kserve: Unable to use KFServing on Kubeflow

/kind bug

What steps did you take and what happened: I was trying to use KFServing for Model Prediction as described here.

MODEL_NAME=flowers-sample
INPUT_PATH=@./input.json
INGRESS_GATEWAY=istio-ingressgateway
CLUSTER_IP=$(kubectl -n istio-system get service $INGRESS_GATEWAY -o jsonpath='{.status.loadBalancer.ingress[0].ip}')
SERVICE_HOSTNAME=$(kubectl get inferenceservice ${MODEL_NAME} -o jsonpath='{.status.url}' | cut -d "/" -f 3)

I realize that CLUSTER_IP & SERVICE_HOSTNAME are blank. On checking the JSON file, it can be figured out that the jsonpath specified for CLUSTER_IP has been modified to spec.clusterIP, whereas the SERVICE_HOSTNAME continues to remain blank leading to failure of the steps that follow.

What did you expect to happen: The commands to execute successfully & output a model prediction.

Anything else you would like to add: I tried to hardcode the SERVICE_HOSTNAME to flowers-sample.default.example.com but that led to the connection time out error.

Environment:

• Istio Version:
• Knative Version:
• KFServing Version:
• Kubeflow version: v1.0.2
• Kfdef: k8s_istio
• Minikube version:
• Kubernetes version: (use kubectl version): Client Version: 1.18 Server Version: 1.15
• OS (e.g. from /etc/os-release): Ubuntu 18.04