DP-800: Developing AI-Enabled Database Solutions

By Microsoft · Question Mode

QuestionQ6

Implement AI capabilities in database solutions

You have an Azure SQL database named SalesDB that includes a table named dbo.Articles. dbo.Articles holds two million articles with embeddings. The articles are updated frequently during the day.

You query the embeddings by using VECTOR_SEARCH.

Users report that semantic search results do not reflect updates until the next day.

You need to ensure the embeddings are updated whenever the articles change. The solution must minimize CPU usage on SalesDB.

Which embedding-maintenance method should you implement?

Explanation

Embeddings should be updated whenever the underlying data they represent changes. Change data capture records only inserted and updated article rows, allowing an Azure Functions app to process those changes asynchronously and regenerate only the affected embeddings. This avoids the CPU cost and write-path latency of invoking embedding generation in a table trigger and avoids repeatedly regenerating embeddings for all two million rows.

Learn more

Community Discussion

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