docling/examples/minimal.py

12 lines
407 B
Python
Raw Normal View History

2024-07-15 09:42:42 +02:00
from docling.datamodel.document import DocumentConversionInput
from docling.document_converter import DocumentConverter
artifacts_path = DocumentConverter.download_models_hf()
doc_converter = DocumentConverter(artifacts_path=artifacts_path)
input = DocumentConversionInput.from_paths(["factsheet.pdf"])
converted_docs = doc_converter.convert(input)
for d in converted_docs:
print(d.render_as_dict())