embedding VS llmware

- Server on Hetzner

Badger wouldn't have made sense to use instead of Postgres. I'm thinking of using Badger for other purposes. I do use ristretto and roaring bitmaps a lot internally.

Struct has a very nice integration with Slack. So, you can actually use Struct as a Slack interface. Essentially, your peers can be using Slack, while you could responding to them via Struct - think Superhuman for Gmail.

We have a good integration with Discord too. Both are being used by OSS companies to generate public knowledge bases from their Slack/Discord conversations.

[1]: https://github.com/struct-chat/embedding

I couldn't agree more. You should check out LLMWare's SLIM agents (https://github.com/llmware-ai/llmware/tree/main/examples/SLI...). It's focusing on pretty much exactly this and chaining multiple local LLMs together.

A really good topic that ties in with this is the need for deterministic sampling (I may have the terminology a bit incorrect) depending on what the model is indended for. The LLMWare team did a good 2 part video on this here as well (https://www.youtube.com/watch?v=7oMTGhSKuNY)

I think dedicated miniture LLMs are the way forward.

Disclaimer - Not affiliated with them in any way, just think it's a really cool project.

I've been building upon the LLMWare project - https://github.com/llmware-ai/llmware - for the past 3 months. The ability to run these models locally on standard consumer CPUs, along with the abstraction provided to chop and change between models and different processes is really cool.

I think these SLIM models are the start of something powerful for automating internal business processes and enhancing the use case of LLMs. Still kinda blows my mind that this is all running on my 3900X and also runs on a bog standard Hetzner server with no GPU.

16. LLMWare by Ai Bloks | Github | tutorial