend": "ollama", - "config": { - "model_name_or_path": os.getenv( - "MEM_READER_EMBEDDER_MODEL", - os.getenv("MOS_EMBEDDER_MODEL", "nomic-embed-text:latest"), - ), - "api_base": ollama_api_base, - }, - } - - return { - "llm": llm_config, - "embedder": embedder_config, - "chunker": { - "backend": "sentence", - "config": { - "tokenizer_or_token_counter": "gpt2", - "chunk_size": 512, - "chunk_overlap": 128, - "min_sentences_per_chunk": 1, - }, - }, - } - - -def main(): - # Parse command line arguments - parser = argparse.ArgumentParser(description="Test Mem-Reader with structured output") - parser.add_argument( - "--format", - choices=["text", "json"], - default="text", - help="Output format: 'text' for structured text, 'json' for JSON format (default: text)", - ) - parser.add_argument( - "--max-memory-length", - type=int, - default=200, - help="Maximum length of memory content to display in text format (default: 200)", - ) - args = parser.parse_args() - - # 1. Create Configuration from environment variables or JSON file - # Try to get config from environment variables first - openai_api_key = os.getenv("OPENAI_API_KEY") - if openai_api_key: - # Use environment variables (similar to server_router_api.py) - config_dict = get_reader_config() - reader_config = SimpleStructMemReaderConfig.model_validate(config_dict) - else: - # Fall back to JSON file - reader_config = SimpleStructMemReaderConfig.from_json_file( - "examples/data/config/simple_struct_reader_config.json" - ) - reader = SimpleStructMemReader(reader_config) - - # 2. Define scene data - scene_data = [ - [ - {"role": "user", "chat_time": "3 May 2025", "content": "I'm feeling a bit down today."}, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "I'm sorry to hear that. Do you want to talk about what's been going on?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "It's just been a tough couple of days, you know? Everything feels a bit overwhelming, and I just can't seem to shake it off.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "It sounds like you're going through a lot right now. Sometimes it helps to talk things out. Is there something specific that's been weighing on you, or is it more of a general feeling?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "It's a mix, I guess. Work's been really stressful, and on top of that, I've been feeling kinda disconnected from the people around me.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "That can be really draining, especially when you're feeling isolated on top of the stress. Do you think there's something from your past that's contributing to how you're feeling now? Sometimes our emotions are tied to older experiences.", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "Yeah, now that you mention it… I've been thinking a lot about my childhood lately. I didn't have the easiest upbringing. My parents were always busy, and I often felt like I had to figure things out on my own. I remember one winter, I got really sick with a high fever. My parents were both working, and I didn't want to bother them. I just lay in bed, crying by myself, not knowing what to do.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "That must have been very lonely. Growing up without that support can really make you feel like you have to handle everything on your own. How do you think that experience has affected you now?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "Yeah, it was really lonely. I remember spending a lot of time doing things on my own, like drawing, because it was my only way to escape. I used to draw animals, and I created my own little world on paper. It was peaceful in a way, just me and my imagination, with no outside distractions.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "Drawing sounds like a beautiful way to express yourself and find some peace in that solitude. It must have been a very quiet and private world for you. Do you think that sense of loneliness from back then has shaped how you connect with others today?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "I think it has. I've always found it hard to let others in. I feel like I have to handle everything on my own. If I rely on someone else, I feel vulnerable, and I start to feel that loneliness again.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "It sounds like this was a protective mechanism that helped you cope with your feelings of loneliness back then. But as you've grown, it seems like this pattern might not be serving you as well anymore. Have you thought about trying to break this cycle, or finding new ways to connect with others?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "I've thought about it, though it's hard. But I also know I can't keep going like this forever. Maybe it's time to seek some help.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "It's a big step, but a positive one. Exploring your emotions and past experiences could really help you understand how they've shaped your present. Therapy could be a great place to start, as it would help you connect with both yourself and others. Would you be open to trying it?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "I'm open to trying. Thank you for encouraging me. It feels like it might be a good starting point for me.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "I'm really glad to hear that. Taking that first step is always difficult, but you've made an important decision. If you need help finding the right therapist, or just want to talk, I'm here for you.", - }, - ], - [ - { - "role": "user", - "chat_time": "3 May 2025", - "content": "This week I've been feeling a bit off, especially when playing tennis. My body just doesn't feel right.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "It sounds like you've been having some physical discomfort lately. Where specifically are you feeling unwell? Is there something particular about tennis that's been difficult?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "I just feel a bit fatigued, and every time I play tennis, my movements feel off. I used to play pretty well, but lately, I've been feeling weak and my movements aren't as coordinated as they used to be.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "Physical discomfort can definitely affect performance, especially in a sport like tennis that requires quick reactions and coordination. Have you noticed anything specific that might be causing these changes? Could it be overtraining, or is there another physical issue making you feel off?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "I think it might be due to stress and lack of sleep recently. I just feel drained all the time. Plus, I've been frustrated with my tennis performance, which makes me feel even worse, like I'm stuck in a vicious cycle.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "Stress and poor sleep quality can definitely affect your physical performance, especially in sports. When you're also feeling down about your performance, it's easy to fall into a negative cycle. Have you tried anything to relieve some of the stress, or to improve your sleep?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "I've tried some relaxation techniques, like deep breathing and simple meditation, but it doesn't seem to help much. I still can't focus during tennis, and I feel like my mind is distracted by other things.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "Relaxation techniques like deep breathing and meditation can help reduce stress, but sometimes we need a more structured approach to improve both our physical and mental state. For example, you might want to focus on specific aspects of your tennis training, or adjust your rest and recovery time. Have you thought about setting smaller goals for yourself? Like focusing on a specific tennis move each day, rather than expecting perfection right away? That might help you gradually regain confidence.", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "That's a good idea. I think I've been expecting too much from myself, which just makes me more anxious. Maybe I can start with small practice sessions and gradually find my rhythm again.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "Exactly! Setting small and clear goals will help reduce pressure and give you a sense of accomplishment. And don't forget that rest is just as important—taking time to recover will help you feel better physically and mentally. Both physical and mental recovery are key to improving your performance and health.", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "Thanks, I feel like I need to rethink a few things. Maybe I really need to be kinder to myself and take things step by step.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "You're on the right track. Rethinking things and giving yourself space and patience is so important. You've already taken the first step, now just keep moving forward, one step at a time. If you need anything, I'm always here to help.", - }, - ], - [ - { - "role": "user", - "chat_time": "3 May 2025", - "content": "Yesterday at 3 PM I had a meeting with my team about the new project. We discussed the timeline and I'm concerned we won't meet the deadline of December 15th.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "I understand your concern about the project timeline. What specific challenges do you think might prevent your team from meeting the December 15th deadline?", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "We have too many requirements to implement in just two weeks. The backend team needs at least until December 10th to finish their part, which leaves almost no time for testing before the deadline.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "That's definitely a tight timeline. Have you considered prioritizing the requirements to focus on the most critical features first? You might also want to discuss with stakeholders about possibly extending the deadline or reducing the scope for this initial release.", - }, - { - "role": "user", - "chat_time": "3 May 2025", - "content": "That's a good point. We have a follow-up meeting scheduled for tomorrow morning at 9:30 AM. I'll suggest we prioritize features and maybe propose pushing the deadline to January 5th next year.", - }, - { - "role": "assistant", - "chat_time": "3 May 2025", - "content": "That sounds like a solid approach. Coming to the meeting with both a prioritization strategy and a specific alternative deadline shows you've thought through the problem carefully. It might also help to bring some data about similar past projects and how long they took to complete, if you have that information available.", - }, - ], - ] - - print("=== Mem-Reader Fast vs Fine Mode Comparison ===\n") - - # 3. Test Fine Mode (default) - print("🔄 Testing FINE mode (default, with LLM processing)...") - start_time = time.time() - fine_memory = reader.get_memory( - scene_data, type="chat", info={"user_id": "user1", "session_id": "session1"}, mode="fine" - ) - fine_time = time.time() - start_time - print(f"✅ Fine mode completed in {fine_time:.2f} seconds") - print(f"📊 Fine mode generated {sum(len(mem_list) for mem_list in fine_memory)} memory items") - - # 4. Test Fast Mode - print("\n⚡ Testing FAST mode (quick processing, no LLM calls)...") - start_time = time.time() - fast_memory = reader.get_memory( - scene_data, type="chat", info={"user_id": "user1", "session_id": "session1"}, mode="fast" - ) - fast_time = time.time() - start_time - print(f"✅ Fast mode completed in {fast_time:.2f} seconds") - print(f"📊 Fast mode generated {sum(len(mem_list) for mem_list in fast_memory)} memory items") - - # 5. Performance Comparison - print("\n📈 Performance Comparison:") - print(f" Fine mode: {fine_time:.2f}s") - print(f" Fast mode: {fast_time:.2f}s") - print(f" Speed improvement: {fine_time / fast_time:.1f}x faster") - - # 6. Show sample results from both modes - print("\n🔍 Sample Results Comparison:") - print("\n--- FINE Mode Results (first 3 items) ---") - for i, mem_list in enumerate(fine_memory[:3]): - for j, mem_item in enumerate(mem_list[:2]): # Show first 2 items from each list - print(f"\n[Scene {i}][Item {j}]") - if args.format == "json": - print_textual_memory_item_json(mem_item, indent=2) - else: - print_textual_memory_item( - mem_item, max_memory_length=args.max_memory_length, indent=2 - ) - - print("\n--- FAST Mode Results (first 3 items) ---") - for i, mem_list in enumerate(fast_memory[:3]): - for j, mem_item in enumerate(mem_list[:2]): # Show first 2 items from each list - print(f"\n[Scene {i}][Item {j}]") - if args.format == "json": - print_textual_memory_item_json(mem_item, indent=2) - else: - print_textual_memory_item( - mem_item, max_memory_length=args.max_memory_length, indent=2 - ) - - # 7. Example of transfer fast mode result into fine result - fast_mode_memories = [ - TextualMemoryItem( - id="4553141b-3a33-4548-b779-e677ec797a9f", - memory="user: Nate:Oh cool! I might check that one out some time soon! I do love watching classics.\nassistant: Joanna:Yep, that movie is awesome. I first watched it around 3 years ago. I even went out and got a physical copy!\nuser: Nate:Sounds cool! Have you seen it a lot? sounds like you know the movie well!\nassistant: Joanna:A few times. It's one of my favorites! I really like the idea and the acting.\nuser: Nate:Cool! I'll definitely check it out. Thanks for the recommendation!\nassistant: Joanna:No problem, Nate! Let me know if you like it!\n", - metadata=TreeNodeTextualMemoryMetadata( - user_id="nate_test", - session_id="root_session", - status="activated", - type="fact", - key="user: Nate:Oh cool", - confidence=0.9900000095367432, - source=None, - tags=["mode:fast", "lang:en", "role:assistant", "role:user"], - visibility=None, - updated_at="2025-10-16T17:16:30.094877+08:00", - memory_type="LongTermMemory", - sources=[ - SourceMessage( - type="chat", - role="user", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=0, - ), - SourceMessage( - type="chat", - role="assistant", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=1, - ), - SourceMessage( - type="chat", - role="user", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=2, - ), - SourceMessage( - type="chat", - role="assistant", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=3, - ), - SourceMessage( - type="chat", - role="user", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=4, - ), - SourceMessage( - type="chat", - role="assistant", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=5, - ), - ], - embedding=None, - created_at="2025-10-16T17:16:30.094919+08:00", - usage=[], - background="", - ), - ), - TextualMemoryItem( - id="752e42fa-92b6-491a-a430-6864a7730fba", - memory="user: Nate:It was! How about you? Do you have any hobbies you love?