this post was submitted on 05 Jun 2024
72 points (91.9% liked)

homeassistant

12009 readers
138 users here now

Home Assistant is open source home automation that puts local control and privacy first. Powered by a worldwide community of tinkerers and DIY enthusiasts. Perfect to run on a Raspberry Pi or a local server. Available for free at home-assistant.io

founded 1 year ago
MODERATORS
GreatAlbatross@feddit.uk
72
Home Assistant 2024.6: Dipping our toes in the world of AI using LLMs (www.home-assistant.io)
submitted 5 months ago by thehatfox@lemmy.world to c/homeassistant@lemmy.world
15 comments fedilink hide all child comments
top 15 comments
sorted by: hot top controversial new old
[–] scrubbles@poptalk.scrubbles.tech 29 points 5 months ago (1 children)

Great, but it's restrictive only letting you use openai and google. I'm already hosting oogabooga text generation, let me use that

[–] Zikeji@programming.dev 19 points 5 months ago (2 children)

I believe that's because those two APIs support function calling, open source support is still coming along.

[–] scrubbles@poptalk.scrubbles.tech 9 points 5 months ago

Ah that makes sense. That's when I'd start using it myself. Self hosted models and audio

[–] wagesj45@kbin.run 3 points 5 months ago (1 children)

Mistral Instruct v0.3 added in function calling, but I don't know if its method for implementation is the same/compatible. Also, it is fairly new and wasn't released all that long ago. Hopefully we'll get there soon. :)

[–] Zikeji@programming.dev 2 points 5 months ago (1 children)

I saw a few others, but the ones I looked at were basically instruct layers where you'd need to add your own parser. I didn't find anything (in my 3 minutes of searching) that offers an openai chat completions endpoint, which is probably the main stopper.

[–] wagesj45@kbin.run 1 points 5 months ago

Looking at the documentation it looks like it relies on Mistral's python tooling to work. I'm fairly dumb, so I don't know if the tool suggestion coming from Mistral is from some kind of separate neural net or as some kind of special response you have to parse (or that their client parses for you?).

[–] geophysicist@discuss.tchncs.de 10 points 5 months ago (4 children)

Okay but when can we use the weather forecast on our dashboards? Functionality was retired with no replacement

[–] Munkisquisher@lemmy.nz 8 points 5 months ago

The free data source was cut off, there's several replacements of varying quality depending on region. The met.no one is good for me.

[–] rach@lemmy.unryzer.eu 1 points 5 months ago

It's still working for me though I remember I needed to change the entity id and a automation a while back

[–] Buelldozer@lemmy.today 1 points 4 months ago (1 children)

What are you referring to when you say "when can we use the weather forecast on our dashboards? "

I've probably got the simplest and most "Out of the Box" dashboard stuff going on you can imagine and I've got forecast data showing with automations that run against it. What am I missing?

[–] muppeth@scribe.disroot.org 1 points 5 months ago

Ok. Npw Its definitely time to migrate my instance to something more powerful then my raspberry pi

[–] bushvin@lemmy.world -1 points 5 months ago (1 children)

Oh cool, implementing mediocre algorithms. What could possibly go wrong?

[–] warmaster@lemmy.world 7 points 5 months ago* (last edited 5 months ago)

Local LLMs have been supported via the Ollama integration since Home Assistant 2024.4. Ollama and the major open source LLM models are not tuned for tool calling, so this has to be built from scratch and was not done in time for this release. We’re collaborating with NVIDIA to get this working – they showed a prototype last week.

Are all Ollama-supported algos mediocre? Which ones would be better?