You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have setup a seperate AI-Server running Ollama and OpenWebUI. I also setup assist in Home Assistant with Home-LLM to use the Gemma2:27b model. That works like a charm, is able to control my devices and answer questions as long as I use the Webbrowser for interaction.
Now to my problem: When using the Home assistant companion app or a ESP32-S3-Box-3 for interaction with the assistant the model prompt is not executed. I can tell by asking the model for the date and time or device stati.
So it works in the browser but not on other voice satellites.
Any ideas where I can look further to solve this problem?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi community,
I have setup a seperate AI-Server running Ollama and OpenWebUI. I also setup assist in Home Assistant with Home-LLM to use the Gemma2:27b model. That works like a charm, is able to control my devices and answer questions as long as I use the Webbrowser for interaction.
Now to my problem: When using the Home assistant companion app or a ESP32-S3-Box-3 for interaction with the assistant the model prompt is not executed. I can tell by asking the model for the date and time or device stati.
So it works in the browser but not on other voice satellites.
Any ideas where I can look further to solve this problem?
Beta Was this translation helpful? Give feedback.
All reactions