A vector database insert may succeed before the document is searchable
In a RAG app, a can accept a saved item before that item is ready for search. A user may upload a PDF, see a ready message, and then ask a question that cannot find anything from the new file.
A change can also be accepted while old results remain reachable for a short time. This makes simple write latency a weak measure for real app behavior.
A better test checks whether the database request was accepted, whether the new vector can be searched, whether work correctly, whether recall has settled, and how much the full path costs in the cloud. VDBBench was used to measure these stages separately: accepted, searchable, fully indexed, and cost.
Key points
- A successful insert does not always mean a document is searchable right away.
- A newly uploaded PDF may be missing from the very next answer.
- updates can briefly leave old results available.
- should measure search readiness and cost, not only write latency.
- VDBBench separates accepted, searchable, fully indexed, and cost stages.