llama-stack-mirror/docs/source/distributions/k8s-benchmark/stack_run_config.yaml

version: '2'
image_name: kubernetes-benchmark-demo
apis:
- agents
- inference
- 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: vllm-safety
    provider_type: remote::vllm
    config:
      url: ${env.VLLM_SAFETY_URL:=http://localhost:8000/v1}
      max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
      api_token: ${env.VLLM_API_TOKEN:=fake}
      tls_verify: ${env.VLLM_TLS_VERIFY:=true}
  - provider_id: mock-vllm-inference
    provider_type: remote::vllm
    config:
      url: http://openai-mock-service:${env.MOCK_INFERENCE_PORT}
      max_tokens: 4096
      api_token: fake
      tls_verify: false
  - provider_id: sentence-transformers
    provider_type: inline::sentence-transformers
    config: {}
  vector_io:
  - provider_id: ${env.ENABLE_CHROMADB:+chromadb}
    provider_type: remote::chromadb
    config:
      url: ${env.CHROMADB_URL:=}
      kvstore:
        type: 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}
  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_store:
        type: 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}
      responses_store:
        type: postgres
        host: ${env.POSTGRES_HOST:=localhost}
        port: ${env.POSTGRES_PORT:=5432}
        db: ${env.POSTGRES_DB:=llamastack}
        user: ${env.POSTGRES_USER:=llamastack}
        password: ${env.POSTGRES_PASSWORD:=llamastack}
  telemetry:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      service_name: "${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: {}
metadata_store:
  type: 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: llamastack_kvstore
inference_store:
  type: 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}
models:
- metadata:
    embedding_dimension: 384
  model_id: all-MiniLM-L6-v2
  provider_id: sentence-transformers
  model_type: embedding
- model_id: ${env.INFERENCE_MODEL}
  provider_id: vllm-inference
  model_type: llm
- model_id: ${env.SAFETY_MODEL}
  provider_id: vllm-safety
  model_type: llm
- model_id: ${env.MOCK_INFERENCE_MODEL}
  provider_id: mock-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