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

[experiments] filter on experiment runs #5681

Open
Tracked by #3398
mikeldking opened this issue Dec 10, 2024 · 2 comments · May be fixed by #5738
Open
Tracked by #3398

[experiments] filter on experiment runs #5681

mikeldking opened this issue Dec 10, 2024 · 2 comments · May be fixed by #5738
Assignees

Comments

@mikeldking
Copy link
Contributor

mikeldking commented Dec 10, 2024

As a user that has just run an experiment with a set of evaluators configured, I want the ability to quickly narrow down to the problematic "runs"

for example might have "has_errors" and "valid_sql" as validators. I want to quickly narrow down the rows to the runs where "has_errors=1" or "valid_sql=0".

@axiomofjoy
Copy link
Contributor

Also see #5015 for additional context

@axiomofjoy axiomofjoy moved this from 📘 Todo to 👨‍💻 In progress in phoenix Dec 11, 2024
@axiomofjoy
Copy link
Contributor

axiomofjoy commented Dec 12, 2024

Some values we may wish to filter on:

  • eval
    • score (equality and inequality)
    • label (equality)
  • latency (greater than or eq)
  • status (success or error)
  • value for input key
  • value for output key

@mikeldking mikeldking moved this from 👨‍💻 In progress to 🔍. Needs Review in phoenix Dec 18, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Status: 🔍. Needs Review
Development

Successfully merging a pull request may close this issue.

2 participants