pgvector.git / summary / log / commit / refs

commit    55aeba8bd6a024c841e9b1d531ec3f3a93c4ae04
Author:   Andrew Kane <andrew@ankane.org>
Date:     Sat Apr 01 05:12:35 2023 +0000

    Added lists to example [skip ci]


README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 246a632c..6cddf897 100644 --- a/README.md +++ b/README.md @@ -196,7 +196,7 @@ SELECT * FROM items WHERE category_id = 123 ORDER BY embedding <-> '[3,1,2]' LIM can be indexed with: ```sql -CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WHERE (category_id = 123); +CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 100) WHERE (category_id = 123); ``` To index many different values of `category_id`, consider [partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html) on `category_id`. [parent: aebe1bae029f]