host = f"{model_server_name}.{stage}.svc.cluster.local"

def set_header(hostname):
    headers = {
        'Host': hostname
    }

    return headers

class ProxyHTTPRequestHandler(BaseHTTPRequestHandler):
    protocol_version = 'HTTP/1.1'
    def req_send(self, url, hostname):
        content_len = int(self.headers.get('content-length', 0))
        post_body = self.rfile.read(content_len)
        req_header = self.parse_headers()

        resp = requests.post(url, data=post_body, headers=merge_two_dicts(req_header, set_header(hostname)), verify=False)
        return resp

url = "http://my-model-a.kserve-test.svc.cluster.local/v1/models/my-model-a:predict"
resp = self.req_send(url, hostname)
print(resp.content)

/v1/models/model_name:predict"

/v2/models/model_name/infer

MODEL_NAME=sklearn-iris
INPUT_PATH=@./iris-input.json
SERVICE_HOSTNAME=$(kubectl get inferenceservice sklearn-iris -o jsonpath='{.status.url}' , cut -d "/" -f 3)
curl -v -H "Host: ${SERVICE_HOSTNAME}" http://${INGRESS_HOST}:${INGRESS_PORT}/v1/models/$MODEL_NAME:predict -d $INPUT_PATH
   Trying 192.168.64.16:31781...
 Connected to 192.168.64.16  (192.168.64.16 ) port 31781 (#0)
> POST /v1/models/sklearn-iris:predict HTTP/1.1
> Host: sklearn-iris.default.example.com
> User-Agent: curl/7.78.0
> Accept: /
> Content-Length: 76
> Content-Type: application/x-www-form-urlencoded
> 
 Mark bundle as not supporting multiuse
< HTTP/1.1 302 Found
< location: /dex/auth?client_id=kubeflow-oidc-authservice&redirect_uri=%2Flogin%2Foidc&response_type=code&scope=profile+email+groups+openid&state=MTY1MjcyODM0NnxFd3dBRUZCWlN6ZDJiWFZpTWxnNGRWaEpkVFk9fFIBBaMr4YRh4f0g-Q7-ZeT_vBPw2OWyqQUXSI7asDpv
< date: Mon, 16 May 2022 19:12:26 GMT
< x-envoy-upstream-service-time: 1
< server: istio-envoy
< content-length: 0
< 
 Connection #0 to host 192.168.64.16 left intact