Updated minimal vlm pipeline example

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak 2025-03-19 13:48:44 +01:00
parent 0875388ce6
commit 9182d8a622

View File

@ -17,7 +17,8 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.pipeline.vlm_pipeline import VlmPipeline
sources = [
"tests/data/2305.03393v1-pg9-img.png",
# "tests/data/2305.03393v1-pg9-img.png",
"tests/data/pdf/2305.03393v1-pg9.pdf",
]
## Use experimental VlmPipeline
@ -73,10 +74,12 @@ for source in sources:
print("")
print(res.document.export_to_markdown())
doctags = ""
for page in res.pages:
print("")
print("Predicted page in DOCTAGS:")
print(page.predictions.vlm_response.text)
doctags += page.predictions.vlm_response.text
res.document.save_as_html(
filename=Path("{}/{}.html".format(out_path, res.input.file.stem)),
@ -87,6 +90,12 @@ for source in sources:
with (out_path / f"{res.input.file.stem}.json").open("w") as fp:
fp.write(json.dumps(res.document.export_to_dict()))
with (out_path / f"{res.input.file.stem}.md").open("w") as fp:
fp.write(res.document.export_to_markdown())
with (out_path / f"{res.input.file.stem}.doctag").open("w") as fp:
fp.write(doctags)
pg_num = res.document.num_pages()
print("")