[Suggestion] Allow LLM fallback on domain questions

koinsxc
Oct 2026
5 posts
0 likes
Member
[Suggestion] Allow LLM fallback on domain questions
Posted Fri Nov 13th 02:23

The specific example I'm interested in is weather. Many weather apps in HA are pretty lacking so I've been using a tool call through my LLM fallback. While the performance is much better (I can ask it for forecasts anywhere, and often further out than HA apps), Sophia treats all weather questions as climate questions and won't forward them to the LLM.

Another potential solution would be to differentiate between weather and climate as domains. I often ask what the weather is outside only for Sophia to tell me one of the temperatures reported by a thermostat in my home (or that the question couldn't nail down a specific entity, presumably because it matches multiple thermostats).

I know this could probably be solved with an LLM trigger phrase, but I don't like the idea of having to "train" my home users :P

Matt
Apr 2025
94 posts
0 likes
Member
Posted Fri Nov 13th 04:32

I can't change that. Sophia's main purpose is to match your sentences to an intent wthin Home Assistant, and it does so fairly agressively. I can't pull that back because if I do, then I'll get complaints from users saying their sentence went to the LLM fallback when it shouldn't have.

You'll need to use the LLM trigger phrase. You can make that phrase as simple as "ask", then simply sent in the message "ask what is the temperature outside?" and it will be forced to the LLM.

Quick Reply

You must be logged in to reply to this thread.

Login Register