Yes, you can! See the “threshold” value/slider. It’s at 0.7 by default, which seems to be a good tradeoff. 1 means exact match or failure, 0 will afaik match anything to everything.
Ah, I didn’t see the Edit, so we’re both in the same boat 😂
Huh, interesting. Does that work with wildcards like “put x on my shopping list”? Also, what are you using for that, if I may ask?
Sorry, I don’t quite follow 😅
What’s the problematic response?
Yay, that’s fantastic to hear!
Also, how’s your experience been with the PE? Getting a readymade device in a nice shell is appealing for sure 😅
Oh, in the demo gif, that’s via a shortcut (holding power for half a second). Sorry, can’t help with wakeword there 😅
Very cool. I’ll definitely look into that, and let you know back here :D
Yeah, fair :)
Glad to be of service… 😄
did you consider metaphone matching?
I did not even know about this. Sounds super interesting. Though it seems to be very language specific?
My original intent was to not rely on language specifics. But maybe we could just define additional steps in the pipeline for specific languages. Hm. I’ll have to think about this some more, but it might definitely be a great idea for a future version, so thanks for telling me about it!!
Finally got this through another comment below. No, this should not be able to happen, unless you yourself have created a custom intent + shell script action in home assistant that runs this. The integration itself does not execute actions/scripts or the like, it just finds the closest string in a list of strings, and then hands that to the official conversation agent/Hassil.
…do you think I’m a bot, or what is this?
Edit: ohh, that’s what the original comment was. Sorry. “lange leitung” today.
Have fun, hope this works out for you! FYI: you can also use an LLM as an additional fallback (first closest-intent, then on failure, LLM). README mentions it further down on Github.
Please do! And if it does drive her crazy, please do open a bug report 😄
Yes, should be completely language agnostic. I’m not a linguist though, so take with a grain of salt 😅
There’s nothing language specific going on though, apart from a slight preference to split slots on word boundaries determined by spaces. So, might work a bit worse in e.g. Japanese.
❌ Sorry, I couldn’t understand that
Ahhh got it 😄 Yeah, I get/got similar stuff with Alexa. Honestly, the STT there is pretty impressive(ly fast), but sometimes it’s incredible nonsense.
I mean, you still need to activate the assistant with your usual wakeword. This/Hassil isn’t really intended to be constantly listening.
Or am I misunderstanding the question? 😅
I don’t really know, sorry :(
If you want to migrate, is going conduit - conduwuit - continuwuity (first version) - continuwuity (current version) maybe an option?
I went with continuwuity and am happy with it. Development happens at a steady pace, with sane priorities. The server is stable and I haven’t had any issues to speak of, despite one minor bug that got resolved very quickly after creating an issue.
Sorry to bother you, hope it’s alright if I ask for some clarification. English isn’t my first language, so I’m a bit uncertain here: is “cad” a euphemism for “racist”, “pedophile”, “shitbrain”, “misogynist”, “felon”, or some equally true and fitting term I’m not aware of?
This started off as a single file in my private nix config, to see if I could get it working at all. In that initial part, some parts were indeed LLM generated (esp. testcases based on my existing intents and failures).
When I noticed that this might actually work and be useful not just for myself though, I moved everything out manually, refactored and cleaned it up, and everything since has just been myself. I guess you’re still right though. I’ll see about adding a disclaimer to the README until I’ve gotten the chance to properly rewrite everything.