import sys from pathlib import Path # Add project root to Python path project_root = Path(__file__).parent.parent sys.path.append(str(project_root)) from config.settings import Settings from huggingface_hub import HfApi def check_dataset_files(): """Check files available in the HuggingFace dataset""" print(f"\nChecking dataset: {Settings.HF_DATASET}") print(f"Using token: {'Present' if Settings.HF_TOKEN else 'Missing'}") api = HfApi(token=Settings.HF_TOKEN) try: files = api.list_repo_files(Settings.HF_DATASET, repo_type="dataset") print("\nFiles in dataset:") for f in files: print(f"- {f}") except Exception as e: print(f"\nError accessing dataset: {type(e).__name__}") print(f"Error details: {str(e)}") if __name__ == "__main__": check_dataset_files()