mirror of
https://github.com/docling-project/docling.git
synced 2025-06-27 05:20:05 +00:00
19fad9261c
* Upgraded Layout Postprocessing, sending old code back to ERZ Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Implement hierachical cluster layout processing Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Pass nested cluster processing through full pipeline Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Pass nested clusters through GLM as payload Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Move to_docling_document from ds-glm to this repo Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Clean up imports again Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * feat(Accelerator): Introduce options to control the num_threads and device from API, envvars, CLI. - Introduce the AcceleratorOptions, AcceleratorDevice and use them to set the device where the models run. - Introduce the accelerator_utils with function to decide the device and resolve the AUTO setting. - Refactor the way how the docling-ibm-models are called to match the new init signature of models. - Translate the accelerator options to the specific inputs for third-party models. - Extend the docling CLI with parameters to set the num_threads and device. - Add new unit tests. - Write new example how to use the accelerator options. * fix: Improve the pydantic objects in the pipeline_options and imports. Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com> * fix: TableStructureModel: Refactor the artifacts path to use the new structure for fast/accurate model Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com> * Updated test ground-truth Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Updated test ground-truth (again), bugfix for empty layout Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * fix: Do proper check to set the device in EasyOCR, RapidOCR. Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com> * Rollback changes from main Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update test gt Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Remove unused debug settings Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Review fixes Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Nail the accelerator defaults for MPS Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com> Co-authored-by: Christoph Auer <cau@zurich.ibm.com> Co-authored-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
64 lines
1.9 KiB
Python
64 lines
1.9 KiB
Python
from pathlib import Path
|
|
|
|
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
|
|
from docling.datamodel.base_models import InputFormat
|
|
from docling.datamodel.pipeline_options import (
|
|
AcceleratorDevice,
|
|
AcceleratorOptions,
|
|
PdfPipelineOptions,
|
|
TesseractCliOcrOptions,
|
|
TesseractOcrOptions,
|
|
)
|
|
from docling.datamodel.settings import settings
|
|
from docling.document_converter import DocumentConverter, PdfFormatOption
|
|
|
|
|
|
def main():
|
|
input_doc = Path("./tests/data/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
|
|
# )
|
|
|
|
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)
|
|
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()
|