Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

The suffix/v1/chat/completion is incorrect, displaying 404 #81

Closed
cabinai opened this issue Feb 6, 2024 · 9 comments
Closed

The suffix/v1/chat/completion is incorrect, displaying 404 #81

cabinai opened this issue Feb 6, 2024 · 9 comments
Labels
question Further information is requested

Comments

@cabinai
Copy link

cabinai commented Feb 6, 2024

The suffix/v1/chat/completion is incorrect, displaying 404

@cabinai
Copy link
Author

cabinai commented Feb 6, 2024

/v1/chat/completions

@RockChinQ
Copy link
Owner

that's /v1/chat/completions

@RockChinQ
Copy link
Owner

Access this path through browser will get 404 indeed, this can only be used by POST method.

@cabinai
Copy link
Author

cabinai commented Feb 6, 2024

OK,Thanks

@cabinai
Copy link
Author

cabinai commented Feb 6, 2024

As for the selection of models, I don't see any description in the document

@cabinai
Copy link
Author

cabinai commented Feb 6, 2024

Also, is it possible to support multiple accounts? I would like to automatically call the second account when the first one expires

@cabinai
Copy link
Author

cabinai commented Feb 6, 2024

I can only initiate the GPT3.5 default model now

@cabinai
Copy link
Author

cabinai commented Feb 6, 2024

The log shows the GPT-4 model, but in reality, GPT3.5 is still being called up. I have confirmed that my account has enabled Plus. Thank you

@RockChinQ
Copy link
Owner

#20

@RockChinQ RockChinQ added the question Further information is requested label Feb 12, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants