Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🤖 Intelligent-Chatbot-using-Retrieval-Augmented-Generation-RAG

Harness the power of AI + Retrieval to get precise, document-specific answers-whether you're researching, studying, or building intelligent systems.

RAG Homepage


📌 What is This?

The RAG Chatbot is an intelligent assistant that combines advanced language models with retrieval-augmented generation (RAG) and conversational memory. It can answer your questions based on:

  • 📄 Uploaded documents (PDF, TXT)
  • 🌐 Webpage URLs

It remembers your previous questions, so you get context-aware, human-like responses.


🚀 Features

  • Conversational Memory: Remembers your chat history for context-rich answers.
  • Multi-source Retrieval: Ask questions about uploaded files or scraped web pages.
  • Modern UI: Built with Streamlit, featuring a sleek navbar, sidebar, and sticky footer.

🛠️ How to Use

  1. Clone the Repo & Install Requirements

    git clone https://github.com/omsingh031/Intelligent-Chatbot-using-Retrieval-Augmented-Generation-RAG-.git
    cd your-repo-name
    pip install -r requirements.txt
    
  2. Set Up Environment Variables
    Create a .env file in the root directory with your API keys and config:

    LANGCHAIN_TRACING_V2=...
    LANGCHAIN_API_KEY=...
    LANGCHAIN_ENDPOINT=...
    LANGCHAIN_PROJECT=...
    
  3. Run the App

    streamlit run app.py
    
  4. Interact!

    • Upload a PDF or TXT file, or enter a webpage URL.
    • Click Load File or Load URL.
    • Ask your question in the chat input.
    • View your conversation history and explore other sections via the navigation bar.

🖥️ Screenshots

User Manual Working of App Chat Example


👥 About Us

Welcome to our RAG Chatbot-an intelligent assistant that bridges human curiosity and machine knowledge through cutting-edge AI.

We are a passionate team of developers, designers, and researchers dedicated to making information retrieval smarter, faster, and more contextual.
Our mission: To make AI more human-centric by combining advanced language models with intuitive user interfaces and real-world usability.


💼 Team

  • 👨‍💻 Om Kumar Singh – Lead Developer
  • 🧑‍💻 Ashi Jain
  • 🧑‍💻 Vansh Jain
  • 🧑‍💻 Roshmik Agrawal
  • 🧑‍💻 Aadish Chaturvedi
  • 🧑‍💻 Shambhavi Dubey

🌍 Why This Matters

In a world overflowing with unstructured information, our chatbot serves as a personal researcher, quickly digging through content and providing meaningful answers-with memory, clarity, and reliability.


🛣️ Future Enhancements

  • Add support for more file types
  • Improve long-term context handling
  • Integrate authentication and user profiles
  • Export chat logs and document references

📫 Contact


📝 License

This project is licensed under the MIT License. See LICENSE for details.


Made with ❤️ by Om Kumar Singh and Team

🤖 Intelligent-Chatbot-using-Retrieval-Augmented-Generation-RAG

About

RAG Chatbot with Conversational Memory is an intelligent assistant that combines Retrieval-Augmented Generation (RAG) with memory. It delivers precise, context-aware answers from your uploaded documents (PDF, TXT) or any webpage URL. Built with Streamlit, LangChain, Google Gemini, and ChromaDB, this chatbot is perfect for students, researchers, etc

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Used by

Contributors

Languages