AI-102 Practice Question: Implement knowledge mining and information extraction solutions
Your knowledge mining solution uses Azure AI Search. Users complain that search results are not relevant. You have enabled semantic search but results still lack context. What should you do to improve relevance?
⚠ Common exam trap
It's easy for candidates to assume enabling the semantic search feature alone is sufficient, but Azure AI Search requires an explicit semantic configuration to map the fields that the semantic model will use for reranking.
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
✓
Ensure the index includes a semantic configuration with title and content fields
Semantic search in Azure AI Search requires a semantic configuration that explicitly maps the title and content fields to be used for semantic ranking. Without this configuration, the search engine cannot apply the deep neural network models that understand context and intent, so results remain based on keyword matching even when the semantic search feature is enabled.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Ensure the index includes a semantic configuration with title and content fields
Why this is correct
Semantic search ranks results using a semantic configuration that designates title and content fields for caption and answer generation. Without that configuration, semantic ranking cannot use the fields, so relevance and contextual captions remain poor.
- ✗
Increase the number of partitions to handle more data
Why it's wrong here
Partitions increase index storage and write throughput across shards; they do not change how documents are scored or add semantic understanding. Tempting because scaling the index sounds beneficial, but partitions would be correct when index size or ingestion volume exceeds capacity, not for relevance problems.
- ✗
Configure a scoring profile with boosting based on metadata
Why it's wrong here
Scoring profiles boost or filter by document metadata fields; they cannot inject semantic context into queries or re-rank results by meaning. Tempting because boosting tunes relevance, but it would be correct when metadata reliably signals importance, not when semantic search already runs and results still lack contextual understanding.
- ✗
Increase the number of replicas to improve query performance
Why it's wrong here
Replicas add query throughput and availability for concurrent searches; they do not alter ranking or add semantic context. Tempting because scaling sounds like a relevance fix, but replicas would be correct for handling higher query volumes or load balancing, not for improving result relevance.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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.