llama-stack-mirror/llama_stack/templates/remote-vllm/run-with-safety.yaml

version: '2'
image_name: remote-vllm
apis:
- agents
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
providers:
  inference:
  - provider_id: vllm-inference
    provider_type: remote::vllm
    config:
      url: ${env.VLLM_URL}
      max_tokens: ${env.VLLM_MAX_TOKENS:4096}
      api_token: ${env.VLLM_API_TOKEN:fake}
  - provider_id: vllm-safety
    provider_type: remote::vllm
    config:
      url: ${env.SAFETY_VLLM_URL}
      max_tokens: ${env.VLLM_MAX_TOKENS:4096}
      api_token: ${env.VLLM_API_TOKEN:fake}
  - provider_id: sentence-transformers
    provider_type: inline::sentence-transformers
    config: {}
  vector_io:
  - provider_id: faiss
    provider_type: inline::faiss
    config:
      kvstore:
        type: sqlite
        namespace: null
        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/faiss_store.db
  safety:
  - provider_id: llama-guard
    provider_type: inline::llama-guard
    config: {}
  agents:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      persistence_store:
        type: sqlite
        namespace: null
        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/agents_store.db
  eval:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config: {}
  datasetio:
  - provider_id: huggingface
    provider_type: remote::huggingface
    config: {}
  - provider_id: localfs
    provider_type: inline::localfs
    config: {}
  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: ${env.OPENAI_API_KEY:}
  telemetry:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/remote-vllm/trace_store.db}
  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: code-interpreter
    provider_type: inline::code-interpreter
    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
  - provider_id: model-context-protocol
    provider_type: remote::model-context-protocol
    config: {}
  - provider_id: wolfram-alpha
    provider_type: remote::wolfram-alpha
    config: {}
  preprocessing:
  - provider_id: basic
    provider_type: inline::basic
    config: {}
  - provider_id: simple_chunking
    provider_type: inline::simple_chunking
    config: {}
metadata_store:
  type: sqlite
  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db
models:
- metadata: {}
  model_id: ${env.INFERENCE_MODEL}
  provider_id: vllm-inference
  model_type: llm
- metadata: {}
  model_id: ${env.SAFETY_MODEL}
  provider_id: vllm-safety
  model_type: llm
- metadata:
    embedding_dimension: 384
  model_id: all-MiniLM-L6-v2
  provider_id: sentence-transformers
  model_type: embedding
shields:
- shield_id: ${env.SAFETY_MODEL}
vector_dbs: []
datasets: []
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::websearch
  provider_id: tavily-search
- toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
  provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
  provider_id: wolfram-alpha
preprocessors:
- preprocessor_id: builtin::basic
  provider_id: basic
- preprocessor_id: builtin::chunking
  provider_id: simple_chunking
server:
  port: 8321