AI-103 Information Extraction Practice Test 4 — 15 Questions

Question 1

You are automating document processing. You want to trigger a workflow only after a Document Intelligence operation finishes. What is the standard way to implement this?

Accepted Answer

Poll the 'operation-location' URL. The Document Intelligence API returns a 'operation-location' URL; you poll this URL to check the status until completion.

Answer

Use a fixed-delay thread sleep

Answer

Use a WebSocket

Answer

Wait for a push notification

Question 2

Your company requires strict data privacy. Where should you host your Document Intelligence resources to ensure data remains in a specific region?

Accepted Answer

Regional Azure resource. Choosing the appropriate Azure region during resource creation ensures data residency compliance.

Answer

Any available region

Answer

Global service endpoint

Answer

Public multi-region endpoint

Question 3

You are extracting data from tables. The layout model is missing specific column headers. How can you improve the results?

Accepted Answer

Use a Custom Neural model. Training a custom model allows you to define specific fields, including complex table structures.

Answer

Increase image resolution

Answer

Use the Read API

Answer

Enable 'document-classify' feature

Question 4

What is the primary purpose of the 'selection marks' detection in the layout model?

Accepted Answer

To detect checkboxes and radio buttons. Selection marks (like checkboxes) are critical for forms where users indicate options.

Answer

To OCR printed text

Answer

To identify table borders

Answer

To find handwritten signatures

Question 5

Which tool provides a graphical user interface for labeling documents for custom models?

Accepted Answer

Document Intelligence Studio. Document Intelligence Studio is the web-based tool provided by Azure for labeling and training.

Answer

Azure CLI

Answer

Azure Storage Explorer

Answer

Visual Studio Code

Question 6

You are integrating Document Intelligence with Azure Blob Storage. You need to provide the model with a set of documents for training. How should you prepare the data?

Accepted Answer

Upload files and corresponding .labels.json and .ocr.json files. Training requires documents to be stored in an Azure Blob Storage container with associated .labels.json files generated by the labeling tool.

Answer

Convert all files to CSV

Answer

Store files in an Azure SQL database

Answer

Upload raw files only

Question 7

Your application is receiving 429 errors from the Document Intelligence service. What does this indicate?

Accepted Answer

Rate limit exceeded. A 429 error indicates 'Too Many Requests', meaning the application has exceeded its quota or rate limit.

Answer

Authentication failed

Answer

Server-side error

Answer

The request is malformed

Question 8

You are using Document Intelligence to classify documents into different types (e.g., invoices, bank statements). Which model is most appropriate?

Accepted Answer

Custom classification model. The 'custom classification' model is designed to group documents into predefined categories.

Answer

Prebuilt-invoice

Answer

Read model

Answer

Custom extraction model

Question 9

You need to secure the communication between your app and Document Intelligence using a private endpoint. What is the primary benefit?

Accepted Answer

Traffic stays within the Azure private network. Private endpoints ensure traffic flows over the private Azure backbone network, avoiding the public internet.

Answer

Reduced cost

Answer

Faster inference speeds

Answer

Increased throughput limits

Question 10

You need to extract information from a business card. Which prebuilt model should you select?

Accepted Answer

prebuilt-businessCard. The 'prebuilt-businessCard' model is specifically optimized for contact details on business cards.

Answer

prebuilt-taxDocument

Answer

prebuilt-idDocument

Answer

prebuilt-layout

Question 11

Which TWO of the following are prerequisites for training a custom extraction model?

Accepted Answer

A set of labeled data in JSON format. You need a source of files in Azure Blob Storage and the files must be associated with valid labels (via .labels.json).

Answer

An Azure SQL database

Answer

A pre-existing template model

Answer

A pre-installed local labeling agent

Question 12

Which TWO metrics are reported by Document Intelligence Studio to evaluate model performance?

Accepted Answer

Recall. Precision and Recall are the core metrics provided for every field in a custom model.

Answer

Throughput

Answer

Latencey

Answer

Confidence score

Question 13

Which THREE file types are supported for direct processing by the Document Intelligence API?

Accepted Answer

TIFF. PDF, JPEG, and TIFF (and PNG) are standard supported input formats.

Answer

DOCX

Answer

PPTX

Question 14

Which THREE fields are typically returned by the prebuilt-receipt model?

Accepted Answer

MerchantName. The prebuilt-receipt model extracts MerchantName, TransactionDate, and Total, among others.

Answer

EmployeeID

Answer

PatientName

Question 15

Which TWO of the following are valid ways to authenticate to the Document Intelligence service?

Accepted Answer

API Key. Authentication is primarily handled through an API key or Microsoft Entra ID (RBAC).

Answer

FTP Credentials

Answer

SSH Key

Answer

SQL Server Authentication