Oh wow, awesome!

Thank you for your sacrifice :D

While I don’t like it, it’s not hidden either:

https://bentopdf.com/privacy.html

There should definitely be an option to disable this for self-hosting, but if it’s just a counter for how often each tool is used by all users combined… Eh…

(Stirling also has something similar)

Why not open a PR to make it configurable? The maintainer is super active and friendly.

Thanks for the recommendation! That looks interesting indeed.

This entire topic is probably a sinkhole of complexity. It’s great to have somewhere to look for inspiration!

Yeah those are good points. Also noticed the CDN thing, it’s a bit annoying for a privacy-first project… But should be an easy fix 😄

Stirling’s backend is Java. So, yeah, heavy and slow sounds about right.

Please read the title of the post again. I do not want to use an LLM. Selfhosted is bad enough, but feeding my data to OpenAI is worse.

Yep, that’s the idea! This post basically boils down to “does this exist for HASS already, or do I need to implement it?” and the answer, unfortunately, seems to be the latter.

Thanks, had not heard of this before! From skimming the link, it seems that the integration with HASS mostly focuses on providing wyoming endpoints (STT, TTS, wakeword), right? (Un)fortunately, that’s the part that’s already working really well 😄

However, the idea of just writing a stand-alone application with Ollama-compatible endpoints, but not actually putting an LLM behind it is genius, I had not thought about that. That could really simplify stuff if I decide to write a custom intent handler. So, yeah, thanks for the link!!

Thanks for your input! The problem with the LLM approach for me is mostly that I have so many entities, HASS exposing them all (or even the subset of those I really, really want) is already big enough to slow everything to a crawl, and to get bad results from all models I’ve tried. I’ll give the model you mentioned another shot though.

However, I really don’t want to use an LLM for this. It seems brittle and like overkill at the same time. As you said, intent classification is a wee bit older than LLMs.

Unfortunately, the sentence template matching approach alone isn’t sufficient, because quite frequently, the STT is imperfect. With HomeAssistant, currently the intent “turn off all lights” is, for example, not understood if STT produces “turn off all light”. And sure, you can extend the template for that. But what about

• turn of all lights
• turn off wall lights
• turnip off all lights
• off all lights
• off all fights
• …

A human would go “huh? oh, sure, I’ll turn off all lights”. An LLM might as well. But a fuzzy matching / closest Levensthein distance approach should be more than sufficient for this, too.

Basically, I generally like the sentence template approach used by HASS, but it just needs that little bit of additional robustness against imperfections.

Thanks for sharing your experience! I have actually mostly been testing with a good desk mic, and expect recognition to get worse with room mics… The hardware I bought are seeed ReSpeaker mic arrays, I am somewhat hopeful about them.

Adding a lot of alternative sentences does indeed help, at least to a certain degree. However, my issue is less with “it should recognize various different commands for the same action”, and more “if I mumble, misspeak, or add a swear word on my third attempt, it should still just pick the most likely intent”, and that’s what’s currently missing from the ecosystem, as far as I can tell.

Though I must conceit, copying your strategy might be a viable stop-gap solution to get rid of Alexa. I’ll have to pay around with it a bit more.

That all said, if you find a better intent matcher or another solution, please do report back as I am very interested in an easier solution that does not require me to think of all possible sentence ahead of time.

Roger.

Never heard about willow before - is it this one? Seems there is still recent activity in the repo - did the creator only recently pass away? Or did someone continue the project?

How’s your experience been with it?

And sure, will do!

To be fair, you can simply selfhost MinIO.

Lol, exact same situation here.

Quick question, did the migration to continuwuity break calls for you as well?

I have a small plastic freezer bag in my pocket, which I use turned inside-out to open the door.

My GF has severe (no, severe) OCD, and among all the rituals that are, objectively, pointless… This is the one that I wholeheartedly understand and agree with.

The comments here are awful. I am sorry for the abuse you are receiving.

I’m a staunch atheist myself, and even for some of the same reasons others are mentioning in their rage-comments. That being said, hating a person for their religious beliefs alone is baffling, and yes, makes you a bigot.

The exception I would make here is for situation and people where they, based on their religious beliefs hate you, and there’s nothing that can be done about it.I also would not call it bigoted to hate religious institutions for the discord and pain they inflict on the world.

But hating people because “well I was able to see through religion, so I am justified in hating everyone that did not and is still religious” is just such a disingenuous take. It denies the reality of indoctrination-like upbringings, of the differing educations people receive, and puts all religious people into a single “enemy” group.

I’m not US-American, as I assume many of these commenters are; where I live, the proportion of religious people is a lot lower, and the religiosity is… less pronounced, let’s say. It is much more difficult to find someone here who would, for example, go “Homosexuality is a sin according to the bible. Therefore I hate you.”; most religious people seem to have a differentiated opinion about these things, usually being more in line with “I believe there’s a God that loves us. The bible was written by fallible humans whose biases are present in the texts”.

Don’t get me wrong, I still think they are wrong in this and pity them for the time and energy lost on pleasing an imaginary being, and for the pain their beliefs can inflict upon themselves; but ultimately, that’s up to each individual person, and it does not justify hate.

Heavenly Delusion OP

Same; can you also, by any chance, wiggle them?

It’s not about prohibiting e2ee; it’s about enforcing client-side scanning.

Yes, that also breaks e2ee, but they can still go “nooo! E2ee is still perfectly fine and legal! You know, as long as we get to read anything anyways”

And realistically, this will probably end up being implemented on an OS-level as well. So even using a self-hosted matrix server would not be immune.

Not to mention that both you and your conversation partner needs to take steps to evade this; one party is not sufficient.

Not OP, but: watched Haruhi a while back in English Dub, because there’s no German one. It was ok. The main POV character’s monotone voice was fitting in a fun way, but almost everyone else still has this fake energy to it (esp Haruhi and Asahina). Really hard to describe.

In general it’s baffling to me how fake English dubs sound, especially because there clearly are a lot of talented English voice actors doing the voices for cartoons etc.

I have the privilege of comparing the English Dubs to the German ones for a lot of shows, and it’s really interesting how, while the German VAs sound distinctly different from the Japanese originals, they sound natural and not overacted, while the English counterparts almost always sound like they were told “make it sound as fake as possible”.