DP-800: Developing AI-Enabled Database Solutions

By Microsoft · Question Mode

QuestionQ54

VerifiedImplement AI capabilities in database solutions

You have an Azure SQL database with a table named stores. The stores table has a description column and an embedding vector column.

You need to implement a hybrid search query that:

  • Uses full-text search on description for the keyword portion.
  • Returns the top 20 results using a combined score weighted as 60% vector distance and 40% full-text rank.

How should you configure the query components?

Select
Semantic query operator/function:
Keyword retrieval operator/function:
Final ranking expression:
Explanation

VECTOR_DISTANCE produces a distance where smaller values are nearer, so sorting the combined score ascending favors closer vectors. CONTAINSTABLE performs full-text matching and returns a RANK value. Because full-text rank increases for better matches (0 through 1000), 1.0 - RANK/1000.0 converts it into a lower-is-better distance-like score before applying the 40% weight; vector distance receives the remaining 60%.

Learn more

Community Discussion

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