fix: Stabilize label extraction #7499
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
dosubot
bot
added
the
size:XS
anticorrelator
force-pushed
the
dustin/stabilize-label-extraction
branch
from
5fa6d86 to
7e5a347
Compare
dosubot
bot
added
size:S
axiomofjoy
approved these changes
May 13, 2025
GeLi2001
pushed a commit
that referenced
this pull request
May 21, 2025
* Stabilize label extraction * Improve logging messages * Update test to use correct response (falls back to normal prompt) * Update df in test
efontan-dialpad
pushed a commit
to gluru/phoenix
that referenced
this pull request
May 28, 2025
* Stabilize label extraction * Improve logging messages * Update test to use correct response (falls back to normal prompt) * Update df in test
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Outdated suggestions cannot be applied.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.
When setting
provide_explanation=Trueinllm_classify, failing to provide a compatible label extraction function will sometimes lead to unexpectedNOT_PARSABLElabels when trying to pull out the label from the LLM output.This falls back to attempting to snap the entire LLM output to rails in case the default parsing function cannot split the label from the explanation (our internal convention is to delimit using
label: