Skip to content

Latest commit

 

History

History
67 lines (56 loc) · 2.99 KB

README.md

File metadata and controls

67 lines (56 loc) · 2.99 KB

📄🤖 Chat with Multiple PDFs using LLaMA, Streamlit, Hugging Face & FAISS

📝 Overview

Chat with Multiple PDFs is an AI-powered chatbot that enables users to interact with multiple PDF documents simultaneously. Using advanced Natural Language Processing (NLP) and machine learning, the system allows users to ask questions and retrieve relevant answers directly from the content of uploaded PDFs.

This application leverages the LLaMA language model for understanding and processing queries, FAISS (Facebook AI Similarity Search) for efficient document indexing and retrieval, and Hugging Face transformers for deep learning capabilities. The user interface is built with Streamlit, ensuring a smooth and interactive experience.

Whether you're analyzing research papers, legal documents, technical manuals, or any other text-heavy PDFs, this project provides a streamlined way to extract key insights without manually searching through documents. It is particularly useful for students, researchers, data analysts, and professionals who frequently work with large sets of documents.

🚀 Features

  • ✅ Upload Multiple PDFs – Supports multi-document interaction.
  • ✅ Conversational AI – Ask questions and get answers from PDFs.
  • ✅ Fast & Accurate – Uses FAISS for efficient vector search.
  • ✅ LLaMA-powered Chatbot – Advanced NLP capabilities.
  • ✅ Easy-to-Use UI – Built with Streamlit for seamless experience.

🛠️ Tech Stack

  • 📌 Frontend: Streamlit
  • 📌 Backend: Python
  • 📌 Model: LLaMA (via Hugging Face)
  • 📌 Vector Search: FAISS
  • 📌 Libraries: LangChain, PyMuPDF, OpenAI API (optional)

🖥️ Installation & Setup

1️⃣ Clone the Repository

git clone https://github.com/DeveloperMK07/Chat_With_PDF.git 
    cd Chat_With_PDF

2️⃣ Create a Virtual Environment (Optional but Recommended)

python -m venv venv
    source venv/bin/activate  # On macOS/Linux
    venv\Scripts\activate  # On Windows

3️⃣ Install Dependencies

pip install -r requirements.txt

4️⃣ Run the Application

streamlit run app.py

Now, open http://localhost:8501 in your browser to start chatting with your PDFs! 🎉

🌟 Future Enhancements

  • Add support for image-based PDFs (OCR)
  • Improve response accuracy with RAG-based models
  • Deploy on AWS, Hugging Face Spaces, or Render

📬 Contact & Support

💡 Created by DeveloperMK07