Exam AI-100 topic 1 question 29 discussion

Actual exam question from Microsoft's AI-100

Question #: 29
Topic #: 1

Your company is building custom models that integrate into microservices architecture on Azure Kubernetes Services (AKS).
The model is built by using Python and published to AKS.
You need to update the model and enable Azure Application Insights for the model.
What should you use?

A. the Azure CLI
B. MLNET Model Builder
C. the Azure Machine Learning SDK
D. the Azure portal

Show Suggested Answer

Suggested Answer: C 🗳️
You can set up Azure Application Insights for Azure Machine Learning. Application Insights gives you the opportunity to monitor:
✑ Request rates, response times, and failure rates.
✑ Dependency rates, response times, and failure rates.
✑ Exceptions.
Requirements include an Azure Machine Learning workspace, a local directory that contains your scripts, and the Azure Machine Learning SDK for Python installed.
References:
https://docs.microsoft.com/bs-latn-ba/azure/machine-learning/service/how-to-enable-app-insights

by Daniel_vahid at Feb. 13, 2020, 8:16 p.m.

Comments

Submit Cancel

lchvce

Highly Voted 5 years, 1 month ago

You can not update your model using Azure Portal

upvoted 13 times

BleadFast

4 years, 2 months ago

Just to make somethings clearer. you can't update the AKS to use APP insights using the portal after the AKS is deployed.

upvoted 1 times

...

rveney

Most Recent 1 year, 11 months ago

Azure portal (option D) is the recommended choice for updating the model and enabling Azure Application Insights in this scenario, as it provides an intuitive and user-friendly interface for managing AKS resources and configuring services.

upvoted 1 times

rveney

1 year, 11 months ago

To update the model and enable Azure Application Insights for the model in a microservices architecture on Azure Kubernetes Services (AKS), you should use: C. the Azure Machine Learning SDK The Azure Machine Learning SDK provides comprehensive tools and libraries for managing and deploying machine learning models on Azure. It allows you to create, update, and deploy models using Python, making it suitable for your scenario.

upvoted 1 times

...

demonstrous

4 years, 1 month ago

Answer is C. Azure Machine Learning SDK. from azureml.core.webservice import Webservice aks_service= Webservice(ws, "my-service-name") then you Update your service and enable Azure Application Insights aks_service.update(enable_app_insights=True) Portal does not offer any option like such neither az ml cli. Note: You can enable data collection at the time of deployment using Studio i.e., ml.azure.com but once published then SDK is only solution.

upvoted 1 times

...

AlfuryDB

4 years, 2 months ago

https://docs.microsoft.com/en-us/learn/modules/monitor-models-with-azure-machine-learning/2-enable-application-insights given answer is 100% correct

upvoted 1 times

...

Daniel_vahid

5 years, 3 months ago

Azure Portal and SDK both seem correct to me.

upvoted 2 times

jorama

5 years ago

When the model has been deployed, you need to use the SDK to enable App Insights

upvoted 9 times

...

Cornholioz

4 years, 3 months ago

ML SDK and the ML Studio can be used to enable APP Insights. ML SDK is the correct answer here since ML Studio is not an option... and because only one answer is expected. Reference: documentation referenced in the answer.

upvoted 2 times

...