Exam DP-100 topic 3 question 123 discussion

Actual exam question from Microsoft's DP-100

Question #: 123
Topic #: 3

You use the Azure Machine Learning Python SDK to create a batch inference pipeline.

You must publish the batch inference pipeline so that business groups in your organization can use the pipeline. Each business group must be able to specify a different location for the data that the pipeline submits to the model for scoring.

You need to publish the pipeline.

What should you do?

A. Create multiple endpoints for the published pipeline service and have each business group submit jobs to its own endpoint.
B. Define a PipelineParameter object for the pipeline and use it to specify the business group-specific input dataset for each pipeline run.
C. Define a OutputFileDatasetConfig object for the pipeline and use the object to specify the business group-specific input dataset for each pipeline run.
D. Have each business group run the pipeline on local compute and use a local file for the input data.

Show Suggested Answer

Suggested Answer: B 🗳️

by sap_dg at March 27, 2023, 5:37 p.m.

Comments

Submit Cancel

evangelist

6 months, 1 week ago

Selected Answer: B

Create multiple endpoints: Creating multiple endpoints for each business group is not efficient or scalable. It also complicates the management and maintenance of the pipeline.

upvoted 1 times

...

phdykd

1 year, 4 months ago

B PipelineParameter

upvoted 1 times

...

fqc

1 year, 7 months ago

A PipelineParameter object can be used to specify a parameter that can be passed to the pipeline when it is run. In this case, the parameter can be used to specify the location of the input dataset for the business group. This allows each business group to specify a different location for the data that the pipeline submits to the model for scoring.

upvoted 2 times

...

sap_dg

1 year, 8 months ago

Correct!

upvoted 1 times

...