Andrew Kane

Hi @Ngalstyan4, thanks for another PR! Will consider adding the array -> `sparsevec` casts in 0.8.0 (and give more feedback at that time). I'm hesitant to add a `sparsevec` ->...

Hi @Ngalstyan4, merged the array to `sparsevec` casts in the commit above (and plan to release with 0.8.0 - #677). I'd like to hold off on `sparsevec` -> `real[]` (still...

Hi @xfalcox, thanks for sharing! The data is really interesting. I've done some initial work for int8 vectors in the [intvec branch](https://github.com/pgvector/pgvector/compare/intvec), but want to focus on improving filtering before...

Hi all, just pushed an implementation of fp8 vectors (e4m3) to the [minivec branch](https://github.com/pgvector/pgvector/compare/minivec) for anyone who wants to try it (in a non-production environment). Edit: I think e3m4 may...

Here's a formula that works with the `main` branch (`brew install text-generation-inference --head`): ```ruby class TextGenerationInference < Formula include Language::Python::Virtualenv desc "Large Language Model Text Generation Inference" homepage "https://hf.co/docs/text-generation-inference" url...

It looks like you're running a different installation of TGI (`/opt/anaconda3/bin/text-generation-server` isn't the Homebrew install).

fwiw, I submitted 3.1.1 to Homebrew, but couldn't get it fully working: https://github.com/Homebrew/homebrew-core/pull/209731 Someone is welcome to resubmit if they can figure it out.

fwiw, the `scope` option was just fixed in #1712.

Hi @jeffblake and @maria-lau, thanks for the suggestions. Searchkick 6 will have two options to enable this: customizing the queue name (#1634) and the parent job class (#1478).

@pashkinelfe It'd be good to understand how this happens, since Postgres allocates [an extra 100K bytes](https://github.com/postgres/postgres/blob/master/src/backend/storage/ipc/ipci.c#L112) for small allocations. We could request the shared memory up front when the extension...