Câu 18: AI-200: Developing AI Cloud Solutions on Azure

An application performs similarity search across 5 million embeddings stored in Azure Database for PostgreSQL with pgvector. Queries often filter by department before ranking by cosine distance.P95 latency for vector similarity queries exceeds the SLA target. Monitoring shows sustained high CPU use during query execution. You need to reduce P95 latency for filtered vector similarity queries. What should you do?

1. A. Create B-tree indexes on frequently filtered metadata columns. — đáp án hiện tại
2. B. Store embeddings as JSON.
3. C. Increase embedding dimensionality.
4. D. Increase statement timeout.