how to set gpt-4o
bluegithupu opened this issue · 4 comments
Policy and info
- Maintainers will close issues that have been stale for 14 days if they contain relevant answers.
- Adding the label "sweep" will automatically turn the issue into a coded pull request. Works best for mechanical tasks. More info/syntax at: https://docs.sweep.dev/
Description
A clear and concise description of how the documentation at https://gpt-engineer.readthedocs.io/en/latest/ is providing wrong/insufficient information.
Suggestion
How can it be improved
Hey, we'll take a look into this; in the meantime, @AntonOsika worked on a PR where GPT-4o will be a default model. You can check it here #1151
Anton has merged his code now, and gpt-4o is the default model - so you should just be able to pull the latest code and run as per normal @bluegithupu
Hey @bluegithupu - we just mentioned this during our technical planning meeting. You should be able to specify different models using our model argument.
Generally, you can use
gpte --help
Then it will show you that there's a model argument taking model id string which you can use for different models (like the gpt-4-turbo you mentioned or the previous default gpt-4-turbo.
This screenshot is courtesy of @zigabrencic 🙏
the help flag should be added to the documentation, and each option should be fully document as well