Dve - an embeddings and vector search library for Apple devices

Hi Ziggit!
Introducing the dve vector engine(aka dve). dve is a library for creating and searching vector embeddings locally on Apple devices.

This last year I was working on an app for Macs which required doing vector search. The local AI/ML libraries for Apple devices are lacking, which means the only real option is to use an API. I didn’t want to do that, so I started working on my own library. What I’m calling a “vector engine” is really just a combination of an in-memory vector database and a local embedding model runtime.

A couple weeks ago, I decided to split off my vector engine from the app which was using it. I’ve spent that time cleaning it up and making it more usuable for other people. It only supports Macs for now, and may be rough around the edges. But it’s been working for me pretty well for the past year.

This is my first time releasing a Zig library, so feedback is greatly appreciated.

Repo: GitHub - emmettmcdow/dve: dve is a library for creating and searching vector embeddings locally on Apple devices · GitHub