RapidOCR

from upsonic.ocr import OCR
from upsonic.ocr.layer_1.engines import RapidOCREngine
# Also available: from upsonic.ocr import RapidOCREngine

# Create engine instance
engine = RapidOCREngine(languages=['en'], confidence_threshold=0.5)

# Create OCR orchestrator
ocr = OCR(layer_1_ocr_engine=engine)

# Extract text from image
text = ocr.get_text('invoice.png')
print(text)

# Process PDF
result = ocr.process_file('document.pdf')
print(f"Extracted {len(result.text)} characters from {result.page_count} pages")