PaddleOCR

from upsonic.ocr import OCR
from upsonic.ocr.paddleocr import PaddleOCR, PPStructureV3, PPChatOCRv4, PaddleOCRVL

# General OCR (PP-OCRv5)
ocr = OCR(PaddleOCR, lang='en', ocr_version='PP-OCRv5')
text = ocr.get_text('document.pdf')

# Advanced document structure recognition
ocr_structure = OCR(
    PPStructureV3,
    use_table_recognition=True,
    use_formula_recognition=True
)
result = ocr_structure.process_file('research_paper.pdf')

# Chat-based document understanding
ocr_chat = OCR(
    PPChatOCRv4,
    use_table_recognition=True,
    use_seal_recognition=True
)

# Vision-Language document understanding
ocr_vl = OCR(
    PaddleOCRVL,
    use_layout_detection=True,
    use_chart_recognition=True,
    format_block_content=True
)