raitap 0.9.0

Python library to assess the responsibility level of AI models for integration into MLOps workflows.

RAITAP is a Python library to assess the responsibility level of AI models. It is designed to be easily integrated into existing MLOps workflows.

It is a wrapper around existing XAI frameworks, which provides a consistent API, allowing you to easily switch your configuration, combine frameworks, and obtain consolidated outputs.

RAITAP currently assesses the following 2 responsible AI dimensions:

• Transparency
• Robustness

as defined in Towards the certification of AI-based systems and MLOps as enabler of trustworthy AI

Quick start

uv add raitap
uv run raitap --demo

This runs the bundled self-contained demo.yaml (tiny dataset, CPU, no setup required). For a more realistic consumer integration, see the standalone example/ project at the repo root. For the full ZHAW thesis demo, see contributor-configs/lwise-ham10000/.

For more information

• as a consumer/user: consumer documentation
• as a contributor: contributor documentation

Showcase

CLI run	Generated report