Well you can always move to tiger cloud if you want it managed :)
And this is PostgreSQL licensed just like our pg_textsearch which has been adopted to Googles AlloyDB and microsofts HorizonDB already, so there is hope!
I'm currently running VectorChord and I love it - with a fast backing disk, it's cut my postgres cost in half. Excited to see competition in low-RAM vector index tools. RAMageddon seems to be creating incentives to find more ways to take advantage of how fast modern nvme drives are!
> TLDR: We are launching pg_vectorsearch, a new open-source PostgreSQL extension that makes vector search dramatically faster and more cost-efficient. Its new PRISM index uses partitioning and compression instead of HNSW's graph-based approach, delivering faster queries with a fraction of the memory and significantly faster index builds. At 100 million vectors, PRISM achieved 6 ms query latency on a machine with 4× less memory than HNSW, with index builds over 20× faster.
There are zero hits for 'blog' on the README and zero hits for the file name 'benchmark'. It's not a me problem; I put in reasonable effort. I am not going to scour the README one link at a time.
It’s there. Titled “Announcing pg_vectorsearch: Scalable Open-Source Vector Search in PostgreSQL”. In paragraph: “ The result: an index that is significantly faster”
Dark side of the PRISM! The image on the repo 100% inspired by Dark Side of The Moon by Pink Floyd.
Sadly if cloud providers don't offer it on managed postgres then not many people can use it...
Well you can always move to tiger cloud if you want it managed :) And this is PostgreSQL licensed just like our pg_textsearch which has been adopted to Googles AlloyDB and microsofts HorizonDB already, so there is hope!
I'm currently running VectorChord and I love it - with a fast backing disk, it's cut my postgres cost in half. Excited to see competition in low-RAM vector index tools. RAMageddon seems to be creating incentives to find more ways to take advantage of how fast modern nvme drives are!
I am the main contributor of pg_vectorsearch. If you try both, let us know about your experience and how we can improve.
Does it support filtering though?
Edit: post filtering only
I don't understand how people are efficiently implementing tenant/user/permission scopes with these indexes.
Checks notes, one dayabase per client, per user, per project ... etc
Multi-column indexes for multi-tenant tables is planned for a future release.
LanceDB supports push down and list/array membership through DataFusion.
from the accompanying blog post: https://www.tigerdata.com/blog/announcing-pg_vectorsearch-sc...
> TLDR: We are launching pg_vectorsearch, a new open-source PostgreSQL extension that makes vector search dramatically faster and more cost-efficient. Its new PRISM index uses partitioning and compression instead of HNSW's graph-based approach, delivering faster queries with a fraction of the memory and significantly faster index builds. At 100 million vectors, PRISM achieved 6 ms query latency on a machine with 4× less memory than HNSW, with index builds over 20× faster.
Btw, I do work for Tiger Data/timescale, but am not at all associated with this team. I just found this release really exciting.
I sent the thread to Erik (the main contributor) though, so if you have feedback or questions, good chance that he'll see it.
Shouldn't you lead with your benchmarks if you're fast? qps and precision/recall, please.
benchmarks are in the blog post and the benchmarking suite is also open sourced alongside it.
There are zero hits for 'blog' on the README and zero hits for the file name 'benchmark'. It's not a me problem; I put in reasonable effort. I am not going to scour the README one link at a time.
There's a link in the README, but it is not named blog.
Here's the link to the numbers for your convenience:
https://www.tigerdata.com/blog/announcing-pg_vectorsearch-sc...
It’s there. Titled “Announcing pg_vectorsearch: Scalable Open-Source Vector Search in PostgreSQL”. In paragraph: “ The result: an index that is significantly faster”
https://news.ycombinator.com/item?id=50086249