Courseiva

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

Your Azure AI Search indexer is failing to index a large number of PDFs from Azure Blob Storage. The error log shows 'Document extraction timeout' for many documents. You need to resolve this issue without losing data. What should you do?

⚠ Common exam trap

A common mix-up: candidates confuse 'indexer execution timeout' with 'document extraction timeout' and assume the solution must involve changing parsing modes or splitting files, rather than adjusting the indexer's maximum runtime.

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

Increase the indexer execution timeout in the indexer definition

The 'Document extraction timeout' error indicates that the indexer is taking longer than the default 24-hour timeout to process certain PDFs. Increasing the indexer execution timeout in the indexer definition allows the indexer to continue processing these large documents without losing data, as it extends the maximum time the indexer can run for a single execution.

Answer analysis

Option-by-option breakdown

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

  • Increase the indexer execution timeout in the indexer definition

    Why this is correct

    The timeout can be increased to allow large documents to be processed.

  • Change the parsing mode of the indexer to 'text'

    Why it's wrong here

    PDFs are already parsed as text; changing parsing mode doesn't address timeout.

  • Split large PDFs into smaller files before uploading

    Why it's wrong here

    This requires manual effort and re-uploading; not a direct solution within the existing pipeline.

  • Enable incremental enrichment on the skillset

    Why it's wrong here

    Incremental enrichment affects caching, not extraction timeout.

Visual reference

Client Recursive Resolver Root DNS (13 root servers) TLD DNS (.com, .org, …) Authoritative example.com query IP addr answer

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

This AI-102 question is part of Courseiva's 945-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

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.