lightspeed-stack-byok-okp-rag.yaml

name: Lightspeed Core Service (LCS)
service:
  host: localhost
  port: 8080
  auth_enabled: false
  workers: 1
  color_log: true
  access_log: true
llama_stack:
  use_as_library_client: false
  url: http://localhost:8321
  api_key: xyzzy
user_data_collection:
  feedback_enabled: true
  feedback_storage: "/tmp/data/feedback"
  transcripts_enabled: true
  transcripts_storage: "/tmp/data/transcripts"
authentication:
  module: "noop"
quota_handlers:
  sqlite:
      db_path: quota.sqlite
  limiters:
    - name: user_monthly_limits
      type: user_limiter
      initial_quota: 50
      quota_increase: 50
      period: "30 seconds"
    - name: cluster_monthly_limits
      type: cluster_limiter
      initial_quota: 100
      quota_increase: 100
      period: "30 seconds"
  scheduler:
    # scheduler ticks in seconds
    period: 10
byok_rag:
  - rag_id: ocp-docs           # referenced in rag.inline / rag.tool
    rag_type: inline::faiss
    embedding_dimension: 1024
    vector_db_id: vs_123       # Llama-stack vector_store_id
    db_path: /tmp/ocp.faiss
    score_multiplier: 1.0      # Weight for this vector store's results (Inline RAG only)
  - rag_id: knowledge-base     # referenced in rag.inline / rag.tool
    rag_type: inline::faiss
    embedding_dimension: 384
    vector_db_id: vs_456       # Llama-stack vector_store_id
    db_path: /tmp/kb.faiss
    score_multiplier: 1.2      # Weight for this vector store's results (Inline RAG only)

# RAG configuration
rag:
  # Inline RAG: context injected before the LLM request from the listed sources
  # List rag_ids from byok_rag, or 'okp' to include OKP
  inline:
    - ocp-docs
    - knowledge-base
    - okp
  # Tool RAG: LLM can call file_search on demand to retrieve context
  # List rag_ids from byok_rag, or 'okp' to include OKP
  # Omit to use all registered BYOK stores (backward compatibility)
  tool:
    - ocp-docs
    - knowledge-base

# OKP provider settings (only used when 'okp' is listed in rag.inline or rag.tool)
okp:
  offline: true    # true = use parent_id for source URLs, false = use reference_url
  # Additional Solr filter query applied to every OKP search request.
  # Use Solr boolean syntax
  # chunk_filter_query: "product:*ansible* AND product:*openshift*"