shenchucheng

是不是用了最新代码，教程是基于0.5.2版本，新版metagpt需要相应修改一下

目前仅在openai下做了测试，其他模型需要进一步适配

@azurewtl Thanks for your improvements. It works when I call `define_log_level(print_level="DEBUG")` in my Python script entry if I want to print the LLM stream log. However, I'm considering whether to...

> @shenchucheng Can you confirm if this issue has been resolved? @geekan Fixxed by https://github.com/geekan/MetaGPT/pull/867.

@wangwenju269 哈喽，有一些问题先请问下 1. 为什么代码是写在tests目录下？ 2. 我看大部分的提示词都是中文，是必须使用中文提示词，还是什么原因呢？

@2495165664 . This is a good example, but the introduction of `stream_pipe` has intruded upon the original implementation. We can optimize it. With the help of `metagpt.logs.set_llm_stream_logfunc` and `contextvars.ContextVar`, we...

@azurewtl Thank you for bringing up this issue. I'd like to clarify your suggestion: Are you proposing to add a new log_level configuration and treat llm stream output as debug...

@azurewtl It sounds pretty good, we'd love to see your PR.

Have you installed the Mermaid CLI and changed the MMDC configuration? https://github.com/geekan/MetaGPT/blob/2cfa7af826767049181c6bf0b8d492ec6c0803b3/config/config.yaml#L70

Please try again.