AI-102 Implement an agentic solution Practice Question
You are designing an agent that uses Azure AI Search as a knowledge store. The agent must handle multiple languages. Which feature should you configure in Azure AI Search to ensure the agent retrieves relevant results for queries in different languages?
⚠ Common exam trap
It's easy for candidates to confuse semantic search (which improves relevance via AI) with language-specific text processing, assuming semantic search alone can handle multilingual queries, but semantic search still relies on the underlying analyzer for tokenization and cannot perform language-specific stemming or stop word removal.
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
✓
Language analyzers
Language analyzers in Azure AI Search are specifically designed to handle linguistic variations across different languages, such as stemming, stop word removal, and tokenization rules. By configuring the appropriate language analyzer (e.g., 'en.microsoft' for English or 'fr.microsoft' for French) on a searchable field, the agent can retrieve relevant results for queries in multiple languages because the analyzer processes both the indexed content and the query string using the same language-specific rules.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Scoring profiles
Why it's wrong here
Scoring profiles boost relevance by weighting fields or functions, but they do not translate or analyse query text across languages. Language-specific retrieval requires a language analyser on the field, which tokenises and stems each language correctly. Scoring profiles suit ranking tuning within a single language, such as promoting recent documents.
- ✓
Language analyzers
Why this is correct
Language analyzers apply language-specific tokenisation, stemming and stop-word rules per field, so indexed content and queries in each language are processed consistently. This lexical matching satisfies the stem's requirement that the agent retrieve relevant results across multiple languages.
- ✗
Semantic search
Why it's wrong here
Semantic search reranks results using language models but does not translate queries, so cross-language retrieval still fails unless the index holds matching-language content. It is correct when improving relevance ranking of natural-language queries within one language.
- ✗
Synonym maps
Why it's wrong here
Synonym maps expand equivalent terms within one language and do not translate queries, so a French query will not match English documents. They are correct when users employ varied jargon or abbreviations for the same concept in a single-language index.
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.