mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-31 14:34:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updated example

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak 2025-03-19 14:40:21 +01:00
parent 40b3f597f3
commit e13fa5ade8
1 changed files with 8 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
docs/examples/minimal_vlm_pipeline.py
View File

@ -68,18 +68,13 @@ for source in sources:
res = converter.convert(source) res = converter.convert(source)
print("------------------------------------------------")
print("MD:")
print("------------------------------------------------")
print("") print("")
print(res.document.export_to_markdown()) print(res.document.export_to_markdown())
doctags = ""
for page in res.pages: for page in res.pages:
print("") print("")
print("Predicted page in DOCTAGS:") print("Predicted page in DOCTAGS:")
print(page.predictions.vlm_response.text) print(page.predictions.vlm_response.text)
doctags += page.predictions.vlm_response.text
res.document.save_as_html( res.document.save_as_html(
filename=Path("{}/{}.html".format(out_path, res.input.file.stem)), filename=Path("{}/{}.html".format(out_path, res.input.file.stem)),
@ -90,14 +85,17 @@ for source in sources:
with (out_path / f"{res.input.file.stem}.json").open("w") as fp: with (out_path / f"{res.input.file.stem}.json").open("w") as fp:
fp.write(json.dumps(res.document.export_to_dict())) fp.write(json.dumps(res.document.export_to_dict()))
with (out_path / f"{res.input.file.stem}.md").open("w") as fp: res.document.save_as_json(
fp.write(res.document.export_to_markdown()) out_path / f"{res.input.file.stem}.md",
image_mode=ImageRefMode.PLACEHOLDER,
)
with (out_path / f"{res.input.file.stem}.doctag").open("w") as fp: res.document.save_as_markdown(
fp.write(doctags) out_path / f"{res.input.file.stem}.md",
image_mode=ImageRefMode.PLACEHOLDER,
)
pg_num = res.document.num_pages() pg_num = res.document.num_pages()
print("") print("")
inference_time = time.time() - start_time inference_time = time.time() - start_time
print( print(