apiVersion: "serving.kubeflow.org/v1beta1"
 kind: "InferenceService"
 metadata:
   name: "sklearn-iris"
 spec:
   predictor:
     sklearn:
      storageUri: " gs://kfserving-samples/models/sklearn/iris "

import requests
 
 data = {
   "instances": [
     [6.8,  2.8,  4.8,  1.4],
    [6.0,  3.4,  4.5,  1.6]
   ]
 }

url = "http://sklearn-iris.dev.svc.cluster.local/v1/models/sklearn-iris:predict"
headers = {
 "Host" : "sklearn-iris.dev.svc.cluster.local",
 }
 
response = requests.post(url, headers=headers, json=data)
 
print("Status Code", response.status_code)
print("JSON Response ", response.json())

$ k get inferenceservice my-model-b -o yaml
...
status:
  address:
    url: http://my-model-b.kserve-test.svc.cluster.local/v1/models/my-model-b:predict