You can install Ollama in a docker container and use that to install models to run locally. Some are really small and still pretty effective, like Llama 3.2 is only 3B and some are as little as 1B. It can be accessed through the terminal or you can use something like OpenWeb UI to have a more “ChatGPT” like interface.

Thanks for this!

I really liked Kagi at first, especially since I use it mainly for programming as well, but recently I feel like the quality has gone downhill. Right around the time they integrated the Brave stuff I’ve noticed a significant amount of me having to scroll down past the usual Google-like fluff results before getting to actually relevant information. It’s a little sad to see because when I first used it, it was so good now it basically feels like a skinned Google-lite at this point. I’m still a customer but only because I haven’t found a good alternative yet.

Thanks for the explanation! Your explanation led me down a rabbit hole of seeing if there’s a way to cancel an await call, from what I can tell there was no clear way to do so. In my case I ended up connecting the signal to a secondary function instead of utilizing the await command, I’m not entirely sure if there’s an advantage to utilizing one method over the other.

I didn’t have access to my computer when I posted this so I was hoping to get some info while I was away from it. Thanks to another commenter, it looks like it has a very minimal impact. Good to know for future reference!

Thanks so much for testing that out! That’s very informative and even more thorough than what I was looking for! I wasn’t at my computer when I posted this so I couldn’t test it myself.

I ended up connecting the signal to a secondary function to run on finished to avoid any potential memory errors, but it’s super helpful to know that the performance impact is minimal.