Yeah, how does this work? Do I need to setup the tools in home assistant or do I need setup tools with system prompt / modelfile on the ollama server? The ollama integration says the AI instructions use homeassiant templating. Do I need to create a custom template prompt that passes the info to the ollama server in way that works with the tools? https://www.home-assistant.io/docs/configuration/templating/
Well, it's not an actual sensor. The sun "sensor" is built into home assistant and is pre-calculated. It uses the sensor interface to keep things constant when creating custom automation. I could just create a automation that reads it out the when I say a specific phrase. I'm just trying to use ollama so I don't have to create custom automation for everything.
It just has to read me what the Sun Next sensor says. I exposed it in the assist setting and it clearly knows it exits. I think I'm having some issue with the tools but I'm not sure how you're suppose to set it up.
Nice! Does the onscreen keyboard work in the login screen? If it doesn't it probably will soon. My understanding is that the wayland onscreen keyboard issues have been fixed really recently.
I was mostly just testing if I could use it without a keyboard and mouse. Which has not been the case with other distros I have tried. It's mostly firefox and the login screen having issues with the onscreen keyboard and the UI not scaling or accecpting touch input well that has been my problem with linux on a tablet.
Yeah, I firefox and the login screen didn't work well with the onscreen keyboard when I tried fedora. I ended up using it with the keyboard attahed. That's why I was so excited when everything worked with PostmarketOS.
I don't think they need pairing. It just worked for me. It's a generic one off amazon. The Microsoft one I got with the tablet broke after a month and the replacement one also broke after a month. I'm still kind of mad about it like 4 year later.
I messed around with home assistant and the ollama integration. I have passed on it and just use the default one with voice commands I set up. I couldn't really get ollama to do or say anything useful. Like I asked it what's a good time to run on a treadmill for beginners and it told me it's not a doctor.
Also, accidentally deleting all your valuable data without a working backup is a valuable lesson that I like to take the time to re-learn every few years.
Mine seems to have plenty of capacity left but has trouble powering my xr glasses below 60% if I'm gaming. Also if it's cold it will shut off under load until it's warmed up. I got mine really early around May 2022 I think.
One of my biggest regrets when purchasing pc components was not buying a 2080 two weeks before the 3080 came out. I ended up stuck with my rX 5700xt in my new build for like 2 years until prices came back down.
Yeah, how does this work? Do I need to setup the tools in home assistant or do I need setup tools with system prompt / modelfile on the ollama server? The ollama integration says the AI instructions use homeassiant templating. Do I need to create a custom template prompt that passes the info to the ollama server in way that works with the tools? https://www.home-assistant.io/docs/configuration/templating/