# SPARKNET RAG Configuration
# ===========================

# Vector Store Configuration
vector_store:
  # Store type: "chromadb" (default)
  type: chromadb

  # ChromaDB settings
  chromadb:
    persist_directory: ./data/vectorstore
    collection_name: sparknet_documents
    anonymized_telemetry: false

  # Search settings
  default_top_k: 5
  similarity_threshold: 0.7

# Embedding Configuration
embeddings:
  # Adapter type: "ollama" (default) or "openai"
  adapter_type: ollama

  # Ollama settings (local, default)
  ollama:
    base_url: http://localhost:11434
    model: nomic-embed-text  # Options: nomic-embed-text, mxbai-embed-large, all-minilm

  # OpenAI settings (optional, feature-flagged)
  openai:
    enabled: false
    model: text-embedding-3-small  # Options: text-embedding-3-small, text-embedding-3-large
    # api_key: ${OPENAI_API_KEY}  # Use env var

  # Common settings
  batch_size: 32
  timeout: 60

  # Caching
  enable_cache: true
  cache_directory: ./data/embedding_cache

# Indexer Configuration
indexer:
  # Batch processing
  batch_size: 32

  # Metadata to index
  include_bbox: true
  include_page: true
  include_chunk_type: true

  # Filtering
  skip_empty_chunks: true
  min_chunk_length: 10

# Retriever Configuration
retriever:
  # Search parameters
  default_top_k: 5
  similarity_threshold: 0.7
  max_results: 20

  # Reranking (future)
  enable_reranking: false
  rerank_top_k: 10

  # Evidence settings
  include_evidence: true
  evidence_snippet_length: 200

# Generator Configuration
generator:
  # LLM provider: "ollama" (default) or "openai"
  llm_provider: ollama

  # Ollama settings
  ollama:
    base_url: http://localhost:11434
    model: llama3.2:3b  # Options: llama3.2:3b, llama3.1:8b, mistral

  # OpenAI settings (optional)
  openai:
    model: gpt-4o-mini  # Options: gpt-4o-mini, gpt-4o
    # api_key: ${OPENAI_API_KEY}  # Use env var

  # Generation settings
  temperature: 0.1
  max_tokens: 1024
  timeout: 120

  # Citation settings
  require_citations: true
  citation_format: "[{index}]"

  # Abstention settings
  abstain_on_low_confidence: true
  confidence_threshold: 0.6

# Query Processing
query:
  # Query expansion
  expand_queries: false
  max_expansions: 3

  # Hybrid search (future)
  enable_hybrid: false
  keyword_weight: 0.3
  semantic_weight: 0.7

# Metadata Filtering
filters:
  # Supported filter types
  supported:
    - document_id
    - chunk_type
    - page
    - confidence_min

  # Default filters (applied to all queries)
  defaults: {}

# Performance Settings
performance:
  # Connection pooling
  max_connections: 10

  # Timeouts
  embedding_timeout: 60
  search_timeout: 30
  generation_timeout: 120

  # Caching
  query_cache_enabled: true
  query_cache_ttl: 3600  # Seconds

# Logging
logging:
  level: INFO
  include_queries: false  # Log user queries (privacy consideration)
  include_latency: true