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

fix(frontend): create evaluation model testset overlapping issue #2231

Open
wants to merge 5 commits into
base: dev
Choose a base branch
from

Conversation

ashrafchowdury
Copy link
Collaborator

Description

This PR aims to fix the testset overlapping issue in the create new evaluation model, and also added search feature in the component so that finding testsets gets easier.

Related Issue

Closes AGE-1055

Copy link

vercel bot commented Nov 8, 2024

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
agenta ✅ Ready (Inspect) Visit Preview 💬 Add feedback Nov 12, 2024 8:17am
agenta-documentation ✅ Ready (Inspect) Visit Preview 💬 Add feedback Nov 12, 2024 8:17am

@dosubot dosubot bot added size:L This PR changes 100-499 lines, ignoring generated files. bug Something isn't working labels Nov 8, 2024
Copy link
Member

@mmabrouk mmabrouk left a comment

Choose a reason for hiding this comment

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

Thanks @ashrafchowdury

  • I understand this PR adds a search feature right, but I could not understand the testset overlapping issue, the issue does not explain the problem clearly. Can you please explain it and the solution
  • The search feature only works in human evaluation but not in automatic evaluation
  • The tests are failing

@ashrafchowdury
Copy link
Collaborator Author

  • Fixed the auto-evaluation search
  • Fixed test fails
  • This is the testset overlapping issue that is fixed:

image

Copy link

vercel bot commented Nov 19, 2024

Deployment failed with the following error:

Resource is limited - try again in 14 minutes (more than 100, code: "api-deployments-free-per-day").

Copy link
Member

@bekossy bekossy left a comment

Choose a reason for hiding this comment

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

LGTM

@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Nov 20, 2024
@mmabrouk mmabrouk changed the base branch from main to dev December 11, 2024 12:02
Copy link
Member

@bekossy bekossy left a comment

Choose a reason for hiding this comment

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

Thanks for the PR @ashrafchowdury. It looks like the New Evaluation Modal has already been updated, but the Human Evaluation Modal has not. To keep this PR focused, let's limit its scope to updating the Human Evaluation Modal only

@dosubot dosubot bot removed the lgtm This PR has been approved by a maintainer label Dec 13, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working size:L This PR changes 100-499 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants