AI study assistant with RAG - Google Gemini with Drive & Supabase vector search

How it works

A complete AI-powered study assistant system that lets you chat naturally with your documents stored in Google Drive:

The system has two connected workflows:

1. Document Indexing Pipeline (Sub-workflow): • Accepts Google Drive folder URLs • Automatically fetches all files from the folder • Converts documents to plain text • Generates 768-dimensional embeddings using Google Gemini • Stores everything in Supabase vector database for semantic search

2. Study Chat Agent (Main workflow): • Provides a conversational chat interface • Automatically detects and processes Google Drive links shared in chat • Searches your indexed documents using semantic similarity • Maintains conversation history across sessions • Includes calculator for math problems • Responds naturally using Google Gemini 2.5 Pro

Use Cases: Students studying for exams, researchers managing papers, professionals building knowledge bases, anyone needing to query large document collections conversationally.

Set up steps

Prerequisites: • Google Drive OAuth2 credentials • Google Gemini API key (free tier available) • Supabase account with Postgres connection • ~15 minutes setup time