in fulltext_search/search_sharded.py [0:0]
def get_args():
parser = argparse.ArgumentParser()
parser.add_argument(
"--input_dataset", type=str, default="HuggingFaceTB/bisac_expanded_final"
)
parser.add_argument("--n_pages", type=int, default=2000)
parser.add_argument(
"--output_dataset",
type=str,
default="HuggingFaceTB/bisac_boosted_new_index_2000",
)
parser.add_argument("--shard", type=int, required=True)
parser.add_argument("--num_shards", type=int, required=True)
return parser.parse_args()