version: '2'
image_name: kubernetes-benchmark-demo
apis:
- agents
- files
- inference
- files
- safety
- telemetry
- tool_runtime
- vector_io
providers:
  inference:
  - provider_id: vllm-inference
    provider_type: remote::vllm
    config:
      url: ${env.VLLM_URL:=http://localhost:8000/v1}
      max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
      api_token: ${env.VLLM_API_TOKEN:=fake}
      tls_verify: ${env.VLLM_TLS_VERIFY:=true}
  - provider_id: sentence-transformers
    provider_type: inline::sentence-transformers
    config: {}
  files:
  - provider_id: meta-reference-files
    provider_type: inline::localfs
    config:
      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}
      metadata_store:
        table_name: files_metadata
        backend: sql_default
  vector_io:
  - provider_id: ${env.ENABLE_CHROMADB:+chromadb}
    provider_type: remote::chromadb
    config:
      url: ${env.CHROMADB_URL:=}
      persistence:
        namespace: vector_io::chroma_remote
        backend: kv_default
  files:
  - provider_id: meta-reference-files
    provider_type: inline::localfs
    config:
      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}
      metadata_store:
        table_name: files_metadata
        backend: sql_default
  safety:
  - provider_id: llama-guard
    provider_type: inline::llama-guard
    config:
      excluded_categories: []
  agents:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      persistence:
        agent_state:
          namespace: agents
          backend: kv_default
        responses:
          table_name: responses
          backend: sql_default
          max_write_queue_size: 10000
          num_writers: 4
  telemetry:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
      sinks: ${env.TELEMETRY_SINKS:=console}
  tool_runtime:
  - provider_id: brave-search
    provider_type: remote::brave-search
    config:
      api_key: ${env.BRAVE_SEARCH_API_KEY:+}
      max_results: 3
  - provider_id: tavily-search
    provider_type: remote::tavily-search
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:+}
      max_results: 3
  - 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_default:
      type: kv_postgres
      host: ${env.POSTGRES_HOST:=localhost}
      port: ${env.POSTGRES_PORT:=5432}
      db: ${env.POSTGRES_DB:=llamastack}
      user: ${env.POSTGRES_USER:=llamastack}
      password: ${env.POSTGRES_PASSWORD:=llamastack}
      table_name: ${env.POSTGRES_TABLE_NAME:=llamastack_kvstore}
    sql_default:
      type: sql_postgres
      host: ${env.POSTGRES_HOST:=localhost}
      port: ${env.POSTGRES_PORT:=5432}
      db: ${env.POSTGRES_DB:=llamastack}
      user: ${env.POSTGRES_USER:=llamastack}
      password: ${env.POSTGRES_PASSWORD:=llamastack}
  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
registered_resources:
  models:
  - metadata:
      embedding_dimension: 768
    model_id: nomic-embed-text-v1.5
    provider_id: sentence-transformers
    model_type: embedding
  - model_id: ${env.INFERENCE_MODEL}
    provider_id: vllm-inference
    model_type: llm
  shields:
  - shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
  vector_dbs: []
  datasets: []
  scoring_fns: []
  benchmarks: []
  tool_groups:
  - toolgroup_id: builtin::websearch
    provider_id: tavily-search
  - toolgroup_id: builtin::rag
    provider_id: rag-runtime
server:
  port: 8323
telemetry:
  enabled: true
vector_stores:
  default_provider_id: chromadb
  default_embedding_model:
    provider_id: sentence-transformers
    model_id: nomic-ai/nomic-embed-text-v1.5