# Devour Example Configuration
# Copy this file to devour.yaml and customize for your needs

version: 1

# Storage paths
storage:
  docs_dir: ./devour_data/docs
  index_dir: ./devour_data/index
  metadata_dir: ./devour_data/metadata

# Embedding settings
embeddings:
  provider: openai           # openai, mock
  model: text-embedding-3-small
  dimensions: 1536
  api_key: ${OPENAI_API_KEY} # Use environment variable
  batch_size: 100

# Vector database
vector_db:
  type: memory               # memory, chromem
  persist: true
  similarity_metric: cosine

# Scraping settings
scraper:
  user_agent: "Devour/1.0 (+https://github.com/yourorg/devour)"
  timeout: 30s
  retry_count: 3
  retry_delay: 5s
  concurrency: 10
  rate_limit: 500ms
  max_depth: 3
  cache_dir: ./devour_data/cache

# Scheduler
scheduler:
  enabled: true
  interval: 72h              # Every 3 days
  check_method: hash         # hash, timestamp
  on_startup: false

# Server settings
server:
  mode: local                # local, remote
  port: 8080
  host: localhost

# Example sources
sources:
  # Web documentation
  - name: example-docs
    type: url
    url: https://docs.example.com
    include:
      - ".*\\.md"
      - ".*\\.html"
    exclude:
      - ".*/api/.*"
      - ".*/legacy/.*"
    schedule: 24h

  # OpenAPI specification
  - name: api-spec
    type: openapi
    url: https://api.example.com/openapi.json
    schedule: 168h           # Weekly

  # GitHub repository
  - name: github-repo
    type: github
    repo: org/repository
    branch: main
    include:
      - "docs/.*"
      - "README.md"
    exclude:
      - "docs/internal/.*"
    # auth_token: ${GITHUB_TOKEN}  # Optional for private repos

  # Local files
  - name: local-docs
    type: local
    path: ./docs
    include:
      - ".*\\.md"
      - ".*\\.txt"