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.

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

[Bug Fixes]: Release Cycle 63 #2302

Merged
merged 16 commits into from
Nov 27, 2024
Merged

[Bug Fixes]: Release Cycle 63 #2302

merged 16 commits into from
Nov 27, 2024

Conversation

aybruhm
Copy link
Member

@aybruhm aybruhm commented Nov 25, 2024 •
edited
Loading

Description

This PR resolves the following release cycle 63 bugs:

  • latency and cost computation
  • rag faithfulness evaluator failing for base response v3
  • rag faithfulness evaluator failing for base response v2
  • debug evaluation model not working for mflix example

@vercel Vercel
Copy link

vercel bot commented Nov 25, 2024 •
edited
Loading

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 27, 2024 9:06am
agenta-documentation ✅ Ready (Inspect) Visit Preview 💬 Add feedback Nov 27, 2024 9:06am

@aybruhm aybruhm changed the title [Bug Fixes]: Release Cycle 63 [Bug Fixes]: TypeError: get_field_value_from_trace_tree() Nov 25, 2024
@aybruhm aybruhm requested a review from jp-agenta November 25, 2024 18:26
@aybruhm aybruhm marked this pull request as ready for review November 25, 2024 18:43
@dosubot dosubot bot added size:M This PR changes 30-99 lines, ignoring generated files. bug Something isn't working labels Nov 25, 2024
mmabrouk
mmabrouk approved these changes Nov 25, 2024
View reviewed changes
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.

lgtm

To QA

@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Nov 25, 2024
@mmabrouk
Copy link
Member

CleanShot 2024-11-25 at 20 08 17@2x
CleanShot 2024-11-25 at 20 08 49@2x

Still failing. The configuration works in the eval debug modal, yet fails when running the evaluation.

@dosubot dosubot bot added size:L This PR changes 100-499 lines, ignoring generated files. and removed size:M This PR changes 30-99 lines, ignoring generated files. labels Nov 26, 2024
@aybruhm
refactor (backend): remove deprecated 'span' attribute in 'time' meta…
2a7c50a 
… and compute latency gotten from invocating app in evaluation
@aybruhm aybruhm requested a review from jp-agenta November 26, 2024 19:58
@aybruhm
chore (backend): remove overhead in computing latency and make use of…
c9142ba 
… metrics.acc.duration.total to get latency (in milliseconds)
@aybruhm aybruhm merged commit a0d9310 into main Nov 27, 2024
12 of 14 checks passed
@aybruhm aybruhm deleted the bug-fixes/release-cycle-63 branch November 27, 2024 09:05
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@jp-agenta jp-agenta jp-agenta approved these changes

@mmabrouk mmabrouk Awaiting requested review from mmabrouk

Assignees
No one assigned
Labels
bug Something isn't working lgtm This PR has been approved by a maintainer size:L This PR changes 100-499 lines, ignoring generated files.
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@aybruhm @mmabrouk @jp-agenta