arguments

class FlagEmbedding.evaluation.beir.arguments.BEIREvalArgs(eval_name: str = None, dataset_dir: str | None = None, force_redownload: bool = False, dataset_names: str | None = None, splits: str = 'test', corpus_embd_save_dir: str = None, output_dir: str = './search_results', search_top_k: int = 1000, rerank_top_k: int = 100, cache_path: str = None, token: str = <factory>, overwrite: bool = False, ignore_identical_ids: bool = False, k_values: int = <factory>, eval_output_method: str = 'markdown', eval_output_path: str = './eval_results.md', eval_metrics: str = <factory>, use_special_instructions: bool = False)

Argument class for BEIR evaluation.