databricks.yml

# This is a Declarative Automation Bundle definition for ai_parse_document_workflow.
# See https://docs.databricks.com/dev-tools/bundles/index.html for documentation.
bundle:
  name: ai_parse_document_workflow

variables:
  catalog:
    description: The catalog name for the workflow
    default: main
  schema:
    description: The schema name for the workflow
    default: default
  source_volume_path:
    description: Source volume path for PDF files
    default: /Volumes/main/default/source_documents
  output_volume_path:
    description: Output volume path for processed images
    default: /Volumes/main/default/parsed_output
  checkpoint_base_path:
    description: Base path for Structured Streaming checkpoints
    default: /tmp/checkpoints/ai_parse_workflow
  raw_table_name:
    description: Table name for raw parsed documents
    default: parsed_documents_raw
  text_table_name:
    description: Table name for extracted text
    default: parsed_documents_text
  structured_table_name:
    description: Table name for structured data
    default: parsed_documents_structured

include:
  - resources/*.yml

targets:
  dev:
    # The default target uses 'mode: development' to create a development copy.
    # - Deployed resources get prefixed with '[dev my_user_name]'
    # - Any job schedules and triggers are paused by default.
    # See also https://docs.databricks.com/dev-tools/bundles/deployment-modes.html.
    mode: development
    default: true
    workspace:
      host: https://your-workspace.cloud.databricks.com

  prod:
    mode: production
    workspace:
      host: https://your-workspace.cloud.databricks.com
    permissions:
      - group_name: users
        level: CAN_VIEW