Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Building a fully local LLM voice assistant to control my smart home

johnthenerd.com

Post reply on HN
Print view View original

61–70 of 194 posts

Re: Building a fully local LLM voice assistant to control my smart home

#61

Post by iandanforth »

balloob wrote: post #52

Founder of Home Assistant here. Great write up! With Home Assistant we plan to integrate similar functionality this year out of the box. OP touches upon some good points that we have also ran into and I would love the local LLM community to solve: * I would love to see a standardized API for local LLMs that is not just a 1:1 copying the ChatGPT API. For example, as Home Assistant talks to a random model, we should be…

Predibase has a writeup that fine-tunes llama-70b to get 99.9% valid JSON out

https://predibase.com/blog/how-to-fine-tune-llama-70b-for-st...

Re: Building a fully local LLM voice assistant to control my smart home

#62

Post by JohnTheNerd »

balloob wrote: post #52

Founder of Home Assistant here. Great write up! With Home Assistant we plan to integrate similar functionality this year out of the box. OP touches upon some good points that we have also ran into and I would love the local LLM community to solve: * I would love to see a standardized API for local LLMs that is not just a 1:1 copying the ChatGPT API. For example, as Home Assistant talks to a random model, we should be…

thank you for building an amazing product!

I suspect cloning OpenAI's API is done for compatibility reasons. most AI-based software already support the GPT-4 API, and OpenAI's official client allows you to override the base URL very easily. a local LLM API is unlikely to be anywhere near as popular, greatly limiting the use cases of such a setup.

a great example is what I did, which would be much more difficult without the ability to run a replica of OpenAI's API.

I will have to admit, I don't know much about LLM internals (and certainly do not understand the math behind transformers) and probably couldn't say much about your second point.

I really wish HomeAssistant allowed streaming the response to Piper instead of having to have the whole response ready at once. I think this would make LLM integration much more performant, especially on consumer-grade hardware like mine. right now, after I finish talking to Whisper, it takes about 8 seconds before I start hearing GlaDOS and the majority of the time is spent waiting for the language model to respond.

I tried to implement it myself and simply create a pull request, but I realized I am not very familiar with the HomeAssistant codebase and didn't know where to start such an implementation. I'll probably take a better look when I have more time on my hands.

Re: Building a fully local LLM voice assistant to control my smart home

#63

Post by jpsouth »

jorvi wrote: post #33
polishdude20 wrote: post #30

Earlier quoted context omitted.

What about like, if I said "switch off the lamp at 3:45" How would you translate the Json you'd get out of that to get the same output? The subject would be "lamp" . Your app code would need to know that lamp is also light.

LLM just are waayyy too dangerous for something like home automation, until it becomes a lot more certain you can guarantee an output for an input. A very dumb innocuous example would be you ordering a single pizza for the two of you, then telling the assistant “actually we’ll treat ourselves, make that two”. Assistant corrects the order to two. Then the next time you order a pizza “because I had a bad day at work”,…

When you think about the damage that could be done with this kind of technology it’s incredible.

Imagine asking your MixAIr to sort out some fresh dough in a bole and then leaving your house for a while. It might begin to spin uncontrollably fast and create an awful lot of hyperbole-y activity.

Re: Building a fully local LLM voice assistant to control my smart home

#64

Post by balloob »

balloob wrote: post #52

Founder of Home Assistant here. Great write up! With Home Assistant we plan to integrate similar functionality this year out of the box. OP touches upon some good points that we have also ran into and I would love the local LLM community to solve: * I would love to see a standardized API for local LLMs that is not just a 1:1 copying the ChatGPT API. For example, as Home Assistant talks to a random model, we should be…

I think that LLMs are going to be really great for home automation and with Home Assistant we couldn't be better prepared as a platform for experimentation for this: all your data is local, fully accessible and Home Assistant is open source and can easily be extended with custom code or interface with custom models. All other major smart home platforms limit you in how you can access your own data.

Here are some things that I expect LLMs to be able to do for Home Assistant users:

Home automation is complicated. Every house has different technology and that means that every Home Assistant installation is made up of a different combination of integrations and things that are possible. We should be able to get LLMs to offer users help with any of the problems they are stuck with, including suggested solutions, that are tailored to their situation. And in their own language. Examples could be: create a dashboard for my train collection or suggest tweaks to my radiators to make sure each room warms up at a similar rate.

Another thing that's awesome about LLMs is that you control them using language. This means that you could write a rule book for your house and let the LLM make sure the rules are enforced. Example rules:

* Make sure the light in the entrance is on when people come home. * Make automated lights turn on at 20% brightness at night. * Turn on the fan when the humidity or air quality is bad.

Home Assistant could ship with a default rule book that users can edit. Such rule books could also become the way one could switch between smart home platforms.

Re: Building a fully local LLM voice assistant to control my smart home

#65

Post by balloob »

JohnTheNerd wrote: post #62
balloob wrote: post #52

Founder of Home Assistant here. Great write up! With Home Assistant we plan to integrate similar functionality this year out of the box. OP touches upon some good points that we have also ran into and I would love the local LLM community to solve: * I would love to see a standardized API for local LLMs that is not just a 1:1 copying the ChatGPT API. For example, as Home Assistant talks to a random model, we should be…

thank you for building an amazing product! I suspect cloning OpenAI's API is done for compatibility reasons. most AI-based software already support the GPT-4 API, and OpenAI's official client allows you to override the base URL very easily. a local LLM API is unlikely to be anywhere near as popular, greatly limiting the use cases of such a setup. a great example is what I did, which would be much more difficult witho…

Streaming responses is definitely something that we should look into. The challenge is that we cannot just stream single words, but would need to find a way to learn how to cut up sentences. Probably starting with paragraphs is a good first start.

