Seldon provides model explanations using its Alibi Open Source library.
We provide an example notebook showing how to deploy an explainer for Tabular, Text and Image models.
Creating your explainer¶
For Alibi explainers that need to be trained you should
Use python 3.6 as the Seldon python wrapper also runs in python 3.6 when it loads your explainer.
Follow the Alibi docs for your particular desired explainer. The Seldon Wrapper presently supports: Anchors (Tabular, Text and Image), KernelShap and Integrated Gradients.
Save your explainer to a file called
explainer.dillusing the dill python package and store on a bucket store or PVC in your cluster. We support gcs, s3 (including Minio) or Azure blob.
For the Seldon Protocol an endpoint path will be exposed for:
http://<ingress-gateway>/seldon/<namespace>/<deployment name>/<predictor name>/api/v1.0/explain
So for example if you deployed:
apiVersion: machinelearning.seldon.io/v1 kind: SeldonDeployment metadata: name: income namespace: seldon spec: name: income annotations: seldon.io/rest-timeout: "100000" predictors: - graph: children:  implementation: SKLEARN_SERVER modelUri: gs://seldon-models/sklearn/income/model-0.23.2 name: classifier explainer: type: AnchorTabular modelUri: gs://seldon-models/sklearn/income/explainer-py36-0.5.2 name: default replicas: 1
And were port forwarding to Ambassador on localhost:8003 then the API call would be: