🤖 Text Summarizer

🚀 Overview

A state-of-the-art text summarization application that leverages advanced NLP techniques and modern software engineering practices. This project demonstrates expertise in machine learning, API development, and production-grade software architecture.

🔥 Key Technical Features

• End-to-End ML Pipeline: Implements a complete machine learning workflow from data ingestion to model deployment
• Production-Ready API: FastAPI-based RESTful API with automatic documentation and type checking
• Advanced NLP: Utilizes transformer-based models for high-quality text summarization
• Scalable Architecture: Docker containerization for easy deployment and scaling
• Robust Error Handling: Comprehensive logging and exception management
• Data Validation: Automated data quality checks and preprocessing
• Model Evaluation: Multiple metrics (ROUGE, BLEU) for comprehensive model assessment

🛠️ Technical Stack

• Backend: Python, FastAPI
• ML Framework: PyTorch, Transformers
• NLP Tools: NLTK, Hugging Face Transformers
• Data Processing: Pandas, NumPy
• API Documentation: Swagger UI (automatic)
• Containerization: Docker
• Version Control: Git

📋 Prerequisites

• Python 3.8+
• pip (Python package installer)
• Git
• Docker (optional, for containerized deployment)

🚀 Quick Start

Local Development Setup

1. Clone and Setup:

git clone https://github.com/yourusername/Text_Summarizer.git
cd Text_Summarizer
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -r requirements.txt

2. Run the Application:

# Start the API server
python app.py

# Access the API documentation
# Open http://localhost:8080/docs in your browser

Docker Deployment

# Build and run with Docker
docker build -t text-summarizer .
docker run -p 8080:8080 text-summarizer

📁 Project Architecture

Text_Summarizer/
├── src/                    # Core application code
│   ├── components/        # ML pipeline components
│   ├── pipeline/          # Training and prediction pipelines
│   └── utils/             # Utility functions
├── config/                # Configuration management
├── research/             # Jupyter notebooks and experiments
├── main.py               # Training pipeline entry point
├── app.py                # FastAPI application
├── requirements.txt      # Project dependencies
├── setup.py             # Package configuration
└── Dockerfile           # Container configuration

🔌 API Endpoints

Endpoint	Method	Description
/	GET	API documentation
/train	GET	Initiate model training
/predict	POST	Generate text summary

Example API Usage

import requests

# Generate summary
response = requests.post(
    "http://localhost:8080/predict",
    json={"text": "Your long text here..."}
)
summary = response.json()

🧪 Model Performance

The model is evaluated using multiple metrics:

• ROUGE Score
• BLEU Score

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

📝 License

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

👨‍💻 Author

Your Name

• GitHub: @Hardik1608
• LinkedIn: Hardik Soni

---

⭐ Star this repository if you find it useful!