Campus Chatbot with NLP

A full-stack intelligent chatbot application designed for university/campus environments, featuring NLP-based question answering, timetable management, and student services.

Overview

This project consists of three main components:

1. NLP Training Pipeline - Uses sentence transformers for semantic understanding of campus-related queries
2. Backend API - FastAPI server providing RESTful endpoints for chatbot functionalities
3. Frontend UI - React-based user interface with Material-UI components

Features

• NLP-Powered Q&A: Semantic search using sentence embeddings and cosine similarity
• Timetable Management: Access class schedules and timetables
• Student Services:
  • Submit complaints
  • Share suggestions
  • View mess menu
  • View cafe menu
• Data Integration: Handles classes, subjects, teachers, and scheduling information

Project Structure

invie-chatbot/
├── chat/
│   ├── backend/
│   │   └── main.py              # FastAPI backend server
│   └── frontend/
│       ├── public/              # Static assets
│       └── src/
│           ├── App.js           # Main React component
│           └── index.js         # Entry point
├── chatbot_nlp_training.ipynb   # NLP model training notebook
├── timetablecsv.ipynb           # Timetable processing notebook
├── classes.csv                  # Class data
├── subjects.csv                 # Subject data
├── teachers.csv                 # Teacher data
├── processed_qa_data.csv        # Preprocessed Q&A pairs
├── question_embeddings.npy      # Pre-computed question embeddings
└── new queries.json             # Query dataset

Tech Stack

Backend

• FastAPI - Modern Python web framework
• CORS Middleware - Cross-origin resource sharing support

Frontend

• React 19 - UI framework
• Material-UI (MUI) - Component library
• Emotion - CSS-in-JS styling

NLP/ML

• sentence-transformers - Sentence embeddings
• scikit-learn - Cosine similarity and ML utilities
• pandas - Data manipulation
• numpy - Numerical computations

Installation

Prerequisites

• Python 3.8+
• Node.js 14+
• npm or yarn

Backend Setup

# Navigate to backend directory
cd chat/backend

# Install Python dependencies
pip install fastapi uvicorn sentence-transformers scikit-learn pandas numpy

# Run the backend server
uvicorn main:app --reload --host 0.0.0.0 --port 8000

Frontend Setup

# Navigate to frontend directory
cd chat/frontend

# Install dependencies
npm install

# Start the development server
npm start

The frontend will be available at http://localhost:3000 and the backend at http://localhost:8000.

NLP Training

The chatbot uses a pre-trained sentence transformer model to understand and respond to queries:

1. Open the training notebook:

   jupyter notebook chatbot_nlp_training.ipynb

2. Training Process:

   • Load Q&A data from JSON files
   • Preprocess questions (lowercase, remove special characters)
   • Generate sentence embeddings using SentenceTransformer
   • Compute cosine similarity for query matching
   • Save embeddings to question_embeddings.npy

3. Model: Uses pre-trained sentence transformer models (e.g., all-MiniLM-L6-v2) for semantic understanding

API Endpoints

Method	Endpoint	Description
GET	/	Health check
GET	/timetable	Fetch timetable data
POST	/complaint	Submit a complaint
POST	/suggestion	Submit a suggestion
GET	/mess-menu	Get mess menu
GET	/cafe-menu	Get cafe menu

Data Files

• classes.csv - Class schedules and information
• subjects.csv - Subject details and metadata
• teachers.csv - Faculty information
• processed_qa_data.csv - Cleaned question-answer pairs
• question_embeddings.npy - Pre-computed embeddings for fast retrieval
• new queries.json - Sample queries for testing

Frontend Features

• Modern gradient background design
• Responsive Material-UI components
• Real-time backend connectivity check
• Clean and intuitive user interface

Development

Running Tests (Frontend)

cd chat/frontend
npm test

Building for Production

cd chat/frontend
npm run build

Usage Example

1. Start the backend server
2. Launch the frontend application
3. The chatbot will connect to the backend automatically
4. Users can:
   • Ask questions about campus facilities
   • Check timetables
   • Submit feedback
   • View dining options

Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

License

This project is open source and available for educational purposes.

Acknowledgments

• Sentence Transformers library for NLP capabilities
• FastAPI for the robust backend framework
• Material-UI for the beautiful UI components

Contact

For questions or support, please open an issue in the repository.

---

Note: This is a development version. For production deployment, ensure proper security measures, environment variables, and API authentication are implemented.