run.yaml

version: 2

apis:
- responses
- batches
- files
- inference
- tool_runtime
- conversations
- vector_io

distro_name: starter

providers:
  inference:
  - provider_id: openai # This ID is a reference to 'providers.inference'
    provider_type: remote::openai
    config:
      api_key: ${env.OPENAI_API_KEY}
      allowed_models: ["${env.E2E_OPENAI_MODEL:=gpt-4o-mini}"]
  - provider_id: sentence-transformers
    provider_type: inline::sentence-transformers
  files:
  - config:
      metadata_store:
        table_name: files_metadata
        backend: sql_default
      storage_dir: ~/.llama/storage/files
    provider_id: meta-reference-files
    provider_type: inline::localfs
  tool_runtime:
  - config: {} # Enable the RAG tool
    provider_id: file-search
    provider_type: inline::file-search
  - config: {} # Enable MCP (Model Context Protocol) support
    provider_id: model-context-protocol
    provider_type: remote::model-context-protocol
  vector_io:
  - config:
      persistence:
        namespace: vector_io::faiss
        backend: kv_default
    provider_id: faiss
    provider_type: inline::faiss
  responses:
  - config:
      persistence:
        responses:
          table_name: agents_responses
          backend: sql_default
    provider_id: builtin
    provider_type: inline::builtin
  batches:
  - config:
      sqlstore:
        table_name: batches
        backend: sql_default
    provider_id: reference
    provider_type: inline::reference
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.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:
      table_name: prompts
      backend: sql_default
    connectors:
      table_name: connectors
      backend: sql_default
registered_resources:
  models: []
  vector_stores: []
# REQUIRED: This section is necessary for file_search tool calls to work.
# Without it, OGX's file-search runtime silently fails all file_search operations
# with no error logged.
vector_stores:
  # LCORE-1498: Disables OGX RAG annotation generation
  # causing unwanted citation/file markers in model output.
  annotation_prompt_params:
    enable_annotations: false
  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