Skip to content

LCORE-603: Lightspeed core needs to fully support Faiss VectorIO provider #935

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
are-ces wants to merge 1 commit into
base: main
Choose a base branch
from
Open

LCORE-603: Lightspeed core needs to fully support Faiss VectorIO provider #935

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docker-compose-library.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@ services:
- ./lightspeed-stack.yaml:/app-root/lightspeed-stack.yaml:Z
- ./run.yaml:/app-root/run.yaml:Z
- ${GCP_KEYS_PATH:-./tmp/.gcp-keys-dummy}:/opt/app-root/.gcp-keys:ro
- ./tests/e2e/rag:/opt/app-root/src/.llama/storage/rag:Z
environment:
- BRAVE_SEARCH_API_KEY=${BRAVE_SEARCH_API_KEY:-}
- TAVILY_SEARCH_API_KEY=${TAVILY_SEARCH_API_KEY:-}
Expand Down
1 change: 1 addition & 0 deletions docker-compose.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@ services:
volumes:
- ./run.yaml:/opt/app-root/run.yaml:Z
- ${GCP_KEYS_PATH:-./tmp/.gcp-keys-dummy}:/opt/app-root/.gcp-keys:ro
- ./tests/e2e/rag:/opt/app-root/src/.llama/storage/rag:Z
environment:
- BRAVE_SEARCH_API_KEY=${BRAVE_SEARCH_API_KEY:-}
- TAVILY_SEARCH_API_KEY=${TAVILY_SEARCH_API_KEY:-}
Expand Down
4 changes: 2 additions & 2 deletions docs/providers.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,7 +100,7 @@ Red Hat providers:
| Name | Type | Pip Dependencies | Supported in LCS |
|---|---|---|:---:|
| code-scanner | inline | `codeshield` | ❌ |
| llama-guard | inline | — | ✅ |
| llama-guard | inline | — | ❌ |
| prompt-guard | inline | `transformers[accelerate]`, `torch --index-url https://download.pytorch.org/whl/cpu` | ❌ |
| bedrock | remote | `boto3` | ❌ |
| nvidia | remote | `requests` | ❌ |
Expand Down Expand Up @@ -157,7 +157,7 @@ Red Hat providers:

| Name | Type | Pip Dependencies | Supported in LCS |
|---|---|---|:---:|
| rag-runtime | inline | `chardet`,`pypdf`, `tqdm`, `numpy`, `scikit-learn`, `scipy`, `nltk`, `sentencepiece`, `transformers` | ❌ |
| rag-runtime | inline | `chardet`,`pypdf`, `tqdm`, `numpy`, `scikit-learn`, `scipy`, `nltk`, `sentencepiece`, `transformers` | ✅ |
| bing-search | remote | `requests` | ❌ |
| brave-search | remote | `requests` | ❌ |
| model-context-protocol | remote | `mcp>=1.8.1` | ✅ |
Expand Down
239 changes: 136 additions & 103 deletions examples/azure-run.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,128 +1,161 @@
version: '2'
image_name: minimal-viable-llama-stack-configuration
version: 2
image_name: azure-configuration

apis:
- agents
- datasetio
- eval
- files
- inference
- post_training
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
- agents
- batches
- datasetio
- eval
- files
- inference
- safety
- scoring
- telemetry
- tool_runtime
- vector_io

benchmarks: []
container_image: null
conversations_store:
db_path: ~/.llama/storage/conversations.db
type: sqlite
datasets: []
external_providers_dir: null
# external_providers_dir: /opt/app-root/src/.llama/providers.d
inference_store:
db_path: .llama/distributions/ollama/inference_store.db
db_path: ~/.llama/storage/inference-store.db
type: sqlite
logging: null
metadata_store:
db_path: .llama/distributions/ollama/registry.db
namespace: null
db_path: ~/.llama/storage/registry.db
type: sqlite

providers:
files:
- provider_id: localfs
provider_type: inline::localfs
inference:
- provider_id: azure
provider_type: remote::azure
config:
api_key: ${env.AZURE_API_KEY}
api_base: https://ols-test.openai.azure.com/
api_version: 2024-02-15-preview
Copy link
Contributor

@coderabbitai coderabbitai bot Jan 13, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

🧩 Analysis chain

🌐 Web query:

Azure OpenAI API versions 2024 2025 latest current

💡 Result:

Short answer

  • Latest GA Azure OpenAI Service API version: 2024-06-01. [1]
  • Latest preview / Foundry API versions (most recent preview cycle): 2025-04-01-preview (and incremental preview dates like 2025-03-01-preview, 2025-02-01-preview, 2024-12-01-preview are documented). [2]

Notes

  • Microsoft documents the API-version lifecycle and change history for Azure OpenAI / Foundry (preview versions listed through 2025-04-01-preview). [2]
  • If you use the Assistants API, v1 is being retired (migration to v2 required—retirement notices in 2025), so check the specific retirement date for your region. [3]

Sources

  1. Rollout / Azure OpenAI Service summary (latest GA = 2024-06-01). [4]
  2. Microsoft Learn — Azure OpenAI / Foundry API version lifecycle (preview releases through 2025-04-01-preview). [2]
  3. Announcement / notices re: Assistants API v1 retirement. [3]

Would you like direct links to the specific Microsoft docs or help updating code to a particular api-version?

