AI-200 Practice Question: Which Azure AI Search capability allows you to extract text from images and PDF documents…
Which Azure AI Search capability allows you to extract text from images and PDF documents during indexer execution using AI cognitive skills?
⚠ Common exam trap
AI-200 often tests whether candidates confuse query-time features (semantic configurations, scoring profiles) with index-time enrichment (skillsets) for OCR and document extraction.
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
✓
Skillsets
Skillsets in Azure AI Search define a pipeline of cognitive skills (such as OCR, image analysis, entity recognition, and text translation) that run during indexer execution to enrich content. To extract text from images and PDFs, you attach a skillset to the indexer, and skills like OCR or Document Extraction process the content. Semantic configurations, scoring profiles, and vector profiles do not perform content extraction.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Semantic configurations
Why it's wrong here
A semantic configuration tells semantic ranking which fields hold the title, main content and keywords, so it can re-rank results and produce captions and answers at query time. It runs after documents are indexed and does not extract text. Pulling text out of images and PDFs during indexing is done by a skillset with OCR and related skills attached to the indexer.
- ✗
Scoring profiles
Why it's wrong here
Scoring profiles adjust relevance ranking through boost weights and functions applied to search results, so they cannot run OCR or document cracking during indexer execution. They are tempting because both features are configured on the index, but scoring profiles would be correct when promoting fresher or tagged documents in result ordering.
- ✓
Skillsets
Why this is correct
A skillset defines the AI enrichment pipeline an indexer runs on each document: OCR to read printed and handwritten text in images, including images inside PDFs, text merge to combine it with the document's own text, plus skills such as language detection, entity recognition, key phrase extraction, text splitting and embedding generation. The indexer needs image extraction enabled for OCR to receive images.
- ✗
Vector profiles
Why it's wrong here
Vector profiles configure HNSW or exhaustive KNN algorithms and embedding dimensions for similarity search, so they never invoke skillsets or OCR during indexing. They are tempting because vector search is central to AI enrichment pipelines, but they would be correct only when tuning recall and latency for vectorised queries, not for extracting text from images.
About these practice questions
This AI-200 question is part of Courseiva's 418-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 →
You might also like
Similar AI-200 questions
- You are designing an application that stores vector embeddings in Azure Cosmos DB for NoSQL. You want to ensure that vec…
- Which Azure service provides a fully managed NoSQL database with native vector search capabilities and turnkey multi-reg…
- You are designing an enterprise search architecture on Azure that requires hybrid search capabilities. Which THREE compo…
- You are integrating Azure OpenAI Service's text-embedding-ada-002 model with Azure AI Search. You want to automate the g…
- You are storing vector embeddings generated by Azure OpenAI in Azure Cosmos DB for NoSQL. Which built-in SQL function mu…
Written and reviewed by Johnson Ajibi, MSc IT Security
Security Systems Architect · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
This AI-200 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-200 exam.