AI-103: Developing AI Apps and Agents on AzureDemo

By Microsoft · Question Mode

QuestionQ82

Implement generative AI and agentic solutions

You have a Microsoft Foundry agent that grounds its responses using an Azure Search index. The index includes:

  • Searchable text fields for product names and product codes
  • A vector field that stores embeddings for product descriptions

You need to ensure that users can query the index using:

  • Exact product names or codes
  • Natural language descriptions of the products

What should you configure?

  • A vector search only
  • B hybrid search
  • C keyword search only
  • D semantic search only
Explanation

Hybrid search in Azure AI Search combines traditional full-text (keyword) search with vector search in a single query request. This allows exact-match queries against text fields (such as product names and codes) to be resolved via keyword search, while natural language queries are resolved via vector similarity search against the embeddings field, with results merged and ranked together. Using only vector search would degrade exact-match retrieval of names/codes, and using only keyword or semantic search would not leverage the vector embeddings for natural language description matching.

Learn more

Community Discussion

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