Information Extraction →mediumMultiple ChoiceObjective-mapped

AI-103 Information Extraction Practice Question

You are configuring a custom extraction model in Azure AI Document Intelligence and want to compose multiple specialized models into a single endpoint that automatically classifies and routes documents. Which REST API endpoint should you use to create this composed model?

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

POST /documentintelligence/documentModels:compose?api-version=2024-02-29-preview

Composed models (orchestration or composed models) are created using the documentModels:build or compose operations depending on the API version. Specifically, the compose operation combines multiple model IDs.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
PUT /documentintelligence/documentModels/{modelId}?api-version=2024-02-29-preview
Why it's wrong here
This PUT endpoint is used for model creation/annotation storage, not model composition.
✓
POST /documentintelligence/documentModels:compose?api-version=2024-02-29-preview
Why this is correct
The compose endpoint combines multiple custom models into a single composed model.
✗
POST /documentintelligence/documentModels:train?api-version=2024-02-29-preview
Why it's wrong here
Train is used for training a single model from labeled or unlabeled data, not composing existing models.
✗
POST /documentintelligence/models:classify?api-version=2024-02-29-preview
Why it's wrong here
There is no classify endpoint for model composition.

About these practice questions

This AI-103 question is part of Courseiva's 510-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

Written and reviewed by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

Last reviewed August 2026 · checked against the official Microsoft exam blueprint

Ready to practise?

Put this into practice with a full scored session.

Start practice session

Practice tests

Work through a scored set and see where your weak spots actually are.

AI-103 Practice Questions 2 — 50 Questions→AI-103 Practice Exam 4 — 20 Questions→AI-103 Practice Test 4 — 25 Questions→

Domain-focused practice

Each of these maps to a scored section of the exam blueprint.

Information Extraction Plan And Manage AN Azure AI Solution Text Analysis Implement Generative AI And Agentic Solutions

Filter by question format

Filter questions by type — troubleshooting, exhibit, drag-and-drop, multi-select, and more.

Browse scenarios

Practice by topic

Target a specific weak area. Each page focuses on one exam topic with questions, explanations and a concept guide.

Information Extraction practice questions AI-103 fundamentals practice questions AI-103 troubleshooting practice questions

Continue studying

AI-103 practice test All Microsoft practice questions Study guide

This AI-103 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-103 exam.