README.md

metadata

title: AI Note Summarizer
emoji: 🚀
colorFrom: red
colorTo: red
sdk: streamlit
app_file: src/streamlit_app.py
app_port: 8501
tags:
  - streamlit
pinned: false
short_description: Streamlit template space
license: mit

📝 AI Notes Summarizer

A powerful web application that transforms lengthy documents and notes into concise, bullet-point summaries using state-of-the-art AI models.

---

📋 Table of Contents

• ✨ Features
• 🚀 Quick Start
  • Option 1: Docker (Recommended)
  • Option 2: Local Installation
• 📖 Usage Guide
• 🖼️ Screenshots
• 🛠️ Technical Details
• 🐳 Docker Deployment
• 🔧 Configuration
• 🚨 Troubleshooting
• 🤝 Contributing
• 📄 License
• 🙏 Acknowledgments
• 📞 Support

---

✨ Features

• PDF Processing: Upload PDF files and extract text content automatically
• Direct Text Input: Paste text content directly for immediate summarization
• AI-Powered Summarization: Uses Hugging Face Transformers (BART, T5) for high-quality summaries
• Bullet-Point Format: Clean, readable bullet-point summaries
• Multiple AI Models: Choose from different pre-trained models
• Customizable Length: Adjust summary length (Short, Medium, Long)
• Progress Tracking: Real-time progress indicators during processing
• Download Summaries: Save generated summaries as text files
• Statistics: View compression ratios and word counts
• Error Handling: Comprehensive error handling and user feedback

🚀 Quick Start

Option 1: Docker (Recommended)

Prerequisites

• Docker and Docker Compose installed
• Internet connection (for downloading AI models)

Using Docker Compose (Easiest)

# Clone the repository
git clone https://github.com/midlaj-muhammed/AI-Note-Summarizer.git
cd AI-Note-Summarizer

# Start the application
docker-compose up -d

# Access the application at http://localhost:8501

Using Docker Scripts

# Build the Docker image
./docker-build.sh

# Run the container
./docker-run.sh

# For development with live code reloading
./docker-dev.sh

Manual Docker Commands

# Build the image
docker build -t ai-notes-summarizer .

# Run the container
docker run -p 8501:8501 ai-notes-summarizer

Option 2: Local Installation

Prerequisites

• Python 3.8 or higher
• pip (Python package installer)
• Internet connection (for downloading AI models)

Installation Steps

1. Clone the repository

   git clone https://github.com/midlaj-muhammed/AI-Note-Summarizer.git
   cd AI-Note-Summarizer
   

2. Install dependencies

   pip install -r requirements.txt
   

3. Run the application

   streamlit run app.py
   

4. Open your browser

   • The application will automatically open at http://localhost:8501
   • If it doesn't open automatically, navigate to the URL manually

📖 Usage Guide

PDF Summarization

1. Upload PDF: Click on the "📄 PDF Upload" tab
2. Select File: Choose a PDF file (max 10MB)
3. Process: Click "📖 Extract & Summarize PDF"
4. Review: View the extracted text preview
5. Get Summary: The AI will generate a bullet-point summary
6. Download: Save the summary using the download button

Text Summarization

1. Input Text: Click on the "📝 Text Input" tab
2. Paste Content: Enter or paste your text (minimum 100 characters)
3. Summarize: Click "🚀 Summarize Text"
4. Review: View the generated summary
5. Download: Save the summary as needed

Settings

• AI Model: Choose from BART (recommended), T5, or DistilBART
• Summary Length: Select Short, Medium, or Long summaries
• Statistics: View word counts and compression ratios

🛠️ Technical Details

Architecture

ai-notes-summarizer/
├── app.py                 # Main Streamlit application
├── modules/
│   ├── __init__.py
│   ├── pdf_processor.py   # PDF text extraction
│   ├── text_summarizer.py # AI summarization
│   └── utils.py          # Utility functions
├── requirements.txt       # Python dependencies
└── README.md             # This file

AI Models

• BART (facebook/bart-large-cnn): Best quality, recommended for most use cases
• T5 Small: Faster processing, good for shorter texts
• DistilBART: Balanced performance and speed

Dependencies

• Streamlit: Web application framework
• Transformers: Hugging Face AI models
• PyTorch: Deep learning framework
• PyPDF2: PDF text extraction
• Additional utilities: See requirements.txt

🔧 Configuration

Model Selection

You can change the default model by modifying the TextSummarizer initialization in app.py:

text_summarizer = TextSummarizer(model_name="your-preferred-model")

Summary Length

Adjust default summary lengths in modules/text_summarizer.py:

self.min_summary_length = 50  # Minimum words
self.max_summary_length = 300  # Maximum words

File Size Limits

Modify PDF file size limits in modules/pdf_processor.py:

self.max_file_size = 10 * 1024 * 1024  # 10MB

🚨 Troubleshooting

Common Issues

1. Model Loading Errors

   • Ensure stable internet connection
   • Check available disk space (models can be 1-2GB)
   • Try switching to a smaller model (T5 Small or DistilBART)

2. PDF Processing Issues

   • Ensure PDF is not encrypted
   • Check if PDF contains readable text (not just images)
   • Try with a smaller PDF file

3. Memory Errors

   • Reduce text length
   • Close other applications
   • Try using CPU instead of GPU

4. Slow Performance

   • Use GPU if available
   • Choose smaller models for faster processing
   • Process shorter text chunks

