mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 04:24:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update example export code

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2024-10-14 16:40:40 +02:00
parent a50ba57a1f
commit 3f0b01702b
1 changed files with 3 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
examples/batch_convert.py
View File

@ -13,7 +13,7 @@ from docling.document_converter import DocumentConverter
_log = logging.getLogger(__name__) _log = logging.getLogger(__name__)
USE_V2 = True USE_V2 = True
USE_LEGACY = True USE_LEGACY = False
def export_documents( def export_documents(
@ -34,23 +34,11 @@ def export_documents(
if USE_V2: if USE_V2:
# Export Docling document format to JSON (experimental): # Export Docling document format to JSON (experimental):
with (output_dir / f"{doc_filename}.json").open("w") as fp: with (output_dir / f"{doc_filename}.json").open("w") as fp:
fp.write( fp.write(json.dumps(conv_res.document.export_to_dict()))
json.dumps(
conv_res.document.model_dump(
mode="json", by_alias=True, exclude_none=True
)
)
) # TODO to be replaced with convenience method
# Export Docling document format to YAML (experimental): # Export Docling document format to YAML (experimental):
with (output_dir / f"{doc_filename}.yaml").open("w") as fp: with (output_dir / f"{doc_filename}.yaml").open("w") as fp:
fp.write( fp.write(yaml.safe_dump(conv_res.document.export_to_dict()))
yaml.safe_dump(
conv_res.document.model_dump(
mode="json", by_alias=True, exclude_none=True
)
)
) # TODO to be replaced with convenience method
# Export Docling document format to doctags (experimental): # Export Docling document format to doctags (experimental):
with (output_dir / f"{doc_filename}.doctags.txt").open("w") as fp: with (output_dir / f"{doc_filename}.doctags.txt").open("w") as fp: