shreyaskarnik / distillama Goto Github PK

Is your feature request related to a problem? Please describe.
i could not try the extension due to my ollama being hosted in a truenas scale server, i can use it with the ip and port of the server, but i didn't see any options on how to use it here

Describe the solution you'd like
A settings option where you can enter ollama host

Describe alternatives you've considered
well for now, i had to install ollama in my pc as a alternative

Additional context
no additional context

now when I use the chat functionality, it will just return the whole response at the same time.
what should I do to make the response will be display one chunk by one chunk?

Thanks for your awesome work here. I have a more architectural question—As deployment is a challenge for non-technical users, is it possible to wrap a llama model directly into the chrome extension JS code? Or are there any limitations to chrome extension memory/storage/CPU that would make that difficult or impossible? Thanks!