A documentation portal stores articles in Azure SQL Database. Users frequently search for exact error codes like 'ERROR 404' and 'SQLSTATE 42000'. The search must return articles containing these exact strings, not just semantically related content. The team also wants to rank articles by how many times the error code appears. What should they implement?

Create a full-text index and use FREETEXT to search for the error code as a natural language phrase.

Use LIKE '%ERROR 404%' queries and order by LEN(article_text) to rank longer articles first.

Enable full-text search and use CONTAINS with the exact error code as a quoted phrase, then order by the rank from CONTAINSTABLE.

Use VECTOR_SEARCH with embeddings of the error codes to find articles with similar codes.

Which component is essential for implementing semantic vector search in a database solution?

An embedding model that converts text into numerical vectors

What is the primary purpose of semantic vector search in intelligent search solutions?

To replace all relational queries in a database

To perform fast exact matches on large text columns

To find items based on the meaning and context of the query rather than exact keyword matches

To compress data to reduce storage costs

A team is designing a vector table for 5 million product images. Each image is embedded into a 1536-dimensional vector. They need to store the vectors efficiently and support fast similarity search. Which column definition and index strategy should they use?

NVARCHAR(MAX) column with a full-text index.

VARBINARY(8000) column with a nonclustered index.

VECTOR(1536) column with an ANN index.

FLOAT array column with a clustered columnstore index.

Microsoft Certified:SQL AI Developer Associate

Domain 3Objective 2

Design and Implement Intelligent Search DP-800 Practice Questions (Page 5)

Part of the Implement AI capabilities in database solutions domain, which accounts for 25–30% of the DP-800 exam. Microsoft does not publish an official question count, but from its 120-minute exam (~50–80 total, ~13–24 in this domain), expect 4–8 from this objective — we provide 47 practice questions to prepare you well beyond it. (estimate)

47questions here

10free pages

10concepts

25–30%of the exam

Questions 21–25

21application · medium
A documentation portal stores articles in Azure SQL Database. Users frequently search for exact error codes like 'ERROR 404' and 'SQLSTATE 42000'. The search must return articles containing these exact strings, not just semantically related content. The team also wants to rank articles by how many times the error code appears. What should they implement?
Select an answer first
22foundation · easy
Which component is essential for implementing semantic vector search in a database solution?
Select an answer first
23foundation · easy
What is the primary purpose of semantic vector search in intelligent search solutions?
Select an answer first
24application · medium
A team is designing a vector table for 5 million product images. Each image is embedded into a 1536-dimensional vector. They need to store the vectors efficiently and support fast similarity search. Which column definition and index strategy should they use?
Select an answer first
25foundation · easy
Which distance metric is commonly used with vector indexes to measure similarity?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to DP-800

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Microsoft. “DP-800” is a trademark of its owner, used for identification only.

Design and Implement Intelligent Search DP-800 Practice Questions (Page 5)

Questions 21–25

Which component is essential for implementing semantic vector search in a database solution?

What is the primary purpose of semantic vector search in intelligent search solutions?

A team is designing a vector table for 5 million product images. Each image is embedded into a 1536-dimensional vector. They need to store the vectors efficiently and support fast similarity search. Which column definition and index strategy should they use?

Which distance metric is commonly used with vector indexes to measure similarity?

Keep studying — Implement AI capabilities in database solutions