Shishir Patil

Hey @sreenivasmrpivot, thanks for your interest. The OG Gorilla paper looked at how do you train (fine-tine) an LLM that can retrieve the right API with the right arguments. This...

Thanks for raising this @mbalunovic! If you want to go ahead and raise a PR we'd be happy to welcome you as a contributor :)

Thanks for raising this @rgbkrk and the detailed example! We made this design choice thinking it might be better this way especially in those scenarios where you might want to...

Hey @fakerybakery I think you raised this in reference to the OpenFunctions release? We have a mistral trained model, but the performance is not that great 👀 It might just...

Hey @HalukCemDemirhan I just checked and saw that some of the calls are "hypothetical"! Can you verify that every call is actually executable?

I was thinking maybe you can just push commits to the current PR, rather than start a new PR?

Hey @hermansh-id ! Thank you for this and appreciate your contribution! This LGTM. One quick suggestion - can you suggest default configs and platform configs that you tested it on?...

Hey @wangbochao1 we use the AST parser to generate the `function_call` from the string. This should not be happening, have you tried this https://github.com/ShishirPatil/gorilla/blob/d8b3433e618c8af0db3ec9c71d7300007980b265/openfunctions/inference_local.py#L24 ?

Do you mind giving an example, @Shane-Burns-Dot-US ? I think I have a hunch of what you are referring to, but not sure If I fully understood this. Thanks!

Thanks for your kind words, and thanks for flagging this @giuliastro Is this through WSL, or through a powershell, or a different modality?