Process OCR

client.ocr.process(
    document: OCRDocumentParam,
    model: Optional[str] = None
) -> OCRResponse

from dedalus_labs import DedalusLabs
import base64

client = DedalusLabs()

# Process a PDF document
with open("document.pdf", "rb") as f:
    pdf_data = base64.b64encode(f.read()).decode("utf-8")

response = client.ocr.process(
    document={
        "document_url": f"data:application/pdf;base64,{pdf_data}"
    }
)

for page in response.pages:
    print(f"Page {page.index}:")
    print(page.markdown)
    print("---")

# Process an image file
with open("receipt.png", "rb") as f:
    image_data = base64.b64encode(f.read()).decode("utf-8")

response = client.ocr.process(
    document={
        "document_url": f"data:image/png;base64,{image_data}",
        "type": "receipt"
    }
)

print("Extracted text:")
print(response.pages[0].markdown)

# Process multiple pages and save markdown output
with open("report.pdf", "rb") as f:
    pdf_data = base64.b64encode(f.read()).decode("utf-8")

response = client.ocr.process(
    document={
        "document_url": f"data:application/pdf;base64,{pdf_data}"
    }
)

with open("output.md", "w") as f:
    for page in response.pages:
        f.write(f"# Page {page.index + 1}\n\n")
        f.write(page.markdown)
        f.write("\n\n")

print(f"Processed {len(response.pages)} pages")
print(f"Model used: {response.model}")

# Process a JPEG image
import base64
from pathlib import Path

image_path = Path("scan.jpg")
image_data = base64.b64encode(image_path.read_bytes()).decode("utf-8")

response = client.ocr.process(
    document={
        "document_url": f"data:image/jpeg;base64,{image_data}"
    },
    model="mistral-ocr-latest"
)

markdown_text = response.pages[0].markdown
print(markdown_text)

# Helper function to process any file
def process_document_ocr(file_path: str):
    """Process a document file with OCR and return markdown text."""
    from pathlib import Path
    import base64
    import mimetypes
    
    path = Path(file_path)
    mime_type = mimetypes.guess_type(file_path)[0] or "application/octet-stream"
    
    file_data = base64.b64encode(path.read_bytes()).decode("utf-8")
    
    response = client.ocr.process(
        document={
            "document_url": f"data:{mime_type};base64,{file_data}"
        }
    )
    
    return "\n\n".join(page.markdown for page in response.pages)

# Use the helper function
text = process_document_ocr("invoice.pdf")
print(text)