From 14355b9312de9632a5a2b7bc6292581156a31f56 Mon Sep 17 00:00:00 2001 From: Andrew Kane Date: Fri, 31 Mar 2023 21:46:38 -0700 Subject: [PATCH] Updated readme [skip ci] --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index c682cdf..5678e08 100644 --- a/README.md +++ b/README.md @@ -113,7 +113,9 @@ SELECT category_id, AVG(embedding) FROM items GROUP BY category_id; ## Indexing -By default, pgvector performs exact nearest neighbor search, which provides perfect recall. If this is too slow for your application, you can add an index to use approximate nearest neighbor search. Unlike typical indexes which only affect performance, you will see different results (lower recall) for queries after adding an approximate index. +By default, pgvector performs exact nearest neighbor search, which provides perfect recall. + +You can add an index to use approximate nearest neighbor search, which trades some recall for performance. *Unlike typical indexes, you will see different results for queries after adding an approximate index.* Two keys to achieving good recall are: