mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updated vlm pipeline assembly and smol docling model code to support updated doctags

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak
2025-01-17 17:54:55 +01:00
parent f6d123a01c
commit 0fe12d819a
3 changed files with 29 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
docs/examples/minimal_smol_docling.py
View File

@@ -13,6 +13,7 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.pipeline.vlm_pipeline import VlmPipeline
sources = [
# "https://arxiv.org/pdf/2408.09869"
# "tests/data/2305.03393v1-pg9-img.png",
"tests/data/2305.03393v1-pg9.pdf",
# "demo_data/page.png",
@@ -60,8 +61,14 @@ for source in sources:
print("")
print(res.document.export_to_markdown())
with (out_path / f"{res.input.file.stem}.html").open("w") as fp:
fp.write(res.document.export_to_html())
# with (out_path / f"{res.input.file.stem}.html").open("w") as fp:
# fp.write(res.document.export_to_html())
res.document.save_as_html(
filename=Path("{}/{}.html".format(out_path, res.input.file.stem)),
image_mode=ImageRefMode.REFERENCED,
labels=[*DEFAULT_EXPORT_LABELS, DocItemLabel.FOOTNOTE],
)
with (out_path / f"{res.input.file.stem}.json").open("w") as fp:
fp.write(json.dumps(res.document.export_to_dict()))