refactor: extract LLM call logging into shared evaluator_utils helper by smflorentino · Pull Request #1520 · UiPath/uipath-python
Navigation Menu
{{ message }}
UiPath / uipath-python Public
- Notifications You must be signed in to change notification settings
- Fork 23
Open
smflorentino wants to merge 1 commit intomainfrom
Open
refactor: extract LLM call logging into shared evaluator_utils helper#1520
smflorentino wants to merge 1 commit intomainfrom
refactor: extract LLM call logging into shared evaluator_utils helper#1520
smflorentino wants to merge 1 commit intomainfrom
Conversation
Copy link Copy Markdown
Collaborator
Summary
- Extract logging from
llm_as_judge_evaluatorintoevaluator_utils.pyfor reuse across LLM evaluators - Apply to
legacy_llm_as_judge_evaluator, andlegacy_trajectory_evaluator
Test plan
- Added unit tests for
_call_llm_with_logging(success, error wrapping, HTTP error logging, JSON fallback) - All 1685 existing tests pass
This is critical to diagnose LLM errors in LLM-based evaluators.
🤖 Generated with Claude Code
github-actions
bot
added
test:uipath-langchain
labels
Mar 27, 2026Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
smflorentino
force-pushed
the
sflorentino/extract-llm-logging-helper
branch
from
291be21 to
c3379ec
Compare
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
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
1 participant