You signed in with another tab or window.Reload to refresh your session.You signed out in another tab or window.Reload to refresh your session.You switched accounts on another tab or window.Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+2-2Lines changed: 2 additions & 2 deletions
Original file line number
Diff line number
Diff line change
@@ -937,7 +937,7 @@ ALTER TABLE items ALTER COLUMN embedding SET STORAGE PLAIN;
937
937
938
938
####Why are there less results for a query after adding an HNSW index?
939
939
940
-
Results are limited by the size of the dynamic candidate list (`hnsw.ef_search`). There may be even less results due to dead tuples or filtering conditions in the query.We recommend setting`hnsw.ef_search` to at least twice the`LIMIT` of the query. If you need more than 500 results, use an IVFFlat index instead.
940
+
Results are limited by the size of the dynamic candidate list (`hnsw.ef_search`), which is 40 by default. There may be even less results due to dead tuples or filtering conditions in the query.Enabling[iterative index scans](#iterative-index-scans) can help address this.
941
941
942
942
Also, note that`NULL` vectors are not indexed (as well as zero vectors for cosine distance).
943
943
@@ -949,7 +949,7 @@ The index was likely created with too little data for the number of lists. Drop
949
949
DROPINDEX index_name;
950
950
```
951
951
952
-
Results can also be limited by the number of probes (`ivfflat.probes`).
952
+
Results can also be limited by the number of probes (`ivfflat.probes`). Enabling[iterative index scans](#iterative-index-scans) can address this.
953
953
954
954
Also, note that`NULL` vectors are not indexed (as well as zero vectors for cosine distance).