Metrics and Performance

from upsonic.ocr import OCR
from upsonic.ocr.layer_1.engines import EasyOCREngine

# Create engine and orchestrator
engine = EasyOCREngine(languages=['en'])
ocr = OCR(layer_1_ocr_engine=engine)

# Process multiple files
ocr.get_text('document1.pdf')
ocr.get_text('document2.pdf')
ocr.get_text('image.png')

# Get metrics
metrics = ocr.get_metrics()

print(f"Files processed: {metrics.files_processed}")
print(f"Total pages: {metrics.total_pages}")
print(f"Total characters: {metrics.total_characters}")
print(f"Average confidence: {metrics.average_confidence:.2%}")
print(f"Total processing time: {metrics.processing_time_ms:.2f}ms")
print(f"Provider: {metrics.provider}")

# Reset metrics for new batch
ocr.reset_metrics()

from upsonic.ocr import OCR
from upsonic.ocr.layer_1.engines import EasyOCREngine, RapidOCREngine, TesseractOCREngine

def benchmark_providers(file_path):
    """Compare performance of different OCR providers."""
    providers = [
        ('EasyOCR', EasyOCREngine(languages=['en'], gpu=False)),
        ('RapidOCR', RapidOCREngine(languages=['en'])),
        ('Tesseract', TesseractOCREngine(languages=['eng']))
    ]

    results = {}

    for name, engine in providers:
        ocr = OCR(layer_1_ocr_engine=engine)
        ocr.reset_metrics()

        # Process file
        result = ocr.process_file(file_path)

        # Get metrics
        metrics = ocr.get_metrics()

        results[name] = {
            'confidence': result.confidence,
            'processing_time_ms': result.processing_time_ms,
            'characters': len(result.text)
        }

    # Print comparison
    print("Provider Performance Comparison:")
    for name, data in results.items():
        print(f"\n{name}:")
        print(f"  Confidence: {data['confidence']:.2%}")
        print(f"  Time: {data['processing_time_ms']:.2f}ms")
        print(f"  Characters: {data['characters']}")

    return results

# Run benchmark
benchmark_providers('test_document.pdf')