MentorBot: Your AI-Powered Coding Study Companion

Overview

MentorBot is a web-based intelligent tutoring assistant that leverages a Large Language Model (LLM) to help students learn programming concepts more effectively. It supports contextual Q&A, integrates retrieval-augmented generation from curated course materials, and allows users to run code snippets to see results in real-time, fostering interactive learning experiences.

Key Features:

• Contextual Q&A: Provides factually grounded answers using retrieval-augmented generation from embedded course materials.
• Code Execution: Allows users to paste Python code snippets and see the output instantly.
• Personalized Learning: Helps learners understand algorithms, data science principles, and coding best practices at their own pace.

Project Directory Structure

MentorBot/
  README.md                     # This README file
  backend/
    main.py                     # Backend server code (FastAPI)
    requirements.txt            # Python dependencies
    .env                        # Environment variables (e.g., OPENAI_API_KEY)
    data/
      sample_course_material.txt # Embedded course content
    embeddings/
      # Vector database files created at runtime
    venv/                       # Optional virtual environment directory
  frontend/
    package.json                # Frontend package configuration
    src/
      index.js                  # React entry point
      App.js                    # Main App component
      ChatBubble.js             # UI component for chat messages
      ChatInput.js              # UI component for user input
    public/
      index.html                # Frontend HTML template
    node_modules/               # Installed Node.js dependencies

Note:

• venv/ and node_modules/ directories are typically local and not pushed to version control.
• Adjust paths if you have a different structure.

Installation Instructions

Pre-requisites

• Python 3.9+
• Node.js 16+
• An OpenAI API Key (if using OpenAI models)
• (Optional) A virtual environment tool like venv or conda for Python dependency management

Backend Setup

Navigate to the backend directory:

cd MentorBot/backend

Create and activate a virtual environment (recommended):

python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

Install Python dependencies:

pip install --upgrade pip
pip install -r requirements.txt

Set your environment variables:

Create or edit .env file in backend/:

OPENAI_API_KEY=your-openai-api-key-here

Alternatively, set OPENAI_API_KEY as an environment variable in your shell.

Run the backend server:

uvicorn main:app --reload

If successful, the server will be accessible at http://localhost:8000.

Frontend Setup

Open a new terminal (keeping the backend running in another window).

Navigate to the frontend directory:

cd MentorBot/frontend

Install Node.js dependencies:

npm install

Start the frontend development server:

npm start

This will open http://localhost:3000 in your browser.

Verifying Installation

With the backend running on http://localhost:8000 and the frontend on http://localhost:3000, open http://localhost:3000 in your browser.

You should see the MentorBot interface. Ask a question or paste Python code. MentorBot should respond with context-driven answers and/or code execution results.

User Guide

1. Asking Questions:

   • Type your question into the text box at the bottom of the page. For example:
     • “Explain how bubble sort works.”
     • “What is 1+1?”
   • Press Send, and MentorBot will respond using context from the embedded course materials. If relevant info isn’t found, it may rely on general knowledge.

2. Running Code Snippets:

   • Below the question input, there’s another text box for code snippets. Paste a Python code snippet there:

     print("Hello World")

   • Press Send. MentorBot will execute the code and return the output alongside its explanation.

3. Learning Use Cases:

   • Reinforce Concepts: Ask conceptual questions like “How does recursion work?” or “What’s the complexity of merge sort?”
   • Debug Code: Paste a piece of Python code that errors out and ask MentorBot for hints on what went wrong.
   • Explore Algorithms: Request explanations for data structures, machine learning basics, or data science concepts.

4. Limitations and Tips:

   • MentorBot’s responses depend on the provided course materials. For certain advanced queries not covered in the documents, it may rely on general reasoning or may say it doesn’t know.
   • Code execution is limited to Python code snippets and may not handle large or complex scripts. It’s meant for quick demonstrations, not production workloads.
   • If you encounter network errors, ensure both backend and frontend servers are running and check CORS settings.

Troubleshooting

Frontend “Failed to fetch” Error:

• Ensure the backend is running. Check that you’re accessing http://localhost:3000 in the browser and that the backend server runs on http://localhost:8000.
• Consider matching domains (use localhost instead of 127.0.0.1) or updating CORS settings in main.py.

Backend Errors on Startup:

• Check dependencies and ensure your OPENAI_API_KEY is set. Update your requirements.txt or re-install dependencies if version conflicts arise.

Contributing

We welcome contributions! To contribute:

1. Fork this repository.
2. Create a new branch for your changes.
3. Submit a pull request with a clear description of what you improved or fixed.

License

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