AI-102 Question #366: Real Exam Question with Answer & Explanation

Question

Drag and Drop Question You have an Azure subscription that contains an Azure AI Document Intelligence resource named DI1 and a storage account named sa1. The sa1 account contains a blob container named blob1 and an Azure Files share named share1. You plan to build a custom model named Model1 in DI1. You create sample forms and JSON files for Model1. You need to train Model1 and retrieve the ID of the model. Which four actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order. NOTE: More than one order of answer choices is correct. You will receive credit for any of the correct orders you select. Answer:

Explanation

To train a custom Document Intelligence model, you must first upload training data (forms and JSON labels) to Azure Blob Storage (blob1), because Document Intelligence only supports Azure Blob Storage as a training data source - not Azure Files (share1). You then generate a SAS URL for blob1 to grant Document Intelligence secure, time-limited access to the container, call the Build Model REST API to initiate training using that SAS URL, and finally call the Get Model REST API to retrieve the trained model's ID and confirm its status. This sequence ensures proper data accessibility and correct API orchestration.

No community discussion yet for this question.