mirror of
https://github.com/docling-project/docling.git
synced 2025-06-27 05:20:05 +00:00
64ac043786
support running examples from root or subfolder Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
64 lines
2.0 KiB
Python
Vendored
64 lines
2.0 KiB
Python
Vendored
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 (
|
|
PdfPipelineOptions,
|
|
)
|
|
from docling.datamodel.settings import settings
|
|
from docling.document_converter import DocumentConverter, PdfFormatOption
|
|
|
|
|
|
def main():
|
|
data_folder = Path(__file__).parent / "../../tests/data"
|
|
input_doc_path = data_folder / "pdf/2206.01062.pdf"
|
|
|
|
# Explicitly set the accelerator
|
|
# accelerator_options = AcceleratorOptions(
|
|
# num_threads=8, device=AcceleratorDevice.AUTO
|
|
# )
|
|
accelerator_options = AcceleratorOptions(
|
|
num_threads=8, device=AcceleratorDevice.CPU
|
|
)
|
|
# accelerator_options = AcceleratorOptions(
|
|
# num_threads=8, device=AcceleratorDevice.MPS
|
|
# )
|
|
# accelerator_options = AcceleratorOptions(
|
|
# num_threads=8, device=AcceleratorDevice.CUDA
|
|
# )
|
|
|
|
# easyocr doesnt support cuda:N allocation, defaults to cuda:0
|
|
# accelerator_options = AcceleratorOptions(num_threads=8, device="cuda:1")
|
|
|
|
pipeline_options = PdfPipelineOptions()
|
|
pipeline_options.accelerator_options = accelerator_options
|
|
pipeline_options.do_ocr = True
|
|
pipeline_options.do_table_structure = True
|
|
pipeline_options.table_structure_options.do_cell_matching = True
|
|
|
|
converter = DocumentConverter(
|
|
format_options={
|
|
InputFormat.PDF: PdfFormatOption(
|
|
pipeline_options=pipeline_options,
|
|
)
|
|
}
|
|
)
|
|
|
|
# Enable the profiling to measure the time spent
|
|
settings.debug.profile_pipeline_timings = True
|
|
|
|
# Convert the document
|
|
conversion_result = converter.convert(input_doc_path)
|
|
doc = conversion_result.document
|
|
|
|
# List with total time per document
|
|
doc_conversion_secs = conversion_result.timings["pipeline_total"].times
|
|
|
|
md = doc.export_to_markdown()
|
|
print(md)
|
|
print(f"Conversion secs: {doc_conversion_secs}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|