Version: Next
Create with Web UI
To deploy a simple model, we can use the flowers prediction example from KFServing.
- To do this, go to Models.
- Then click New Model Server.
- Copy and paste the yaml below, filling in your namespace for <namespace>, then click Create.apiVersion: "serving.kubeflow.org/v1beta1"kind: "InferenceService"metadata:namespace: <namespace>name: "flower-sample"spec:predictor:tensorflow:storageUri: "gs://kfserving-samples/models/tensorflow/flowers"
- Wait for the resource to finish setting up, to confirm it's running you should see a green check as indicated.
- To test the model, we can use this JupyterLab notebook