Merged
Conversation
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
Collaborator
|
this PR isn't specific to lilac in any way—its an adapter for pandas dataframe. Can we rename the module to reflect that? |
dphuang2
reviewed
Dec 29, 2025
eval_protocol/adapters/lilac.py
Outdated
Comment on lines
+74
to
+94
| def _evaluation_row_to_dict(row: EvaluationRow) -> dict[str, Any]: | ||
| """Convert a single EvaluationRow to a dictionary. | ||
|
|
||
| The output contains JSON-serialized fields that can be reconstructed back | ||
| to EvaluationRow. Users can add their own text columns for clustering. | ||
| """ | ||
| return { | ||
| # Identifiers | ||
| "row_id": row.input_metadata.row_id if row.input_metadata else None, | ||
| # Full data as JSON (for reconstruction) | ||
| "messages_json": json.dumps([_serialize_message(m) for m in row.messages]), | ||
| "tools_json": json.dumps(row.tools) if row.tools else None, | ||
| "ground_truth_json": json.dumps(row.ground_truth) if row.ground_truth else None, | ||
| "input_metadata_json": row.input_metadata.model_dump_json() if row.input_metadata else None, | ||
| "execution_metadata_json": row.execution_metadata.model_dump_json() if row.execution_metadata else None, | ||
| "evaluation_result_json": row.evaluation_result.model_dump_json() if row.evaluation_result else None, | ||
| # Scalar fields for filtering | ||
| "score": row.evaluation_result.score if row.evaluation_result else None, | ||
| "message_count": len(row.messages), | ||
| "has_tools": bool(row.tools), | ||
| } |
Collaborator
There was a problem hiding this comment.
should this helper just live on the EvaluationRow for discovery? Also, how was the final set of keys decided? Why don't we just generically serialize the entire EvaluationRow?
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
2 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.
Note
Adds pandas-based data interchange for evaluation rows and serialization helpers.
adapters/dataframe.pywithevaluation_rows_to_dataframeanddataframe_to_evaluation_rowsconverting viaEvaluationRow.to_dict()/from_dict()EvaluationRowgainsto_dict(JSON underdata_jsonplus convenience fields) andfrom_dict(validates/deserializes) for stable round-trippingadapters/__init__.pybehind optional pandas importWritten by Cursor Bugbot for commit e529f7f. This will update automatically on new commits. Configure here.