RAG Project

A Retrieval-Augmented Generation (RAG) system with a ReAct agent implementation for intelligent document querying.

Overview

This project implements a RAG system that can answer questions based on a collection of PDF documents. It uses FAISS for vector storage and retrieval, combined with a React (Reasoning and Acting) agent for intelligent query processing.

Features

• PDF document ingestion and vector embedding
• FAISS-based vector database for efficient similarity search
• React agent for multi-step reasoning and retrieval
• Interactive chat interface

Project Structure

RAG_Project/
├── src/
│   ├── react_agent.py    # React agent implementation
│   └── utils.py          # Utility functions
├── data/
│   ├── pdfs/             # Source PDF documents
│   └── vector_db/        # FAISS vector database
├── chat_react.py         # Main chat interface
└── requirements.txt      # Python dependencies

Setup

1. Install dependencies:

pip install -r requirements.txt

2. Create a .env file with your API key:

OPENAI_API_KEY=your_api_key_here

3. Run the chat interface:

python chat_react.py

Usage

The system allows you to ask questions about the documents in the PDF collection. The React agent will retrieve relevant information and provide informed answers.

Requirements

• Python 3.11+
• OpenAI API key
• See requirements.txt for package dependencies