Update Azure OpenAI API version to current release.

The api_version: 2024-02-15-preview is outdated. The latest GA version is 2024-06-01, with preview versions available through 2025-04-01-preview. Update to at least the stable 2024-06-01 release to ensure access to current features and improvements.

🤖 Prompt for AI Agents 
In @examples/azure-run.yaml at line 36, Update the api_version value for Azure
OpenAI in the YAML: replace the outdated "2024-02-15-preview" with the stable GA
"2024-06-01" (or a newer preview like "2025-04-01-preview" if preview features
are required) by editing the api_version key in the Azure config block so the
example uses a current supported API version.

- provider_id: openai
provider_type: remote::openai
config:
storage_dir: /tmp/llama-stack-files
api_key: ${env.OPENAI_API_KEY}
- config: {}
provider_id: sentence-transformers
provider_type: inline::sentence-transformers
files:
- config:
metadata_store:
type: sqlite
db_path: .llama/distributions/ollama/files_metadata.db
table_name: files_metadata
backend: sql_default
storage_dir: ~/.llama/storage/files
provider_id: meta-reference-files
provider_type: inline::localfs
safety:
- config:
excluded_categories: []
provider_id: llama-guard
provider_type: inline::llama-guard
scoring:
- config: {}
provider_id: basic
provider_type: inline::basic
tool_runtime:
- config: {}
provider_id: rag-runtime
provider_type: inline::rag-runtime
vector_io:
- config:
persistence:
namespace: vector_io::faiss
backend: kv_default
provider_id: faiss
provider_type: inline::faiss
agents:
- provider_id: meta-reference
- config:
persistence:
agent_state:
namespace: agents_state
backend: kv_default
responses:
table_name: agents_responses
backend: sql_default
provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence_store:
db_path: .llama/distributions/ollama/agents_store.db
namespace: null
type: sqlite
responses_store:
db_path: .llama/distributions/ollama/responses_store.db
type: sqlite
batches:
- config:
kvstore:
namespace: batches_store
backend: kv_default
provider_id: reference
provider_type: inline::reference
datasetio:
- provider_id: huggingface
- config:
kvstore:
namespace: huggingface_datasetio
backend: kv_default
provider_id: huggingface
provider_type: remote::huggingface
config:
- config:
kvstore:
db_path: .llama/distributions/ollama/huggingface_datasetio.db
namespace: null
type: sqlite
- provider_id: localfs
namespace: localfs_datasetio
backend: kv_default
provider_id: localfs
provider_type: inline::localfs
config:
kvstore:
db_path: .llama/distributions/ollama/localfs_datasetio.db
namespace: null
type: sqlite
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
- config:
kvstore:
db_path: .llama/distributions/ollama/meta_reference_eval.db
namespace: null
type: sqlite
inference:
- provider_id: azure
provider_type: remote::azure
config:
api_key: ${env.AZURE_API_KEY}
api_base: https://ols-test.openai.azure.com/
api_version: 2024-02-15-preview
api_type: ${env.AZURE_API_TYPE:=}
post_training:
- provider_id: huggingface
provider_type: inline::huggingface-gpu
config:
checkpoint_format: huggingface
device: cpu
distributed_backend: null
dpo_output_dir: "."
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config:
excluded_categories: []
scoring:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: llm-as-judge
provider_type: inline::llm-as-judge
config: {}
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: '********'
telemetry:
- provider_id: meta-reference
namespace: eval_store
backend: kv_default
provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: 'lightspeed-stack-telemetry'
sinks: sqlite
sqlite_db_path: .llama/distributions/ollama/trace_store.db
tool_runtime:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
scoring_fns: []
server:
auth: null
host: null
port: 8321
quota: null
tls_cafile: null
tls_certfile: null
tls_keyfile: null
shields: []
models:
storage:
backends:
kv_default:
type: kv_sqlite
db_path: ${env.KV_STORE_PATH:=~/.llama/storage/rag/kv_store.db}
sql_default:
type: sql_sqlite
db_path: ${env.SQL_STORE_PATH:=~/.llama/storage/sql_store.db}
stores:
metadata:
namespace: registry
backend: kv_default
inference:
table_name: inference_store
backend: sql_default
max_write_queue_size: 10000
num_writers: 4
conversations:
table_name: openai_conversations
backend: sql_default
prompts:
namespace: prompts
backend: kv_default
registered_resources:
models:
- model_id: gpt-4o-mini
model_type: llm
provider_id: azure
provider_model_id: gpt-4o-mini
model_type: llm
provider_model_id: gpt-4o-mini
shields:
- shield_id: llama-guard
provider_id: llama-guard
provider_shield_id: openai/gpt-4o-mini
datasets: []
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::rag
provider_id: rag-runtime
vector_stores:
default_provider_id: faiss
default_embedding_model:
provider_id: sentence-transformers
model_id: nomic-ai/nomic-embed-text-v1.5
safety:
default_shield_id: llama-guard
telemetry:
enabled: true
Loading
Loading