AI-300: Operationalizing Machine Learning and Generative AI SolutionsDemo

By Microsoft · Question Mode

QuestionQ25

Optimize generative AI systems and model performance

You administer a Retrieval-Augmented Generation (RAG) system that uses Azure AI Search to retrieve documents from an indexed knowledge base.

The system must support these retrieval requirements:

  • Queries containing exact policy identifiers must return the matching documents even when semantic similarity is low.
  • Natural-language questions must prioritize semantically relevant documents even when keywords are not exact matches.

Configure the retrieval approach to meet these requirements.

Select
Exact identifier matching
Natural-language relevance
Explanation

Keyword-based retrieval uses lexical full-text matching, which provides the precision needed for exact identifiers. Vector search retrieves conceptually similar content, while semantic ranking reranks those results to place the most semantically relevant natural-language matches first.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!