mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-01 15:02:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updates for reading-order implementation

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2025-02-10 16:59:52 +01:00
parent a6ee5a4326
commit 27b896b938
2 changed files with 16 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
docs/examples/batch_convert.py
View File

@ -7,10 +7,11 @@ from typing import Iterable
import yaml import yaml
from docling_core.types.doc import ImageRefMode from docling_core.types.doc import ImageRefMode
from docling.datamodel.base_models import ConversionStatus from docling.datamodel.base_models import ConversionStatus, InputFormat
from docling.datamodel.document import ConversionResult from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.datamodel.settings import settings from docling.datamodel.settings import settings
from docling.document_converter import DocumentConverter from docling.document_converter import DocumentConverter, PdfFormatOption
_log = logging.getLogger(__name__) _log = logging.getLogger(__name__)
@ -38,6 +39,10 @@ def export_documents(
output_dir / f"{doc_filename}.json", output_dir / f"{doc_filename}.json",
image_mode=ImageRefMode.PLACEHOLDER, image_mode=ImageRefMode.PLACEHOLDER,
) )
conv_res.document.save_as_html(
output_dir / f"{doc_filename}.html",
image_mode=ImageRefMode.EMBEDDED,
)
conv_res.document.save_as_document_tokens( conv_res.document.save_as_document_tokens(
output_dir / f"{doc_filename}.doctags.txt" output_dir / f"{doc_filename}.doctags.txt"
) )
@ -50,10 +55,6 @@ def export_documents(
image_mode=ImageRefMode.PLACEHOLDER, image_mode=ImageRefMode.PLACEHOLDER,
strict_text=True, strict_text=True,
) )
conv_res.document.save_as_html(
output_dir / f"{doc_filename}.html",
image_mode=ImageRefMode.EMBEDDED,
)
# Export Docling document format to YAML: # Export Docling document format to YAML:
with (output_dir / f"{doc_filename}.yaml").open("w") as fp: with (output_dir / f"{doc_filename}.yaml").open("w") as fp:
@ -125,7 +126,14 @@ def main():
# settings.debug.visualize_tables = True # settings.debug.visualize_tables = True
# settings.debug.visualize_cells = True # settings.debug.visualize_cells = True
doc_converter = DocumentConverter() pipeline_options = PdfPipelineOptions()
pipeline_options.generate_page_images = True
doc_converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
}
)
start_time = time.time() start_time = time.time()

2
poetry.lock generated
View File

@ -879,7 +879,7 @@ transformers = [
type = "git" type = "git"
url = "https://github.com/DS4SD/docling-ibm-models.git" url = "https://github.com/DS4SD/docling-ibm-models.git"
reference = "dev/add-reading-order" reference = "dev/add-reading-order"
resolved_reference = "2f88418a493321a1ee82a01604f617488f6a8feb" resolved_reference = "6892adfa4fcf0878b938e8efc1407dec46e96bdd"
[[package]] [[package]]
name = "docling-parse" name = "docling-parse"