LCORE-332: Lightspeed core needs to fully support WatsonX LLM provider #943
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,168 @@ | ||
| version: 2 | ||
|
|
||
| apis: | ||
| - agents | ||
| - batches | ||
| - datasetio | ||
| - eval | ||
| - files | ||
| - inference | ||
| - safety | ||
| - scoring | ||
| - telemetry | ||
| - tool_runtime | ||
| - vector_io | ||
|
|
||
| benchmarks: [] | ||
| conversations_store: | ||
| db_path: ${env.SQLITE_STORE_DIR:=~/.llama/storage/conversations.db} | ||
| type: sqlite | ||
| datasets: [] | ||
| image_name: starter | ||
| # external_providers_dir: /opt/app-root/src/.llama/providers.d | ||
| inference_store: | ||
| db_path: ${env.SQLITE_STORE_DIR:=~/.llama/storage/inference-store.db} | ||
| type: sqlite | ||
| metadata_store: | ||
| db_path: ${env.SQLITE_STORE_DIR:=~/.llama/storage/registry.db} | ||
| type: sqlite | ||
|
|
||
| providers: | ||
| inference: | ||
| - provider_id: watsonx | ||
| provider_type: remote::watsonx | ||
| config: | ||
| url: ${env.WATSONX_BASE_URL:=https://us-south.ml.cloud.ibm.com} | ||
| api_key: ${env.WATSONX_API_KEY:=key-not-set} | ||
| project_id: ${env.WATSONX_PROJECT_ID:=project-not-set} | ||
| timeout: 1200 | ||
| - provider_id: openai | ||
| provider_type: remote::openai | ||
| config: | ||
| api_key: ${env.OPENAI_API_KEY} | ||
| - config: {} | ||
| provider_id: sentence-transformers | ||
| provider_type: inline::sentence-transformers | ||
| files: | ||
| - config: | ||
| metadata_store: | ||
| table_name: files_metadata | ||
| backend: sql_default | ||
| storage_dir: ${env.SQLITE_STORE_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: | ||
| - 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: '********' | ||
| tool_runtime: | ||
| - config: {} # Enable the RAG tool | ||
| provider_id: rag-runtime | ||
| provider_type: inline::rag-runtime | ||
| vector_io: | ||
| - config: # Define the storage backend for RAG | ||
| persistence: | ||
| namespace: vector_io::faiss | ||
| backend: kv_default | ||
| provider_id: faiss | ||
| provider_type: inline::faiss | ||
| agents: | ||
| - 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 | ||
| batches: | ||
| - config: | ||
| kvstore: | ||
| namespace: batches_store | ||
| backend: kv_default | ||
| provider_id: reference | ||
| provider_type: inline::reference | ||
| datasetio: | ||
| - config: | ||
| kvstore: | ||
| namespace: huggingface_datasetio | ||
| backend: kv_default | ||
| provider_id: huggingface | ||
| provider_type: remote::huggingface | ||
| - config: | ||
| kvstore: | ||
| namespace: localfs_datasetio | ||
| backend: kv_default | ||
| provider_id: localfs | ||
| provider_type: inline::localfs | ||
| eval: | ||
| - config: | ||
| kvstore: | ||
| namespace: eval_store | ||
| backend: kv_default | ||
| provider_id: meta-reference | ||
| provider_type: inline::meta-reference | ||
| scoring_fns: [] | ||
| telemetry: | ||
| enabled: true | ||
| server: | ||
| port: 8321 | ||
| storage: | ||
| backends: | ||
| kv_default: # Define the storage backend type for RAG, in this case registry and RAG are unified i.e. information on registered resources (e.g. models, vector_stores) are saved together with the RAG chunks | ||
| type: kv_sqlite | ||
| db_path: ${env.SQLITE_STORE_DIR:=~/.llama/storage/rag/kv_store.db} | ||
| sql_default: | ||
| type: sql_sqlite | ||
| db_path: ${env.SQLITE_STORE_DIR:=~/.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: custom-watsonx-model | ||
| provider_id: watsonx | ||
| model_type: llm | ||
| provider_model_id: watsonx/meta-llama/llama-3-3-70b-instruct | ||
| shields: | ||
| - shield_id: llama-guard | ||
| provider_id: llama-guard | ||
| provider_shield_id: openai/gpt-4o-mini | ||
| vector_dbs: [] | ||
| datasets: [] | ||
| scoring_fns: [] | ||
| benchmarks: [] | ||
| tool_groups: | ||
| - toolgroup_id: builtin::rag # Register the RAG tool | ||
| provider_id: rag-runtime | ||
| vector_stores: | ||
| default_provider_id: faiss | ||
| default_embedding_model: # Define the default embedding model for RAG | ||
| provider_id: sentence-transformers | ||
| model_id: nomic-ai/nomic-embed-text-v1.5 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.