Got HTTPConnectionPool when I request(post) to kserve example model with python SDK

Question

I runed code case1, case2 in local space with vscode, not Notebooks of kubeflow censtral dashboard.

I'd like to know what I'm missing.

prepared:

• added user

      - email: [email protected]
        hash: 1234          # Actually, hash value
        userID: "myuserid"
        username: myusername
  

• added namespace

  $ kubectl apply -f profile.yaml
  

  apiVersion: kubeflow.org/v1beta1
  kind: Profile
  metadata:
    name: exam-namespace
  spec:
    owner:
      kind: User
      name: [email protected]
    resourceQuotaSpec: {}
  

• served model

  kubeflow Central Dashboard - Models - +NEW MODEL SERVER

  apiVersion: "serving.kserve.io/v1beta1"
  kind: "InferenceService"
  metadata:
    annotations:
      isdecar.istio.is/inject: "false"
    name: "sklearn-iris"
  spec:
    predictor:
      sklearn:
        image: "kserve/sklearnserver:v0.9.0"
        storageUri: "gs://kfserving-examples/models/sklearn/1.0/model"
  

what i did with python sdk

case 1.

using kfp.Client()

import kfp
import requests

HOST = "http://localhost:8080"
NAME_SPACE = "exam-namespace"
USER_NAME = "[email protected]"
USER_PS = '1234'

session = requests.Session()
response = session.get(HOST)

headers = {
        "Content-Type": "application/x-www-form-urlencoded",
}

data = {"login": USER_NAME, "password": USER_PS}
session.post(response.url, headers=headers, data=data)                              
session_cookie = session.cookies.get_dict()["authservice_session"]  


# access kubeflow dashboard
client = kfp.Client(
    host=f"{HOST}/pipeline",
    namespace=f"{NAME_SPACE}",
    cookies=f"authservice_session={session_cookie}")

session_cookie = session.cookies.get_dict()
sklear_iris_input = dict(instances = [
        [6.8, 2.8, 4.8, 1.4],
        [6.0, 3.4, 4.5, 1.6]
    ])

headers = {'Host': "http://sklearn-iris.project-pipeline.example.com"}
res = session.post(f"{HOST}/v1/models/v1/models/sklearn-iris:predict", 
                   headers = headers, 
                   cookies = session_cookie,
                   data = json.dumps(sklear_iris_input))
print(f"res.json : {res.json}")

and, got this..

HTTPSConnectionPool(host='127.0.0.1', port=8080): 
Max retries exceeded with url: /v1/models/v1/models/sklearn-iris:predict (Caused by SSLError(SSLError(1, '[SSL: WRONG_VERSION_NUMBER] wrong version number (_ssl.c:1131)')))

case 2.

using KServeClient()

import requests
import json
    
from kserve import utils, KServeClient

NAME_SPACE = "exam-namespace"
SERVICE_NAME = "sklearn-iris"


kserve = KServeClient()
isvc_resp = kserve.get(SERVICE_NAME, namespace = NAME_SPACE)

# http://sklearn-iris.exam-namespace.svc.cluster.local/v1/models/sklearn-iris:predict
isvc_url = isvc_resp['status']['address']['url']

sklear_iris_input = dict(instances = [
        [6.8, 2.8, 4.8, 1.4],
        [6.0, 3.4, 4.5, 1.6]
    ])

response = requests.post(isvc_url, json = json.dumps(sklear_iris_input))  
print(response.text)

and, got this..

HTTPConnectionPool(host='sklearn-iris-test2.project-pipeline.svc.cluster.local', port=80): 
Max retries exceeded with url: /v1/models/sklearn-iris-test2:predict (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7fe70aa8e9a0>: Failed to establish a new connection: [Errno -2] Name or service not known'))

1. After adding a new user to dex and creating a namespace via profile.yaml, do I need to add specific information to the AuthorizationPolicy?
2. I installed kubernetes and kubeflow on this desktop and port-forwarded through istio-ingressgate. And I ran the code case1,case2 in locally, is there any problem with setting host to localhost:8080?
3. If the above two questions don't have anything I need to do, how should the HTTPConnectionPool be resolved?