README.md

---
title: Template Final Assignment
emoji: 🕵🏻‍♂️
colorFrom: indigo
colorTo: indigo
sdk: gradio
sdk_version: 5.25.2
app_file: app.py
pinned: false
hf_oauth: true
# optional, default duration is 8 hours/480 minutes. Max duration is 30 days/43200 minutes.
hf_oauth_expiration_minutes: 480
---


# 🧠 AI RAG Agent - Final Project (LangGraph + Supabase)

This project is a Retrieval-Augmented Generation (RAG) agent built using **LangGraph**, **LangChain**, and **Supabase** as a vector store.  
It allows users to query a custom knowledge base hosted in their own Supabase instance.

---

## 📋 Features

- 🔎 RAG: Use your Supabase + FAISS for retrieval
- 🤖 LLM-powered: Gemini or other models via LangChain
- 🌐 Optional web search fallback (Tavily or Arxiv)
- 🔒 Keep your API keys secure with private `.env`

---

## 🚀 How to Use

### 1. Clone this Space

Click the **"Duplicate Space"** button at the top-right to create your own copy.

---

### 2. Configure `.env` Variables

Inside your cloned Space, go to the **"Files"** tab, create a file named `.env`, and add the following variables:

```env
SUPABASE_URL=your_supabase_url
SUPABASE_SERVICE_KEY=your_supabase_service_key
GOOGLE_API_KEY=your_google_api_key
TAVILY_API_KEY=your_tavily_api_key  # optional if using Tavily tool


Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference