Change the output interface of evaluate #8003
Merged
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
TomeHirata
commented
Mar 24, 2025
39 tasks
chenmoneygithub
approved these changes
Mar 25, 2025
Collaborator
chenmoneygithub
left a comment
chenmoneygithub
left a comment
There was a problem hiding this comment.
Solid work! LGTM with one minor comment.
Let's talk offline for potential breakage, and align on the release schedule.
TomeHirata
force-pushed
the
feat/evaluate-response
branch
from
7aeb618 to
ed8fd13
Compare
chenmoneygithub
approved these changes
Mar 27, 2025
TomeHirata
force-pushed
the
feat/evaluate-response
branch
from
2f7a26e to
ce1ea2d
Compare
22 tasks
|
please merge the PR to be able to get the individual example level evaluation score. This will be useful for mlflow tracing. |
|
Hi @okhat, could you review this PR when you have a moment? Thanks! |
TomeHirata
force-pushed
the
feat/evaluate-response
branch
from
cb0c5bd to
a718520
Compare
okhat
reviewed
Jun 19, 2025
dspy/primitives/prediction.py
Outdated
| def __eq__(self, other): | ||
| if isinstance(other, (float, int)): | ||
| return self.__float__() == other | ||
| elif isinstance(other, Prediction): |
Collaborator
There was a problem hiding this comment.
Hmm this is really dangerous! It's a really bad idea. Why did we add this?
Collaborator
Author
There was a problem hiding this comment.
This was added mainly for two reasons:
- To support the existing logic that compares the equality of evaluation outputs. Users may also do
eval(program_1)==eval(program_2)in their code - Completeness for the comparison operator of dspy.Prediction. It is not consistent if
>=works fordspy.Predictionbut==does not
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.
In this PR, we change the output interface of
Evaluate.__call__.Instead of returning either score, (score, outputs), (score, scores, outputs) based on arguments, it will always return EvaluationResult containing the following fields:
Since this is a breaking change, this should be released in the next minor release rather than a patch release.
Resolve mlflow/mlflow#15476