Skip to main content
Vector search is approximate: it probes a subset of the index’s vector clusters rather than scanning every vector. Probing more clusters improves recall (i.e. how often the true nearest neighbors are returned) at the cost of higher latency. One session-level setting controls this tradeoff:
​
default:0.02
The recall/latency driver: a ceiling on how much probe work a query may spend, expressed as a fraction of each segment’s clusters. For instance, at the default value of 0.02, at most 2% of a segment’s cluster-scan work is spent. Must be between 0.000001 and 1.0, where 1.0 allows an exhaustive scan.Within the ceiling, clusters that provably cannot improve the current top-K are skipped automatically using per-cluster bounds stored in the index; this skipping never reduces recall, so raising the ceiling only ever improves it.
Recall also depends on the index’s training_sample_ratio and max_leaf_size, set at build time. See Index Options.

​
Quantization settings

Quantization settings in vector_fields take effect only during CREATE INDEX and REINDEX. Changing quantization with ALTER INDEX ... SET (vector_fields = ...) does not affect new or existing segments until REINDEX rebuilds the index.