usearch VS beepy

Might have a look at this library:

https://github.com/unum-cloud/usearch

It does HNSW and there is a SQLite related project, though not quite the same thing.

Another worth mentioning in this thread is usearch, though not a separate algorithm, based on HNSW with a bunch of optimizations https://github.com/unum-cloud/usearch

I've used usearch successfully for a small project: https://github.com/unum-cloud/usearch/

The hardest (still missing) part of efficient cosine computation distance computation is picking a good epsilon for the `sqrt` calculation and avoiding "division by zero" problems.

We have an open issue about it in USearch and a related one in SimSIMD itself, so if you have any suggestions, please share your insights - they would impact millions of devices using the library (directly on servers and mobile, and through projects like ClickHouse and some of the Google repos): https://github.com/unum-cloud/usearch/issues/320

As you scale, you may benefit from these two projects I maintain, and the Big Tech uses :)

https://github.com/unum-cloud/usearch - for faster search

https://github.com/unum-cloud/uform - for cheaper multi-lingual multi-modal embeddings

> It doesn't appear to query CPUID

Yes, I'm actually looking for a good way to do it for other projects as well. I've looked into a couple more libs, and here is the best I've come up with so far: https://github.com/unum-cloud/usearch/blob/f942b6f334b31716f...

> Your substring routines have multiplicative worst case

Yes, that is true. It's a very simple stupid trick, just happens to work well for me :)

> It seems quite likely that your confirmation step

We have a different library internally at Unum, that avoids this shortcoming. It has a few thousand lines of C++ templates with SIMD intrinsics... and it's definitely more efficient, but the margins aren't always high. So I kept the pure C version with inlined functions as minimal and simple as possible.

> It would actually be possible to hook Stringzilla up to `memchr`'s benchmark suite if you were interested. :-)

Yes, that would be a fun thing to do! I haven't had time to look into `memchr` yet, but would expect great perf from your lib as well. For me the State of the Art is Intel HyperScan. Probably the most advanced SIMD library overall, not just for strings. I was very impressed with their perf ~5 years ago. But the repo is 200 K LOC... So get ready to invest a weekend :)

That said, I'm a bit slammed with work right now, including open-source. Hoping to ship a new major release in UCall this week, and a minor one in USearch :)

Author here — happy to answer any questions! This is more of a "I'm working on a new project" rather than an official release, the extension itself is still a work-in-progress. A link to the project: https://github.com/asg017/sqlite-vec

I have a pretty specific vision of what v0.1.0 of this extension will look like, but it'll take a few more weeks to get there. This blog post was more for letting users of sqlite-vss (a previous vector search SQLite extension I wrote) know what will be coming next. There will be a much bigger release when that is ready.

But in general, I'm super excited to have an easy embeddable vector search alternative! Especially one that runs on all operating system, in WASM, mobile devices, Raspberry Pis, etc. I personally I'm trying to run a lil' semantic search app on my Beepy[0], which is a ton of fun to play with.

[0] https://beepy.sqfmi.com/

This is the hardware that I wish Beepy had: https://beepy.sqfmi.com

By the way, does anyone know why all of these devices use the Arabic BlackBerry keyboard? Was there a particular surplus of this layout?

This is quite small, but you get Linux running on a hard to find Raspberry Pi Zero 2 W. https://beepy.sqfmi.com/

Hey there, just saw this kit, that makes a Zero board the brains of a handheld console. The thing is that the kit was just about 50 units made.

Beepberry by SQFMI looks like a nice cyber deck, but can't find any good videos on YouTube for this. just this YouTube short by JeffGeerling

The Beepberry isn't far off: https://beepberry.sqfmi.com/ looks like it's got a Blackberry keyboard. Missing LTE, but since it's just a raspberry pi zero, you could probably hack one in directly to a serial port on the GPIO. Needs a case though, but 3D printing one shouldn't be hard.

But I think the general market for this kind of device is really tiny; phones and tablets can do this pretty well, and appeal to general consumers

I am not sure but from Beepberry repository, the 3rd step about the setup script installs a kernel module to drive the LCD screen. The device tree file lists compatible chip including Broadcom SoC bcm2835, bcm2708 and bcm2709.