Victor Dibia

Thanks for the clarification. Your use case is clear and makes sense. @sonichi … Is there a goog pattern to hook in a function to the human response call back....

Hi @plusnarrative-phillip , Thanks for sharing the feedback above. Some notes. - Socket connection breakage. In general, managing sockets in a multithreaded manner while handling errors and automatic reconnection is...

@ronaldpereira , Thanks, this looks like a valuable PR enabling the ability to add default_headers. Two things: - it seems that you have made changes to `client.py`. I would separate...

@Giova200 , thanks for mentioning this. I think this is related to #2050. Essentially, some models/endpoints require `max_tokens` to be explicitly which seems to be the case with `lmstudio`. I...

There is quite a bit of work to support custom agents from studio. We are currently focused on stabilizing the experience for two agent and groupchat workflows. Support for other...

@nicho2, Thanks for noting this. There indeed was a bug where `sanitize_agent_config` was called twice for agents in groupchat leading to the duplicate message. I pushed a fix which should...

Good observation here. My initial intuition is the model thinks the code being generated is part of a human-in-the-loop chat (which is expected for a chat finetuned model), where the...

> @victordibia The field "**admin_name**" is declared twice with the exact same specifications and default value from **AgentConfig** under **datamodel.py.** version: autogenstudio 0.0.56rc1 Thanks. Fixed.

Hi Ross, Same as code. Would be nice if you could send me a link to what you build.. I'm happy to share it on my blog. Victor. On 15/08/2015...

Recording of the autogenui. Main steps - [optional] create a new conda environment - pip install autogenui (or you can install from source on github ... clone repo ... pip...