kserve

import os from kubernetes import client as k8s_client from kserve import KServeClient, constants, utils from kserve import V1beta1InferenceService, V1beta1InferenceServiceSpec, V1beta1PredictorSpec, V1beta1SKLearnSpec # --- Configuration and Client Initialization --- # This example assumes kubectl is configured to connect to a Kubernetes cluster. # For in-cluster execution, uncomment `k8s_client.config.load_incluster_config()`. # For local execution, ensure your ~/.kube/config is set up. try: k8s_client.config.load_kube_config() except k8s_client.config.config_exception.ConfigException: print("Warning: Could not load kube-config. Attempting in-cluster config.") try: k8s_client.config.load_incluster_config() except k8s_client.config.config_exception.ConfigException: print("Error: Could not load any Kubernetes config. Please ensure kubectl is configured or run within a cluster.") exit(1) api_version = constants.KSERVE_API_VERSION kserve_client = KServeClient() namespace = os.environ.get('K8S_NAMESPACE', 'default') # Use an environment variable or default service_name = 'sklearn-iris-quickstart' # --- Define an InferenceService --- isvc = V1beta1InferenceService( api_version=api_version, kind=constants.KSERVE_KIND, metadata=k8s_client.V1ObjectMeta( name=service_name, namespace=namespace ), spec=V1beta1InferenceServiceSpec( predictor=V1beta1PredictorSpec( sklearn=V1beta1SKLearnSpec( storage_uri='gs://kfserving-examples/models/sklearn/iris', protocol_version='v1' ) ) ) ) print(f"Creating InferenceService '{service_name}' in namespace '{namespace}'...") # --- Create and Wait for InferenceService --- try: kserve_client.create(isvc) print(f"InferenceService '{service_name}' created. Waiting for it to be ready...") kserve_client.wait_isvc_ready(service_name, namespace=namespace) print(f"InferenceService '{service_name}' is ready:") print(kserve_client.get(service_name, namespace=namespace)) # Example of how to delete the service: # kserve_client.delete(service_name, namespace=namespace) # print(f"InferenceService '{service_name}' deleted.") except Exception as e: print(f"Failed to create or wait for InferenceService: {e}") # Attempt cleanup if creation partially succeeded but failed later try: kserve_client.delete(service_name, namespace=namespace) print(f"Attempted cleanup of '{service_name}'.") except Exception as cleanup_e: print(f"Failed to clean up '{service_name}': {cleanup_e}")