Asynchronously evaluate the output string pairs.
aevaluate_string_pairs(
self,
*,
prediction: str,
prediction_b: str,
reference: str | None = None,
input: str | None = None,
**kwargs: Any = {}
) -> dict| Name | Type | Description |
|---|---|---|
prediction* | str | The output string from the first model. |
prediction_b* | str | The output string from the second model. |
reference | Optional[str] | Default: NoneThe expected output / reference string. |
input | Optional[str] | Default: NoneThe input string. |
**kwargs | Any | Default: {}Additional keyword arguments, such as callbacks and optional reference strings. |