torchss

Thank You for the writeup. I think I'm starting to understand what's going on but want to verify. 1. These queries on their own, individually: ``` INSERT INTO Location (...

This will be a relief. The lack of function calling support is having me: - write prompts that work around it using phrasing like `"If you cannot fill this JSON,...

This is fantastic. Would this also have the ability to put a constraint on how much "thinking" the model does and force thinking to stop based off an user provided...

> This makes me think we could add an option to limit the number of thinking tokens This WOULD BE PHENOMENAL! A lot of my `dsPy` metrics fail because the...

Yes, both v2.2.3, v2.2.4 are (`wget https://github.com/espanso/espanso/releases/download/v2.2.x/espanso-debian-x11-amd64.deb`) unusable on x11 Ubuntu 22.04 and up (not tested on wayland) and will break the existing installation. We should put a prominent notice...

Stephen, much thanks for the quick response. I would be OK compiling from source if needed _or_ running espanso in docker but I have personal distaste, non-technical objections to AppImage,...

> I think the new releases are compiled against versions of the libraries that are ahead of our machines. It's a problem we're aware of. ok > I have no...

@Martech-WorkShop are you able to build from source? If all the setup is difficult, we can consider writing a Dockerfile to do the compilation (not to run espanso itself, just...

This is what I used to compile the latest (v2.2.4) for Ubuntu. You might have to adjust a bit if it doesn't output an executable that works for you: ```...

A LiteLLM core provider would be fantastic especially with OpenAI-compatible API endpoint support Outlines support would be a tremendous value add alongside this https://github.com/google/langextract/issues/101