from pathlib import Path

from docling.datamodel.accelerator_options import AcceleratorDevice, AcceleratorOptions
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import OcrMode, PdfPipelineOptions, RapidOcrOptions
from docling.document_converter import DocumentConverter, PdfFormatOption

options = PdfPipelineOptions(
    do_ocr=True,
    do_table_structure=True,
    ocr_options=RapidOcrOptions(
        backend="onnxruntime",
        lang=["en"],
        mode=OcrMode.FULL_PAGE,
    ),
    accelerator_options=AcceleratorOptions(device=AcceleratorDevice.CPU, num_threads=4),
)
converter = DocumentConverter(
    format_options={InputFormat.PDF: PdfFormatOption(pipeline_options=options)}
)
result = converter.convert("scanned-order.pdf")
markdown = result.document.export_to_markdown()
Path("scanned-order.md").write_text(markdown, encoding="utf-8")
print(markdown)