Google Drive to Supabase Vector DB Sync for RAG Apps

This n8n workflow automates the synchronization of documents from Google Drive to a Supabase vector database, optimized for Retrieval-Augmented Generation (RAG) applications. When a file is added or modified in a specified Google Drive folder, the workflow triggers to extract textual content, split it into manageable chunks, and enrich each chunk with contextual metadata such as summaries, document details, and timestamps. Embeddings are then generated using OpenAI models, enabling semantic search capabilities. Existing records for modified files are intelligently replaced to keep the database current.

The benefits include maintaining a real-time, context-aware vector store without manual intervention, reducing setup time for RAG pipelines, and improving retrieval accuracy through enriched metadata. This ensures hybrid searches (vector + keyword) perform optimally for AI applications like chatbots, knowledge bases, and recommendation systems.

Ideal use cases span e-commerce (product docs and catalogs), customer support (knowledge bases), research (document repositories), and any scenario requiring up-to-date vector data from cloud storage. It saves hours of scripting and monitoring, scaling effortlessly with Google Drive usage.