Olicorne

Very long for me too on android. I ended up deleting appdata then reloading the whole graph. It took a while but it worked. I think the notification "loading changes...

I just want to tell that I too would like this feature : I'm using [logseq](https://github.com/logseq/logseq/issues) synced via syncthing to markor (because markor is way faster than logseq currently...) and...

This issue is still present in vesion 4.41.0 According to [this issue](https://github.com/andergisomon/dtp-nlp-demo/issues/1) it's happening since 4.17.0 and maybe in 4.16.0 Here are the commits that cause extensive change to the...

Thanks for the quick reply! To me, at least disabling the warning seems a progress as I can't imagine a user pasting twice a feed if he/she has not encountered...

Same here edit: related to #216 The issue is simply to do `python -m pip install pyvis==0.3.1` after uninstalling first

> It would also be nice to have a shortcut to toggle web search (and other tools) on and off. As well as a way to toggle: * start an...

No they do not ? I don't know if I'm missing something though. 

Well I think it works from "quick and fast" to "large and not far from SOTA" depending on the model size. The model take a language as input, for example...

I would be so interested in this I must say :) Regarding model size : lots of quantized versions exist now

Oh okay thanks. I guess I was mislead by `docker run ghcr.io/berriai/litellm:main-latest --config your_config.yaml` that appears first. But above all I'm deeply convinced that if the user specified --config to...