Model explainability answers the question: "Why did my model make this prediction" for a given instance. KServe integrates with Alibi Explainer which implements a black-box algorithm by generating a lot of similar looking instances for a given instance and send out to the model server to produce an explanation.
Additionally, KServe also integrates with The AI Explainability 360 (AIX360) toolkit, an LF AI Foundation incubation project, which is an open-source library that supports the interpretability and explainability of datasets and machine learning models. The AI Explainability 360 Python package includes a comprehensive set of algorithms that cover different dimensions of explanations along with proxy explainability metrics. In addition to native algorithms, AIX360 also provides algorithms from LIME and Shap.
|Deploy Alibi Image Explainer||Imagenet Explainer|
|Deploy Alibi Income Explainer||Income Explainer|
|Deploy Alibi Text Explainer||Alibi Text Explainer|