BenchmarkDT-2026-0176
Metadata filters cost more than expected at scale
Pre-filtering and post-filtering behave very differently once the corpus passes a hundred million vectors.
6 minBig Data & Vector DBs
Selective filters that eliminate most of the corpus can turn an approximate index into something close to a scan, depending on how the engine applies them.
The behaviour is documented unevenly across vendors. Measure it on your own selectivity distribution before committing to a partitioning scheme.