\nassistant: Joanna:Yeah! Besides writing, I also enjoy reading, watching movies, and exploring nature. Anything else you enjoy doing, Nate?\nuser: Nate:Playing video games and watching movies are my main hobbies.\nassistant: Joanna:Cool, Nate! So we both have similar interests. What type of movies do you like best?\nuser: Nate:I love action and sci-fi movies, the effects are so cool! What about you, what's your favorite genre?\nassistant: Joanna:I'm all about dramas and romcoms. I love getting immersed in the feelings and plots.\nuser: Nate:Wow, movies can be so powerful! Do you have any recommendations for me?\nassistant: Joanna:Yeah, totally! Have you seen this romantic drama that's all about memory and relationships? It's such a good one.\nuser: Nate:Oh cool! I might check that one out some time soon! I do love watching classics.\nassistant: Joanna:Yep, that movie is awesome. I first watched it around 3 years ago. I even went out and got a physical copy!\n", - metadata=TreeNodeTextualMemoryMetadata( - user_id="nate_test", - session_id="root_session", - status="activated", - type="fact", - key="user: Nate:It was", - confidence=0.9900000095367432, - source=None, - tags=["mode:fast", "lang:en", "role:assistant", "role:user"], - visibility=None, - updated_at="2025-10-16T17:16:30.095726+08:00", - memory_type="LongTermMemory", - sources=[ - SourceMessage( - type="chat", - role="user", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=0, - ), - SourceMessage( - type="chat", - role="assistant", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=1, - ), - SourceMessage( - type="chat", - role="user", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=2, - ), - SourceMessage( - type="chat", - role="assistant", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=3, - ), - SourceMessage( - type="chat", - role="user", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=4, - ), - SourceMessage( - type="chat", - role="assistant", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=5, - ), - SourceMessage( - type="chat", - role="user", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=6, - ), - SourceMessage( - type="chat", - role="assistant", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=7, - ), - SourceMessage( - type="chat", - role="user", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=8, - ), - SourceMessage( - type="chat", - role="assistant", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=9, - ), - ], - embedding=None, - created_at="2025-10-16T17:16:30.095767+08:00", - usage=[], - background="", - ), - ), - TextualMemoryItem( - id="c9cf448c-deee-43a8-bafd-eb15fde535b2", - memory="user: Nate:Hey Joanna! Long time no see! What's up? Anything fun going on?\nassistant: Joanna:Hey Nate! Long time no see! I've been working on a project lately - it's been pretty cool. What about you - any fun projects or hobbies?\nuser: Nate:Hey Joanna! That's cool! I won my first video game tournament last week - so exciting!\nassistant: Joanna:Wow Nate! Congrats on winning! Tell me more - what game was it?\nuser: Nate:Thanks! it's a team shooter game.\nassistant: Joanna:Wow, great job! What was is called?\nuser: Nate:The game was called Counter-Strike: Global Offensive, and me and my team had a blast to the very end!\nassistant: Joanna:Cool, Nate! Sounds like a fun experience, even if I'm not into games.\nuser: Nate:It was! How about you? Do you have any hobbies you love?\nassistant: Joanna:Yeah! Besides writing, I also enjoy reading, watching movies, and exploring nature. Anything else you enjoy doing, Nate?\n", - metadata=TreeNodeTextualMemoryMetadata( - user_id="nate_test", - session_id="root_session", - status="activated", - type="fact", - key="user: Nate:Hey Joanna", - confidence=0.9900000095367432, - source=None, - tags=["mode:fast", "lang:en", "role:assistant", "role:user"], - visibility=None, - updated_at="2025-10-16T17:16:30.098208+08:00", - memory_type="LongTermMemory", - sources=[ - SourceMessage( - type="chat", - role="user", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=0, - ), - SourceMessage( - type="chat", - role="assistant", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=1, - ), - SourceMessage( - type="chat", - role="user", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=2, - ), - SourceMessage( - type="chat", - role="assistant", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=3, - ), - SourceMessage( - type="chat", - role="user", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=4, - ), - SourceMessage( - type="chat", - role="assistant", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=5, - ), - SourceMessage( - type="chat", - role="user", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=6, - ), - SourceMessage( - type="chat", - role="assistant", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=7, - ), - SourceMessage( - type="chat", - role="user", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=8, - ), - SourceMessage( - type="chat", - role="assistant", - chat_time="7:31 pm on 21 January, 2022", - message_id=None, - content=None, - doc_path=None, - index=9, - ), - ], - embedding=None, - created_at="2025-10-16T17:16:30.098246+08:00", - usage=[], - background="", - ), - ), - ] - fine_memories = reader.fine_transfer_simple_mem(fast_mode_memories, type="chat") - print("\n--- Transfer Mode Results (first 3 items) ---") - for i, mem_list in enumerate(fine_memories[:3]): - for j, mem_item in enumerate(mem_list[:2]): # Show first 2 items from each list - print(f"\n[Scene {i}][Item {j}]") - if args.format == "json": - print_textual_memory_item_json(mem_item, indent=2) - else: - print_textual_memory_item( - mem_item, max_memory_length=args.max_memory_length, indent=2 - ) - - # 7. Example of processing documents (only in fine mode) - print("\n=== Processing Documents (Fine Mode Only) ===") - # Example document paths (you should replace these with actual document paths) - doc_paths = [ - "text1.txt", - "text2.txt", - ] - - try: - # 6. Acquiring memories from documents - doc_memory = reader.get_memory( - doc_paths, - "doc", - info={ - "user_id": "1111", - "session_id": "2222", - }, - mode="fine", - ) - total_items = sum(len(mem_list) for mem_list in doc_memory) - print(f"\n📄 Document Memory generated {total_items} items") - - # Print structured document memory items - if doc_memory: - print("\n--- Document Memory Items (first 3) ---") - for i, mem_list in enumerate(doc_memory[:3]): - for j, mem_item in enumerate(mem_list[:3]): # Show first 3 items from each document - print(f"\n[Document {i}][Item {j}]") - if args.format == "json": - print_textual_memory_item_json(mem_item, indent=2) - else: - print_textual_memory_item( - mem_item, max_memory_length=args.max_memory_length, indent=2 - ) - except Exception as e: - print(f"⚠️ Document processing failed: {e}") - print(" (This is expected if document files don't exist)") - - print("\n🎯 Summary:") - print(f" • Fast mode: {fast_time:.2f}s - Quick processing, no LLM calls") - print(f" • Fine mode: {fine_time:.2f}s - Full LLM processing for better understanding") - print(" • Use fast mode for: Real-time applications, high-throughput scenarios") - print(" • Use fine mode for: Quality analysis, detailed memory extraction") - - -if __name__ == "__main__": - main() diff --git a/examples/mem_reader/utils.py b/examples/mem_reader/utils.py new file mode 100644 index 000000000..0ac3e4d6a --- /dev/null +++ b/examples/mem_reader/utils.py @@ -0,0 +1,84 @@ +"""Utility functions for MemReader examples.""" + +import json +import pprint + +from typing import Any + +from memos.memories.textual.item import TextualMemoryItem + + +def _truncate(s: str, max_len: int | None) -> str: + if max_len is None or len(s) <= max_len: + return s + return s[:max_len] + "..." + + +def sanitize_for_print(obj: Any, *, max_str_len: int | None = 500) -> Any: + """ + Recursively sanitize data for pretty printing: + - Long strings are truncated + - Strings keep real newlines (so box printer can render multi-line) + """ + if isinstance(obj, str): + return _truncate(obj, max_str_len) + if isinstance(obj, dict): + return {k: sanitize_for_print(v, max_str_len=max_str_len) for k, v in obj.items()} + if isinstance(obj, list): + return [sanitize_for_print(v, max_str_len=max_str_len) for v in obj] + if isinstance(obj, tuple): + return tuple(sanitize_for_print(v, max_str_len=max_str_len) for v in obj) + return obj + + +def pretty_print_dict(d: dict, *, max_str_len: int | None = 500): + """Print a dictionary in a pretty bordered box (handles multiline strings).""" + d2 = sanitize_for_print(d, max_str_len=max_str_len) + + # Prefer JSON formatting if possible, fallback to pprint + try: + text = json.dumps(d2, indent=2, ensure_ascii=False) + except (TypeError, ValueError): + text = pprint.pformat(d2, indent=2, width=120) + + # Expand the JSON/pprint output into lines + lines: list[str] = [] + for line in text.splitlines(): + # If a line itself contains literal "\n" sequences (rare), leave it; + # real newlines are already split by splitlines(). + lines.append(line) + + # Prevent extremely wide boxes (optional safety) + max_len = max(len(line) for line in lines) if lines else 0 + border = "═" * (max_len + 4) + + print(f"╔{border}╗") + for line in lines: + print(f"║ {line.ljust(max_len)} ║") + print(f"╚{border}╝") + + +def print_memory_item( + item: TextualMemoryItem, + indent: int = 0, + max_memory_length: int | None = 300, # None = 不截断 +): + """Print a TextualMemoryItem in a structured format.""" + prefix = " " * indent + print(f"{prefix}--- Memory Item ---") + print(f"{prefix}Type: {item.metadata.memory_type}") + + mem = item.memory or "" + mem_preview = mem if max_memory_length is None else _truncate(mem, max_memory_length) + print(f"{prefix}Memory: {mem_preview}") + + if item.metadata.tags: + print(f"{prefix}Tags: {item.metadata.tags}") + + if item.metadata.confidence is not None: + print(f"{prefix}Confidence: {item.metadata.confidence}") + + if hasattr(item.metadata, "sources") and item.metadata.sources: + print(f"{prefix}Sources ({len(item.metadata.sources)}):") + for source in item.metadata.sources: + print(f"{prefix} - {source.type} (role: {getattr(source, 'role', 'N/A')})") From 1844b962a7a7edb9ac0f2eefe655ae2d2e0349c2 Mon Sep 17 00:00:00 2001 From: HanshuZhou <118414084+zhouhanshu@users.noreply.github.com> Date: Fri, 16 Jan 2026 16:53:16 +0800 Subject: [PATCH 39/47] update example of mem_chat (#892) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Co-authored-by: 周函数 --- ...t_w_generated_cube_explicit_memory_only.py | 231 ++++++++++-------- examples/mem_chat/simple_mem_chat.py | 33 --- 2 files changed, 126 insertions(+), 138 deletions(-) delete mode 100644 examples/mem_chat/simple_mem_chat.py diff --git a/examples/mem_chat/chat_w_generated_cube_explicit_memory_only.py b/examples/mem_chat/chat_w_generated_cube_explicit_memory_only.py index a1cce6e8a..2c72fd192 100644 --- a/examples/mem_chat/chat_w_generated_cube_explicit_memory_only.py +++ b/examples/mem_chat/chat_w_generated_cube_explicit_memory_only.py @@ -1,127 +1,148 @@ +import os +import sys + + +# Add project root to python path to ensure src modules can be imported +sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../../../src"))) + from memos.configs.mem_chat import MemChatConfigFactory from memos.configs.mem_cube import GeneralMemCubeConfig from memos.mem_chat.factory import MemChatFactory from memos.mem_cube.general import GeneralMemCube -mem_chat_config = MemChatConfigFactory.model_validate( - { - "backend": "simple", - "config": { - "user_id": "user_123", - "chat_llm": { - "backend": "ollama", - "config": { - "model_name_or_path": "qwen3:1.7b", - "temperature": 0.0, - "remove_think_prefix": True, - "max_tokens": 4096, - }, - }, - "max_turns_window": 20, - "top_k": 5, - "enable_textual_memory": True, - "enable_activation_memory": False, - "enable_parametric_memory": False, - }, - } -) -mem_chat = MemChatFactory.from_config(mem_chat_config) - -# Initialize_memory_cube -config = GeneralMemCubeConfig.model_validate( - { - "user_id": "user03alice", - "cube_id": "user03alice/mem_cube_tree", - "text_mem": { - "backend": "tree_text", - "config": { - "extractor_llm": { - "backend": "ollama", - "config": { - "model_name_or_path": "qwen3:1.7b", - "temperature": 0.0, - "remove_think_prefix": True, - "max_tokens": 8192, - }, - }, - "dispatcher_llm": { - "backend": "ollama", - "config": { - "model_name_or_path": "qwen3:1.7b", - "temperature": 0.0, - "remove_think_prefix": True, - "max_tokens": 8192, - }, - }, - "graph_db": { - "backend": "neo4j", - "config": { - "uri": "bolt://localhost:7687", - "user": "neo4j", - "password": "12345678", - "db_name": "user03alice_mem_cube_3", - "auto_create": True, - }, - }, - "embedder": { - "backend": "ollama", - "config": { - "model_name_or_path": "nomic-embed-text:latest", - }, - }, - }, - }, - "act_mem": { - "backend": "kv_cache", +def get_mem_chat_config() -> MemChatConfigFactory: + """ + Generates the configuration object for MemChat. + + MemChat is the top-level component for user interaction, responsible for managing the conversation flow, + invoking the LLM, and interacting with the memory module. + The configuration includes: + - user_id: User identifier + - chat_llm: LLM configuration used for chat (uses OpenAI compatible interface here) + - max_turns_window: Size of the conversation history window + - enable_textual_memory: Whether to enable textual memory (Explicit Memory) + """ + return MemChatConfigFactory.model_validate( + { + "backend": "simple", "config": { - "memory_filename": "activation_memory.pickle", - "extractor_llm": { - "backend": "huggingface", + "user_id": "user_123", + "chat_llm": { + "backend": "openai", "config": { - "model_name_or_path": "Qwen/Qwen3-1.7B", + # Prioritize getting sensitive information and model configuration from environment variables + "model_name_or_path": os.getenv("MOS_CHAT_MODEL", "gpt-4o"), "temperature": 0.8, "max_tokens": 1024, "top_p": 0.9, "top_k": 