seehi
seehi
Is it reproducible, could you provide more details, like the code that was executed. Additionally, does this issue describe the same problem as this: https://github.com/geekan/MetaGPT/issues/1162
The reason is that [parse_outputs](https://github.com/geekan/MetaGPT/blob/main/metagpt/actions/di/execute_nb_code.py) has a parameter `keep_len` with a default value of 2000, which should be configurable later on. You can try to modify it manually to see...
Working on optimizing that.
You can check [the code](https://github.com/geekan/MetaGPT/blob/main/metagpt/software_company.py#L41): set config's project_name. Using `typer` or `fire` to parse command args.
@garylin2099 could you take a look at this?
It seems the error is caused by RateLimited, but there isn't a retry attempt in the code. You can try to use `retry_if_exception_type()` instead of `retry_if_exception_type(ConnectionError)` in the [retry](https://github.com/geekan/MetaGPT/blob/main/metagpt/provider/base_llm.py#L192) to...
It depends on the capabilities of the LLM.
FYI: @garylin2099
It might be supported later, and if possible, you can also provide a PR. FYI: @better629
Sounds good, but the priority might not be that high.