Courseiva
Implement Generative AI And Agentic SolutionsmediumMultiple ChoiceObjective-mapped

AI-103 Implement Generative AI And Agentic Solutions Practice Question

You are designing a RAG solution using Azure AI Search and Azure OpenAI. Users report that when querying technical documentation, the system misses highly relevant paragraphs because the exact keywords do not match the user's conversational query. How should you configure Azure AI Search to improve retrieval accuracy?

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 semantic ranking on the Azure AI Search index and use hybrid search combining vector embeddings and keyword BM25.

Semantic ranking in Azure AI Search applies advanced machine learning models to understand the intent of the query and re-rank search results based on semantic relevance rather than pure keyword matching.

Answer analysis

Option-by-option breakdown

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

  • Switch the index analyzer to a standard whitespace analyzer to prevent stemming issues.

    Why it's wrong here

    A whitespace analyzer would make keyword matching even stricter, worsening the problem.

  • Enable semantic ranking on the Azure AI Search index and use hybrid search combining vector embeddings and keyword BM25.

    Why this is correct

    Hybrid search combined with semantic ranking bridges the gap between keyword mismatches and semantic meaning.

  • Increase the number of retrieved documents (top_k) from 3 to 20 without changing the query type.

    Why it's wrong here

    Retrieving 20 documents introduces noise and exceeds context window limits without addressing the underlying keyword mismatch.

  • Convert all documents to uppercase before indexing to ensure case-insensitive matching.

    Why it's wrong here

    Case sensitivity is already handled by default keyword tokenizers; this does not solve conceptual mismatches.

About these practice questions

One of 510 original AI-103 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 and reviewed by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

Last reviewed August 2026 · checked against the official Microsoft exam blueprint

This AI-103 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-103 exam.