Skip to content
NEWError doctor and Watchtower: failed n8n runs explained in plain words, and emailed to you. See what is new

Library / RAG & Knowledge Bases

RAG & Knowledge Bases

Load Google Drive Files into a PGVector Database

On a schedule or manual start, the workflow loops through Google Drive files, splits the text, creates OpenAI embeddings and stores them in a Postgres PGVector store.

What it does

# Vector DB Loader from Google Drive ## Overview Automated workflow: Vector DB Loader from Google Drive. This workflow integrates 12 different services: stickyNote, textSplitterRecursiveCharacterTextSplitter, scheduleTrigger, googleDrive, switch. It contains 22 nodes and follows best practices for error handling and security. ## Workflow Details - Total Nodes: 22 - Node Types: 12 - Error Handling: ✅ Implemented - Security: ✅ Hardened (no sensitive data) - Documentation: ✅ Complete ## Node Breakdown - Default Data Loader: documentDefaultDataLoader - Recursive Character Text Splitter: textSplitterRecursiveCharacterTextSplitter - Embeddings OpenAI: embeddingsOpenAi - Postgres PGVector Store: vectorStorePGVector - When clicking ‘Test workflow’: manualTrigger - Loop Over Items: splitInBatches - Move File: googleDrive - Download File: googleDrive - Search Folder: googleDrive - Schedule Trigger: scheduleTrigger - ... and 12 more nodes ## Usage Instructions 1. Configure Credentials: Set up all required API keys and credentials 2. Update Variables: Replace any placeholder values with actual data 3. Test Workflow: Run in test mode to verify functionality 4. Deploy: Activate the workflow for production use ## Security Notes - All sensitive data has been removed or replaced with placeholders - Error handling is implemented for reliability - Follow security best practices when configuring credentials ## Troubleshooting - Check error logs if workflow fails - Verify all credentials are properly configured - Ensure all required services are accessible

The steps

  1. Default Data Loader
  2. Recursive Character Text Splitter
  3. Embeddings OpenAI
  4. Postgres PGVector Store
  5. When clicking ‘Test workflow’
  6. Loop Over Items
  7. Move File
  8. Download File
  9. Search Folder
  10. Schedule Trigger
  11. Switch
  12. Extract from PDF
  13. Extract from Text
  14. Extract from JSON

22 steps in total.

Similar automations