ops/scripts/ingest.py

import os
import sys
import logging
import asyncio

# The script runs inside the 'mcp' container where the WORKDIR is '/app'.
# The 'core' module is at '/app/core'. We need to add '/app' to the Python path.
sys.path.insert(0, '/app')

from core.discovery import discover_all_schemas
from core.graph import import_schema, close_graph_driver

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)

async def main():
    """
    Main asynchronous function to run the full schema discovery and ingestion process.
    """
    logger.info("Starting schema ingestion process...")
    
    try:
        # Step 1: Discover schemas from all connected SQLite databases
        logger.info("Discovering schemas from all databases...")
        all_schemas = await discover_all_schemas()
        
        if not all_schemas:
            logger.warning("No schemas were discovered. Ingestion cannot proceed.")
            return

        logger.info(f"Discovered {len(all_schemas)} schemas. Now ingesting into Neo4j...")

        # Step 2: Import each discovered schema into Neo4j
        for schema_data in all_schemas:
            try:
                import_schema(schema_data)
                logger.info(f"Successfully ingested schema for: {schema_data['database_name']}")
            except Exception as e:
                logger.error(f"Failed to ingest schema for {schema_data['database_name']}: {e}", exc_info=True)
        
        logger.info("Schema ingestion process completed successfully.")

    except Exception as e:
        logger.critical(f"A critical error occurred during the ingestion process: {e}", exc_info=True)
    finally:
        # Step 3: Ensure all connections are closed
        close_graph_driver()
        logger.info("Neo4j connection closed.")

if __name__ == "__main__":
    asyncio.run(main())