gossip_semantic_search/dataset_processor/__main__.py

import sys
import os

project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '..'))
sys.path.append(project_root)
print(project_root)

import argparse

import yaml

from dataset_processor import DatasetProcessor

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        '--config', type=str, help='Chemin vers le fichier YAML de configuration.', required=True
    )

    args = parser.parse_args()
    with open(args.config, 'r') as file:
        config = yaml.safe_load(file)

    dataset_processor = DatasetProcessor(
        dataset_path=config.get('dataset_path'),
        saved_processed_dataset_path=config.get('saved_processed_dataset_path'))
    dataset_processor.run()

if __name__ == '__main__':
    main()