Cohee

Docs are now fixed.

I find it positive that this gained some traction recently. The absence of min p sampling has been a huge downside of Ollama for local LM researchers. > the response...

Macros should be working in image prompts without any modifications since day 1 of the ImageGen extension.

> Another suggestion I can give is that if there would be an option to choose which language model or API do you want the templates to be handled by,...

Macros and extensions are not aware of prefills. You have to monitor the generated prompts to figure it out

Here's a reference on how to clean extracted PDF text. It's a Python package, but you can get an overall idea. https://github.com/pd3f/dehyphen Toast fixes are okay by me.

You can run it under extras as a separate module, I think it's fine and better than whatever solutions using pure regex are.

> Do you prefer if I replace the current sentence embedder with flair, or is it better to have both? You can have both. Just install dehyphen as a requirement...

This doesn't require backward compatibility as it's a built-in plugin using an API that nothing else is using.

The preferred way of adding functionality is server plugins. > fast local RAG embeddings provider Any reason why transformer.js embeddings do not work for you? > local websearch result parser...