PRODUCTION SCENARIO
A Generative AI Engineer must index 900 million 768-dimension vectors. The source table changes once per night, and the product owner has accepted up to 250 ms of added query latency in exchange for lower cost.
Which Vector Search configuration fits these requirements?
Answering here is anonymous. Nothing is saved unless you sign in.
Show answer and explanation
Answer: A storage-optimized endpoint with a Delta Sync index in Triggered mode
Storage-optimized endpoints support over one billion vectors at dimension 768 with roughly 250 ms of added latency, well past the capacity a standard endpoint serves. A nightly refresh needs only a Triggered sync, so the streaming cost of Continuous mode buys nothing here.
Official Source: https://docs.databricks.com/aws/en/vector-search/vector-search ↗