Updated readme [skip ci]

This commit is contained in:
Andrew Kane
2023-03-31 21:31:38 -07:00
parent f3df137db6
commit f534d9878a

View File

@@ -118,7 +118,7 @@ By default, pgvector performs exact nearest neighbor search, which provides perf
Two important things to achieve good recall are:
1. Create the index *after* the table has some data
2. Choose an appropriate value for lists (lower is better for recall, higher is better for speed)
2. Choose an appropriate number of lists (lower is better for recall, higher is better for speed)
A good place to start is: