DP-800: Developing AI-Enabled Database Solutions

Question

You have an Azure SQL database containing tables named dbo.ProductDocs and dbo.ProductDocsEmbeddings. dbo.ProductDocs stores product documentation and has these columns:

DocID (int)
Title (nvarchar(200))
Body (nvarchar(max))
LastModified (datetime2)

The documentation is edited throughout the day.

dbo.ProductDocsEmbeddings has the following columns:

DocID (int)
ChunkOrder (int)
ChunkText (nvarchar(max))
Embedding (vector(1536))

The current embedding pipeline runs once each night.

You need to ensure embeddings are updated whenever the underlying documentation content changes. The solution must not require a nightly batch process.

What should you include in the solution?

Explanation

Azure SQL change tracking records committed DML changes for enabled tables and lets an application retrieve the rows that changed and then read their current values. An incremental embedding process can use those changes to regenerate the affected chunks and vectors as documentation is edited, rather than relying on a nightly batch. Microsoft Learn describes change tracking as a lightweight mechanism for identifying changed rows and obtaining their latest data from the tracked table.

Learn more

DP-800: Developing AI-Enabled Database Solutions

AstroTutor

Notes

Readiness

QuestionQ58

Community Discussion