Welcome to TrustyAI’s documentation!

Red Hat’s TrustyAI-Python library provides XAI explanations of decision services and predictive models for both enterprise and data science use-cases.

This library is designed to provide a set of Python bindings to the main TrustyAI Java toolkit, to allow for easier access to the toolkit in data science and prototyping use cases. This means the library benefits from both the speed of Java as well as the ease-of-use of Python; our whitepaper shows that the TrustyAI-Python LIME and SHAP explainers can run faster than the the official implementations.

Installation

pip install trustyai

Tutorial and Examples

To get started, check out the Tutorial. For more usage examples, see the example notebooks:

• LIME

• SHAP

• Counterfactuals

GitHub Repos

• TrustyAI Python

• TrustyAI Python Examples

• TrustyAI Java

Paper

TrustyAI Explainability Toolkit, 2022

Contents

Indices and tables

• Index

• Module Index

• Search Page