LLM-Web-Summarizer

A powerful web application that leverages Large Language Models (LLMs) to automatically summarize web content. Simply provide a URL, and get an intelligent summary powered by local Ollama models.

🌟 Features

• URL-based Summarization: Extract and summarize content from any web URL
• Local LLM Processing: Uses Ollama for privacy-focused, offline text processing
• Web Interface: Clean, intuitive Streamlit-based user interface
• Multiple Format Support: Handles various web content types and structures
• Jupyter Notebook: Interactive development environment for experimentation

🛠️ Technology Stack

• Frontend: Streamlit
• Web Scraping: BeautifulSoup4 + Requests
• LLM Integration: Ollama
• Language: Python 3.8+
• Development: Jupyter Notebook, IPython

📋 Prerequisites

Before running this application, ensure you have:

1. Python 3.8 or higher installed
2. Ollama installed and running locally
3. At least one LLM model downloaded in Ollama (e.g., llama2, mistral, etc.)

🔽 Ollama Download & Setup

Step 1: Download Ollama

Visit the official Ollama website: https://ollama.com/download

Windows

1. Download: Go to https://ollama.com/download

2. Click: "Download for Windows" button

3. Run: Execute the downloaded .exe file

4. Install: Follow the installation wizard

5. Alternative: Use Package Manager

   # Using winget
   winget install ollama
   
   # Using chocolatey
   choco install ollama

macOS

1. Download: Go to https://ollama.com/download
2. Click: "Download for macOS" button
3. Install: Open the downloaded .dmg file and drag Ollama to Applications
4. Alternative: Use Homebrew

   brew install ollama

Linux

1. Quick Install: Use the official install script

   curl -fsSL https://ollama.com/install.sh | sh

2. Manual Download: Visit https://ollama.com/download and download the Linux binary

3. Package Managers:

   # Ubuntu/Debian (if available)
   sudo apt install ollama
   
   # Arch Linux
   yay -S ollama

Step 2: Verify Installation

After installation, verify Ollama is working:

# Check if Ollama is installed
ollama --version

# Start Ollama service
ollama serve

Step 3: Download LLM Models

Choose and download at least one model:

# Popular models (choose one or more)

# Llama 2 (7B) - Good balance of performance and speed
ollama pull llama2

# Mistral (7B) - Fast and efficient
ollama pull mistral

# Code Llama (7B) - Great for code-related tasks
ollama pull codellama

# Llama 2 (13B) - Better performance, larger size
ollama pull llama2:13b

# Check available models
ollama list

Step 4: Test Ollama

Test if everything is working:

# Test with a simple prompt
ollama run llama2 "Hello, how are you?"

# Or start an interactive session
ollama run llama2

🚀 Installation & Setup

1. Clone the repository

   git clone https://github.com/NhanPhamThanh-IT/LLM-Web-Summarizer.git
   cd LLM-Web-Summarizer

2. Create a virtual environment (recommended)

   python -m venv venv
   
   # Activate virtual environment
   # Windows
   venv\Scripts\activate
   
   # macOS/Linux
   source venv/bin/activate

3. Install dependencies

   pip install -r requirements.txt

4. Ensure Ollama is running

   # Start Ollama service (if not already running)
   ollama serve
   
   # In a new terminal, verify models are available
   ollama list

5. Run the Streamlit application

   streamlit run text_summary_app.py

6. Access the application

   • Open your browser and go to http://localhost:8501

📖 Usage

Web Application

1. Start the application using the installation steps above
2. Enter a URL in the input field
3. Click "Summarize" to process the content
4. View the summary generated by the LLM

Jupyter Notebook

For development and experimentation:

jupyter notebook text_summarize.ipynb

🏗️ Project Structure

LLM-Web-Summarizer/
├── text_summary_app.py      # Main Streamlit application
├── text_summarize.ipynb     # Jupyter notebook for development
├── requirements.txt         # Python dependencies
├── README.md               # Project documentation
└── .gitignore             # Git ignore file

🔧 Configuration

Changing the LLM Model

Edit the summarize function in text_summary_app.py:

def summarize(text):
    response = ollama.chat(model='your-preferred-model', messages=[
        {
            'role': 'user',
            'content': f'Summarize the following text: {text}'
        }
    ])
    return response['message']['content']

Available Models

You can use any of these models in your application:

• llama2 - General purpose, good balance
• mistral - Fast and efficient
• codellama - Best for code-related content
• llama2:13b - More capable but slower
• mixtral - Advanced reasoning capabilities

Customizing Summarization Prompts

Modify the prompt in the summarize function to adjust the summarization style:

content = f'Provide a detailed summary with key points: {text}'
# or
content = f'Create a brief, bullet-point summary: {text}'

🐛 Troubleshooting

Common Issues

1. Ollama Not Found

   Error: ollama: command not found
   

   Solution:

   • Ensure Ollama is properly installed from https://ollama.com/download
   • Restart your terminal after installation
   • Check if Ollama is in your PATH

2. Ollama Connection Error

   Error: Connection refused
   

   Solution:

   • Ensure Ollama service is running (ollama serve)
   • Check if port 11434 is available
   • Try restarting Ollama service

3. Model Not Found

   Error: Model 'llama2' not found
   

   Solution:

   • Download the model (ollama pull llama2)
   • Check available models (ollama list)
   • Verify model name spelling in your code

4. Streamlit Port Already in Use

   Error: Port 8501 is already in use
   

   Solution: Use a different port

   streamlit run text_summary_app.py --server.port 8502

5. Web Scraping Blocked

   Error: 403 Forbidden
   

   Solution: Some websites block automated requests. Try different URLs or add headers to requests.

6. Slow Performance Solution:

   • Use smaller models like mistral instead of llama2:13b
   • Ensure sufficient RAM is available
   • Close other resource-intensive applications

📊 Model Recommendations

Model	Size	Speed	Quality	Use Case
mistral	7B	Fast	Good	General summarization
llama2	7B	Medium	Very Good	Balanced performance
codellama	7B	Medium	Good	Technical content
llama2:13b	13B	Slow	Excellent	High-quality summaries

🤝 Contributing

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

📝 License

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

🙏 Acknowledgments

• Ollama for providing local LLM capabilities
• Streamlit for the excellent web framework
• BeautifulSoup for web scraping functionality

📧 Contact

Pham Thanh Nhan - ptnhanit230104@gmail.com

Project Link: https://github.com/NhanPhamThanh-IT/LLM-Web-Summarizer

---

⭐ If this project helped you, please give it a star!