Re: Building a fully local LLM voice assistant to control my smart home

#66

Post by nox101 »

balloob wrote: post #52

Founder of Home Assistant here. Great write up! With Home Assistant we plan to integrate similar functionality this year out of the box. OP touches upon some good points that we have also ran into and I would love the local LLM community to solve: * I would love to see a standardized API for local LLMs that is not just a 1:1 copying the ChatGPT API. For example, as Home Assistant talks to a random model, we should be…

I can't help but think of someone downloading "Best Assistant Ever LLM" which pretends to be good but unlocks the doors for thieves or whatever.

Is that a dumb fear? With an app I need to trust the app maker. With an app that takes random LLMs I also need to trust the LLM maker.

For text gen, or image gen I don't care but for home automation, suddenly it matters if the LLM unlocks my doors, turns on/off my cameras, turns on/off my heat/aircon, sprinklers, lights, etc...

Re: Building a fully local LLM voice assistant to control my smart home

#67

Post by balloob »

mofosyne wrote: post #59
balloob wrote: post #52

Founder of Home Assistant here. Great write up! With Home Assistant we plan to integrate similar functionality this year out of the box. OP touches upon some good points that we have also ran into and I would love the local LLM community to solve: * I would love to see a standardized API for local LLMs that is not just a 1:1 copying the ChatGPT API. For example, as Home Assistant talks to a random model, we should be…

Regarding accessible local LLMs have you heard of the llamafiles project? It allows for packaging one executable LLM that works on Mac, windows and Linux. Currently pushing for application note https://github.com/Mozilla-Ocho/llamafile/pull/178 to encourage integration. Would be good to hear your thoughts on making it easier for home assistant to integrate with llamafiles. Also as an idea, maybe you could certify rec…

As a user of Home Assistant, I would want to easily be able to try out different AI models with a single click from the user interface.

Home Assistant allows users to install add-ons which are Docker containers + metadata. This is how today users install Whisper or Piper for STT and TTS. Both these engines have a wrapper that speaks Wyoming, our voice assistant standard to integrate such engines, among other things. (https://github.com/rhasspy/rhasspy3/blob/master/docs/wyoming...)

If we rely on just the ChatGPT API to allow interacting with a model, we wouldn't know what capabilities the model has and so can't know what features to use to get valid JSON actions out. Can we pass our function definitions or should we extend the prompt with instructions on how to generate JSON?

Re: Building a fully local LLM voice assistant to control my smart home

#68

Post by JohnTheNerd »

balloob wrote: post #65
JohnTheNerd wrote: post #62

Earlier quoted context omitted.

thank you for building an amazing product! I suspect cloning OpenAI's API is done for compatibility reasons. most AI-based software already support the GPT-4 API, and OpenAI's official client allows you to override the base URL very easily. a local LLM API is unlikely to be anywhere near as popular, greatly limiting the use cases of such a setup. a great example is what I did, which would be much more difficult witho…

Streaming responses is definitely something that we should look into. The challenge is that we cannot just stream single words, but would need to find a way to learn how to cut up sentences. Probably starting with paragraphs is a good first start.

alternatively, could we not simply split by common characters such as newlines and periods, to split it within sentences? it would be fragile with special handling required for numbers with decimal points and probably various other edge cases, though.

there are also Python libraries meant for natural language parsing[0] that could do that task for us. I even see examples on stack overflow[1] that simply split text into sentences.

[0]: https://www.nltk.org/ [1]: https://stackoverflow.com/questions/4576077/how-can-i-split-...

Re: Building a fully local LLM voice assistant to control my smart home

#69

Post by balloob »

nox101 wrote: post #66
balloob wrote: post #52

Founder of Home Assistant here. Great write up! With Home Assistant we plan to integrate similar functionality this year out of the box. OP touches upon some good points that we have also ran into and I would love the local LLM community to solve: * I would love to see a standardized API for local LLMs that is not just a 1:1 copying the ChatGPT API. For example, as Home Assistant talks to a random model, we should be…

I can't help but think of someone downloading "Best Assistant Ever LLM" which pretends to be good but unlocks the doors for thieves or whatever. Is that a dumb fear? With an app I need to trust the app maker. With an app that takes random LLMs I also need to trust the LLM maker. For text gen, or image gen I don't care but for home automation, suddenly it matters if the LLM unlocks my doors, turns on/off my cameras, t…

That could be solved by using something like Anthropic's Constitutional AI[1]. This works by adding a 2nd LLM that makes sure the first LLM acts according to a set of rules (the constitution). This could include a rule to block unlocking the door unless a valid code has been presented.

[1]: https://www-files.anthropic.com/production/images/Anthropic_...

Re: Building a fully local LLM voice assistant to control my smart home

#70

Post by Lienetic »

gerdesj wrote: post #50
Lienetic wrote: post #29

Earlier quoted context omitted.

Can you share a bit more about why you're deploying HA in customer sites? I'm also a fan of HA and am interested to learn more about what you're doing and how it's going!

Here's how shit happens! We move to remote working due to a pandemic. Many of my customers do CAD on powerful gear in the office. They also have a ISO14001 registration (environmental standard) or not but want these gas guzzlers shut down at night. So they want to be able to wake up their PCs and shut them down remotely. I'm already flooded with VPN requirements and the other day to day stuff. I recall an add on for…

This is so interesting! Are all these people asking you "can I..." questions just people you work with day-to-day and you've become their "go-to guy for smart stuff?"

Do you find it a pain to have to manage all of this for people?

Post reply on HN