Here, when I ran the code for deployment using AKSCompute, I am getting an error
Tips: You can try get_logs(): https://aka.ms/debugimage#dockerlog or local deployment: https://aka.ms/debugimage#debug-locally to debug if deployment takes longer than 10 minutes. Running 2023-04-20 11:42:01+05:30 Creating Container Registry if not exists. 2023-04-20 11:42:01+05:30 Registering the environment. 2023-04-20 11:42:02+05:30 Use the existing image. 2023-04-20 11:42:03+05:30 Creating resources in AKS. 2023-04-20 11:42:04+05:30 Submitting deployment to compute. 2023-04-20 11:42:04+05:30 Checking the status of deployment aiops-model-service-error. Failed Output exceeds the size limit. Open the full output data in a text editor Service deployment polling reached non-successful terminal state, current service state: Failed Operation ID: f65019a8-3178-48e7-b28b-1c65d28f13de More information can be found using '.get_logs()' Error: { "code": "KubernetesDeploymentFailed", "statusCode": 400, "message": "Kubernetes Deployment failed", "details": [ { "code": "CrashLoopBackOff", "message": "Your container application crashed as it does not have AzureML serving stack. Make sure you have 'azureml-defaults>=1.0.45' package in your pip dependencies, it contains requirements for the AzureML serving stack." }, { "code": "DeploymentFailed", "message": "Your container endpoint is not available. Please follow the steps to debug:
inference_config = InferenceConfig(source_directory = './service_files',
entry_script="scoring_script.py",
environment=myenv)
deploy_config = AksWebservice.deploy_configuration(cpu_cores = 0.1,
memory_gb = 0.5)
model = ws.models['model_from_run_local_5']
service = Model.deploy(workspace=ws,
name = 'aiops-model-service-error',
models = [model],
inference_config = inference_config,
deployment_config = deploy_config,
deployment_target = production_cluster)
service.wait_for_deployment(show_output = True)
This is the code and environment I usedenvironment. I even tried using AMLCompute but I am getting same error.
