Compare predictions (as traces) from 2 or more runs.
DynamicComparisonRunEvaluator(
self,
func: Callable[[Sequence[Run], Optional[Example]], Union[_COMPARISON_OUTPUT, Awaitable[_COMPARISON_OUTPUT]]],
afunc: Optional[Callable[[Sequence[Run], Optional[Example]], Awaitable[_COMPARISON_OUTPUT]]] = None
)| Name | Type | Description |
|---|---|---|
func* | Callable | A function that takes a |