AI-102 Practice Question: Implement knowledge mining and information extraction solutions
Which THREE factors should you consider when designing a knowledge mining solution that uses Azure AI Search and custom skills to extract insights from large volumes of documents?
⚠ Common exam trap
Many candidates confuse knowledge store projections (output storage) with indexing performance, or assume semantic ranking is a mandatory skillset component, when in fact it is an optional query-time feature.
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
✓
The maximum execution time of the custom skill must fit within the indexer timeout
Option B is correct because custom skills run inside the indexer execution pipeline, and each skill invocation must complete within the indexer's timeout limits (for example, the default HTTP timeout of 3 minutes 30 seconds for a WebApiSkill); a long-running custom skill will cause the indexer to fail or time out. Option C is correct because enabling incremental enrichment (by setting the indexer's data source change detection and using a high-water mark) lets Azure AI Search skip documents whose content has not changed, avoiding unnecessary re-invocation of expensive custom skills and reducing cost and processing time. Option E is correct because the indexer can invoke skills concurrently across documents, so a custom skill must not depend on shared mutable state or on a specific call order; making it stateless and idempotent ensures consistent, repeatable enrichment results under parallel execution. Option A is not a primary design factor here because knowledge store projections are an output concern and do not fundamentally constrain the design of the custom-skill enrichment pipeline in the way timeout, incremental enrichment, and statelessness do. Option D is incorrect because semantic ranking is configured on the search index/query side (semantic configuration), not as a required element of the skillset, so it is not a factor in designing the custom-skill extraction pipeline.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
The number of knowledge store projections affects indexing speed
Why it's wrong here
Knowledge store projections write enriched output to storage; they do not govern how fast the indexer reads and enriches documents, so indexing speed is unaffected by their count. They are tempting because projections are a genuine design decision, and would be the right focus when planning storage shape and downstream analytics rather than throughput.
- ✓
The maximum execution time of the custom skill must fit within the indexer timeout
Why this is correct
Custom skills execute synchronously inside the indexer's enrichment pipeline, so a skill exceeding the indexer timeout aborts the run and leaves documents partially enriched. Sizing skill execution against that timeout is therefore a core design constraint for large document volumes.
- ✓
Incremental enrichment should be enabled to avoid reprocessing unchanged documents
Why this is correct
Incremental enrichment uses change detection to reprocess only documents whose content or skills have altered, avoiding full re-indexing of unchanged material. For large volumes this directly controls enrichment cost and indexer runtime, satisfying the efficiency constraint implied by the scenario.
- ✗
Semantic ranking configuration must be included in the skillset
Why it's wrong here
Semantic ranking is configured on the index as a semantic configuration and queried via semantic parameters; it is not declared inside a skillset, which only defines enrichment steps. It is tempting because semantic ranking is a real Azure AI Search feature, and would be the correct area to tune when improving relevance of query results.
- ✓
The custom skill should be stateless and idempotent to allow parallel execution
Why this is correct
Indexers invoke custom skills concurrently across documents, so a skill holding per-document state or producing different output on repeat calls causes inconsistent enrichment. Stateless, idempotent design guarantees identical results regardless of execution order or retries, enabling safe parallel execution.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-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 →
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.