Create RAG vector database from Google Drive documents using Gemini & Supabase

How it works

This workflow automates the process of converting Google Drive documents into searchable vector embeddings for AI-powered applications:

• Takes a Google Drive folder URL as input • Initializes a Supabase vector database with pgvector extension • Fetches all files from the specified Drive folder • Downloads and converts each file to plain text • Generates 768-dimensional embeddings using Google Gemini • Stores documents with embeddings in Supabase for semantic search

Built for the Study Agent workflow to power document-based Q&A, but also works perfectly for any RAG system, AI chatbot, knowledge base, or semantic search application that needs to query document collections.

Set up steps

Prerequisites: • Google Drive OAuth2 credentials • Supabase account with Postgres connection details • Google Gemini API key (free tier available)

Setup time: ~10 minutes

Steps: 1. Add your Google Drive OAuth2 credentials to the Google Drive nodes 2. Configure Supabase Postgres credentials in the SQL node 3. Add Supabase API credentials to the Vector Store node 4. Add Google Gemini API key to the Embeddings node 5. Update the input with your Drive folder URL 6. Execute the workflow