Gracefully handle errors in evals #2295
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Docs Preview
|
dmontagu
force-pushed
the
dmontagu/graceful-evals-error-handling
branch
from
5fe2ebf to
6bb2a3f
Compare
DouweM
requested changes
Jul 25, 2025
| except Exception as e: | ||
| return [ | ||
| EvaluatorFailure( | ||
| name=evaluator.get_default_evaluation_name(), error_msg=f'{type(e).__name__}: {e}', source=evaluator |
There was a problem hiding this comment.
Can we attach the exception itself so it can be read programmatically to get the stack trace if so desired? It wouldn't be serialized of course.
| inputs=case.inputs, | ||
| metadata=case.metadata, | ||
| expected_output=case.expected_output, | ||
| error_msg=f'{type(exc).__name__}: {exc}', |
There was a problem hiding this comment.
As with EvaluatorFailure, I'd like to include the exception itself
@dmontagu Can't we handle missing fields by just using the default value of |
|
This PR is stale, and will be closed in 3 days if no reply is received. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Also adds retry functionality. Builds on top of the work in #2282.
Still need to:
Note: I think this is technically a breaking change because it adds some fields to the ReportCase and EvaluationReport classes, so deserialization might not work on existing data. Given we are still 0.X I guess it's worth a bump to minor version(?) but I expect it won't be very disruptive in practice..