Microsoft · DP-800
Search and vector data
DP-800 · Lesson 18 of 20 · 2:20:29
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Prepare for the DP-800 exam (Microsoft Certified: SQL AI Developer Associate). In this lesson: choosing between full-text, semantic vector, and hybrid search, full-text indexes and predicates, the vector data type and its size, and the vector functions VECTOR_DISTANCE, VECTOR_SEARCH, VECTOR_NORMALIZE, and VECTORPROPERTY. Includes three original practice questions.
Preview the topics
- Support agents search tickets for the exact phrase disk quota exceeded, and want only the tickets that contain it, sorted by relevance. What should they use?
- A table in Azure SQL Database will hold twelve million embeddings of 1,536 dimensions, and storage must shrink, with a small loss of precision accepted. What should the team choose?
- Embeddings from a model that does not normalize its output give inconsistent dot product rankings. What should the team apply before storing them?