Skip to content

Judge API V2 | Implement CLI #1759

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 3 commits into from
Jun 14, 2025
Merged

Judge API V2 | Implement CLI #1759

merged 3 commits into from
Jun 14, 2025

Conversation

kaisopos
Copy link
Contributor

@kaisopos kaisopos commented Jun 13, 2025 •
edited
Loading

Description

Judge API V2: Implement the CLI

CLI

oumi judge_v2 \
  --judge-config judge_config.yaml \
  --inference-config inference_config.yaml \
  --input-file input.jsonl \
  --output-file output.jsonl

Terminal Output
image

Related issues

Towards OPE-1327

Before submitting

  • This PR only changes documentation. (You can ignore the following checks in that case)
  • Did you read the contributor guideline Pull Request guidelines?
  • Did you link the issue(s) related to this PR in the section above?
  • Did you add / update tests where needed?

Reviewers

At least one review from a member of oumi-ai/oumi-staff is required.

wizeng23
wizeng23 reviewed Jun 13, 2025
View reviewed changes
Copy link
Contributor

@wizeng23 wizeng23 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I might be missing context, but to me it feels weird to add an oumi verb called judge_v2.

  • Is there a reason we can't just replace the old judge verb logic with this one?
  • If we still want some of the functionality of the old judge verb, could we either add this new logic under the same verb, controlled by a flag, or give this verb a more descriptive name than just v2?

@kaisopos
Copy link
Contributor Author

I might be missing context, but to me it feels weird to add an oumi verb called judge_v2.

  • Is there a reason we can't just replace the old judge verb logic with this one?
  • If we still want some of the functionality of the old judge verb, could we either add this new logic under the same verb, controlled by a flag, or give this verb a more descriptive name than just v2?

Restricted Judge V2 under the env flag OUMI_EXPERIMENTAL_JUDGE_V2, as discussed offline.
The plan is to add a deprecation notice for V1 and fully replace with V2 in 1-2 versions.

@kaisopos kaisopos merged commit 1016b6b into main Jun 14, 2025
5 checks passed
@kaisopos kaisopos deleted the kostas/judge_v2_cli branch June 14, 2025 09:33
penfever pushed a commit that referenced this pull request Aug 27, 2025
@kaisopos
Judge API V2 | Implement CLI (#1759)
9656865
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@wizeng23 wizeng23 wizeng23 left review comments

@oelachqar oelachqar oelachqar approved these changes

@taenin taenin Awaiting requested review from taenin

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@kaisopos @oelachqar @wizeng23