Eric Curtin
Eric Curtin
But yes a documentation addition to install huggingface would be enough to close this issue for now. It's deliberately not a strong dependancy because it can be hard to install...
https://diffusionbee.com/ an example of a similar tool
This might be the best tool to look into to start as it uses the same library as llama.cpp: https://github.com/leejet/stable-diffusion.cpp GGML
Here's a UI for it: https://jellybox.com/
I don't expect llama.cpp to ever get this functionality, it's like whisper.cpp just another different form of AI inferencing Although all three of these projects use [ggml](https://github.com/ggml-org/ggml) llama.cpp, whisper.cpp, stable-diffusion.cpp
@utherp0 if you open the PR to mention this somewhere I'll merge it. I'm curious why I never encountered this, I'm on macOS most of the time. I'm on 15.3.1...
I read this as jinja support basically which we will look into soon. Tagging @engelmi for awareness
> Does this mean that ramalama does not support tool calling yet? If so, might be nice to add to the issue title. Depends on the tool, some are compatible,...
Tool calling has been available in llama.cpp for a long time via llama-server (which is the backend for "ramalama serve") but not all tools like that API, so it depends.
> Does this mean that ramalama does not support tool calling yet? If so, might be nice to add to the issue title. jinja is a template format. What is...