llama-stack-mirror/src/llama_stack/distributions/starter-gpu/run.yaml

version: 2
image_name: starter-gpu
apis:
- agents
- batches
- datasetio
- eval
- files
- inference
- post_training
- safety
- scoring
- tool_runtime
- vector_io
providers:
  inference:
  - provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
    provider_type: remote::cerebras
    config:
      base_url: https://api.cerebras.ai/v1
      api_key: ${env.CEREBRAS_API_KEY:=}
  - provider_id: ${env.OLLAMA_URL:+ollama}
    provider_type: remote::ollama
    config:
      base_url: ${env.OLLAMA_URL:=http://localhost:11434/v1}
  - provider_id: ${env.VLLM_URL:+vllm}
    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: ${env.TGI_URL:+tgi}
    provider_type: remote::tgi
    config:
      base_url: ${env.TGI_URL:=}
  - provider_id: fireworks
    provider_type: remote::fireworks
    config:
      base_url: https://api.fireworks.ai/inference/v1
      api_key: ${env.FIREWORKS_API_KEY:=}
  - provider_id: together
    provider_type: remote::together
    config:
      base_url: https://api.together.xyz/v1
      api_key: ${env.TOGETHER_API_KEY:=}
  - provider_id: bedrock
    provider_type: remote::bedrock
    config:
      api_key: ${env.AWS_BEARER_TOKEN_BEDROCK:=}
      region_name: ${env.AWS_DEFAULT_REGION:=us-east-2}
  - provider_id: ${env.NVIDIA_API_KEY:+nvidia}
    provider_type: remote::nvidia
    config:
      base_url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com/v1}
      api_key: ${env.NVIDIA_API_KEY:=}
  - 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: anthropic
    provider_type: remote::anthropic
    config:
      api_key: ${env.ANTHROPIC_API_KEY:=}
  - provider_id: gemini
    provider_type: remote::gemini
    config:
      api_key: ${env.GEMINI_API_KEY:=}
  - provider_id: ${env.VERTEX_AI_PROJECT:+vertexai}
    provider_type: remote::vertexai
    config:
      project: ${env.VERTEX_AI_PROJECT:=}
      location: ${env.VERTEX_AI_LOCATION:=us-central1}
  - provider_id: groq
    provider_type: remote::groq
    config:
      base_url: https://api.groq.com/openai/v1
      api_key: ${env.GROQ_API_KEY:=}
  - provider_id: sambanova
    provider_type: remote::sambanova
    config:
      base_url: https://api.sambanova.ai/v1
      api_key: ${env.SAMBANOVA_API_KEY:=}
  - provider_id: ${env.AZURE_API_KEY:+azure}
    provider_type: remote::azure
    config:
      api_key: ${env.AZURE_API_KEY:=}
      base_url: ${env.AZURE_API_BASE:=}
      api_version: ${env.AZURE_API_VERSION:=}
      api_type: ${env.AZURE_API_TYPE:=}
  - provider_id: sentence-transformers
    provider_type: inline::sentence-transformers
  vector_io:
  - provider_id: faiss
    provider_type: inline::faiss
    config:
      persistence:
        namespace: vector_io::faiss
        backend: kv_default
  - provider_id: sqlite-vec
    provider_type: inline::sqlite-vec
    config:
      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/sqlite_vec.db
      persistence:
        namespace: vector_io::sqlite_vec
        backend: kv_default
  - provider_id: ${env.MILVUS_URL:+milvus}
    provider_type: inline::milvus
    config:
      db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/starter-gpu}/milvus.db
      persistence:
        namespace: vector_io::milvus
        backend: kv_default
  - provider_id: ${env.CHROMADB_URL:+chromadb}
    provider_type: remote::chromadb
    config:
      url: ${env.CHROMADB_URL:=}
      persistence:
        namespace: vector_io::chroma_remote
        backend: kv_default
  - provider_id: ${env.PGVECTOR_DB:+pgvector}
    provider_type: remote::pgvector
    config:
      host: ${env.PGVECTOR_HOST:=localhost}
      port: ${env.PGVECTOR_PORT:=5432}
      db: ${env.PGVECTOR_DB:=}
      user: ${env.PGVECTOR_USER:=}
      password: ${env.PGVECTOR_PASSWORD:=}
      persistence:
        namespace: vector_io::pgvector
        backend: kv_default
  - provider_id: ${env.QDRANT_URL:+qdrant}
    provider_type: remote::qdrant
    config:
      api_key: ${env.QDRANT_API_KEY:=}
      persistence:
        namespace: vector_io::qdrant_remote
        backend: kv_default
  - provider_id: ${env.WEAVIATE_CLUSTER_URL:+weaviate}
    provider_type: remote::weaviate
    config:
      weaviate_api_key: null
      weaviate_cluster_url: ${env.WEAVIATE_CLUSTER_URL:=localhost:8080}
      persistence:
        namespace: vector_io::weaviate
        backend: kv_default
  files:
  - provider_id: meta-reference-files
    provider_type: inline::localfs
    config:
      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter-gpu/files}
      metadata_store:
        table_name: files_metadata
        backend: sql_default
  safety:
  - provider_id: llama-guard
    provider_type: inline::llama-guard
    config:
      excluded_categories: []
  - provider_id: code-scanner
    provider_type: inline::code-scanner
  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
  post_training:
  - provider_id: huggingface-gpu
    provider_type: inline::huggingface-gpu
    config:
      checkpoint_format: huggingface
      distributed_backend: null
      device: cpu
      dpo_output_dir: ~/.llama/distributions/starter-gpu/dpo_output
  eval:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      kvstore:
        namespace: eval
        backend: kv_default
  datasetio:
  - provider_id: huggingface
    provider_type: remote::huggingface
    config:
      kvstore:
        namespace: datasetio::huggingface
        backend: kv_default
  - provider_id: localfs
    provider_type: inline::localfs
    config:
      kvstore:
        namespace: datasetio::localfs
        backend: kv_default
  scoring:
  - provider_id: basic
    provider_type: inline::basic
  - provider_id: llm-as-judge
    provider_type: inline::llm-as-judge
  - provider_id: braintrust
    provider_type: inline::braintrust
    config:
      openai_api_key: ${env.OPENAI_API_KEY:=}
  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
  - provider_id: model-context-protocol
    provider_type: remote::model-context-protocol
  batches:
  - provider_id: reference
    provider_type: inline::reference
    config:
      kvstore:
        namespace: batches
        backend: kv_default
storage:
  backends:
    kv_default:
      type: kv_sqlite
      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/kvstore.db
    sql_default:
      type: sql_sqlite
      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/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: []
  shields:
  - shield_id: llama-guard
    provider_id: ${env.SAFETY_MODEL:+llama-guard}
    provider_shield_id: ${env.SAFETY_MODEL:=}
  - shield_id: code-scanner
    provider_id: ${env.CODE_SCANNER_MODEL:+code-scanner}
    provider_shield_id: ${env.CODE_SCANNER_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
server:
  port: 8321
telemetry:
  enabled: true
vector_stores:
  default_provider_id: faiss
  default_embedding_model:
    provider_id: sentence-transformers
    model_id: nomic-ai/nomic-embed-text-v1.5
safety:
  default_shield_id: llama-guard