RAG PDF Chat App

This project lets you upload PDFs, extract and structure their data, and chat with your documents using Retrieval-Augmented Generation (RAG) powered by a FastAPI backend and a modern Next.js frontend.

Features

• Upload PDFs and extract their content
• Store and search document chunks using ChromaDB
• Query with your choice of AI model
• Modern ChatGPT-style web UI (Next.js)
• FastAPI backend for PDF processing, embedding, and chat

Tech Stack

• Frontend: Next.js (React, TypeScript)
• Backend: FastAPI (Python)
• Vector Store: ChromaDB
• Embeddings: HuggingFace (all-MiniLM-L6-v2)

---

Setup Instructions

1. Backend (FastAPI)

1. Install dependencies:

   pip install -r requirements.txt
   pip install fastapi uvicorn python-multipart

2. Set your AI API key:
   • Create a .env file with:

     API_KEY=your_api_key_here
     

3. Run the backend:

   uvicorn backend.main:app --reload

   The backend will be available at http://localhost:8000.

2. Frontend (Next.js)

1. Install dependencies:

   cd frontend
   npm install

2. Run the frontend:

   npm run dev

   The frontend will be available at http://localhost:3000.

---

Usage

• Upload a PDF using the chat UI.
• Ask questions about the document in a ChatGPT-style interface.
• View answers and chat history.

---