Here’s another addition to my aspiring blog: https://www.rahuljuliato.com/posts/ellama
This post outlines the process of setting up Ollama as a server and Ellama as an Emacs client. The result is a localized AI companion that enhances your Emacs experience.
Embracing the world of Emacs has been a delightful journey, and I can’t wait to share it with all of you!
that’s so cool, thanks!
I think I’m gonna need new hardware if I want to play with this…
Nice!
Ollama runs in CPU mode if you don’t have a GPU, also there are models that can be used with 4Gb of RAM.
Things won’t be fast but for experimenting it is enought :)
Is there any way to have it use company-mode so that it suggests ways to complete what you are typing? Just having it show the next most likely word would be great. That’s a feature I’d really like to try in emacs, but haven’t seen any packages that provide it.
Not now. And personally I don’t think it will be useful. But I see how it can be done. In that case hardest thing is to collect good context for completion. Without it this would be dummy t9.
Melpa says it’s not found?`