Question 370
A service wants indexed approximate semantic lookup rather than sorting a full table by scalar distance. Which implementation step most directly addresses this requirement?
Explanation
Correct Answer
VECTOR_SEARCH can use supported vector indexes for efficient similarity retrieval. Create the supported vector index and query using VECTOR_SEARCH with measured recall. Query plans/latency show indexed retrieval and recall thresholds pass.
Incorrect Answers
Indexed approximate search requires supported vector index/query mechanisms and plan verification.
ANN trades recall for resource performance; evaluate both with an exact or labeled baseline.
The model, dimension, metric, index and query must follow a coherent tested similarity contract. The appropriate case-specific action is: Create the supported vector index and query using VECTOR_SEARCH with measured recall.