Crucial Exams

Microsoft Azure AI Engineer Associate AI-102 Practice Question

You have created a custom extraction model (v1) by training on 12 unlabeled sample documents in Azure AI Document Intelligence Studio. A production API uses the model through the alias "invoices-prod", which you published after the first training. During user acceptance testing you discover several fields are missing, so you upload five additional representative documents and retrain the model, which produces a new version (v2).

You must evaluate v2 without disrupting the application that is still calling alias "invoices-prod". What should you do next?

  • Republish version v2 to the existing alias "invoices-prod" and roll back if problems occur.

  • Publish version v2 by assigning it a new alias such as "invoices-staging", then call that alias during testing.

  • Rename the model ID of version v2 and update the production application to call the new ID when testing is complete.

  • Delete the alias "invoices-prod" from version v1, then publish version v2 with the same alias.

Microsoft Azure AI Engineer Associate AI-102
Implement knowledge mining and information extraction solutions
Your Score:
Settings & Objectives
Random Mixed
Questions are selected randomly from all chosen topics, with a preference for those you haven’t seen before. You may see several questions from the same objective or domain in a row.
Rotate by Objective
Questions cycle through each objective or domain in turn, helping you avoid long streaks of questions from the same area. You may see some repeat questions, but the distribution will be more balanced across topics.

Check or uncheck an objective to set which questions you will receive.

Wipe Score
Bash, the Crucial Exams Chat Bot
AI Bot