Great, but it’s restrictive only letting you use openai and google. I’m already hosting oogabooga text generation, let me use that
I believe that’s because those two APIs support function calling, open source support is still coming along.
Ah that makes sense. That’s when I’d start using it myself. Self hosted models and audio
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. :)
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.
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?).
Okay but when can we use the weather forecast on our dashboards? Functionality was retired with no replacement
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.
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?
Ok. Npw Its definitely time to migrate my instance to something more powerful then my raspberry pi
Oh cool, implementing mediocre algorithms. What could possibly go wrong?
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?