50, - "add_generation_prompt": True, - "remove_think_prefix": False, + "api_key": os.getenv("OPENAI_API_KEY"), + "api_base": os.getenv("OPENAI_API_BASE"), }, }, + "max_turns_window": 20, + "top_k": 5, + # Enable textual memory functionality, allowing the system to retrieve and store explicit memories + "enable_textual_memory": True, + # This example demonstrates only explicit memory, so activation memory and parametric memory are disabled + "enable_activation_memory": False, + "enable_parametric_memory": False, }, - }, - "para_mem": { - "backend": "lora", - "config": { - "memory_filename": "parametric_memory.adapter", - "extractor_llm": { - "backend": "huggingface", - "config": { - "model_name_or_path": "Qwen/Qwen3-1.7B", - "temperature": 0.8, - "max_tokens": 1024, - "top_p": 0.9, - "top_k": 50, - "add_generation_prompt": True, - "remove_think_prefix": False, + } + ) + + +def get_mem_cube_config() -> GeneralMemCubeConfig: + """ + Generates the configuration object for GeneralMemCube. + + MemCube (Memory Cube) is the core storage and management unit for memory. + GeneralMemCube is a general implementation of the memory cube, supporting extraction, vectorized storage, and retrieval of textual memory. + The configuration includes: + - user_id / cube_id: Identifiers for the user and the cube to which the memory belongs + - text_mem: Specific configuration for textual memory + - extractor_llm: LLM used to extract memory fragments from the conversation + - vector_db: Database used to store memory vectors (uses Qdrant here) + - embedder: Model used to generate text vectors (uses OpenAI compatible interface here) + """ + return GeneralMemCubeConfig.model_validate( + { + "user_id": "user03alice", + "cube_id": "user03alice/mem_cube_tree", + "text_mem": { + "backend": "general_text", + "config": { + "cube_id": "user03alice/mem_cube_general", + "memory_filename": "textual_memory.json", + "extractor_llm": { + "backend": "openai", + "config": { + "model_name_or_path": os.getenv("MOS_CHAT_MODEL", "gpt-4o"), + "temperature": 0.8, + "max_tokens": 1024, + "top_p": 0.9, + "top_k": 50, + "api_key": os.getenv("OPENAI_API_KEY"), + "api_base": os.getenv("OPENAI_API_BASE"), + }, + }, + "vector_db": { + "backend": "qdrant", + "config": { + "collection_name": "user03alice_mem_cube_general", + "vector_dimension": 1024, + "distance_metric": "cosine", + }, + }, + "embedder": { + "backend": os.getenv("MOS_EMBEDDER_BACKEND", "universal_api"), + "config": { + "provider": "openai", + "api_key": os.getenv("MOS_EMBEDDER_API_KEY", "EMPTY"), + "model_name_or_path": os.getenv("MOS_EMBEDDER_MODEL", "bge-m3"), + "base_url": os.getenv("MOS_EMBEDDER_API_BASE"), + }, }, }, }, - }, - }, -) + } + ) + + +def main(): + """ + Main program entry point: + 1. Initialize MemChat (Conversation Controller) + 2. Initialize MemCube (Memory Storage) + 3. Mount MemCube to MemChat + 4. Start the chat loop + 5. Save memory after the chat ends + """ + print("Initializing MemChat...") + mem_chat_config = get_mem_chat_config() + mem_chat = MemChatFactory.from_config(mem_chat_config) + + print("Initializing MemCube...") + mem_cube_config = get_mem_cube_config() + mem_cube = GeneralMemCube(mem_cube_config) -# Initialize the MemCube with the configuration -mem_cube = GeneralMemCube(config) + # Mount the initialized memory cube onto the chat system + # This allows MemChat to perform memory retrieval (search) and organization (organize) via mem_cube during the conversation + mem_chat.mem_cube = mem_cube -# TODO: Read memory and prepare data -# Hope to read user docs and save in a file + print("Starting Chat Session...") + try: + mem_chat.run() + except KeyboardInterrupt: + print("\nChat session interrupted.") + finally: + # Ensure memory is persisted to disk before the program exits + # The dump method saves the in-memory memory state to the specified path + print("Saving memory cube...") + mem_chat.mem_cube.dump("new_cube_path") + print("Memory cube saved to 'new_cube_path'.") -# TODO: Organize MemoryCube -# Call Tree.add() -# save in memory cube -# chat and search and organize -mem_chat.mem_cube = mem_cube -mem_chat.run() -mem_chat.mem_cube.dump("new_cube_path") +if __name__ == "__main__": + main() diff --git a/examples/mem_chat/simple_mem_chat.py b/examples/mem_chat/simple_mem_chat.py deleted file mode 100644 index a6b4f5cbe..000000000 --- a/examples/mem_chat/simple_mem_chat.py +++ /dev/null @@ -1,33 +0,0 @@ -from memos.configs.mem_chat import MemChatConfigFactory -from memos.mem_chat.factory import MemChatFactory -from memos.mem_cube.general import GeneralMemCube - - -config = MemChatConfigFactory.model_validate( - { - "backend": "simple", - "config": { - "user_id": "user_123", - "chat_llm": { - "backend": "huggingface", - "config": { - "model_name_or_path": "Qwen/Qwen3-1.7B", - "temperature": 0.1, - "remove_think_prefix": True, - "max_tokens": 4096, - }, - }, - "max_turns_window": 20, - "top_k": 5, - "enable_textual_memory": True, - "enable_activation_memory": False, - "enable_parametric_memory": False, - }, - } -) -mem_chat = MemChatFactory.from_config(config) -mem_chat.mem_cube = GeneralMemCube.init_from_dir("examples/data/mem_cube_2") - -mem_chat.run() - -mem_chat.mem_cube.dump("tmp/mem_cube") From b12e41b7619cb8baf25c7149a62e75f3ea2d4b06 Mon Sep 17 00:00:00 2001 From: Wenqiang Wei Date: Sun, 18 Jan 2026 16:12:18 +0800 Subject: [PATCH 40/47] fix: example config bug --- examples/data/config/tree_config_shared_database.json | 2 +- src/memos/llms/hf.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/data/config/tree_config_shared_database.json b/examples/data/config/tree_config_shared_database.json index a0a9bc3a3..6dd1a9220 100644 --- a/examples/data/config/tree_config_shared_database.json +++ b/examples/data/config/tree_config_shared_database.json @@ -58,6 +58,6 @@ "WorkingMemory": 200, "LongTermMemory": 20000, "UserMemory": 30000 - } + }, "memory_filename": "tree_textual_memories.json" } diff --git a/src/memos/llms/hf.py b/src/memos/llms/hf.py index b5fc4ba13..0dd841c1a 100644 --- a/src/memos/llms/hf.py +++ b/src/memos/llms/hf.py @@ -51,7 +51,7 @@ def __init__(self, config: HFLLMConfig): self.config.model_name_or_path, torch_dtype="auto", device_map="auto" ) self.tokenizer = AutoTokenizer.from_pretrained( - self.config.model_name_or_path, use_fast=True + self.config.model_name_or_path, use_fast=True, force_download=True ) # Logits processors for sampling From 48e11da21ad0abc32d3ccc60d0187feb52e12768 Mon Sep 17 00:00:00 2001 From: bittergreen Date: Sun, 18 Jan 2026 19:15:06 +0800 Subject: [PATCH 41/47] docs: Delete deprecated examples. --- examples/basic_modules/nebular_example.py | 361 ------------------ examples/basic_modules/parser.py | 15 - .../tree_textual_memory_reasoner.py | 167 -------- 3 files changed, 543 deletions(-) delete mode 100644 examples/basic_modules/nebular_example.py delete mode 100644 examples/basic_modules/parser.py delete mode 100644 examples/basic_modules/tree_textual_memory_reasoner.py diff --git a/examples/basic_modules/nebular_example.py b/examples/basic_modules/nebular_example.py deleted file mode 100644 index 13f88e3f3..000000000 --- a/examples/basic_modules/nebular_example.py +++ /dev/null @@ -1,361 +0,0 @@ -import json -import os - -from datetime import datetime, timezone - -import numpy as np - -from dotenv import load_dotenv - -from memos.configs.embedder import EmbedderConfigFactory -from memos.configs.graph_db import GraphDBConfigFactory -from memos.embedders.factory import EmbedderFactory -from memos.graph_dbs.factory import GraphStoreFactory -from memos.memories.textual.item import TextualMemoryItem, TreeNodeTextualMemoryMetadata - - -load_dotenv() - - -def show(nebular_data): - from memos.configs.graph_db import Neo4jGraphDBConfig - from memos.graph_dbs.neo4j import Neo4jGraphDB - - tree_config = Neo4jGraphDBConfig.from_json_file("../../examples/data/config/neo4j_config.json") - tree_config.use_multi_db = True - tree_config.db_name = "nebular-show2" - - neo4j_db = Neo4jGraphDB(tree_config) - neo4j_db.clear() - neo4j_db.import_graph(nebular_data) - - -embedder_config = EmbedderConfigFactory.model_validate( - { - "backend": "universal_api", - "config": { - "provider": "openai", - "api_key": os.getenv("OPENAI_API_KEY", "sk-xxxxx"), - "model_name_or_path": "text-embedding-3-large", - "base_url": os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1"), - }, - } -) -embedder = EmbedderFactory.from_config(embedder_config) -embedder_dimension = 3072 - - -def embed_memory_item(memory: str) -> list[float]: - embedding = embedder.embed([memory])[0] - embedding_np = np.array(embedding, dtype=np.float32) - embedding_list = embedding_np.tolist() - return embedding_list - - -def example_shared_db(db_name: str = "shared-traval-group"): - """ - Example: Single(Shared)-DB multi-tenant (logical isolation) - Multiple users' data in the same Neo4j DB with user_name as a tag. - """ - # users - user_list = ["travel_member_alice", "travel_member_bob"] - - for user_name in user_list: - # Step 1: Build factory config - config = GraphDBConfigFactory( - backend="nebular", - config={ - "uri": json.loads(os.getenv("NEBULAR_HOSTS", "localhost")), - "user": os.getenv("NEBULAR_USER", "root"), - "password": os.getenv("NEBULAR_PASSWORD", "xxxxxx"), - "space": db_name, - "user_name": user_name, - "use_multi_db": False, - "auto_create": True, - "embedding_dimension": embedder_dimension, - }, - ) - - # Step 2: Instantiate graph store - graph = GraphStoreFactory.from_config(config) - print(f"\n[INFO] Working in shared DB: {db_name}, for user: {user_name}") - graph.clear() - - # Step 3: Create topic node - topic = TextualMemoryItem( - memory="This research addresses long-term multi-UAV navigation for energy-efficient communication coverage.", - metadata=TreeNodeTextualMemoryMetadata( - memory_type="LongTermMemory", - key="Multi-UAV Long-Term Coverage", - hierarchy_level="topic", - type="fact", - memory_time="2024-01-01", - source="file", - sources=["paper://multi-uav-coverage/intro"], - status="activated", - confidence=95.0, - tags=["UAV", "coverage", "multi-agent"], - entities=["UAV", "coverage", "navigation"], - visibility="public", - updated_at=datetime.now().isoformat(), - embedding=embed_memory_item( - "This research addresses long-term " - "multi-UAV navigation for " - "energy-efficient communication " - "coverage." - ), - ), - ) - - graph.add_node( - id=topic.id, memory=topic.memory, metadata=topic.metadata.model_dump(exclude_none=True) - ) - - # Step 4: Add a concept for each user - concept = TextualMemoryItem( - memory=f"Itinerary plan for {user_name}", - metadata=TreeNodeTextualMemoryMetadata( - memory_type="LongTermMemory", - key="Multi-UAV Long-Term Coverage", - hierarchy_level="concept", - type="fact", - memory_time="2024-01-01", - source="file", - sources=["paper://multi-uav-coverage/intro"], - status="activated", - confidence=95.0, - tags=["UAV", "coverage", "multi-agent"], - entities=["UAV", "coverage", "navigation"], - visibility="public", - updated_at=datetime.now().isoformat(), - embedding=embed_memory_item(f"Itinerary plan for {user_name}"), - ), - ) - - graph.add_node( - id=concept.id, - memory=concept.memory, - metadata=concept.metadata.model_dump(exclude_none=True), - ) - - # Link concept to topic - graph.add_edge(source_id=concept.id, target_id=topic.id, type="RELATE_TO") - print(f"[INFO] Added nodes for {user_name}") - - # Step 5: Query and print ALL for verification - print("\n=== Export entire DB (for verification, includes ALL users) ===") - graph = GraphStoreFactory.from_config(config) - all_graph_data = graph.export_graph() - print(str(all_graph_data)[:1000]) - - # Step 6: Search for alice's data only - print("\n=== Search for travel_member_alice ===") - config_alice = GraphDBConfigFactory( - backend="nebular", - config={ - "uri": json.loads(os.getenv("NEBULAR_HOSTS", "localhost")), - "user": os.getenv("NEBULAR_USER", "root"), - "password": os.getenv("NEBULAR_PASSWORD", "xxxxxx"), - "space": db_name, - "user_name": user_list[0], - "auto_create": True, - "embedding_dimension": embedder_dimension, - "use_multi_db": False, - }, - ) - graph_alice = GraphStoreFactory.from_config(config_alice) - nodes = graph_alice.search_by_embedding(vector=embed_memory_item("travel itinerary"), top_k=3) - for node in nodes: - print(str(graph_alice.get_node(node["id"]))[:1000]) - - -def run_user_session( - user_name: str, - db_name: str, - topic_text: str, - concept_texts: list[str], - fact_texts: list[str], -): - print(f"\n=== {user_name} starts building their memory graph ===") - - # Manually initialize correct GraphDB class - config = GraphDBConfigFactory( - backend="nebular", - config={ - "uri": json.loads(os.getenv("NEBULAR_HOSTS", "localhost")), - "user": os.getenv("NEBULAR_USER", "root"), - "password": os.getenv("NEBULAR_PASSWORD", "xxxxxx"), - "space": db_name, - "user_name": user_name, - "use_multi_db": False, - "auto_create": True, - "embedding_dimension": embedder_dimension, - }, - ) - graph = GraphStoreFactory.from_config(config) - - # Start with a clean slate for this user - graph.clear() - - now = datetime.now(timezone.utc).isoformat() - - # === Step 1: Create a root topic node (e.g., user's research focus) === - topic = TextualMemoryItem( - memory=topic_text, - metadata=TreeNodeTextualMemoryMetadata( - memory_type="LongTermMemory", - key="Research Topic", - hierarchy_level="topic", - type="fact", - memory_time="2024-01-01", - status="activated", - visibility="public", - tags=["research", "rl"], - updated_at=now, - embedding=embed_memory_item(topic_text), - ), - ) - graph.add_node(topic.id, topic.memory, topic.metadata.model_dump(exclude_none=True)) - - # === Step 2: Create two concept nodes linked to the topic === - concept_items = [] - for i, text in enumerate(concept_texts): - concept = TextualMemoryItem( - memory=text, - metadata=TreeNodeTextualMemoryMetadata( - memory_type="LongTermMemory", - key=f"Concept {i + 1}", - hierarchy_level="concept", - type="fact", - memory_time="2024-01-01", - status="activated", - visibility="public", - updated_at=now, - embedding=embed_memory_item(text), - tags=["concept"], - confidence=90 + i, - ), - ) - graph.add_node(concept.id, concept.memory, concept.metadata.model_dump(exclude_none=True)) - graph.add_edge(topic.id, concept.id, type="PARENT") - concept_items.append(concept) - - # === Step 3: Create supporting facts under each concept === - for i, text in enumerate(fact_texts): - fact = TextualMemoryItem( - memory=text, - metadata=TreeNodeTextualMemoryMetadata( - memory_type="WorkingMemory", - key=f"Fact {i + 1}", - hierarchy_level="fact", - type="fact", - memory_time="2024-01-01", - status="activated", - visibility="public", - updated_at=now, - embedding=embed_memory_item(text), - confidence=85.0, - tags=["fact"], - ), - ) - graph.add_node(fact.id, fact.memory, fact.metadata.model_dump(exclude_none=True)) - graph.add_edge(concept_items[i % len(concept_items)].id, fact.id, type="PARENT") - - # === Step 4: Retrieve memory using semantic search === - vector = embed_memory_item("How is memory retrieved?") - search_result = graph.search_by_embedding(vector, top_k=2) - for r in search_result: - node = graph.get_node(r["id"]) - print("🔍 Search result:", node["memory"]) - - # === Step 5: Tag-based neighborhood discovery === - neighbors = graph.get_neighbors_by_tag(["concept"], exclude_ids=[], top_k=2) - print("📎 Tag-related nodes:", [neighbor["memory"] for neighbor in neighbors]) - - # === Step 6: Retrieve children (facts) of first concept === - children = graph.get_children_with_embeddings(concept_items[0].id) - print("📍 Children of concept:", [child["memory"] for child in children]) - - # === Step 7: Export a local subgraph and grouped statistics === - subgraph = graph.get_subgraph(topic.id, depth=2) - print("📌 Subgraph node count:", len(subgraph["neighbors"])) - - stats = graph.get_grouped_counts(["memory_type", "status"]) - print("📊 Grouped counts:", stats) - - # === Step 8: Demonstrate updates and cleanup === - graph.update_node( - concept_items[0].id, {"confidence": 99.0, "created_at": "2025-07-24T20:11:56.375687"} - ) - graph.remove_oldest_memory("WorkingMemory", keep_latest=1) - graph.delete_edge(topic.id, concept_items[0].id, type="PARENT") - graph.delete_node(concept_items[1].id) - - # === Step 9: Export and re-import the entire graph structure === - exported = graph.export_graph() - graph.import_graph(exported) - print("📦 Graph exported and re-imported, total nodes:", len(exported["nodes"])) - - # ==================================== - # 🔍 Step 10: extra function - # ==================================== - print(f"\n=== 🔍 Extra Tests for user: {user_name} ===") - - print(" - Memory count:", graph.get_memory_count("LongTermMemory")) - print(" - Node count:", graph.count_nodes("LongTermMemory")) - print(" - All LongTermMemory items:", graph.get_all_memory_items("LongTermMemory")) - - if len(exported["edges"]) > 0: - n1, n2 = exported["edges"][0]["source"], exported["edges"][0]["target"] - print(" - Edge exists?", graph.edge_exists(n1, n2, exported["edges"][0]["type"])) - print(" - Edges for node:", graph.get_edges(n1)) - - filters = [{"field": "memory_type", "op": "=", "value": "LongTermMemory"}] - print(" - Metadata query result:", graph.get_by_metadata(filters)) - print( - " - Optimization candidates:", graph.get_structure_optimization_candidates("LongTermMemory") - ) - try: - graph.drop_database() - except ValueError as e: - print(" - drop_database raised ValueError as expected:", e) - - -def example_complex_shared_db(db_name: str = "shared-traval-group-complex"): - # User 1: Alice explores structured memory for LLMs - run_user_session( - user_name="alice", - db_name=db_name, - topic_text="Alice studies structured memory and long-term memory optimization in LLMs.", - concept_texts=[ - "Short-term memory can be simulated using WorkingMemory blocks.", - "A structured memory graph improves retrieval precision for agents.", - ], - fact_texts=[ - "Embedding search is used to find semantically similar memory items.", - "User memories are stored as node-edge structures that support hierarchical reasoning.", - ], - ) - - # User 2: Bob focuses on GNN-based reasoning - run_user_session( - user_name="bob", - db_name=db_name, - topic_text="Bob investigates how graph neural networks can support knowledge reasoning.", - concept_texts=[ - "GNNs can learn high-order relations among entities.", - "Attention mechanisms in graphs improve inference precision.", - ], - fact_texts=[ - "GAT outperforms GCN in graph classification tasks.", - "Multi-hop reasoning helps answer complex queries.", - ], - ) - - -if __name__ == "__main__": - print("\n=== Example: Single-DB ===") - example_shared_db(db_name="shared_traval_group-new") - - print("\n=== Example: Single-DB-Complex ===") - example_complex_shared_db(db_name="shared-traval-group-complex-new2") diff --git a/examples/basic_modules/parser.py b/examples/basic_modules/parser.py deleted file mode 100644 index c063964b7..000000000 --- a/examples/basic_modules/parser.py +++ /dev/null @@ -1,15 +0,0 @@ -from memos.configs.parser import ParserConfigFactory -from memos.parsers.factory import ParserFactory - - -config = ParserConfigFactory.model_validate( - { - "backend": "markitdown", - "config": {}, - } -) -parser = ParserFactory.from_config(config) -file_path = "README.md" -markdown_text = parser.parse(file_path) -print("Markdown text:\n", markdown_text) -print("==" * 20) diff --git a/examples/basic_modules/tree_textual_memory_reasoner.py b/examples/basic_modules/tree_textual_memory_reasoner.py deleted file mode 100644 index 369787458..000000000 --- a/examples/basic_modules/tree_textual_memory_reasoner.py +++ /dev/null @@ -1,167 +0,0 @@ -from memos import log -from memos.configs.embedder import EmbedderConfigFactory -from memos.configs.graph_db import GraphDBConfigFactory -from memos.configs.llm import LLMConfigFactory -from memos.embedders.factory import EmbedderFactory -from memos.graph_dbs.factory import GraphStoreFactory -from memos.llms.factory import LLMFactory -from memos.memories.textual.item import TextualMemoryItem, TreeNodeTextualMemoryMetadata -from memos.memories.textual.tree_text_memory.retrieve.reasoner import MemoryReasoner -from memos.memories.textual.tree_text_memory.retrieve.retrieval_mid_structs import ParsedTaskGoal - - -logger = log.get_logger(__name__) - -embedder_config = EmbedderConfigFactory.model_validate( - { - "backend": "ollama", - "config": { - "model_name_or_path": "nomic-embed-text:latest", - }, - } -) -embedder = EmbedderFactory.from_config(embedder_config) - -# Step 1: Load LLM config and instantiate -config = LLMConfigFactory.model_validate( - { - "backend": "ollama", - "config": { - "model_name_or_path": "qwen3:0.6b", - "temperature": 0.7, - "max_tokens": 1024, - }, - } -) -llm = LLMFactory.from_config(config) - -# Step 1: Prepare a mock ParsedTaskGoal -parsed_goal = ParsedTaskGoal( - memories=[ - "Multi-UAV Long-Term Coverage", - "Coverage Metrics", - "Reward Function Design", - "Energy Model", - "CT and FT Definition", - "Reward Components", - "Energy Cost Components", - ], - keys=["UAV", "coverage", "energy", "reward"], - tags=[], - goal_type="explanation", -) - -query = "How can multiple UAVs coordinate to maximize coverage while saving energy?" -query_embedding = embedder.embed([query])[0] - - -# Step 2: Initialize graph store -graph_config = GraphDBConfigFactory( - backend="neo4j", - config={ - "uri": "bolt://localhost:7687", - "user": "neo4j", - "password": "12345678", - "db_name": "user06alice", - "auto_create": True, - }, -) -graph_store = GraphStoreFactory.from_config(graph_config) - -ranked_memories = [ - TextualMemoryItem( - id="a88db9ce-3c77-4e83-8d61-aa9ef95c957e", - memory="Coverage performance is measured using CT (Coverage Time) and FT (Fairness Time) metrics.", - metadata=TreeNodeTextualMemoryMetadata( - user_id=None, - session_id=None, - status="activated", - type="fact", - memory_time="2024-01-01", - source="file", - confidence=91.0, - entities=["CT", "FT"], - tags=["coverage", "fairness", "metrics"], - visibility="public", - updated_at="2025-06-11T11:51:24.438001", - memory_type="LongTermMemory", - key="Coverage Metrics", - value="CT and FT used for long-term area and fairness evaluation", - hierarchy_level="concept", - sources=["paper://multi-uav-coverage/metrics"], - embedding=[0.01] * 768, - ), - ), - TextualMemoryItem( - id="c34f5e6b-2d34-4e6f-8c9b-abcdef123456", - memory="The capital of France is Paris, which is known for the Eiffel Tower.", - metadata=TreeNodeTextualMemoryMetadata( - user_id=None, - session_id=None, - status="activated", - type="fact", - memory_time="2024-01-01", - source="file", - confidence=90.0, - entities=["France", "Paris", "Eiffel Tower"], - tags=["geography", "city", "landmark"], - visibility="public", - updated_at="2025-06-11T11:51:24.438001", - memory_type="LongTermMemory", - key="Geography Fact", - value="Paris is the capital of France", - hierarchy_level="concept", - sources=["wikipedia://paris"], - embedding=[0.03] * 768, - ), - ), - TextualMemoryItem( - id="d56a7b8c-3e45-4f7a-9dab-fedcba654321", - memory="Total energy cost is calculated from both mechanical movement and communication transmission.", - metadata=TreeNodeTextualMemoryMetadata( - user_id=None, - session_id=None, - status="activated", - type="fact", - memory_time="2024-01-01", - source="file", - confidence=89.0, - entities=["movement power", "transmission power"], - tags=["energy", "movement", "transmission"], - visibility="public", - updated_at="2025-06-11T11:51:24.438001", - memory_type="LongTermMemory", - key="Energy Cost Components", - value="Includes movement and communication energy", - hierarchy_level="fact", - sources=["paper://multi-uav-coverage/energy-detail"], - embedding=[0.04] * 768, - ), - ), -] - -# Step 7: Init memory retriever -reasoner = MemoryReasoner(llm=llm) - - -# Step 8: Print retrieved memory items before ranking -print("\n=== Retrieved Memory Items (Before Rerank) ===") -for idx, item in enumerate(ranked_memories): - print(f"[Original #{idx + 1}] ID: {item.id}") - print(f"Memory: {item.memory[:200]}...\n") - -# Step 9: Rerank -reasoned_memories = reasoner.reason( - query=query, - ranked_memories=ranked_memories, - parsed_goal=parsed_goal, -) - -# Step 10: Print ranked reasoned memory items with original positions -print("\n=== Memory Items After Reason (Sorted) ===") -id_to_original_rank = {item.id: i + 1 for i, item in enumerate(ranked_memories)} - -for idx, item in enumerate(reasoned_memories): - original_rank = id_to_original_rank.get(item.id, "-") - print(f"[Reasoned #{idx + 1}] ID: {item.id} (Original #{original_rank})") - print(f"Memory: {item.memory[:200]}...\n") From 84ca7a545162221bb6b3f63c358ea34134446519 Mon Sep 17 00:00:00 2001 From: bittergreen Date: Sun, 18 Jan 2026 19:19:52 +0800 Subject: [PATCH 42/47] docs: Adding clear instructions as comments for examples in basic_modules. --- examples/basic_modules/embedder.py | 14 +++++++++++++- examples/basic_modules/llm.py | 8 ++++++++ examples/basic_modules/reranker.py | 17 +++++++++++++++++ 3 files changed, 38 insertions(+), 1 deletion(-) diff --git a/examples/basic_modules/embedder.py b/examples/basic_modules/embedder.py index 7cc7942da..d35dc1797 100644 --- a/examples/basic_modules/embedder.py +++ b/examples/basic_modules/embedder.py @@ -3,7 +3,10 @@ # Scenario 1: Using EmbedderFactory - +# Prerequisites: +# 1. Install Ollama: https://ollama.com/ +# 2. Start Ollama server: `ollama serve` +# 3. Pull the model: `ollama pull nomic-embed-text` config = EmbedderConfigFactory.model_validate( { "backend": "ollama", @@ -33,6 +36,9 @@ # Scenario 3: Using SenTranEmbedder +# Prerequisites: +# 1. Ensure `einops` is installed: `pip install einops` (Required for some HF models like nomic-bert) +# 2. The model `nomic-ai/nomic-embed-text-v1.5` will be downloaded automatically from HuggingFace. config_hf = EmbedderConfigFactory.model_validate( { @@ -49,6 +55,9 @@ print("==" * 20) # === Scenario 4: Using UniversalAPIEmbedder(OpenAI) === +# Prerequisites: +# 1. Set a valid OPENAI_API_KEY +# 2. Ensure the base_url is reachable config_api = EmbedderConfigFactory.model_validate( { @@ -68,6 +77,9 @@ print("Embedding preview:", embedding_api[0][:10]) # === Scenario 5: Using UniversalAPIEmbedder(Azure) === +# Prerequisites: +# 1. Set a valid AZURE_API_KEY +# 2. Ensure the base_url is reachable config_api = EmbedderConfigFactory.model_validate( { diff --git a/examples/basic_modules/llm.py b/examples/basic_modules/llm.py index d33fc9544..fb157c991 100644 --- a/examples/basic_modules/llm.py +++ b/examples/basic_modules/llm.py @@ -5,6 +5,10 @@ # Scenario 1: Using LLMFactory with Ollama Backend # This is the most recommended way! 🌟 +# Prerequisites: +# 1. Install Ollama: https://ollama.com/ +# 2. Start Ollama server: `ollama serve` +# 3. Need python ollama package(>=0.5.0,<0.6.0) config = LLMConfigFactory.model_validate( { @@ -46,6 +50,10 @@ # Scenario 3: Using LLMFactory with OpenAI Backend +# Prerequisites: +# 1. You need a valid OpenAI API key to run this scenario. +# 2. Replace 'sk-xxxx' with your actual API key below. + config = LLMConfigFactory.model_validate( { diff --git a/examples/basic_modules/reranker.py b/examples/basic_modules/reranker.py index 47bf1405c..e5a869789 100644 --- a/examples/basic_modules/reranker.py +++ b/examples/basic_modules/reranker.py @@ -50,6 +50,7 @@ def show_ranked(title: str, ranked: list[tuple[TextualMemoryItem, float]], top_n def main(): # ------------------------------- # 1) Build the embedder (real vectors) + # You may need to set valid OPENAI_API_KEY and OPENAI_API_BASE in your environment variables. # ------------------------------- embedder_cfg = EmbedderConfigFactory.model_validate( { @@ -62,6 +63,22 @@ def main(): }, } ) + """ + # ------------------------------- + # Optional: Build the embedder (using local sentence-transformers) + # ------------------------------- + # Use a local model so no API key is required. + embedder_cfg = EmbedderConfigFactory.model_validate( + { + "backend": "sentence_transformer", + "config": { + "model_name_or_path": "nomic-ai/nomic-embed-text-v1.5", + "trust_remote_code": True, + }, + } + ) + """ + embedder = EmbedderFactory.from_config(embedder_cfg) # ------------------------------- From 31cd681a7d94a003a63e3037dfe2ab0b3362d8ab Mon Sep 17 00:00:00 2001 From: bittergreen Date: Sun, 18 Jan 2026 19:22:00 +0800 Subject: [PATCH 43/47] fix: fixing bugs relevant to examples in basic_module. --- examples/data/config/tree_config_shared_database.json | 2 +- src/memos/graph_dbs/neo4j.