Chi Wang
Chi Wang
> any docs on how to use streaming? Thanks a lot for the help. @ekzhu @jackgerrits could you check if this is in the doc roadmap?
https://github.com/microsoft/autogen/actions/runs/7829772683/job/21362424800?pr=1496 The code format error can be fixed by using pre-commit.
What about catching KeyboardInterruptError in `UserProxyAgent.initiate_chat()`?
This is an open issue that no one is working on. And it's an issue that needs to be addressed. @gagb What's your question about?
This can happen sometimes, especially with weak models. Is gpt-3.5 in use?
@kevin666aa could you follow up?
@gagb @victordibia @afourney might have an answer.
I think the termination reason message is only necessary when the termination is not triggered by a human input. But I'm not a HCI expert. So trying to get help...
https://microsoft.github.io/autogen/docs/reference/agentchat/conversable_agent#initiate_chat set `silent=True` to skip printing. Get the [chat messages](https://microsoft.github.io/autogen/docs/reference/agentchat/conversable_agent#chat_messages) or [last message](https://microsoft.github.io/autogen/docs/reference/agentchat/conversable_agent#last_message) clear cache: https://microsoft.github.io/autogen/docs/reference/oai/completion#clear_cache cache is made per `ChatCompletion.create` request.
Some of the answers are worth adding to the documentation website.