Beibin Li

Looking at the block below, it seems like you have the "human_input_mode" parameter wrong. --- `Provide feedback to agent. Press enter to skip and use auto-reply, or type 'exit' to...

@OTR Thanks for contributing these examples and logs! Code updated. Please try again.

@OTR @rakotomandimby @naourass Thanks for all your interest using AutoGen for Gemini. Do you have any suggestions regarding the "RECITATION" problem for Gemini? As pointed out by @rakotomandimby, there are...

@OTR Thanks for pointing out. The notebook is at: https://github.com/microsoft/autogen/blob/gemini/notebook/agentchat_gemini.ipynb For the installation bug, it seems like a `conversable-agent.jpg` file is in the tmp folder, which caused the issue. Can...

Closing due to inactivity. Gemini is now officially supported by AutoGen, and you can check our roadmap for gemini at: https://github.com/microsoft/autogen/issues/2387

A substitution with "litellm.completion" may not be adequate in this scenario. We may need additional checks. The OpenAI call is still preferred in most cases.

Another suggestion is: we should integrate LiteLLM natively with OAI_CONFIG_LIST, so that users don't need to worry about the backend.

> I'm going through a few things and i spotted a few issues: > > ## Issue 1: `config_list_from_dotenv` > * `config_list_from_dotenv` acts differently since the updates to `completion.py`, it...

Hi Everyone! @ishaan-jaff @sonichi @qingyun-wu Thanks so much for helping integrating LiteLLM into AutoGen! After closely reviewing the code, I'd like to kindly suggest a slight modification: we could utilize...

@libraua Thanks for your answer! @wieniu91 I will add more instructions to the notebook. This PR is still under draft, and we will make more changes in the future.