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/data/config/tree_config_shared_database.json b/examples/data/config/tree_config_shared_database.json index a0a9bc3a3..6dd1a9220 100644 --- a/examples/data/config/tree_config_shared_database.json +++ b/examples/data/config/tree_config_shared_database.json @@ -58,6 +58,6 @@ "WorkingMemory": 200, "LongTermMemory": 20000, "UserMemory": 30000 - } + }, "memory_filename": "tree_textual_memories.json" } diff --git a/src/memos/graph_dbs/neo4j.py b/src/memos/graph_dbs/neo4j.py index 64aedc8f4..2cf9ae32f 100644 --- a/src/memos/graph_dbs/neo4j.py +++ b/src/memos/graph_dbs/neo4j.py @@ -1687,7 +1687,7 @@ def _parse_node(self, node_data: dict[str, Any]) -> dict[str, Any]: node.pop("user_name", None) # serialization - if node["sources"]: + if node.get("sources"): for idx in range(len(node["sources"])): if not ( isinstance(node["sources"][idx], str) From 95563f88e6c5783f823b10c153ca0a6badb7b8f1 Mon Sep 17 00:00:00 2001 From: bittergreen Date: Sun, 18 Jan 2026 20:53:09 +0800 Subject: [PATCH 44/47] doc: Adding clear instructions as comments for examples in mem_scheduler. --- examples/mem_scheduler/api_w_scheduler.py | 9 +++++++++ examples/mem_scheduler/memos_w_scheduler.py | 7 +++++++ examples/mem_scheduler/redis_example.py | 8 ++++++++ examples/mem_scheduler/run_async_tasks.py | 9 +++++++++ 4 files changed, 33 insertions(+) diff --git a/examples/mem_scheduler/api_w_scheduler.py b/examples/mem_scheduler/api_w_scheduler.py index ba3d64bf1..b02161c12 100644 --- a/examples/mem_scheduler/api_w_scheduler.py +++ b/examples/mem_scheduler/api_w_scheduler.py @@ -1,3 +1,12 @@ +""" +# Prerequisites & Configuration +# To run this script, you must have the following services +# running and configured in your .env file (or environment variables): +# 1. Redis (Required for TaskStatusTracker and Scheduler Queue) +# 2. Graph Database (Required for Memory Storage) +# 3. Vector Database (Required if using Neo4j Community or Preference Memory) +""" + import sys from pathlib import Path diff --git a/examples/mem_scheduler/memos_w_scheduler.py b/examples/mem_scheduler/memos_w_scheduler.py index 55e966b5a..b7250a677 100644 --- a/examples/mem_scheduler/memos_w_scheduler.py +++ b/examples/mem_scheduler/memos_w_scheduler.py @@ -1,3 +1,10 @@ +# Prerequisites & Configuration +# To run this script, you must have the following services +# running and configured in your .env file (or environment variables): +# 1. Redis (Required for TaskStatusTracker and Scheduler Queue) +# 2. Graph Database (Required for Memory Storage) +# 3. Vector Database (Required if using Neo4j Community or Preference Memory) + import asyncio import json import os diff --git a/examples/mem_scheduler/redis_example.py b/examples/mem_scheduler/redis_example.py index 9f7ca4139..00989c424 100644 --- a/examples/mem_scheduler/redis_example.py +++ b/examples/mem_scheduler/redis_example.py @@ -1,3 +1,11 @@ +# Prerequisites: +# 1. Ensure a Redis server is running locally on the default port (6379). +# You can start it with: `redis-server` +# On macOS with Homebrew: `/opt/homebrew/bin/redis-server` or `brew services start redis` +# On Linux: `sudo service redis-server start` +# 2. If Redis is running on a different host/port, update the configuration or environment variables accordingly. + + import sys import time diff --git a/examples/mem_scheduler/run_async_tasks.py b/examples/mem_scheduler/run_async_tasks.py index 7f544c3da..fbb5a7bcc 100644 --- a/examples/mem_scheduler/run_async_tasks.py +++ b/examples/mem_scheduler/run_async_tasks.py @@ -1,3 +1,12 @@ +""" +# Prerequisites & Configuration +# To run this script, you must have the following services +# running and configured in your .env file (or environment variables): +# 1. Redis (Required for TaskStatusTracker and Scheduler Queue) +# 2. Graph Database (Required for Memory Storage) +# 3. Vector Database (Required if using Neo4j Community or Preference Memory) +""" + from pathlib import Path from time import sleep From 47df601f292f00a0391161bbb7cc2fdc7cc7b444 Mon Sep 17 00:00:00 2001 From: bittergreen Date: Sun, 18 Jan 2026 21:31:25 +0800 Subject: [PATCH 45/47] fix: Fix example bug caused by using the default SchedulerLocalQueue(without .show_task_status method). --- examples/mem_scheduler/show_redis_status.py | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/examples/mem_scheduler/show_redis_status.py b/examples/mem_scheduler/show_redis_status.py index d88e86655..94a915588 100644 --- a/examples/mem_scheduler/show_redis_status.py +++ b/examples/mem_scheduler/show_redis_status.py @@ -1,10 +1,25 @@ +""" +# Prerequisites: +# 1. Ensure a Redis server is running locally on the default port (6379). +# You can start it with: `redis-server` +# On macOS with Homebrew: `/opt/homebrew/bin/redis-server` or `brew services start redis` +# On Linux: `sudo service redis-server start` +# 2. If Redis is running on a different host/port, update the configuration or environment variables accordingly. +""" + import time -from memos.api.routers.server_router import mem_scheduler +from memos.mem_scheduler.task_schedule_modules.orchestrator import SchedulerOrchestrator from memos.mem_scheduler.task_schedule_modules.redis_queue import SchedulerRedisQueue -queue = mem_scheduler.memos_message_queue.memos_message_queue +# Explicitly initialize Redis queue for monitoring +queue = SchedulerRedisQueue( + max_len=None, + consumer_group="scheduler_group", + consumer_name="monitor_consumer", + orchestrator=SchedulerOrchestrator(), +) def fetch_status( From d0f3bab577786252edc206f17707487d05e0b898 Mon Sep 17 00:00:00 2001 From: CaralHsi Date: Mon, 19 Jan 2026 14:16:39 +0800 Subject: [PATCH 46/47] revert: "doc: Examples update and related minor bug fix" (#899) Revert "doc: Examples update and related minor bug fix" --- examples/basic_modules/embedder.py | 14 +- examples/basic_modules/llm.py | 8 - examples/basic_modules/nebular_example.py | 361 ++++++++++++++++++ examples/basic_modules/parser.py | 15 + examples/basic_modules/reranker.py | 17 - .../tree_textual_memory_reasoner.py | 167 ++++++++ examples/mem_scheduler/api_w_scheduler.py | 9 - examples/mem_scheduler/memos_w_scheduler.py | 7 - examples/mem_scheduler/redis_example.py | 8 - examples/mem_scheduler/run_async_tasks.py | 9 - examples/mem_scheduler/show_redis_status.py | 19 +- src/memos/graph_dbs/neo4j.py | 2 +- 12 files changed, 547 insertions(+), 89 deletions(-) create mode 100644 examples/basic_modules/nebular_example.py create mode 100644 examples/basic_modules/parser.py create mode 100644 examples/basic_modules/tree_textual_memory_reasoner.py diff --git a/examples/basic_modules/embedder.py b/examples/basic_modules/embedder.py index d35dc1797..7cc7942da 100644 --- a/examples/basic_modules/embedder.py +++ b/examples/basic_modules/embedder.py @@ -3,10 +3,7 @@ # Scenario 1: Using EmbedderFactory -# Prerequisites: -# 1. Install Ollama: https://ollama.com/ -# 2. Start Ollama server: `ollama serve` -# 3. Pull the model: `ollama pull nomic-embed-text` + config = EmbedderConfigFactory.model_validate( { "backend": "ollama", @@ -36,9 +33,6 @@ # Scenario 3: Using SenTranEmbedder -# Prerequisites: -# 1. Ensure `einops` is installed: `pip install einops` (Required for some HF models like nomic-bert) -# 2. The model `nomic-ai/nomic-embed-text-v1.5` will be downloaded automatically from HuggingFace. config_hf = EmbedderConfigFactory.model_validate( { @@ -55,9 +49,6 @@ print("==" * 20) # === Scenario 4: Using UniversalAPIEmbedder(OpenAI) === -# Prerequisites: -# 1. Set a valid OPENAI_API_KEY -# 2. Ensure the base_url is reachable config_api = EmbedderConfigFactory.model_validate( { @@ -77,9 +68,6 @@ print("Embedding preview:", embedding_api[0][:10]) # === Scenario 5: Using UniversalAPIEmbedder(Azure) === -# Prerequisites: -# 1. Set a valid AZURE_API_KEY -# 2. Ensure the base_url is reachable config_api = EmbedderConfigFactory.model_validate( { diff --git a/examples/basic_modules/llm.py b/examples/basic_modules/llm.py index fb157c991..d33fc9544 100644 --- a/examples/basic_modules/llm.py +++ b/examples/basic_modules/llm.py @@ -5,10 +5,6 @@ # Scenario 1: Using LLMFactory with Ollama Backend # This is the most recommended way! 🌟 -# Prerequisites: -# 1. Install Ollama: https://ollama.com/ -# 2. Start Ollama server: `ollama serve` -# 3. Need python ollama package(>=0.5.0,<0.6.0) config = LLMConfigFactory.model_validate( { @@ -50,10 +46,6 @@ # Scenario 3: Using LLMFactory with OpenAI Backend -# Prerequisites: -# 1. You need a valid OpenAI API key to run this scenario. -# 2. Replace 'sk-xxxx' with your actual API key below. - config = LLMConfigFactory.model_validate( { diff --git a/examples/basic_modules/nebular_example.py b/examples/basic_modules/nebular_example.py new file mode 100644 index 000000000..13f88e3f3 --- /dev/null +++ b/examples/basic_modules/nebular_example.py @@ -0,0 +1,361 @@ +import json +import os + +from datetime import datetime, timezone + +import numpy as np + +from dotenv import load_dotenv + +from memos.configs.embedder import EmbedderConfigFactory +from memos.configs.graph_db import GraphDBConfigFactory +from memos.embedders.factory import EmbedderFactory +from memos.graph_dbs.factory import GraphStoreFactory +from memos.memories.textual.item import TextualMemoryItem, TreeNodeTextualMemoryMetadata + + +load_dotenv() + + +def show(nebular_data): + from memos.configs.graph_db import Neo4jGraphDBConfig + from memos.graph_dbs.neo4j import Neo4jGraphDB + + tree_config = Neo4jGraphDBConfig.from_json_file("../../examples/data/config/neo4j_config.json") + tree_config.use_multi_db = True + tree_config.db_name = "nebular-show2" + + neo4j_db = Neo4jGraphDB(tree_config) + neo4j_db.clear() + neo4j_db.import_graph(nebular_data) + + +embedder_config = EmbedderConfigFactory.model_validate( + { + "backend": "universal_api", + "config": { + "provider": "openai", + "api_key": os.getenv("OPENAI_API_KEY", "sk-xxxxx"), + "model_name_or_path": "text-embedding-3-large", + "base_url": os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1"), + }, + } +) +embedder = EmbedderFactory.from_config(embedder_config) +embedder_dimension = 3072 + + +def embed_memory_item(memory: str) -> list[float]: + embedding = embedder.embed([memory])[0] + embedding_np = np.array(embedding, dtype=np.float32) + embedding_list = embedding_np.tolist() + return embedding_list + + +def example_shared_db(db_name: str = "shared-traval-group"): + """ + Example: Single(Shared)-DB multi-tenant (logical isolation) + Multiple users' data in the same Neo4j DB with user_name as a tag. + """ + # users + user_list = ["travel_member_alice", "travel_member_bob"] + + for user_name in user_list: + # Step 1: Build factory config + config = GraphDBConfigFactory( + backend="nebular", + config={ + "uri": json.loads(os.getenv("NEBULAR_HOSTS", "localhost")), + "user": os.getenv("NEBULAR_USER", "root"), + "password": os.getenv("NEBULAR_PASSWORD", "xxxxxx"), + "space": db_name, + "user_name": user_name, + "use_multi_db": False, + "auto_create": True, + "embedding_dimension": embedder_dimension, + }, + ) + + # Step 2: Instantiate graph store + graph = GraphStoreFactory.from_config(config) + print(f"\n[INFO] Working in shared DB: {db_name}, for user: {user_name}") + graph.clear() + + # Step 3: Create topic node + topic = TextualMemoryItem( + memory="This research addresses long-term multi-UAV navigation for energy-efficient communication coverage.", + metadata=TreeNodeTextualMemoryMetadata( + memory_type="LongTermMemory", + key="Multi-UAV Long-Term Coverage", + hierarchy_level="topic", + type="fact", + memory_time="2024-01-01", + source="file", + sources=["paper://multi-uav-coverage/intro"], + status="activated", + confidence=95.0, + tags=["UAV", "coverage", "multi-agent"], + entities=["UAV", "coverage", "navigation"], + visibility="public", + updated_at=datetime.now().isoformat(), + embedding=embed_memory_item( + "This research addresses long-term " + "multi-UAV navigation for " + "energy-efficient communication " + "coverage." + ), + ), + ) + + graph.add_node( + id=topic.id, memory=topic.memory, metadata=topic.metadata.model_dump(exclude_none=True) + ) + + # Step 4: Add a concept for each user + concept = TextualMemoryItem( + memory=f"Itinerary plan for {user_name}", + metadata=TreeNodeTextualMemoryMetadata( + memory_type="LongTermMemory", + key="Multi-UAV Long-Term Coverage", + hierarchy_level="concept", + type="fact", + memory_time="2024-01-01", + source="file", + sources=["paper://multi-uav-coverage/intro"], + status="activated", + confidence=95.0, + tags=["UAV", "coverage", "multi-agent"], + entities=["UAV", "coverage", "navigation"], + visibility="public", + updated_at=datetime.now().isoformat(), + embedding=embed_memory_item(f"Itinerary plan for {user_name}"), + ), + ) + + graph.add_node( + id=concept.id, + memory=concept.memory, + metadata=concept.metadata.model_dump(exclude_none=True), + ) + + # Link concept to topic + graph.add_edge(source_id=concept.id, target_id=topic.id, type="RELATE_TO") + print(f"[INFO] Added nodes for {user_name}") + + # Step 5: Query and print ALL for verification + print("\n=== Export entire DB (for verification, includes ALL users) ===") + graph = GraphStoreFactory.from_config(config) + all_graph_data = graph.export_graph() + print(str(all_graph_data)[:1000]) + + # Step 6: Search for alice's data only + print("\n=== Search for travel_member_alice ===") + config_alice = GraphDBConfigFactory( + backend="nebular", + config={ + "uri": json.loads(os.getenv("NEBULAR_HOSTS", "localhost")), + "user": os.getenv("NEBULAR_USER", "root"), + "password": os.getenv("NEBULAR_PASSWORD", "xxxxxx"), + "space": db_name, + "user_name": user_list[0], + "auto_create": True, + "embedding_dimension": embedder_dimension, + "use_multi_db": False, + }, + ) + graph_alice = GraphStoreFactory.from_config(config_alice) + nodes = graph_alice.search_by_embedding(vector=embed_memory_item("travel itinerary"), top_k=3) + for node in nodes: + print(str(graph_alice.get_node(node["id"]))[:1000]) + + +def run_user_session( + user_name: str, + db_name: str, + topic_text: str, + concept_texts: list[str], + fact_texts: list[str], +): + print(f"\n=== {user_name} starts building their memory graph ===") + + # Manually initialize correct GraphDB class + config = GraphDBConfigFactory( + backend="nebular", + config={ + "uri": json.loads(os.getenv("NEBULAR_HOSTS", "localhost")), + "user": os.getenv("NEBULAR_USER", "root"), + "password": os.getenv("NEBULAR_PASSWORD", "xxxxxx"), + "space": db_name, + "user_name": user_name, + "use_multi_db": False, + "auto_create": True, + "embedding_dimension": embedder_dimension, + }, + ) + graph = GraphStoreFactory.from_config(config) + + # Start with a clean slate for this user + graph.clear() + + now = datetime.now(timezone.utc).isoformat() + + # === Step 