You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@kvrocks.apache.org by "adulau (via GitHub)" <gi...@apache.org> on 2025/03/28 13:57:26 UTC

[D] efficient similarity search in kvrocks and faiss library [kvrocks]

GitHub user adulau created a discussion: efficient similarity search in kvrocks and faiss library

Something we were wondering: is there any ongoing work on supporting efficient storage in **Kvrocks** for [Faiss](https://faiss.ai/)?

I remember some earlier work on Redis called [Redis Vector Similarity Search](https://artefactory.github.io/redis-team-THM/redis-vss.html), but I'm not sure about its current state.

Would it be completely crazy to store dense vectors in **Kvrocks** and perform similarity search directly through Kvrocks?



GitHub link: https://github.com/apache/kvrocks/discussions/2856

----
This is an automatically sent email for issues@kvrocks.apache.org.
To unsubscribe, please send an email to: issues-unsubscribe@kvrocks.apache.org

Re: [D] efficient similarity search in kvrocks and faiss library [kvrocks]

Posted by "git-hulk (via GitHub)" <gi...@apache.org>.

GitHub user git-hulk edited a comment on the discussion: efficient similarity search in kvrocks and faiss library

Hi @adulau, Kvrocks Search has been released since [2.11.0](https://github.com/apache/kvrocks/releases/tag/v2.11.0), you could give it a shot.

GitHub link: https://github.com/apache/kvrocks/discussions/2856#discussioncomment-12653590

----
This is an automatically sent email for issues@kvrocks.apache.org.
To unsubscribe, please send an email to: issues-unsubscribe@kvrocks.apache.org

Re: [D] efficient similarity search in kvrocks and faiss library [kvrocks]

Posted by "git-hulk (via GitHub)" <gi...@apache.org>.

GitHub user git-hulk added a comment to the discussion: efficient similarity search in kvrocks and faiss library

Hi @adulau, Kvrocks Search has been released since [2.11.0](https://github.com/apache/kvrocks/releases/tag/v2.11.0), you could give it shot.

GitHub link: https://github.com/apache/kvrocks/discussions/2856#discussioncomment-12653590

----
This is an automatically sent email for issues@kvrocks.apache.org.
To unsubscribe, please send an email to: issues-unsubscribe@kvrocks.apache.org

Re: [D] efficient similarity search in kvrocks and faiss library [kvrocks]

Posted by "adulau (via GitHub)" <gi...@apache.org>.

GitHub user adulau added a comment to the discussion: efficient similarity search in kvrocks and faiss library

Indeed good point. I don't know how I managed to miss it ;-) 

GitHub link: https://github.com/apache/kvrocks/discussions/2856#discussioncomment-12671661

----
This is an automatically sent email for issues@kvrocks.apache.org.
To unsubscribe, please send an email to: issues-unsubscribe@kvrocks.apache.org

Re: [D] efficient similarity search in kvrocks and faiss library [kvrocks]

Posted by "PragmaTwice (via GitHub)" <gi...@apache.org>.

GitHub user PragmaTwice added a comment to the discussion: efficient similarity search in kvrocks and faiss library

Yeah we have released Kvrocks Search with vector similarity search via HNSW algorithm in 2.11. But note that, it is still quite experimental thus you will probably face some issues. Feel free to try and open issues to us if you encounter problems.

GitHub link: https://github.com/apache/kvrocks/discussions/2856#discussioncomment-12671785

----
This is an automatically sent email for issues@kvrocks.apache.org.
To unsubscribe, please send an email to: issues-unsubscribe@kvrocks.apache.org

Re: [D] efficient similarity search in kvrocks and faiss library [kvrocks]

Posted by "mapleFU (via GitHub)" <gi...@apache.org>.

GitHub user mapleFU added a comment to the discussion: efficient similarity search in kvrocks and faiss library

Recently, rocksdb has add FAISS IVF support, https://github.com/facebook/rocksdb/pull/13258 , maybe this can be also used, or just following the "Search" module

GitHub link: https://github.com/apache/kvrocks/discussions/2856#discussioncomment-12654451

----
This is an automatically sent email for issues@kvrocks.apache.org.
To unsubscribe, please send an email to: issues-unsubscribe@kvrocks.apache.org