🤖 Enhanced AI Tutor System using LLaMA-3 and LangGraph

An adaptive, feedback-based AI tutor system built using:

🧠 Meta's LLaMA-3.2-3B-Instruct
🔄 LangGraph for multi-agent workflow
⚡ Hugging Face Transformers (4-bit quantization for efficiency)
✅ PyTorch, BitsandBytes, Accelerate for seamless GPU usage

🎓 What It Does

This notebook walks you through a complete interactive tutor session that:

📚 Asks a question from a topic you choose
📝 Evaluates your answer and gives structured feedback
🧪 Generates a new practice question
📈 Tracks your progress and adapts difficulty

It's like having your own AI teacher, personalized to your learning!

🚀 Quickstart

🔧 Requirements

Install required packages first:

pip install langgraph transformers accelerate bitsandbytes --quiet
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 --quiet
pip install huggingface_hub --quiet

🔑 Login to Hugging Face

from huggingface_hub import notebook_login
notebook_login()

🏃‍♂️ Run the Notebook

Launch the .ipynb in a Google Colab GPU runtime
Follow the prompts
Learn, improve, repeat 🔁

📁 Project Structure

├── EnhancedTutorSystem.ipynb   
├── README.md                   
├── requirements.txt

🧠 Model Info

This project uses (but does not rehost) Meta's official instruction-tuned model:

The model is loaded via transformers using 4-bit quantization (BitsAndBytes)

Note: You must agree to Meta's license to access the model.

🎯 Features

✍️ Adaptive questions across difficulty levels
📊 Real-time performance tracking
🤓 Intelligent feedback on every answer
💡 LangGraph-powered multi-agent workflow
🧵 Fully reproducible session history

🔜 Coming Soon

🌐 A Hugging Face Space with a user-friendly UI
📝 Student progress export to PDF
🎯 Topic-based quiz sessions
🧪 Integration with LangChain for evaluation metrics

📄 License

This project is released under the MIT License.

🙌 Acknowledgments

🧠 Meta AI for LLaMA-3
🔄 LangGraph by LangChain
🤗 Hugging Face for open infrastructure

📬 Contact / Feedback

Feel free to raise issues or suggestions on GitHub
Or connect via Hugging Face community tab!

Happy learning! 💡