ansible-chatbot-run.yaml

version: '2'
image_name: ansible-chatbot
container_image: ansible-chatbot
apis:
- inference
- vector_io
- safety
- agents
- datasetio
- tool_runtime
- files
providers:
  inference:
  - provider_id: my_rhoai_dev
    provider_type: remote::vllm
    config:
      base_url: ${env.VLLM_URL}
      max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
      api_token: ${env.VLLM_API_TOKEN:=fake}
      tls_verify: ${env.VLLM_TLS_VERIFY:=true}
  - provider_id: gemini
    provider_type: remote::gemini
    config:
      api_key: ${env.GEMINI_API_KEY:=fake}
  - provider_id: openai
    provider_type: remote::openai
    config:
      api_key: ${env.OPENAI_API_KEY:=}
      base_url: ${env.OPENAI_BASE_URL:=https://api.openai.com/v1}
  - provider_id: sentence-transformers
    provider_type: inline::sentence-transformers
    config: {}
  vector_io:
  - provider_id: aap_faiss
    provider_type: inline::faiss
    config:
      persistence:
        namespace: vector_io::faiss
        backend: kv_rag
  safety:
  - provider_id: llama-guard
    provider_type: inline::llama-guard
    config:
      excluded_categories: []
  agents:
  - provider_id: lightspeed_inline_agent
    provider_type: inline::lightspeed_inline_agent
    config:
#      chatbot_temperature_override: 1.0
      persistence:
        agent_state:
          namespace: agents_state
          backend: kv_default
        responses:
          table_name: agent_responses
          backend: sql_default
      tools_filter:
        enabled: true
        model_id: ${env.INFERENCE_MODEL_FILTER:=}
        always_include_tools:
        - knowledge_search
  datasetio:
  - provider_id: localfs
    provider_type: inline::localfs
    config:
      kvstore:
        namespace: localfs_datasetio
        backend: kv_default
  files:
  - provider_id: meta-reference-files
    provider_type: inline::localfs
    config:
      storage_dir: ${env.PROVIDERS_DB_DIR:=/.llama/data/distributions/ansible-chatbot}/files
      metadata_store:
        table_name: files_metadata
        backend: sql_default
  tool_runtime:
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
  - provider_id: model-context-protocol
    provider_type: remote::model-context-protocol
    config: {}
storage:
  backends:
    kv_rag:
      type: kv_sqlite
      db_path: ${env.VECTOR_DB_DIR:=/.llama/data/distributions/ansible-chatbot}/aap_faiss_store.db
    kv_default:
      type: kv_sqlite
      db_path: ${env.KV_STORE_DB_DIR:=/.llama/data/distributions/ansible-chatbot}/kv_store.db
    sql_default:
      type: sql_sqlite
      db_path: ${env.SQL_STORE_DB_DIR:=/.llama/data/distributions/ansible-chatbot}/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:
    - metadata: {}
      model_id: ${env.INFERENCE_PROVIDER_ID:=my_rhoai_dev}/${env.INFERENCE_MODEL}
      provider_id: ${env.INFERENCE_PROVIDER_ID:=my_rhoai_dev}
      provider_model_id: null
    - metadata:
        embedding_dimension: 768
      model_id: sentence-transformers/all-mpnet-base-v2
      provider_id: sentence-transformers
      provider_model_id: ${env.EMBEDDINGS_MODEL:=/.llama/data/embeddings_model}
      model_type: embedding
  shields: []
  vector_stores:
    - metadata: {}
      vector_store_id: ${env.PROVIDER_VECTOR_DB_ID:=}
      embedding_model: sentence-transformers/${env.EMBEDDINGS_MODEL:=/.llama/data/embeddings_model}
      embedding_dimension: 768
      provider_id: aap_faiss
  datasets: []
  scoring_fns: []
  benchmarks: []
  tool_groups:
    - toolgroup_id: builtin::rag
      provider_id: rag-runtime
  safety:
    - default_shield_id: llama-guard
vector_stores:
  default_provider_id: aap_faiss
  default_embedding_model: # Define the default embedding model for RAG
    provider_id: sentence-transformers
    model_id: /.llama/data/embeddings_model
  annotation_prompt_params:
    enable_annotations: true
    annotation_instruction_template: >
      When appropriate, cite sources at the end of sentences using doc_url and doc_title format. 
      Citing sources is not always required because citations are handled externally. 
      Never include any citation that is in the form '<| file-id |>'.
logging: null
server:
  port: 8321
  tls_certfile: null
  tls_keyfile: null
  tls_cafile: null
  auth: null
  disable_ipv6: false
external_providers_dir: ${env.EXTERNAL_PROVIDERS_DIR:=/.llama/providers.d}