Skip to content

Using a prompt version in Evals #2475

@vikramsg

Description

@vikramsg

Confirm this is an issue with the Python library and not an underlying OpenAI API

  • This is an issue with the Python library

Describe the bug

Hey folks,
Not sure if this is a bug or a missing feature. Let me know if I should ask this somewhere else.

On the OpenAI platform, we have prompt versioning available as well as evals. Now, what I want to do is, whenever I update the prompt in the prompt version, I want to be able to kick off an existing eval with the updated prompt.

So, is there a way in the eval endpoint, to point to a prompt with a version?

To Reproduce

  1. In the evals endpoint, put a prompt version somewhere.

Code snippets

OS

macOS

Python version

python 3.12.11

Library version

openai v1.97

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions