Skip to content

Latest commit

 

History

History
157 lines (114 loc) · 4.35 KB

README.md

File metadata and controls

157 lines (114 loc) · 4.35 KB

Youtube-Transcript-to-SPARC-FRAMEWORK

Python Version License Code style: black

This is heavily inspired by https://github.com/ruvnet/sparc/blob/main/README.md. Thank you, RuV!

Translating technical youtube transcripts into SPARC artifacts to guide LLMs to solid software development. This framework processes transcripts through Specification, Pseudocode, Architecture, Refinement, and Completion phases to generate comprehensive development plans.

🌟 Features

  • Youtube Transcript Processing: Convert technical video transcripts into structured development artifacts
  • SPARC Methodology:
    • Specification: Detailed requirements analysis
    • Pseudocode: Implementation blueprints
    • Architecture: System design and components
    • Refinement: Optimizations and improvements
    • Completion: Final implementation guidance
  • Advanced LLM Integration: Supports multiple models (GPT-4o, O1-mini, etc.)
  • Interactive Development: Chat-based development guidance

🚀 Quick Start

Installation

# Clone the repository
git clone https://github.com/FrancyJGLisboa/Youtube-Transcript-to-SPARC-FRAMEWORK.git
cd Youtube-Transcript-to-SPARC-FRAMEWORK

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: .\venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Set up environment variables
cp env .env
# Edit .env with your API keys and preferences

Basic Usage

# Generate development plan from transcript
sparc generate examples/example_transcript.txt

# With project name and chat simulation
sparc generate examples/example_transcript.txt -n my_project --simulate-chat

📁 Project Structure

Youtube-Transcript-to-SPARC-FRAMEWORK/
├── examples/                    # Example transcripts
├── sparc_generator/            # Main package
│   ├── __init__.py
│   ├── sparc_generator.py      # Core implementation
│   ├── sparc_cli.py           # CLI interface
│   └── sparc_prompts.yaml     # Prompt templates
├── requirements.txt           # Project dependencies
├── setup.py                   # Package setup
├── test_sparc.sh             # Test script
└── .env                      # Configuration

⚙️ Configuration

Create a .env file with your settings:

# Required
OPENAI_API_KEY=your-api-key-here

# Optional
MODEL=gpt-4o              # Default model
OUTPUT_DIR=output         # Output directory

📤 Generated Artifacts

The framework generates a complete development plan:

output/project_name/
├── artifacts/
│   ├── specification.md
│   ├── pseudocode.md
│   ├── architecture.md
│   ├── refinement.md
│   └── completion.md
├── development_plan.json
└── usage_log.json

🛠 Advanced Usage

Model Selection

# List available models
sparc list-models

# Use specific model
sparc generate transcript.txt -m o1-mini

# Get model recommendations
sparc recommend-model

Development Simulation

# Generate plan with interactive development guidance
sparc generate transcript.txt --simulate-chat

📝 Examples

Example transcript processing:

# Process example technical video
sparc generate examples/example_transcript.txt -n tech_project

# Review generated artifacts
cat output/tech_project/artifacts/specification.md

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the repository
  2. Create your 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 licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

  • OpenAI for API support
  • Youtube for content accessibility
  • Community contributors

📞 Support

  • Create an issue for bug reports or feature requests
  • Check documentation for guidance
  • Contact maintainers for additional support