I just listened to <@U01NZ4D0LDD> on The Changelog...
# community-helpe
em1nos
09/11/2022, 8:01 AMI just listened to @Jason Bosco on The Changelog podcast.
Could you tell us a bit more about Vector Search? Sounds amazing!
How does it work?
What can we expect to be able to do, that we can't do right now with Typesense?
Is the RC publicly available?
I'm guessing the release of Vector Search is a few versions away? We should not expect it soon?
k
Kishore Nallan
09/11/2022, 10:11 AM👋 @em1nos
We've a RC build available already where you can try it out:
typesense/typesense:0.24.0.rcn12What can we expect to be able to do, that we can't do right now with Typesense?It allows you to do things like recommendations by building an embedding (which are vectors) which can be indexed into Typesense and searched using a vector query for fetching recommended items. Still need to work on the docs that show how you can build a model that produces vector embeddings etc. if you aren't familiar with that.
e
em1nos
09/11/2022, 10:15 AMThat's so interesting, but way over my head for now! I hope you guys can make this easy to work with.
k
Kishore Nallan
09/11/2022, 10:16 AMThat's the goal. We are just starting with the foundational stuff. Do you have any use cases in mind?
e
em1nos
09/11/2022, 10:19 AMWell, I'm actually using Typesense as part of a "find product matches" pipeline where I'm trying to find matching products within two datasets. I'm not sure if vector search can be of any use in that application.
em1nos
09/11/2022, 10:19 AMI'm running a product/price comparison website, so I'm sure vector search will be of use in some way somewhere in the application.
k
Kishore Nallan
09/11/2022, 10:20 AMVector search works for recommendations and personalization.
e
em1nos
09/11/2022, 10:22 AMOK. I see. Maybe I got it wrong then what vector search actually is 🙂 I was thinking AI/ML stuff "more in general", and that it could be useful even outside of recommendations and personalization.
em1nos
09/11/2022, 2:04 PMI guess vector search IS useful in many different contexts. We just need to understand it to really be able to make use of it.
For anyone interested in reading more about vector search:
https://www.infoworld.com/article/3634357/what-is-vector-search-better-search-through-ai.html
Or just google it, I guess.
em1nos
09/11/2022, 2:04 PMMy use case would be "deduplication" which is mentioned in that article.
a
Andrew Sittermann
09/12/2022, 5:03 PMHey @Kishore Nallan this sounds mega awesome. Will it work in foreign languages, in our case German?
Andrew Sittermann
09/12/2022, 5:03 PMWe have been thinking how to find similar court judgements
k
Kishore Nallan
09/13/2022, 5:46 AMWhat we are beginning with is the ability to index vectors and then do nearest neighbor search on them. So you still need to use a machine learning toolkit to convert the judgements into vectors instead of text but once you do that you can find similar court judgments by doing a nearest neighbor vector search.
a
Andrew Sittermann
09/13/2022, 6:23 PMGot it. Thanks @Kishore Nallan