AI-900: Consuming Azure ML Designer Inference Pipelines with REST Endpoints

Deploying predictive models for consumption demands publishing real-time endpoints. Learn how Azure ML publishes REST APIs for client apps to leverage trained machine learning pipelines.

Question

You use Azure Machine Learning designer to publish an inference pipeline. Which two parameters should you use to consume the pipeline?
Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.

A. the model name
B. the training endpoint
C. the authentication key
D. the REST endpoint

Answer

C. the authentication key
D. the REST endpoint

Explanation

The correct answer is C. the authentication key and D. the REST endpoint.

To consume an inference pipeline published by Azure Machine Learning designer, you need to use the authentication key and the REST endpoint of the pipeline. The authentication key is a secret token that is used to authorize requests to the pipeline. The REST endpoint is a URL that exposes the pipeline as a web service that can be invoked by any HTTP client.

The other options are not correct for the following reasons:

• the model name: This is the name of the machine learning model that is used in the inference pipeline. It is not a parameter that is used to consume the pipeline, as it does not identify or authorize the pipeline.
• the training endpoint: This is the URL that exposes the training pipeline as a web service that can be used to retrain the model. It is not a parameter that is used to consume the inference pipeline, as it does not invoke the inference pipeline.

References

Microsoft Docs > Azure > Machine Learning > Run batch predictions using Azure Machine Learning designer

Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Fundamentals AI-900 exam and earn Microsoft Azure AI Fundamentals AI-900 certification.