1: Create a root topic node (e.g., user's research focus) === + topic = TextualMemoryItem( + memory=topic_text, + metadata=TreeNodeTextualMemoryMetadata( + memory_type="LongTermMemory", + key="Research Topic", + hierarchy_level="topic", + type="fact", + memory_time="2024-01-01", + status="activated", + visibility="public", + tags=["research", "rl"], + updated_at=now, + embedding=embed_memory_item(topic_text), + ), + ) + graph.add_node(topic.id, topic.memory, topic.metadata.model_dump(exclude_none=True)) + + # === Step 2: Create two concept nodes linked to the topic === + concept_items = [] + for i, text in enumerate(concept_texts): + concept = TextualMemoryItem( + memory=text, + metadata=TreeNodeTextualMemoryMetadata( + memory_type="LongTermMemory", + key=f"Concept {i + 1}", + hierarchy_level="concept", + type="fact", + memory_time="2024-01-01", + status="activated", + visibility="public", + updated_at=now, + embedding=embed_memory_item(text), + tags=["concept"], + confidence=90 + i, + ), + ) + graph.add_node(concept.id, concept.memory, concept.metadata.model_dump(exclude_none=True)) + graph.add_edge(topic.id, concept.id, type="PARENT") + concept_items.append(concept) + + # === Step 3: Create supporting facts under each concept === + for i, text in enumerate(fact_texts): + fact = TextualMemoryItem( + memory=text, + metadata=TreeNodeTextualMemoryMetadata( + memory_type="WorkingMemory", + key=f"Fact {i + 1}", + hierarchy_level="fact", + type="fact", + memory_time="2024-01-01", + status="activated", + visibility="public", + updated_at=now, + embedding=embed_memory_item(text), + confidence=85.0, + tags=["fact"], + ), + ) + graph.add_node(fact.id, fact.memory, fact.metadata.model_dump(exclude_none=True)) + graph.add_edge(concept_items[i % len(concept_items)].id, fact.id, type="PARENT") + + # === Step 4: Retrieve memory using semantic search === + vector = embed_memory_item("How is memory retrieved?") + search_result = graph.search_by_embedding(vector, top_k=2) + for r in search_result: + node = graph.get_node(r["id"]) + print("🔍 Search result:", node["memory"]) + + # === Step 5: Tag-based neighborhood discovery === + neighbors = graph.get_neighbors_by_tag(["concept"], exclude_ids=[], top_k=2) + print("📎 Tag-related nodes:", [neighbor["memory"] for neighbor in neighbors]) + + # === Step 6: Retrieve children (facts) of first concept === + children = graph.get_children_with_embeddings(concept_items[0].id) + print("📍 Children of concept:", [child["memory"] for child in children]) + + # === Step 7: Export a local subgraph and grouped statistics === + subgraph = graph.get_subgraph(topic.id, depth=2) + print("📌 Subgraph node count:", len(subgraph["neighbors"])) + + stats = graph.get_grouped_counts(["memory_type", "status"]) + print("📊 Grouped counts:", stats) + + # === Step 8: Demonstrate updates and cleanup === + graph.update_node( + concept_items[0].id, {"confidence": 99.0, "created_at": "2025-07-24T20:11:56.375687"} + ) + graph.remove_oldest_memory("WorkingMemory", keep_latest=1) + graph.delete_edge(topic.id, concept_items[0].id, type="PARENT") + graph.delete_node(concept_items[1].id) + + # === Step 9: Export and re-import the entire graph structure === + exported = graph.export_graph() + graph.import_graph(exported) + print("📦 Graph exported and re-imported, total nodes:", len(exported["nodes"])) + + # ==================================== + # 🔍 Step 10: extra function + # ==================================== + print(f"\n=== 🔍 Extra Tests for user: {user_name} ===") + + print(" - Memory count:", graph.get_memory_count("LongTermMemory")) + print(" - Node count:", graph.count_nodes("LongTermMemory")) + print(" - All LongTermMemory items:", graph.get_all_memory_items("LongTermMemory")) + + if len(exported["edges"]) > 0: + n1, n2 = exported["edges"][0]["source"], exported["edges"][0]["target"] + print(" - Edge exists?", graph.edge_exists(n1, n2, exported["edges"][0]["type"])) + print(" - Edges for node:", graph.get_edges(n1)) + + filters = [{"field": "memory_type", "op": "=", "value": "LongTermMemory"}] + print(" - Metadata query result:", graph.get_by_metadata(filters)) + print( + " - Optimization candidates:", graph.get_structure_optimization_candidates("LongTermMemory") + ) + try: + graph.drop_database() + except ValueError as e: + print(" - drop_database raised ValueError as expected:", e) + + +def example_complex_shared_db(db_name: str = "shared-traval-group-complex"): + # User 1: Alice explores structured memory for LLMs + run_user_session( + user_name="alice", + db_name=db_name, + topic_text="Alice studies structured memory and long-term memory optimization in LLMs.", + concept_texts=[ + "Short-term memory can be simulated using WorkingMemory blocks.", + "A structured memory graph improves retrieval precision for agents.", + ], + fact_texts=[ + "Embedding search is used to find semantically similar memory items.", + "User memories are stored as node-edge structures that support hierarchical reasoning.", + ], + ) + + # User 2: Bob focuses on GNN-based reasoning + run_user_session( + user_name="bob", + db_name=db_name, + topic_text="Bob investigates how graph neural networks can support knowledge reasoning.", + concept_texts=[ + "GNNs can learn high-order relations among entities.", + "Attention mechanisms in graphs improve inference precision.", + ], + fact_texts=[ + "GAT outperforms GCN in graph classification tasks.", + "Multi-hop reasoning helps answer complex queries.", + ], + ) + + +if __name__ == "__main__": + print("\n=== Example: Single-DB ===") + example_shared_db(db_name="shared_traval_group-new") + + print("\n=== Example: Single-DB-Complex ===") + example_complex_shared_db(db_name="shared-traval-group-complex-new2") diff --git a/examples/basic_modules/parser.py b/examples/basic_modules/parser.py new file mode 100644 index 000000000..c063964b7 --- /dev/null +++ b/examples/basic_modules/parser.py @@ -0,0 +1,15 @@ +from memos.configs.parser import ParserConfigFactory +from memos.parsers.factory import ParserFactory + + +config = ParserConfigFactory.model_validate( + { + "backend": "markitdown", + "config": {}, + } +) +parser = ParserFactory.from_config(config) +file_path = "README.md" +markdown_text = parser.parse(file_path) +print("Markdown text:\n", markdown_text) +print("==" * 20) diff --git a/examples/basic_modules/reranker.py b/examples/basic_modules/reranker.py index e5a869789..47bf1405c 100644 --- a/examples/basic_modules/reranker.py +++ b/examples/basic_modules/reranker.py @@ -50,7 +50,6 @@ def show_ranked(title: str, ranked: list[tuple[TextualMemoryItem, float]], top_n def main(): # ------------------------------- # 1) Build the embedder (real vectors) - # You may need to set valid OPENAI_API_KEY and OPENAI_API_BASE in your environment variables. # ------------------------------- embedder_cfg = EmbedderConfigFactory.model_validate( { @@ -63,22 +62,6 @@ def main(): }, } ) - """ - # ------------------------------- - # Optional: Build the embedder (using local sentence-transformers) - # ------------------------------- - # Use a local model so no API key is required. - embedder_cfg = EmbedderConfigFactory.model_validate( - { - "backend": "sentence_transformer", - "config": { - "model_name_or_path": "nomic-ai/nomic-embed-text-v1.5", - "trust_remote_code": True, - }, - } - ) - """ - embedder = EmbedderFactory.from_config(embedder_cfg) # ------------------------------- diff --git a/examples/basic_modules/tree_textual_memory_reasoner.py b/examples/basic_modules/tree_textual_memory_reasoner.py new file mode 100644 index 000000000..369787458 --- /dev/null +++ b/examples/basic_modules/tree_textual_memory_reasoner.py @@ -0,0 +1,167 @@ +from memos import log +from memos.configs.embedder import EmbedderConfigFactory +from memos.configs.graph_db import GraphDBConfigFactory +from memos.configs.llm import LLMConfigFactory +from memos.embedders.factory import EmbedderFactory +from memos.graph_dbs.factory import GraphStoreFactory +from memos.llms.factory import LLMFactory +from memos.memories.textual.item import TextualMemoryItem, TreeNodeTextualMemoryMetadata +from memos.memories.textual.tree_text_memory.retrieve.reasoner import MemoryReasoner +from memos.memories.textual.tree_text_memory.retrieve.retrieval_mid_structs import ParsedTaskGoal + + +logger = log.get_logger(__name__) + +embedder_config = EmbedderConfigFactory.model_validate( + { + "backend": "ollama", + "config": { + "model_name_or_path": "nomic-embed-text:latest", + }, + } +) +embedder = EmbedderFactory.from_config(embedder_config) + +# Step 1: Load LLM config and instantiate +config = LLMConfigFactory.model_validate( + { + "backend": "ollama", + "config": { + "model_name_or_path": "qwen3:0.6b", + "temperature": 0.7, + "max_tokens": 1024, + }, + } +) +llm = LLMFactory.from_config(config) + +# Step 1: Prepare a mock ParsedTaskGoal +parsed_goal = ParsedTaskGoal( + memories=[ + "Multi-UAV Long-Term Coverage", + "Coverage Metrics", + "Reward Function Design", + "Energy Model", + "CT and FT Definition", + "Reward Components", + "Energy Cost Components", + ], + keys=["UAV", "coverage", "energy", "reward"], + tags=[], + goal_type="explanation", +) + +query = "How can multiple UAVs coordinate to maximize coverage while saving energy?" +query_embedding = embedder.embed([query])[0] + + +# Step 2: Initialize graph store +graph_config = GraphDBConfigFactory( + backend="neo4j", + config={ + "uri": "bolt://localhost:7687", + "user": "neo4j", + "password": "12345678", + "db_name": "user06alice", + "auto_create": True, + }, +) +graph_store = GraphStoreFactory.from_config(graph_config) + +ranked_memories = [ + TextualMemoryItem( + id="a88db9ce-3c77-4e83-8d61-aa9ef95c957e", + memory="Coverage performance is measured using CT (Coverage Time) and FT (Fairness Time) metrics.", + metadata=TreeNodeTextualMemoryMetadata( + user_id=None, + session_id=None, + status="activated", + type="fact", + memory_time="2024-01-01", + source="file", + confidence=91.0, + entities=["CT", "FT"], + tags=["coverage", "fairness", "metrics"], + visibility="public", + updated_at="2025-06-11T11:51:24.438001", + memory_type="LongTermMemory", + key="Coverage Metrics", + value="CT and FT used for long-term area and fairness evaluation", + hierarchy_level="concept", + sources=["paper://multi-uav-coverage/metrics"], + embedding=[0.01] * 768, + ), + ), + TextualMemoryItem( + id="c34f5e6b-2d34-4e6f-8c9b-abcdef123456", + memory="The capital of France is Paris, which is known for the Eiffel Tower.", + metadata=TreeNodeTextualMemoryMetadata( + user_id=None, + session_id=None, + status="activated", + type="fact", + memory_time="2024-01-01", + source="file", + confidence=90.0, + entities=["France", "Paris", "Eiffel Tower"], + tags=["geography", "city", "landmark"], + visibility="public", + updated_at="2025-06-11T11:51:24.438001", + memory_type="LongTermMemory", + key="Geography Fact", + value="Paris is the capital of France", + hierarchy_level="concept", + sources=["wikipedia://paris"], + embedding=[0.03] * 768, + ), + ), + TextualMemoryItem( + id="d56a7b8c-3e45-4f7a-9dab-fedcba654321", + memory="Total energy cost is calculated from both mechanical movement and communication transmission.", + metadata=TreeNodeTextualMemoryMetadata( + user_id=None, + session_id=None, + status="activated", + type="fact", + memory_time="2024-01-01", + source="file", + confidence=89.0, + entities=["movement power", "transmission power"], + tags=["energy", "movement", "transmission"], + visibility="public", + updated_at="2025-06-11T11:51:24.438001", + memory_type="LongTermMemory", + key="Energy Cost Components", + value="Includes movement and communication energy", + hierarchy_level="fact", + sources=["paper://multi-uav-coverage/energy-detail"], + embedding=[0.04] * 768, + ), + ), +] + +# Step 7: Init memory retriever +reasoner = MemoryReasoner(llm=llm) + + +# Step 8: Print retrieved memory items before ranking +print("\n=== Retrieved Memory Items (Before Rerank) ===") +for idx, item in enumerate(ranked_memories): + print(f"[Original #{idx + 1}] ID: {item.id}") + print(f"Memory: {item.memory[:200]}...\n") + +# Step 9: Rerank +reasoned_memories = reasoner.reason( + query=query, + ranked_memories=ranked_memories, + parsed_goal=parsed_goal, +) + +# Step 10: Print ranked reasoned memory items with original positions +print("\n=== Memory Items After Reason (Sorted) ===") +id_to_original_rank = {item.id: i + 1 for i, item in enumerate(ranked_memories)} + +for idx, item in enumerate(reasoned_memories): + original_rank = id_to_original_rank.get(item.id, "-") + print(f"[Reasoned #{idx + 1}] ID: {item.id} (Original #{original_rank})") + print(f"Memory: {item.memory[:200]}...