Self-hosted voice assistant with mobile app
from eager_eagle@lemmy.world to selfhosted@lemmy.world on 21 Feb 20:44
https://lemmy.world/post/43424949
from eager_eagle@lemmy.world to selfhosted@lemmy.world on 21 Feb 20:44
https://lemmy.world/post/43424949
Any experiences with a self-hosted assistant like the modern Google Assistant? Looking for something LLM-powered that is smarter than older assistants that would just try to call 3rd party tools directly and miss or misunderstand requests half of the time.
I’d like integration with a mobile app to use it from the phone and while driving. I see Home Assistant has an Android Auto integration. Has anyone used this, or another similar option? Any blatant limitations?
threaded - newest
Multi-billion dollar companies like Google and Apple can’t even figure this shit out, doubt some nerd is gonna do it for free.
LOL they can’t even reliably turn the lights on, WTF are you talking about?
maybe last you tried it was over 6 months ago, maybe you’re using the old google assistant, or idk, but it definitely works for me
Everything I’ve read says Gemini is like 10x worse than Google Assistant.
Home Assistant can absolutely do that. If you are ok with simple intent based phrasing it’ll do it out of the box. If you want complex understanding and reasoning you’ll have to run a local LLM, like Llama, on top of it
yeah, that’s what I’m looking for. Do you know of a way to integrate ollama with HA?
I don’t think there’s a straightforward way like a HACS integration yet, but you can access Ollama from the web with open-webui and save the page to your homepage:
<img alt="" src="https://sh.itjust.works/pictrs/image/ae206b55-421f-4035-ac6a-a51774739fcd.jpeg">
Just be warned, you’ll need a lot of resources depending on which model you choose and its parameter count (4B, 7B etc) – Gemma3 4B uses around 3GB storage, 0.5GB RAM and 4GB of VRAM to respond. It’s a compromise as I can’t get replacement RAM, and tends to be wildly inaccurate with large responses. The one I’d rather use, Dolphin-Mixtral 22B, takes 80GB storage and 17GB min RAM, the latter of which I can’t afford to take from my other services.
Home Assistant can do that, the quality will really depend on what hardware you have to run the LLM. If you only have a CPU you’ll be waiting 20 seconds for a response, which could also be pretty poor if you have to run a small quantized model
Maybe things have improved but the last time I tried the Home Assistant er- assistant, it was garbage at anything other than the most basic commands given perfectly.
You have to run an LLM of your own and link it, if you want quality even close to approaching Google, but the Home Assistant with the Nabu Casa “Home Assistant Voice Preview Edition” speakers are working well enough for me. I don’t use it for much beyond controlling my home automation components, though. But it’s still very early tech anf it doesn’t understand all that much unless you add a lot of your own configurations. I eventually plan to add an LLM, but even just running on the home assistant yellow hardware with a raspberry pi compute module 5 works ok for the basics though there is a slight delay.
I haven’t tried, but Nabu Casa also offers a subscription service for the voice processing if you want something more robust and can’t host your own LLM, but thst means sending your data out, even if they have good privacy policies, which I’m not interested in, because while I somewhat trust Nabu Casa’s current business model and policies, being hosted in the US means it’s susceptible to the current regime’s police-state policies. I’m waiting for hardware costs to recover from the AI bubble to self host an LLM, personally.