-
Notifications
You must be signed in to change notification settings - Fork 20
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
Is create_completion missing arguments? #36
Comments
Hey @potaslab , Here you have an example: the_prompt = "Explain Julia metaprogramming in about 10 words."
create_completion(
ENV["OPENAI_API_KEY"],
"text-davinci-003";
prompt=the_prompt
) Here you can see it in action: |
I think I understand what you mean by "missing" - the prompt is missing in the sense that it is a keyword argument (thus technically not required). Although the example above works well, the |
Thanks for the example. I wasn't able to work that out from the documentation. I think that example would greatly help others if it were in the documentation, especially since some of the models work with Also, thanks for your hard work, its greatly appreciated! |
I do agree that we should create a separate issue for adding some examples (incl. for the new OpenAI functionality), but perhaps this issue can be closed now? |
I would prefer to tag this as a won't-fix, particularly since the completions API is now legacy and is slated for deprecation. |
We may also wish to consider deprecating those functions so that users can transition to the chat API instead. |
I hope this isn't a silly question, but is create_completion missing an argument for including a prompt? Or is it possible to provide an example of how to create a completion for a prompt? Apologies if I am missing something.
The text was updated successfully, but these errors were encountered: