lightspeed-stack-inline-rag.yaml

name: Lightspeed Core Service (LCS)
service:
  host: 0.0.0.0
  port: 8080
  auth_enabled: false
  workers: 1
  color_log: true
  access_log: true
llama_stack:
  use_as_library_client: false
  url: http://llama-stack:8321
  api_key: xyzzy
user_data_collection:
  feedback_enabled: true
  feedback_storage: "/tmp/data/feedback"
  transcripts_enabled: true
  transcripts_storage: "/tmp/data/transcripts"

conversation_cache:
  type: "sqlite"
  sqlite:
    db_path: "/tmp/data/conversation-cache.db"

authentication:
  module: "noop"
inference:
  default_provider: openai
  default_model: gpt-4o-mini

byok_rag:
  - rag_id: e2e-test-docs
    rag_type: inline::faiss
    embedding_model: sentence-transformers/all-mpnet-base-v2
    embedding_dimension: 768
    vector_db_id: ${env.FAISS_VECTOR_STORE_ID}
    db_path: ${env.KV_RAG_PATH:=~/.llama/storage/rag/kv_store.db}
    score_multiplier: 1.0

rag:
  inline:
    - e2e-test-docs