EvaluationResult#

class langsmith.evaluation.evaluator.EvaluationResult[source]#

Bases: BaseModel

Evaluation result.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param comment: str | None = None#: An explanation regarding the evaluation.

param correction: Dict | None = None#: What the correct value should be, if applicable.

param evaluator_info: Dict [Optional]#: Additional information about the evaluator.

param feedback_config: FeedbackConfig | dict | None = None#: The configuration used to generate this feedback.

param key: str [Required]#: The aspect, metric name, or label for this evaluation.

param score: StrictBool | StrictInt | StrictFloat | None = None#: The numeric score for this evaluation.

param source_run_id: UUID | str | None = None#: The ID of the trace of the evaluator itself.

param target_run_id: UUID | str | None = None#

The ID of the trace this evaluation is applied to.

If none provided, the evaluation feedback is applied to the root trace being.

param value: Dict | str | None = None#: The value for this evaluation, if not numeric.