Courseiva

AI-102 Practice Question: Implement knowledge mining and information extraction solutions

A company is building a knowledge mining solution using Azure AI Search. They need to extract entities from a large set of PDF documents stored in Azure Blob Storage. The solution must use a built-in AI skill to identify people, organizations, and locations. Which TWO actions should be taken? (Choose two.)

⚠ Common exam trap

Candidates may mistakenly believe that a custom analyzer (Option A) or custom skill (Option C) is needed, but built-in skills suffice. Also, they may overlook that OCR (Option D) must be enabled to process scanned PDFs before entity recognition.

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

Enable OCR (Optical Character Recognition) in the indexer configuration.

OCR (Optical Character Recognition) is required to extract text from scanned PDFs before entity recognition can be applied. Option E is correct because the built-in Entity Recognition skill identifies people, organizations, and locations. Option A is incorrect because custom analyzers affect indexing and querying, not entity extraction. Option B is incorrect because the Key Phrase Extraction skill extracts key phrases, not named entities. Option C is incorrect because a custom skill is unnecessary when a built-in skill already meets the requirement.

Answer analysis

Option-by-option breakdown

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

  • Configure the index to use a custom analyzer.

    Why it's wrong here

    Custom analyzers are for text analysis, not entity extraction.

  • Add the Key Phrase Extraction skill to the skillset.

    Why it's wrong here

    Key Phrase Extraction extracts key phrases, not specific entity types.

  • Deploy a custom skill using Azure Functions to extract entities.

    Why it's wrong here

    Built-in skills are available; a custom skill is not required.

  • Enable OCR (Optical Character Recognition) in the indexer configuration.

    Why this is correct

    OCR extracts text from PDFs so that the Entity Recognition skill can process it.

  • Add the Entity Recognition skill to the skillset.

    Why this is correct

    The Entity Recognition skill extracts entities like people, organizations, and locations.

Quick reference

Azure Blob Storage Tier Comparison

TierStorage CostRetrieval CostLatencyUse Case
HotHighestLowestImmediateActive data, frequent reads
CoolLowerHigherImmediateData accessed < once / month
ColdLower stillHigherImmediateData accessed < once / quarter
ArchiveLowestHighest + rehydration delayHoursLong-term compliance retention

About these practice questions

One of 945 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This AI-102 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-102 exam.