Text Improvement Assistant is an AI-powered tool that helps improve text quality using DSPy and large language models. It provides a web interface for text enhancement with reasoning and issue identification.

The assistant uses a few-shot learning approach to improve text quality:

1. Examples: You can save example improvements that demonstrate the kind of changes you want. Each example contains:

   • Original input text
   • Reasoning behind the changes
   • Issues identified
   • Improved version

2. Learning: When improving new text, the system:

   • Uses your saved examples to understand your style preferences
   • Applies similar improvement patterns to new inputs
   • Provides detailed reasoning for changes
   • Identifies potential issues
   • Generates improved versions

3. Customization: You can:

   • Add successful improvements as new examples
   • Edit existing examples
   • Provide custom instructions
   • Generate multiple variations

• 🌐 Web Interface: User-friendly Streamlit interface
• 🔄 Multiple Completions: Generate multiple improved versions
• 📝 Example Management: Save and edit example improvements
• 🤖 DSPy Integration: Leverages DSPy for LLM optimization
• 🔍 Detailed Analysis: Provides reasoning and identifies issues

# Clone the repository
git clone https://github.com/tom-doerr/text_improvement.git
cd text_improvement

# Install dependencies
pip install -r requirements.txt

# Set up your OpenRouter API key
export OPENROUTER_API_KEY='your-api-key'

streamlit run app.py

Visit http://localhost:8501 in your browser.

The system uses:

• DSPy with Claude 3.5 Sonnet model
• JSON storage for examples and instructions
• Streamlit for web interface
• Temperature of 2.0 for varied outputs

# Install development dependencies
pip install -r requirements-dev.txt

# Run linting
flake8

1. Fork the repository
2. Create your 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

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