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
I know that Milvus supports vector query and scalar filter which enables us to do ANN on a specific subset of dataset.
I'm just wondering how does Milvus support this feature on the architecture level?
As far as I know, we can do post filter (search for a bunch of nearest neighbor and filter out top K that satisfy the scalar filter). However this method seems not efficient. I failed to Google the answer/article that help me understand it.
Can anyone share some brief intro/articles that can help me get a little deeper understanding on this?
Many thanks!
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I know that Milvus supports vector query and scalar filter which enables us to do ANN on a specific subset of dataset.
I'm just wondering how does Milvus support this feature on the architecture level?
As far as I know, we can do post filter (search for a bunch of nearest neighbor and filter out top K that satisfy the scalar filter). However this method seems not efficient. I failed to Google the answer/article that help me understand it.
Can anyone share some brief intro/articles that can help me get a little deeper understanding on this?
Many thanks!
Beta Was this translation helpful? Give feedback.
All reactions