Knowledge bases at scale: halfvec, a text index per collection, ef_search raised to the candidates wanted

A search asking for more than 10 passages got at most 40 candidates from
HNSW, pgvector's default ef_search. The full-text arm scored every chunk
holding a word of the question before limiting, over the whole
organization's GIN index; it now takes candidates by ts_rank from the
collection's own partial index and scores those. New collections index
halfvec on pgvector 0.7 and later (up to 4000 dimensions).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-10-08 22:08:29 +02:00
1 parent 42d3b7ea22
commit 9c675e7293
7 files changed
+223 -26

No files matched your search

+5
View File
@@ -45,6 +45,11 @@ is available to everyone who may use them.
A collection stays with the model it was made with: vectors from two
models cannot be compared.
With pgvector 0.7 or later a collection's index is kept at half
precision (`halfvec`), which halves its memory and takes models of up to
4000 dimensions; with an older pgvector the limit is 2000. A collection
keeps the kind it was made with.
## For administrators
### Make a collection