"""
Generate a synthetic KYC document dataset for training a VLM on document 
extraction and classification tasks.

Produces document images for: Aadhar, PAN, Passport, Visa, Election Card
with corresponding extraction ground truth in JSON format.

Usage:
    pip install datasets Pillow faker huggingface_hub
    python generate_kyc_dataset.py

Output: Pushes to HuggingFace Hub as Jwalit/kyc-document-extraction-vlm
"""

# See full script at: https://huggingface.co/datasets/Jwalit/kyc-document-extraction-vlm
# The dataset has already been generated and pushed.
# Re-run this script only if you want to regenerate with different parameters.

print("Dataset already generated at: https://huggingface.co/datasets/Jwalit/kyc-document-extraction-vlm")
print("To regenerate, uncomment the code below and run.")