🌟 FAISSHub: Supabase-Powered RAG Platform
FAISSHub enables users to upload JSON files to create dedicated, knowledge-aware chatbots using Supabase as the backend.
Indexing: The Python backend parses the JSON, generates embeddings, and securely inserts the vectors and associated text content into a PostgreSQL table using the pgvector extension.
Chatbot (RAG): When a user queries, the backend generates a query embedding and executes a fast similarity search directly in Supabase. The retrieved text context is then sent to an LLM to generate a grounded response.
Deployment: The chatbot is accessible via a robust API and an easily embeddable iFrame widget, secured by Supabase Auth and Row-Level Security (RLS).
It provides a secure, scalable, and simplified way to build and deploy custom knowledge-based AI.
Built With
- fastapi
- nextjs
- python
- supabase
Log in or sign up for Devpost to join the conversation.