Fixes to preserve page image and demo export to html

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak
2025-01-10 10:50:35 +01:00
parent 3c4c647615
commit 1b968e4984
4 changed files with 24 additions and 16 deletions

View File

@@ -1,3 +1,5 @@
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 PdfPipelineOptions
@@ -9,19 +11,21 @@ from docling.pipeline.vlm_pipeline import VlmPipeline
source = "tests/data/2305.03393v1-pg9.pdf"
pipeline_options = PdfPipelineOptions()
pipeline_options.generate_page_images = True
pipeline_options.artifacts_path = "model_artifacts"
from docling_core.types.doc import DocItemLabel, ImageRefMode
from docling_core.types.doc.document import DEFAULT_EXPORT_LABELS
converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_cls=VlmPipeline,
pipeline_options=pipeline_options,
backend=DoclingParseDocumentBackend,
),
InputFormat.IMAGE: PdfFormatOption(
pipeline_cls=VlmPipeline,
pipeline_options=pipeline_options,
backend=DoclingParseDocumentBackend,
),
}
)
@@ -33,11 +37,11 @@ print("")
result = converter.convert(source)
print("------------")
print("result:")
print("------------")
print("")
print(result)
# print("------------")
# print("result:")
# print("------------")
# print("")
# print(result)
print("------------")
print("MD:")
@@ -45,6 +49,13 @@ print("------------")
print("")
print(result.document.export_to_markdown())
Path("scratch").mkdir(parents=True, exist_ok=True)
result.document.save_as_html(
filename=Path("scratch/smol_export.html"),
image_mode=ImageRefMode.REFERENCED,
labels=[*DEFAULT_EXPORT_LABELS, DocItemLabel.FOOTNOTE],
)
print("")
print("============")
print("done!")