gpt-commit

🚀 Automatically generate Git commit messages using GPT (OpenAI) or local models via Ollama.

✨ Features

• Uses git diff --cached to summarize staged changes
• Works with OpenAI GPT models (gpt-3.5-turbo, gpt-4)
• Supports local LLMs via Ollama
• CLI tool: simple, fast, dev-friendly

📦 Installation

From PyPI

pip install gpt-commit

From Source

git clone https://github.com/yourusername/gpt-commit.git
cd gpt-commit
pip install -e .

🔧 Setup

OpenAI Backend

1. Get your API key from OpenAI
2. Set the environment variable:

   export OPENAI_API_KEY='your-api-key'

   Or create a .env file in your project root:

   OPENAI_API_KEY=your-api-key
   

Ollama Backend

1. Install Ollama
2. Pull a model (e.g., CodeLlama):

   ollama pull codellama

🚀 Usage

1. Stage your changes:

   git add .

2. Generate a commit message:

   # Using OpenAI (default)
   gpt-commit --backend openai --model gpt-4
   
   # Using Ollama
   gpt-commit --backend ollama --model codellama
   
   # Auto-commit with the generated message
   gpt-commit --commit

🔍 Options

• --backend: Choose between 'openai' or 'ollama' (default: 'ollama')
• --model: Specify the model name (default: 'gpt-4' for OpenAI, 'codellama' for Ollama)
• --commit: Automatically commit with the generated message

🤝 Contributing

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

📝 License

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