def evaluate()

in src/alpaca_eval/main.py [0:0]

• 18 lines of code
• 1 McCabe index (conditional complexity)

def evaluate(
    model_outputs: Optional[AnyLoadableDF] = None,
    reference_outputs: AnyLoadableDF = constants.ALPACAEVAL_REFERENCE_OUTPUTS,
    annotators_config: AnyPath = constants.DEFAULT_ANNOTATOR_CONFIG,
    name: Optional[str] = None,
    output_path: Optional[Union[AnyPath, str]] = "auto",
    precomputed_leaderboard: Optional[Union[str, AnyPath, AnyData]] = "auto",
    is_overwrite_leaderboard: bool = False,
    leaderboard_mode_to_print: Optional[Union[str, Sequence[str]]] = "minimal",
    current_leaderboard_mode: str = "community",
    is_return_instead_of_print: bool = False,
    fn_metric: Union[str, callable] = "pairwise_to_winrate",
    sort_by: str = "win_rate",
    is_cache_leaderboard: Optional[bool] = None,
    max_instances: Optional[int] = None,
    annotation_kwargs: Optional[dict[str, Any]] = None,
    Annotator=annotators.PairwiseAnnotator,
    **annotator_kwargs,