AI-103 Certification Practice Question #36

Question

You have a chat app in a Microsoft Foundry project and an Azure AI Search vectorized index.
You need to connect to the index to meet the following requirements:
Complex questions must retrieve information from multiple chunks.
Multi-turn conversations must influence retrieval planning.
Retrievals must run in parallel to reduce latency.
Which retrieval approach should you use?

Accepted Answer

The three requirements map one-to-one to agentic RAG as documented by Azure AI Search. Complex questions retrieving from multiple chunks → agentic retrieval decomposes a complex query into multiple focused subqueries for better coverage. Multi-turn conversations influencing retrieval planning → its context-aware query planner reads chat history so follow-ups retain context. Retrievals running in parallel to reduce latency → subqueries execute simultaneously rather than sequentially. Classic RAG uses a single sequential query and ignores conversation history; iterative retrieval refines queries in a sequential loop (not parallel); chain of thought is a model reasoning/prompting pattern, not a retrieval architecture. The Suggested Answer (B) and MS Learn agree, giving high confidence.

More AI-103 practice questions