RecSys provides a clean interface for building and using recommendation systems using PyTorch and PyTorch Lightning.
- Support for the four stages of recommendations (retrieval, filter, score, reorder)
- Built on top of PyTorch and PyTorch Lightning for easy training and inference
Install latest release from pypi with:
pip install recsysHere is an example of how to use the library to train and use a recommendation system:
#TODO
To run the library test run pytest from the main directory
We welcome contributions to this library! If you have an idea for a new feature or have found a bug, please open an issue on the GitHub repository to discuss it.
If you would like to contribute code, please follow these steps:
- Fork the repository
- Create a new branch for your feature or bug fix
- Implement your changes
- Write tests for your changes (if applicable)
- Run the existing tests to ensure they still pass
- Submit a pull request from your branch to the master branch of the repository