dima/supabase
1
0 Fork 0
mirror of https://github.com/supabase/supabase.git synced 2026-10-05 09:25:06 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update apps/www/_blog/2023-07-13-pgvector-performance.mdx

Browse Source
This commit is contained in:
egor authored and GitHub committed 2023-07-13 16:12:52 +03:00
1 parent 6614644d7a
commit 574b0f35f2
1 file changed
+1 -1
Download Patch File Download Diff File Expand all files Collapse all files
apps/www/_blog/2023-07-13-pgvector-performance.mdx
+1 -1
View File
@@ -198,7 +198,7 @@ Another way to improve performance without throwing more compute would be to inc
We ran a test to measure the impact of list size: we uploaded 90,000 vectors from the Wikipedia dataset and then queried 10,000 vectors from the same dataset. The documentation recommends to use `lists` constant of `number of vectors / 1000`. In this case, it would be 90.
But as our experiment shows, we can improve `select` speed if we increase lists (i.e. with more lists in the index we need to get less index data to get the same precision). So for 95% precision, we can take any of:
But as our experiment shows, we can improve RPS if we increase `lists` (i.e. with more lists in the index we need to get less index data to get the same precision). So for 95% precision, we can take any of:
- 3% of index data = 270 lists
- 6% of index data = 90 lists