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
+1Lines changed: 1 addition & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -7,6 +7,7 @@ This Plugin allows you to score Elasticsearch documents based on embedding-vecto
7
7
give it a try.
8
8
* I gained this substantial speed improvement by using the lucene index directly
9
9
* I developed it for my workplace which needs to pick KNN from a set of ~4M vectors. our current ES setup is able to answer this in ~80ms
10
+
***Note: Elasticsearch introduced a similar vector similarity functions in version 7.4 and above. [Elasticsearch version 8.0] (https://www.elastic.co/blog/introducing-approximate-nearest-neighbor-search-in-elasticsearch-8-0) includes native ANN support. This makes this plug-in obsolete for new Elasticsearch versions, unless for some reason their implementation is slower than this plugin**.
0 commit comments