Microsoft Certified SQL AI Developer Associate certification (DP-800) - Microsoft Exam Questions

You have a Microsoft SQL Server 2025 instance that contains a database named SalesDB SalesDB supports a Retrieval Augmented Generation (RAG) pattern for internal support tickets. The SQL Server instance runs without any outbound network connectivity. You plan to generate embeddings inside the SQL Server instance and store them in a table for vector similarity queries. You need to ensure that only a database user account named AlApplicationUser can run embedding generation by using the model.

Which two actions should you perform? Each correct answer presents part of the solution.

NOTE: Each correct selection is worth one point.

You need to design a generative Al solution that uses a Microsoft SOL Server 2025 database named

DB1 as a data source. The solution must generate responses that meet the following requirements:

• Ait' grounded In the latest transactional and reference data stored in D61

• Do NOT require retraining or fine-tuning the language model when the data changes

• Can include citations or references to the source data used in the response

Which scenario is the best use case for implementing a Retrieval Augmented Generation (RAG) pattern? More than one answer choice may achieve the goal. Select the BEST answer

You have an Azure SQL database that contains tables named dbo.ProduetDocs and dbo.ProductuocsEnbeddings. dbo.ProductOocs contains product documentation and the following columns:

• Docld (int)

• Title (nvdrchdr(200))

• Body (nvarthar(max))

• LastHodified (datetime2)
The documentation is edited throughout the day. dbo.ProductDocsEabeddings contains the following columns:

• Dotid (int)

• ChunkOrder (int)

• ChunkText (nvarchar(aax))

• Embedding (vector(1536))
The current embedding pipeline runs once per night Vou need to ensure that embeddings are updated every time the underlying documentation content changes The solution must NOT 'equire a nightly batch process.

What should you include in the solution?

Your team is developing an Azure SQL dataset solution from a locally cloned GitHub repository by using Microsoft Visual Studio Code and GitHub Copilot Chat. You need to disable the GitHub Copilot repository-level instructions for yourself without affecting other users.

What should you do?

You need to recommend a solution to lesolve the slow dashboard query issue. What should you recommend?