\n") diff --git a/examples/mem_scheduler/api_w_scheduler.py b/examples/mem_scheduler/api_w_scheduler.py index b02161c12..ba3d64bf1 100644 --- a/examples/mem_scheduler/api_w_scheduler.py +++ b/examples/mem_scheduler/api_w_scheduler.py @@ -1,12 +1,3 @@ -""" -# Prerequisites & Configuration -# To run this script, you must have the following services -# running and configured in your .env file (or environment variables): -# 1. Redis (Required for TaskStatusTracker and Scheduler Queue) -# 2. Graph Database (Required for Memory Storage) -# 3. Vector Database (Required if using Neo4j Community or Preference Memory) -""" - import sys from pathlib import Path diff --git a/examples/mem_scheduler/memos_w_scheduler.py b/examples/mem_scheduler/memos_w_scheduler.py index b7250a677..55e966b5a 100644 --- a/examples/mem_scheduler/memos_w_scheduler.py +++ b/examples/mem_scheduler/memos_w_scheduler.py @@ -1,10 +1,3 @@ -# Prerequisites & Configuration -# To run this script, you must have the following services -# running and configured in your .env file (or environment variables): -# 1. Redis (Required for TaskStatusTracker and Scheduler Queue) -# 2. Graph Database (Required for Memory Storage) -# 3. Vector Database (Required if using Neo4j Community or Preference Memory) - import asyncio import json import os diff --git a/examples/mem_scheduler/redis_example.py b/examples/mem_scheduler/redis_example.py index 00989c424..9f7ca4139 100644 --- a/examples/mem_scheduler/redis_example.py +++ b/examples/mem_scheduler/redis_example.py @@ -1,11 +1,3 @@ -# Prerequisites: -# 1. Ensure a Redis server is running locally on the default port (6379). -# You can start it with: `redis-server` -# On macOS with Homebrew: `/opt/homebrew/bin/redis-server` or `brew services start redis` -# On Linux: `sudo service redis-server start` -# 2. If Redis is running on a different host/port, update the configuration or environment variables accordingly. - - import sys import time diff --git a/examples/mem_scheduler/run_async_tasks.py b/examples/mem_scheduler/run_async_tasks.py index fbb5a7bcc..7f544c3da 100644 --- a/examples/mem_scheduler/run_async_tasks.py +++ b/examples/mem_scheduler/run_async_tasks.py @@ -1,12 +1,3 @@ -""" -# Prerequisites & Configuration -# To run this script, you must have the following services -# running and configured in your .env file (or environment variables): -# 1. Redis (Required for TaskStatusTracker and Scheduler Queue) -# 2. Graph Database (Required for Memory Storage) -# 3. Vector Database (Required if using Neo4j Community or Preference Memory) -""" - from pathlib import Path from time import sleep diff --git a/examples/mem_scheduler/show_redis_status.py b/examples/mem_scheduler/show_redis_status.py index 94a915588..d88e86655 100644 --- a/examples/mem_scheduler/show_redis_status.py +++ b/examples/mem_scheduler/show_redis_status.py @@ -1,25 +1,10 @@ -""" -# Prerequisites: -# 1. Ensure a Redis server is running locally on the default port (6379). -# You can start it with: `redis-server` -# On macOS with Homebrew: `/opt/homebrew/bin/redis-server` or `brew services start redis` -# On Linux: `sudo service redis-server start` -# 2. If Redis is running on a different host/port, update the configuration or environment variables accordingly. -""" - import time -from memos.mem_scheduler.task_schedule_modules.orchestrator import SchedulerOrchestrator +from memos.api.routers.server_router import mem_scheduler from memos.mem_scheduler.task_schedule_modules.redis_queue import SchedulerRedisQueue -# Explicitly initialize Redis queue for monitoring -queue = SchedulerRedisQueue( - max_len=None, - consumer_group="scheduler_group", - consumer_name="monitor_consumer", - orchestrator=SchedulerOrchestrator(), -) +queue = mem_scheduler.memos_message_queue.memos_message_queue def fetch_status( diff --git a/src/memos/graph_dbs/neo4j.py b/src/memos/graph_dbs/neo4j.py index 2cf9ae32f..64aedc8f4 100644 --- a/src/memos/graph_dbs/neo4j.py +++ b/src/memos/graph_dbs/neo4j.py @@ -1687,7 +1687,7 @@ def _parse_node(self, node_data: dict[str, Any]) -> dict[str, Any]: node.pop("user_name", None) # serialization - if node.get("sources"): + if node["sources"]: for idx in range(len(node["sources"])): if not ( isinstance(node["sources"][idx], str) From 0cd396030fe16d068ef48081bd775b8708ce3481 Mon Sep 17 00:00:00 2001 From: Qi Weng Date: Mon, 19 Jan 2026 15:16:37 +0800 Subject: [PATCH 47/47] doc: Examples update and related minor bug fix (#900) Revert "revert: "doc: Examples update and related minor bug fix" (#899)" The test failed because of other reasons than commits in this pr, so we revert this revert. This reverts commit d0f3bab577786252edc206f17707487d05e0b898. Co-authored-by: CaralHsi --- examples/basic_modules/embedder.py | 14 +- examples/basic_modules/llm.py | 8 + examples/basic_modules/nebular_example.py | 361 ------------------ examples/basic_modules/parser.py | 15 - examples/basic_modules/reranker.py | 17 + .../tree_textual_memory_reasoner.py | 167 -------- examples/mem_scheduler/api_w_scheduler.py | 9 + examples/mem_scheduler/memos_w_scheduler.py | 7 + examples/mem_scheduler/redis_example.py | 8 + examples/mem_scheduler/run_async_tasks.py | 9 + examples/mem_scheduler/show_redis_status.py | 19 +- src/memos/graph_dbs/neo4j.py | 2 +- 12 files changed, 89 insertions(+), 547 deletions(-) delete mode 100644 examples/basic_modules/nebular_example.py delete mode 100644 examples/basic_modules/parser.py delete mode 100644 examples/basic_modules/tree_textual_memory_reasoner.py diff --git a/examples/basic_modules/embedder.py b/examples/basic_modules/embedder.py index 7cc7942da..d35dc1797 100644 --- a/examples/basic_modules/embedder.py +++ b/examples/basic_modules/embedder.py @@ -3,7 +3,10 @@ # Scenario 1: Using EmbedderFactory - +# Prerequisites: +# 1. Install Ollama: https://ollama.com/ +# 2. Start Ollama server: `ollama serve` +# 3. Pull the model: `ollama pull nomic-embed-text` config = EmbedderConfigFactory.model_validate( { "backend": "ollama", @@ -33,6 +36,9 @@ # Scenario 3: Using SenTranEmbedder +# Prerequisites: +# 1. Ensure `einops` is installed: `pip install einops` (Required for some HF models like nomic-bert) +# 2. The model `nomic-ai/nomic-embed-text-v1.5` will be downloaded automatically from HuggingFace. config_hf = EmbedderConfigFactory.model_validate( { @@ -49,6 +55,9 @@ print("==" * 20) # === Scenario 4: Using UniversalAPIEmbedder(OpenAI) === +# Prerequisites: +# 1. Set a valid OPENAI_API_KEY +# 2. Ensure the base_url is reachable config_api = EmbedderConfigFactory.model_validate( { @@ -68,6 +77,9 @@ print("Embedding preview:", embedding_api[0][:10]) # === Scenario 5: Using UniversalAPIEmbedder(Azure) === +# Prerequisites: +# 1. Set a valid AZURE_API_KEY +# 2. Ensure the base_url is reachable config_api = EmbedderConfigFactory.model_validate( { diff --git a/examples/basic_modules/llm.py b/examples/basic_modules/llm.py index d33fc9544..fb157c991 100644 --- a/examples/basic_modules/llm.py +++ b/examples/basic_modules/llm.py @@ -5,6 +5,10 @@ # Scenario 1: Using LLMFactory with Ollama Backend # This is the most recommended way! 🌟 +# Prerequisites: +# 1. Install Ollama: https://ollama.com/ +# 2. Start Ollama server: `ollama serve` +# 3. Need python ollama package(>=0.5.0,<0.6.0) config = LLMConfigFactory.model_validate( { @@ -46,6 +50,10 @@ # Scenario 3: Using LLMFactory with OpenAI Backend +# Prerequisites: +# 1. You need a valid OpenAI API key to run this scenario. +# 2. Replace 'sk-xxxx' with your actual API key below. + config = LLMConfigFactory.model_validate( { diff --git a/examples/basic_modules/nebular_example.py b/examples/basic_modules/nebular_example.py deleted file mode 100644 index 13f88e3f3..000000000 --- a/examples/basic_modules/nebular_example.py +++ /dev/null @@ -1,361 +0,0 @@ -import json -import os - -from datetime import datetime, timezone - -import numpy as np - -from dotenv import load_dotenv - -from memos.configs.embedder import EmbedderConfigFactory -from memos.configs.graph_db import GraphDBConfigFactory -from memos.embedders.factory import EmbedderFactory -from memos.graph_dbs.factory import GraphStoreFactory -from memos.memories.textual.item import TextualMemoryItem, TreeNodeTextualMemoryMetadata - - -load_dotenv() - - -def show(nebular_data): - from memos.configs.graph_db import Neo4jGraphDBConfig - from memos.graph_dbs.neo4j import Neo4jGraphDB - - tree_config = Neo4jGraphDBConfig.from_json_file("../../examples/data/config/neo4j_config.json") - tree_config.use_multi_db = True - tree_config.db_name = "nebular-show2" - - neo4j_db = Neo4jGraphDB(tree_config) - neo4j_db.clear() - neo4j_db.import_graph(nebular_data) - - -embedder_config = EmbedderConfigFactory.model_validate( - { - "backend": "universal_api", - "config": { - "provider": "openai", - "api_key": os.getenv("OPENAI_API_KEY", "sk-xxxxx"), - "model_name_or_path": "text-embedding-3-large", - "base_url": os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1"), - }, - } -) -embedder = EmbedderFactory.from_config(embedder_config) -embedder_dimension = 3072 - - -def embed_memory_item(memory: str) -> list[float]: - embedding = embedder.embed([memory])[0] - embedding_np = np.array(embedding, dtype=np.float32) - embedding_list = embedding_np.tolist() - return embedding_list - - -def example_shared_db(db_name: str = "shared-traval-group"): - """ - Example: Single(Shared)-DB multi-tenant (logical isolation) - Multiple users' data in the same Neo4j DB with user_name as a tag. - """ - # users - user_list = ["travel_member_alice", "travel_member_bob"] - - for user_name in user_list: - # Step 1: Build factory config - config = GraphDBConfigFactory( - backend="nebular", - config={ - "uri": json.loads(os.getenv("NEBULAR_HOSTS", "localhost")), - "user": os.getenv("NEBULAR_USER", "root"), - "password": os.getenv("NEBULAR_PASSWORD", "xxxxxx"), - "space": db_name, - "user_name": user_name, - "use_multi_db": False, - "auto_create": True, - "embedding_dimension": embedder_dimension, - }, - ) - - # Step 2: Instantiate graph store - graph = GraphStoreFactory.from_config(config) - print(f"\n[INFO] Working in shared DB: {db_name}, for user: {user_name}") - graph.clear() - - # Step 3: Create topic node - topic = TextualMemoryItem( - memory="This research addresses long-term multi-UAV navigation for energy-efficient communication coverage.", - metadata=TreeNodeTextualMemoryMetadata( - memory_type="LongTermMemory", - key="Multi-UAV Long-Term Coverage", - hierarchy_level="topic", - type="fact", - memory_time="2024-01-01", - source="file", - sources=["paper://multi-uav-coverage/intro"], - status="activated", - confidence=95.0, - tags=["UAV", "coverage", "multi-agent"], - entities=["UAV", "coverage", "navigation"], - visibility="public", - updated_at=datetime.now().isoformat(), - embedding=embed_memory_item( - "This research addresses long-term " - "multi-UAV navigation for " - "energy-efficient communication " - "coverage." - ), - ), - ) - - graph.add_node( - id=topic.id, memory=topic.memory, metadata=topic.metadata.model_dump(exclude_none=True) - ) - - # Step 4: Add a concept for each user - concept = TextualMemoryItem( - memory=f"Itinerary plan for {user_name}", - metadata=TreeNodeTextualMemoryMetadata( - memory_type="LongTermMemory", - key="Multi-UAV Long-Term Coverage", - hierarchy_level="concept", - type="fact", - memory_time="2024-01-01", - source="file", - sources=["paper://multi-uav-coverage/intro"], - status="activated", - confidence=95.0, - tags=["UAV", "coverage", "multi-agent"], - entities=["UAV", "coverage", "navigation"], - visibility="public", - updated_at=datetime.now().isoformat(), - embedding=embed_memory_item(f"Itinerary plan for {user_name}"), - ), - ) - - graph.add_node( - id=concept.id, - memory=concept.memory, - metadata=concept.metadata.model_dump(exclude_none=True), - ) - - # Link concept to topic - graph.add_edge(source_id=concept.id, target_id=topic.id, type="RELATE_TO") - print(f"[INFO] Added nodes for {user_name}") - - # Step 5: Query and print ALL for verification - print("\n=== Export entire DB (for verification, includes ALL users) ===") - graph = GraphStoreFactory.from_config(config) - all_graph_data = graph.export_graph() - print(str(all_graph_data)[:1000]) - - # Step 6: Search for alice's data only - print("\n=== Search for travel_member_alice ===") - config_alice = GraphDBConfigFactory( - backend="nebular", - config={ - "uri": json.loads(os.getenv("NEBULAR_HOSTS", "localhost")), - "user": os.getenv("NEBULAR_USER", "root"), - "password": os.getenv("NEBULAR_PASSWORD", "xxxxxx"), - "space": db_name, - "user_name": user_list[0], - "auto_create": True, - "embedding_dimension": embedder_dimension, - "use_multi_db": False, - }, - ) - graph_alice = GraphStoreFactory.from_config(config_alice) - nodes = graph_alice.search_by_embedding(vector=embed_memory_item("travel itinerary"), top_k=3) - for node in nodes: - print(str(graph_alice.get_node(node["id"]))[:1000]) - - -def run_user_session( - user_name: str, - db_name: str, - topic_text: str, - concept_texts: list[str], - fact_texts: list[str], -): - print(f"\n=== {user_name} starts building their memory graph ===") - - # Manually initialize correct GraphDB class - config = GraphDBConfigFactory( - backend="nebular", - config={ - "uri": json.loads(os.getenv("NEBULAR_HOSTS", "localhost")), - "user": os.getenv("NEBULAR_USER", "root"), - "password": os.getenv("NEBULAR_PASSWORD", "xxxxxx"), - "space": db_name, - "user_name": user_name, - "use_multi_db": False, - "auto_create": True, - "embedding_dimension": embedder_dimension, - }, - ) - graph = GraphStoreFactory.from_config(config) - - # Start with a clean slate for this user - graph.clear() - - now = datetime.now(timezone.utc).isoformat() - - # === Step 1: Create a root topic node (e.g., user's research focus) === - topic = TextualMemoryItem( - memory=topic_text, - metadata=TreeNodeTextualMemoryMetadata( - memory_type="LongTermMemory", - key="Research Topic", - hierarchy_level="topic", - type="fact", - memory_time="2024-01-01", - status="activated", - visibility="public", - tags=["research", "rl"], - updated_at=now, - embedding=embed_memory_item(topic_text), - ), - ) - graph.add_node(topic.id, topic.memory, topic.metadata.model_dump(exclude_none=True)) - - # === Step 2: Create two concept nodes linked to the topic === - concept_items = [] - for i, text in enumerate(concept_texts): - concept = TextualMemoryItem( - memory=text, - metadata=TreeNodeTextualMemoryMetadata( - memory_type="LongTermMemory", - key=f"Concept {i + 1}", - hierarchy_level="concept", - type="fact", - memory_time="2024-01-01", - status="activated", - visibility="public", - updated_at=now, - embedding=embed_memory_item(text), - tags=["concept"], - confidence=90 + i, - ), - ) - graph.add_node(concept.id, concept.memory, concept.metadata.model_dump(exclude_none=True)) - graph.add_edge(topic.id, concept.id, type="PARENT") - concept_items.append(concept) - - # === Step 3: Create supporting facts under each concept === - for i, text in enumerate(fact_texts): - fact = TextualMemoryItem( - memory=text, - metadata=TreeNodeTextualMemoryMetadata( - memory_type="WorkingMemory", - key=f"Fact {i + 1}", - hierarchy_level="fact", - type="fact", - memory_time="2024-01-01", - status="activated", - visibility="public", - updated_at=now, - embedding=embed_memory_item(text), - confidence=85.0, - tags=["fact"], - ), - ) - graph.add_node(fact.id, fact.memory, fact.metadata.model_dump(exclude_none=True)) - graph.add_edge(concept_items[i % len(concept_items)].id, fact.id, type="PARENT") - - # === Step 4: Retrieve memory using semantic search === - vector = embed_memory_item("How is memory retrieved?") - search_result = graph.search_by_embedding(vector, top_k=2) - for r in search_result: - node = graph.get_node(r["id"]) - print("🔍 Search result:", node["memory"]) - - # === Step 5: Tag-based neighborhood discovery === - neighbors = graph.get_neighbors_by_tag(["concept"], exclude_ids=[], top_k=2) - print("📎 Tag-related nodes:", [neighbor["memory"] for neighbor in neighbors]) - - # === Step 6: Retrieve children (facts) of first concept === - children = graph.get_children_with_embeddings(concept_items[0].id) - print("📍 Children of concept:", [child["memory"] for