Error Messages

• "Text is too short": Minimum 100 characters required
• "No readable text found": PDF may contain only images
• "Model loading error": Check internet connection
• "Out of memory": Reduce text length or restart application

🎯 Best Practices

For Best Results

1. Text Quality: Use well-formatted, coherent text
2. Length: Optimal text length is 500-5000 words
3. Content: Works best with structured content (articles, reports, notes)
4. Model Choice: Use BART for academic/formal content, T5 for general text

Performance Tips

1. GPU Usage: Enable CUDA for faster processing
2. Batch Processing: Process multiple documents separately
3. Model Caching: Models are cached after first load
4. Text Preprocessing: Clean text improves summary quality

🖼️ Screenshots

Main Interface

Clean and intuitive interface with PDF upload and text input options

PDF Processing

Real-time PDF processing with progress indicators

Summary Results

Bullet-point summaries with statistics and download options

Settings Panel

Customizable AI model selection and summary length options

Note: Screenshots are placeholders. Actual screenshots will be added once the application is deployed.

🎥 Demo

🚀 Live Demo (Coming Soon)

📹 Demo Video: Watch on YouTube (Coming Soon)

📄 License

This project is open source and available under the MIT License.

🤝 Contributing

Contributions are welcome! Please feel free to submit issues, feature requests, or pull requests.

🐳 Docker Deployment

Production Deployment

For production deployment, use the standard Docker Compose configuration:

# Start in production mode
docker-compose up -d

# View logs
docker-compose logs -f

# Stop the application
docker-compose down

# Update the application
docker-compose pull
docker-compose up -d

Development Mode

For development with live code reloading:

# Start development environment
docker-compose -f docker-compose.dev.yml up

# Or use the convenience script
./docker-dev.sh

Docker Configuration

Environment Variables

• STREAMLIT_SERVER_PORT: Port for the application (default: 8501)
• TRANSFORMERS_CACHE: Cache directory for AI models
• MAX_FILE_SIZE_MB: Maximum PDF file size (default: 10MB)

Volumes

• model_cache: Persistent storage for downloaded AI models
• logs: Application logs
• uploads: Temporary file storage (optional)

Resource Limits

• Memory: 4GB limit, 2GB reserved
• CPU: 2 cores limit, 1 core reserved

Docker Troubleshooting

1. Container won't start: Check logs with docker-compose logs
2. Out of memory: Increase Docker memory limits
3. Model download fails: Ensure internet connectivity
4. Permission issues: Check file ownership and Docker user settings

🤝 Contributing

We welcome contributions from the community! Here's how you can help:

🌟 Ways to Contribute

• ⭐ Star this repository if you find it useful
• 🐛 Report bugs by opening an issue
• 💡 Suggest features or improvements
• 📖 Improve documentation
• 🔧 Submit pull requests with bug fixes or new features

🚀 Getting Started

1. Fork the repository

   # Click the "Fork" button on GitHub, then:
   git clone https://github.com/YOUR-USERNAME/AI-Note-Summarizer.git
   cd AI-Note-Summarizer
   

2. Create a feature branch

   git checkout -b feature/amazing-feature
   

3. Make your changes

   • Follow the existing code style
   • Add tests for new features
   • Update documentation as needed

4. Test your changes

   # Run basic tests
   python test_basic.py
   
   # Test Docker build
   ./docker-test.sh
   

5. Submit a pull request

   git add .
   git commit -m "Add amazing feature"
   git push origin feature/amazing-feature
   

📋 Development Guidelines

• Code Style: Follow PEP 8 for Python code
• Documentation: Update README.md for new features
• Testing: Add tests for new functionality
• Docker: Ensure Docker compatibility
• Dependencies: Keep requirements.txt updated

🐛 Reporting Issues

When reporting issues, please include:

• Environment details (OS, Python version, Docker version)
• Steps to reproduce the issue
• Expected vs actual behavior
• Error messages or logs
• Screenshots if applicable

Report an Issue →

💬 Discussions

Join our community discussions:

• GitHub Discussions - General questions and ideas
• Issues - Bug reports and feature requests

📄 License

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

🙏 Acknowledgments

🛠️ Built With

• Streamlit - Web application framework
• Hugging Face Transformers - AI/ML models
• PyTorch - Deep learning framework
• PyPDF2 - PDF processing
• Docker - Containerization

🎯 Inspiration

• Inspired by the need for efficient document summarization
• Built to help students, researchers, and professionals save time
• Leverages state-of-the-art AI models for high-quality summaries

🤖 AI Models

Special thanks to the teams behind these amazing models:

• BART by Facebook AI
• T5 by Google Research
• DistilBART by Sam Shleifer

👥 Contributors

Thanks to all contributors who have helped improve this project!

📞 Support

If you encounter any issues or have questions:

🔍 Self-Help Resources

1. 📖 Check the troubleshooting section above
2. 🐛 Review error messages for specific guidance
3. 📦 Ensure all dependencies are properly installed
4. 🔄 Try with different models or settings
5. 🐳 For Docker issues, check container logs: docker-compose logs

💬 Get Help

• 🐛 Bug Reports: Open an Issue
• 💡 Feature Requests: Start a Discussion
• 📧 Direct Contact: Email the maintainer

🌟 Show Your Support

If this project helped you, please consider:

• ⭐ Starring the repository
• 🍴 Forking and contributing
• 📢 Sharing with others
• 💝 Sponsoring the project (Coming Soon)

---

Made with ❤️ by Muhammed Midlaj

Happy Summarizing! 📝✨