Seldon

Seldon Explainability API

Seldon provides a dedicated /explain REST endpoint alongside each deployed model, powered by the Alibi explainability library. The endpoint supports multiple explanation algorithms including SHAP, integrated gradients, and anchor-based methods, allowing users to request human-interpretable explanations for individual model predictions in production.

GitHub

Documentation

📖
Documentation
https://docs.seldon.io/projects/seldon-core/en/latest/reference/apis/v2-protocol.html

API entry from apis.yml

apis.yml Raw ↑ 
aid: seldon:seldon-explainability-api
name: Seldon Explainability API
description: 'Seldon provides a dedicated /explain REST endpoint alongside each deployed model, powered
  by the Alibi explainability library. The endpoint supports multiple explanation algorithms including
  SHAP, integrated gradients, and anchor-based methods, allowing users to request human-interpretable
  explanations for individual model predictions in production.

  '
image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
humanURL: https://docs.seldon.io/projects/seldon-core/en/latest/analytics/drift_detection.html
baseURL: https://docs.seldon.io
tags:
- Explainability
- SHAP
- Alibi
- Model Interpretability
properties:
- type: Documentation
  url: https://docs.seldon.io/projects/seldon-core/en/latest/reference/apis/v2-protocol.html