# haiku.rag configuration for Docker deployment
# See https://ggozad.github.io/haiku.rag/configuration/ for details

environment: production

storage:
  data_dir: /data

ingester:
  # Queue lives next to the LanceDB so both persist in the data volume.
  queue:
    path: /data/ingester.db
  api:
    # Bind to all interfaces inside the container so docker port-mapping works.
    host: 0.0.0.0
  sources:
    - type: fs
      id: docs
      root: /docs
      delete_orphans: true

# Remote document processing with docling-serve
processing:
  converter: docling-serve
  chunker: docling-serve
  chunk_size: 256
  chunker_type: hybrid
  chunking_tokenizer: "Qwen/Qwen3-Embedding-0.6B"
  chunking_merge_peers: true
  chunking_use_markdown_tables: false

providers:
  docling_serve:
    base_url: http://docling-serve:5001
    api_key: ""
  ollama:
    base_url: http://host.docker.internal:11434


# For other providers (OpenAI, Anthropic, VoyageAI, etc.),
# see: https://ggozad.github.io/haiku.rag/configuration/