ResearchEase

This project implements a PDF-based Question and Answer system using LangChain, Hugging Face, and ChromaDB.

Features

• Load multiple PDF files
• Extract and process text from PDFs
• Create embeddings using Hugging Face models
• Interactive Q&A interface with conversational AI

Prerequisites

• Python 3.8+
• Hugging Face API token
• LangChain API key

Installation

1. Clone the repository:

git clone <repository-url>
cd PDF-QnA

2. Create and activate virtual environment:

python -m venv env
source env/bin/activate  # Linux/Mac
env\Scripts\activate     # Windows

3. Install dependencies:

pip install langchain langchain_huggingface langchain_chroma pypdf

Setup

1. Place your PDF files in the data directory
2. Set up your environment variables when prompted:
   • LangChain API key
   • Hugging Face API token

Usage

Run the main script:

python main.py

• Enter your API credentials when prompted