-
Notifications
You must be signed in to change notification settings - Fork 10
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
Add basic support for custom prompts #18
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice. Did a light review.
Seems like there should be a way to test without having to release to PyPI, like with a manuscript & GitHub repo that installs the package from the github URL.
""" | ||
|
||
# OpenAI API key to use | ||
OPENAI_API_KEY = "OPENAI_API_KEY" | ||
|
||
# Language model to use. For example, "text-davinci-003" | ||
# Language model to use. For example, "text-davinci-003", "gpt-3.5-turbo", "gpt-3.5-turbo-0301", etc |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Maybe link to https://platform.openai.com/docs/models/model-endpoint-compatibility and mention which endpoint the models have to be under?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Seems like there should be a way to test without having to release to PyPI, like with a manuscript & GitHub repo that installs the package from the github URL.
Yes, I'll give it a try next time.
Maybe link to https://platform.openai.com/docs/models/model-endpoint-compatibility and mention which endpoint the models have to be under?
Great point. I will add this.
This PR adds basic support for custom prompts. The documentation was added as part of this manubot/rootstock PR.
In general, the code of this repo needs refactoring. This change is already part of a release in PyPI, and therefore is the code used when any user is running the
ai-revision
workflow. This was done so I could test it in GitHub Actions, but we probably need another, safer release mechanism.