mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-13 07:08:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

Working on a first version of DOCX native backend

Browse Source 
Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maxim Lysak
2024-10-04 18:19:40 +02:00
parent 1fa7cd9855
commit cefc34e8d8
4 changed files with 362 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/run_with_formats.py
View File

@@ -13,10 +13,11 @@ from docling.pipeline.simple_model_pipeline import SimpleModelPipeline
from docling.pipeline.standard_pdf_model_pipeline import StandardPdfModelPipeline
input_paths = [
Path("tests/data/wiki_duck.html"),
# Path("tests/data/wiki_duck.html"),
Path("tests/data/word_sample.docx"),
Path("tests/data/powerpoint_sample.pptx"),
Path("tests/data/2206.01062.pdf"),
Path("tests/data/lorem_ipsum.docx"),
# Path("tests/data/powerpoint_sample.pptx"),
# Path("tests/data/2206.01062.pdf"),
]
input = DocumentConversionInput.from_paths(input_paths)