Tesseract

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

# Create engine instance
engine = TesseractOCREngine(languages=['eng'], enhance_contrast=True)

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

# Extract text
text = ocr.get_text('receipt.jpg')
print(text)

# Custom Tesseract configuration
engine_custom = TesseractOCREngine(languages=['eng'], psm=3, oem=3)
ocr_custom = OCR(layer_1_ocr_engine=engine_custom)
result = ocr_custom.process_file('document.pdf')
print(f"Text: {result.text}")