Microsoft · DP-800
Vector and hybrid search
DP-800 · Lesson 19 of 20 · 2:27:11
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: exact and approximate search, vector indexes and VECTOR_SEARCH with the latest syntax, hybrid search with reciprocal rank fusion, and measuring search quality and performance. Includes three original practice questions.
Preview the topics
- A team created a vector index with the cosine metric, but its VECTOR_SEARCH queries ask for the euclidean metric, and they run slowly, with a warning. What is wrong?
- Product P ranks second in full-text search and fourth in vector search, while product Q ranks first in vector search only. With RRF and k = 60, which one ranks higher?
- A team moved from exact search to a vector index, and wants to know whether the results got worse. What should it measure?