child in children]) - - # === Step 7: Export a local subgraph and grouped statistics === - subgraph = graph.get_subgraph(topic.id, depth=2) - print("📌 Subgraph node count:", len(subgraph["neighbors"])) - - stats = graph.get_grouped_counts(["memory_type", "status"]) - print("📊 Grouped counts:", stats) - - # === Step 8: Demonstrate updates and cleanup === - graph.update_node( - concept_items[0].id, {"confidence": 99.0, "created_at": "2025-07-24T20:11:56.375687"} - ) - graph.remove_oldest_memory("WorkingMemory", keep_latest=1) - graph.delete_edge(topic.id, concept_items[0].id, type="PARENT") - graph.delete_node(concept_items[1].id) - - # === Step 9: Export and re-import the entire graph structure === - exported = graph.export_graph() - graph.import_graph(exported) - print("📦 Graph exported and re-imported, total nodes:", len(exported["nodes"])) - - # ==================================== - # 🔍 Step 10: extra function - # ==================================== - print(f"\n=== 🔍 Extra Tests for user: {user_name} ===") - - print(" - Memory count:", graph.get_memory_count("LongTermMemory")) - print(" - Node count:", graph.count_nodes("LongTermMemory")) - print(" - All LongTermMemory items:", graph.get_all_memory_items("LongTermMemory")) - - if len(exported["edges"]) > 0: - n1, n2 = exported["edges"][0]["source"], exported["edges"][0]["target"] - print(" - Edge exists?", graph.edge_exists(n1, n2, exported["edges"][0]["type"])) - print(" - Edges for node:", graph.get_edges(n1)) - - filters = [{"field": "memory_type", "op": "=", "value": "LongTermMemory"}] - print(" - Metadata query result:", graph.get_by_metadata(filters)) - print( - " - Optimization candidates:", graph.get_structure_optimization_candidates("LongTermMemory") - ) - try: - graph.drop_database() - except ValueError as e: - print(" - drop_database raised ValueError as expected:", e) - - -def example_complex_shared_db(db_name: str = "shared-traval-group-complex"): - # User 1: Alice explores structured memory for LLMs - run_user_session( - user_name="alice", - db_name=db_name, - topic_text="Alice studies structured memory and long-term memory optimization in LLMs.", - concept_texts=[ - "Short-term memory can be simulated using WorkingMemory blocks.", - "A structured memory graph improves retrieval precision for agents.", - ], - fact_texts=[ - "Embedding search is used to find semantically similar memory items.", - "User memories are stored as node-edge structures that support hierarchical reasoning.", - ], - ) - - # User 2: Bob focuses on GNN-based reasoning - run_user_session( - user_name="bob", - db_name=db_name, - topic_text="Bob investigates how graph neural networks can support knowledge reasoning.", - concept_texts=[ - "GNNs can learn high-order relations among entities.", - "Attention mechanisms in graphs improve inference precision.", - ], - fact_texts=[ - "GAT outperforms GCN in graph classification tasks.", - "Multi-hop reasoning helps answer complex queries.", - ], - ) - - -if __name__ == "__main__": - print("\n=== Example: Single-DB ===") - example_shared_db(db_name="shared_traval_group-new") - - print("\n=== Example: Single-DB-Complex ===") - example_complex_shared_db(db_name="shared-traval-group-complex-new2") diff --git a/examples/basic_modules/parser.py b/examples/basic_modules/parser.py deleted file mode 100644 index c063964b7..000000000 --- a/examples/basic_modules/parser.py +++ /dev/null @@ -1,15 +0,0 @@ -from memos.configs.parser import ParserConfigFactory -from memos.parsers.factory import ParserFactory - - -config = ParserConfigFactory.model_validate( - { - "backend": "markitdown", - "config": {}, - } -) -parser = ParserFactory.from_config(config) -file_path = "README.md" -markdown_text = parser.parse(file_path) -print("Markdown text:\n", markdown_text) -print("==" * 20) diff --git a/examples/basic_modules/reranker.py b/examples/basic_modules/reranker.py index 47bf1405c..e5a869789 100644 --- a/examples/basic_modules/reranker.py +++ b/examples/basic_modules/reranker.py @@ -50,6 +50,7 @@ def show_ranked(title: str, ranked: list[tuple[TextualMemoryItem, float]], top_n def main(): # ------------------------------- # 1) Build the embedder (real vectors) + # You may need to set valid OPENAI_API_KEY and OPENAI_API_BASE in your environment variables. # ------------------------------- embedder_cfg = EmbedderConfigFactory.model_validate( { @@ -62,6 +63,22 @@ def main(): }, } ) + """ + # ------------------------------- + # Optional: Build the embedder (using local sentence-transformers) + # ------------------------------- + # Use a local model so no API key is required. + embedder_cfg = EmbedderConfigFactory.model_validate( + { + "backend": "sentence_transformer", + "config": { + "model_name_or_path": "nomic-ai/nomic-embed-text-v1.5", + "trust_remote_code": True, + }, + } + ) + """ + embedder = EmbedderFactory.from_config(embedder_cfg) # ------------------------------- diff --git a/examples/basic_modules/tree_textual_memory_reasoner.py b/examples/basic_modules/tree_textual_memory_reasoner.py deleted file mode 100644 index 369787458..000000000 --- a/examples/basic_modules/tree_textual_memory_reasoner.py +++ /dev/null @@ -1,167 +0,0 @@ -from memos import log -from memos.configs.embedder import EmbedderConfigFactory -from memos.configs.graph_db import GraphDBConfigFactory -from memos.configs.llm import LLMConfigFactory -from memos.embedders.factory import EmbedderFactory -from memos.graph_dbs.factory import GraphStoreFactory -from memos.llms.factory import LLMFactory -from memos.memories.textual.item import TextualMemoryItem, TreeNodeTextualMemoryMetadata -from memos.memories.textual.tree_text_memory.retrieve.reasoner import MemoryReasoner -from memos.memories.textual.tree_text_memory.retrieve.retrieval_mid_structs import ParsedTaskGoal - - -logger = log.get_logger(__name__) - -embedder_config = EmbedderConfigFactory.model_validate( - { - "backend": "ollama", - "config": { - "model_name_or_path": "nomic-embed-text:latest", - }, - } -) -embedder = EmbedderFactory.from_config(embedder_config) - -# Step 1: Load LLM config and instantiate -config = LLMConfigFactory.model_validate( - { - "backend": "ollama", - "config": { - "model_name_or_path": "qwen3:0.6b", - "temperature": 0.7, - "max_tokens": 1024, - }, - } -) -llm = LLMFactory.from_config(config) - -# Step 1: Prepare a mock ParsedTaskGoal -parsed_goal = ParsedTaskGoal( - memories=[ - "Multi-UAV Long-Term Coverage", - "Coverage Metrics", - "Reward Function Design", - "Energy Model", - "CT and FT Definition", - "Reward Components", - "Energy Cost Components", - ], - keys=["UAV", "coverage", "energy", "reward"], - tags=[], - goal_type="explanation", -) - -query = "How can multiple UAVs coordinate to maximize coverage while saving energy?" -query_embedding = embedder.embed([query])[0] - - -# Step 2: Initialize graph store -graph_config = GraphDBConfigFactory( - backend="neo4j", - config={ - "uri": "bolt://localhost:7687", - "user": "neo4j", - "password": "12345678", - "db_name": "user06alice", - "auto_create": True, - }, -) -graph_store = GraphStoreFactory.from_config(graph_config) - -ranked_memories = [ - TextualMemoryItem( - id="a88db9ce-3c77-4e83-8d61-aa9ef95c957e", - memory="Coverage performance is measured using CT (Coverage Time) and FT (Fairness Time) metrics.", - metadata=TreeNodeTextualMemoryMetadata( - user_id=None, - session_id=None, - status="activated", - type="fact", - memory_time="2024-01-01", - source="file", - confidence=91.0, - entities=["CT", "FT"], - tags=["coverage", "fairness", "metrics"], - visibility="public", - updated_at="2025-06-11T11:51:24.438001", - memory_type="LongTermMemory", - key="Coverage Metrics", - value="CT and FT used for long-term area and fairness evaluation", - hierarchy_level="concept", - sources=["paper://multi-uav-coverage/metrics"], - embedding=[0.01] * 768, - ), - ), - TextualMemoryItem( - id="c34f5e6b-2d34-4e6f-8c9b-abcdef123456", - memory="The capital of France is Paris, which is known for the Eiffel Tower.", - metadata=TreeNodeTextualMemoryMetadata( - user_id=None, - session_id=None, - status="activated", - type="fact", - memory_time="2024-01-01", - source="file", - confidence=90.0, - entities=["France", "Paris", "Eiffel Tower"], - tags=["geography", "city", "landmark"], - visibility="public", - updated_at="2025-06-11T11:51:24.438001", - memory_type="LongTermMemory", - key="Geography Fact", - value="Paris is the capital of France", - hierarchy_level="concept", - sources=["wikipedia://paris"], - embedding=[0.03] * 768, - ), - ), - TextualMemoryItem( - id="d56a7b8c-3e45-4f7a-9dab-fedcba654321", - memory="Total energy cost is calculated from both mechanical movement and communication transmission.", - metadata=TreeNodeTextualMemoryMetadata( - user_id=None, - session_id=None, - status="activated", - type="fact", - memory_time="2024-01-01", - source="file", - confidence=89.0, - entities=["movement power", "transmission power"], - tags=["energy", "movement", "transmission"], - visibility="public", - updated_at="2025-06-11T11:51:24.438001", - memory_type="LongTermMemory", - key="Energy Cost Components", - value="Includes movement and communication energy", - hierarchy_level="fact", - sources=["paper://multi-uav-coverage/energy-detail"], - embedding=[0.04] * 768, - ), - ), -] - -# Step 7: Init memory retriever -reasoner = MemoryReasoner(llm=llm) - - -# Step 8: Print retrieved memory items before ranking -print("\n=== Retrieved Memory Items (Before Rerank) ===") -for idx, item in enumerate(ranked_memories): - print(f"[Original #{idx + 1}] ID: {item.id}") - print(f"Memory: {item.memory[:200]}...\n") - -# Step 9: Rerank -reasoned_memories = reasoner.reason( - query=query, - ranked_memories=ranked_memories, - parsed_goal=parsed_goal, -) - -# Step 10: Print ranked reasoned memory items with original positions -print("\n=== Memory Items After Reason (Sorted) ===") -id_to_original_rank = {item.id: i + 1 for i, item in enumerate(ranked_memories)} - -for idx, item in enumerate(reasoned_memories): - original_rank = id_to_original_rank.get(item.id, "-") - print(f"[Reasoned #{idx + 1}] ID: {item.id} (Original #{original_rank})") - print(f"Memory: {item.memory[:200]}...\n") diff --git a/examples/mem_scheduler/api_w_scheduler.py b/examples/mem_scheduler/api_w_scheduler.py index ba3d64bf1..b02161c12 100644 --- a/examples/mem_scheduler/api_w_scheduler.py +++ b/examples/mem_scheduler/api_w_scheduler.py @@ -1,3 +1,12 @@ +""" +# Prerequisites & Configuration +# To run this script, you must have the following services +# running and configured in your .env file (or environment variables): +# 1. Redis (Required for TaskStatusTracker and Scheduler Queue) +# 2. Graph Database (Required for Memory Storage) +# 3. Vector Database (Required if using Neo4j Community or Preference Memory) +""" + import sys from pathlib import Path diff --git a/examples/mem_scheduler/memos_w_scheduler.py b/examples/mem_scheduler/memos_w_scheduler.py index 55e966b5a..b7250a677 100644 --- a/examples/mem_scheduler/memos_w_scheduler.py +++ b/examples/mem_scheduler/memos_w_scheduler.py @@ -1,3 +1,10 @@ +# Prerequisites & Configuration +# To run this script, you must have the following services +# running and configured in your .env file (or environment variables): +# 1. Redis (Required for TaskStatusTracker and Scheduler Queue) +# 2. Graph Database (Required for Memory Storage) +# 3. Vector Database (Required if using Neo4j Community or Preference Memory) + import asyncio import json import os diff --git a/examples/mem_scheduler/redis_example.py b/examples/mem_scheduler/redis_example.py index 9f7ca4139..00989c424 100644 --- a/examples/mem_scheduler/redis_example.py +++ b/examples/mem_scheduler/redis_example.py @@ -1,3 +1,11 @@ +# Prerequisites: +# 1. Ensure a Redis server is running locally on the default port (6379). +# You can start it with: `redis-server` +# On macOS with Homebrew: `/opt/homebrew/bin/redis-server` or `brew services start redis` +# On Linux: `sudo service redis-server start` +# 2. If Redis is running on a different host/port, update the configuration or environment variables accordingly. + + import sys import time diff --git a/examples/mem_scheduler/run_async_tasks.py b/examples/mem_scheduler/run_async_tasks.py index 7f544c3da..fbb5a7bcc 100644 --- a/examples/mem_scheduler/run_async_tasks.py +++ b/examples/mem_scheduler/run_async_tasks.py @@ -1,3 +1,12 @@ +""" +# Prerequisites & Configuration +# To run this script, you must have the following services +# running and configured in your .env file (or environment variables): +# 1. Redis (Required for TaskStatusTracker and Scheduler Queue) +# 2. Graph Database (Required for Memory Storage) +# 3. Vector Database (Required if using Neo4j Community or Preference Memory) +""" + from pathlib import Path from time import sleep diff --git a/examples/mem_scheduler/show_redis_status.py b/examples/mem_scheduler/show_redis_status.py index d88e86655..94a915588 100644 --- a/examples/mem_scheduler/show_redis_status.py +++ b/examples/mem_scheduler/show_redis_status.py @@ -1,10 +1,25 @@ +""" +# Prerequisites: +# 1. Ensure a Redis server is running locally on the default port (6379). +# You can start it with: `redis-server` +# On macOS with Homebrew: `/opt/homebrew/bin/redis-server` or `brew services start redis` +# On Linux: `sudo service redis-server start` +# 2. If Redis is running on a different host/port, update the configuration or environment variables accordingly. +""" + import time -from memos.api.routers.server_router import mem_scheduler +from memos.mem_scheduler.task_schedule_modules.orchestrator import SchedulerOrchestrator from memos.mem_scheduler.task_schedule_modules.redis_queue import SchedulerRedisQueue -queue = mem_scheduler.memos_message_queue.memos_message_queue +# Explicitly initialize Redis queue for monitoring +queue = SchedulerRedisQueue( + max_len=None, + consumer_group="scheduler_group", + consumer_name="monitor_consumer", + orchestrator=SchedulerOrchestrator(), +) def fetch_status( diff --git a/src/memos/graph_dbs/neo4j.py b/src/memos/graph_dbs/neo4j.py index 8698b6f73..d0ae5a555 100644 --- a/src/memos/graph_dbs/neo4j.py +++ b/src/memos/graph_dbs/neo4j.py @@ -1705,7 +1705,7 @@ def _parse_node(self, node_data: dict[str, Any]) -> dict[str, Any]: node.pop("user_name", None) # serialization - if node["sources"]: + if node.get("sources"): for idx in range(len(node["sources"])): if not ( isinstance(node["sources"][idx], str)