Why do you intend to migrate from Qdrant? Is there a specific thing you are unhappy with? Or is there a missing feature that would persuade you to stay?
I’m loving the attention here :) — no, the thing I’d be hoping to gain is tighter integration with the rest of my data. For most of my data, I can use transactions, constraints, foreign keys, etc. But for Qdrant, it’s an external system where I have to build that stuff in myself. TL;DR the usual arguments against NoSQL or eventual consistent systems.
That’s interesting! So I suppose the rest of your data is in Postgres? How would you like to integrate it further?
I’m asking because I’m currently prototyping a Postgres extension for Qdrant. It’s just a proof of concept at the moment, but I think it might be valuable to get to know the requirements actual users have.
But learning Nix is a skill that can obsolesce most other build systems, containers, etc. and is a skill probably worth learning if that interests you.
Ah this is great. I’ll migrate to this when it gets more stable.
btw: the
mltag is for the ML-family of programming languages, like OCaml, StandardML, etc.Thanks! Will you need filter feature like https://qdrant.tech/articles/filtrable-hnsw/?
Yes
We have a blog to illustrate the filtering feature: https://modelz.ai/blog/pgvecto-rs-condition-filtering
Gotcha. Are you using qdrant, pinecone, or something else?
qdrant
Hi, Qdrant DevRel employee here.
Why do you intend to migrate from Qdrant? Is there a specific thing you are unhappy with? Or is there a missing feature that would persuade you to stay?
I’m loving the attention here :) — no, the thing I’d be hoping to gain is tighter integration with the rest of my data. For most of my data, I can use transactions, constraints, foreign keys, etc. But for Qdrant, it’s an external system where I have to build that stuff in myself. TL;DR the usual arguments against NoSQL or eventual consistent systems.
Yeah, I think in some cases you just do not need a specialized vector db. We have a blog post for it: https://modelz.ai/blog/pgvector .
PS: I also like the qdrant project.
That’s interesting! So I suppose the rest of your data is in Postgres? How would you like to integrate it further?
I’m asking because I’m currently prototyping a Postgres extension for Qdrant. It’s just a proof of concept at the moment, but I think it might be valuable to get to know the requirements actual users have.
Hi, we already implemented the pre-filter in pgvecto.rs. We will release it and write a blog post for it. Will let you know!
https://github.com/tensorchord/pgvecto.rs/commit/4ba136052cc9420528bc5fa463570113f0f181e5
I’m just using shell.nix. A nice explanation of the benefits over shell.nix/nix-shell would be welcome.
The benefit to me is that there is no need to learn nix :-) /cc @lagoja
But learning Nix is a skill that can obsolesce most other build systems, containers, etc. and is a skill probably worth learning if that interests you.
You should also learn how to darn socks, and make your own toothpaste. Two skills you can use until you die of old age.
Yeah, I agree. It is worth learning for me. But maybe not for everyone. It is why I like devbox.
I think this is the write-up where the author explains how he developed it: https://debugged.it/blog/ssh-direct-to-docker/
Have not read it yet, but looks interesting, because I was curious how you implement a SSH-server replacement.
golang’s ssh package supports that. It is easy to implement a new sshd alternative.
Here is a tiny implementation https://github.com/ContainerSSH/MiniContainerSSH
It’s a super barebones implementation of ContainerSSH to demonstrate how it works