Databricks · Databricks Generative AI Engineer Associate
AI Search (Vector Search)
Databricks Generative AI Engineer Associate · Lesson 11 of 17 · 1:21:26
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 Databricks Certified Generative AI Engineer Associate exam. In this lesson: AI Search, formerly Vector Search: indexes and endpoints governed by Unity Catalog, Delta Sync and Direct Vector Access indexes, triggered and continuous sync, standard and storage-optimized endpoints, and querying the index with num_results, filters, and hybrid search. Includes three original practice questions.
Preview the topics
- Copperline’s manuals change once a week, after the product team publishes its updates. The team wants the index to follow them, at the lowest cost. Which setup fits?
- Copperline will index two billion chunks of past support tickets. A quarter of a second per query is fine, and the index is synced once a night. Which endpoint type fits?
- Customers often type exact part numbers, such as EP-402, and a search on vectors alone often misses the chunk that names that part. Which query option helps most?