Clunky handling of model download problems

[danja]

I think the root cause is probably around Ollama's downloading - prone to failure with my slow connection. There's an outstanding issue nearby over there :

ollama/ollama#941

But I'm sure cleaner handling should be possible. The error report isn't useful - 'Prompt not Fulfilled' or somesuch. More information would be good, and/or some options like Retry/Clear Cache and Retry/Select Another Model. Sorry, I'm lazy, choosing a model should go here as a feature request.

On the (big) positive side, I did have mini-orca 3B locally, installed directly via Ollama. After I changed mistral to orca-mini in the chatd code & npm'd, it found it. Then worked together with info from a a PDF. (Results look hopeless after having spent time with GPT4, but I'm just delighted it runs, good enough for my purposes).

[fezzzza]

My experience is similar, and following tips in #1 I also find that, despite having ollama and several models installed, if mistral is not there then it will try to download mistral, with no care as to whether or not the hard drive is already full. Surely it should query the installed models and choose one, or allow the user to choose, (and I know this control is already in settings).