J's CodeBuddy AI is an advanced, multi-language programming assistant focused on Python and PowerShell code generation. Powered by CodeLlama-13B-Instruct, this application provides intelligent code generation, training data management, and AI comparison features.
-
Multi-Language Support:
- Python code generation
- PowerShell script creation
- Automatic language detection
-
AI-Powered Code Generation:
- Contextual understanding
- Code block generation
- Explanation of generated code
-
Training Data Management:
- Save and organize training examples
- Compare responses from different AI systems
- Filter and review training data
-
Customizable Settings:
- Temperature control for creativity
- Maximum token length
- Language-specific prompts
- Python 3.8+
- CUDA-capable GPU recommended
- Hugging Face account
- Clone the repository:
git clone https://github.com/JoshuaFourie/Codelama-Python.git
cd codebuddy-ai- Create a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows, use `venv\Scripts\activate`- Install dependencies:
pip install -r requirements.txt- Set up Hugging Face Token:
- Go to Hugging Face Tokens
- Create a new token with read access
- Either set an environment variable:
Or input the token when prompted during application startup
export HUGGING_FACE_HUB_TOKEN='your_token_here'
python launcher.py- Modify
theme.pyto customize app branding - Adjust model configurations in
model_manager.py
- Recommended:
- GPU with 16GB+ VRAM
- 32GB RAM
- AMD Ryzen 7800X3D or equivalent
- Minimum:
- 16GB RAM
- CUDA-capable GPU
- Python 3.8+
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Distributed under the MIT License. See LICENSE for more information.