Mark Sze

Okay, running through a set of test programs (which I've put on my repository), it looks good, however there was an issue with parallel tool calling (when the model suggests...

Nice work @arjun-g :)... just need to run `pre-commit run` to tidy up the test file and notebook, and then commit that. That should rectify the "Code formatting / pre-commit-check"...

Hey @opqpop, I'd suggest Together.AI as it supports Llama 3.1 (all sizes): https://docs.together.ai/docs/chat-models We have a Together.AI client class: https://microsoft.github.io/autogen/docs/topics/non-openai-models/cloud-togetherai/ I have noticed that they may have specific function calling...

Hey @Kirushikesh, thanks for creating this. Can I just clarify, it seems more that this is the use of LangChain's huggingface library as opposed to integration with LangChain? Do you...

Thanks @Kirushikesh, would you be able to test some non-OpenAI models, such as Anthropic's and Meta's Llamas. The role and name fields aren't always compatible with AutoGen messages.

> For some reason I am not able to request a review from @marklysze -- double checking what happened there. Thanks @gagb, it may be that my permissions have changed?...

Thanks @Kirushikesh for the Gemini code sample, that worked for me. Unfortunately the notebook code isn't working for me. It's not getting past this block of code in the `init`...

> > > Thats weird-- double checking asap! We are having slightly trouble accessing repo management – will add you asap. > > > > > > @marklysze -- your...

> @marklysze i am not sure what's the issue, its literally loading the model from huggingface. I have tried with `mistralai/Mistral-7B-Instruct-v0.1` model as well it worked. Btw i am running...

> > Thanks @gagb and @jackgerrits, got it and I've accepted, if you can check the role that would be appreciated :) > > All sorted now! Looks good, thanks!