watsonx-run.yaml

version: 2

apis:
- agents
- batches
- datasetio
- eval
- files
- inference
- safety
- scoring
- tool_runtime
- vector_io
      
benchmarks: []
datasets: []
image_name: starter
# external_providers_dir: /opt/app-root/src/.llama/providers.d

providers:
  inference:
  - provider_id: watsonx
    provider_type: remote::watsonx
    config:
      base_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
  - config: {} # Enable MCP (Model Context Protocol) support
    provider_id: model-context-protocol
    provider_type: remote::model-context-protocol
  vector_io:
  - config: # Define the storage backend for RAG
      persistence:
        namespace: vector_io::faiss
        backend: kv_rag
    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: []
server:
  port: 8321
storage:
  backends:
    kv_default:
      type: kv_sqlite
      db_path: ${env.KV_STORE_PATH:=~/.llama/storage/kv_store.db}
    kv_rag: # Define the storage backend type for RAG
      type: kv_sqlite
      db_path: ${env.KV_RAG_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: custom-watsonx-model
    provider_id: watsonx
    model_type: llm
    provider_model_id: watsonx/meta-llama/llama-3-3-70b-instruct
  - model_id: all-mpnet-base-v2
    model_type: embedding
    provider_id: sentence-transformers
    provider_model_id: all-mpnet-base-v2
    metadata:
      embedding_dimension: 768
  shields:
  - shield_id: llama-guard
    provider_id: llama-guard
    provider_shield_id: openai/gpt-4o-mini
  vector_stores: 
  - embedding_dimension: 768
    embedding_model: sentence-transformers/all-mpnet-base-v2
    provider_id: faiss
    vector_store_id: ${env.FAISS_VECTOR_STORE_ID}
  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: all-mpnet-base-v2