JohnnyKHU/holisticai

fork of the primary holistic ai utility codebase for us to work with in AsherInform

Holistic AI

The Holistic AI library is an open-source tool to assess and improve the trustworthiness of AI systems.

Currently, the library offers a set of techniques to easily measure and mitigate Bias across numerous tasks. In the future, it will be extended to include tools for Efficacy, Robustness, Privacy and Explainability as well. This will allow a holistic assessment of AI systems.

• Documentation: https://holistic-ai.readthedocs.io/en/latest/
• Tutorials: https://github.com/holistic-ai/holisticai/tree/main/tutorials
• Source code: https://github.com/holistic-ai/holisticai/tree/main
• Holistic Ai website: https://holisticai.com

Installation:

For metrics, you can use the default installation:

pip install holisticai

For bias visualization and mitigation, you need additional dependencies. You can install them with:

pip install holisticai[methods]

Troubleshooting

on macOS could be necessary some packages before install holisticai library:

brew install cbc pkg-config
python -m pip install cylp
brew install cmake

Contributing

We welcome contributions to the Holistic AI library. If you are interested in contributing, please refer to our contributing guide.