mdipierro
/
SmolDocling-256M-Demo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix

This commit is contained in:
Maurizio Dipierro 2025-03-19 16:57:31 +01:00
parent 5b9eafdf6a
commit 2ffed2f71e
1 changed files with 13 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
app.py
View File

@ -118,21 +118,21 @@ def model_inference(
# After finishing the streamer loop: # After finishing the streamer loop:
cleaned_output = full_output.replace("<end_of_utterance>", "").strip() cleaned_output = full_output.replace("<end_of_utterance>", "").strip()
final_output = cleaned_output
# If markdown conversion is needed, combine it with cleaned_output if cleaned_output:
yield cleaned_output
# Now, since cleaned_output exists, we can safely use it.
if any(tag in cleaned_output for tag in ["<doctag>", "<otsl>", "<code>", "<chart>", "<formula>"]): if any(tag in cleaned_output for tag in ["<doctag>", "<otsl>", "<code>", "<chart>", "<formula>"]):
doctag_output = cleaned_output doctag_output = cleaned_output
if "<chart>" in doctag_output: if "<chart>" in doctag_output:
doctag_output = doctag_output.replace("<chart>", "<otsl>").replace("</chart>", "</otsl>") doctag_output = doctag_output.replace("<chart>", "<otsl>").replace("</chart>", "</otsl>")
doctag_output = re.sub(r'(<loc_500>)(?!.*<loc_500>)<[^>]+>', r'\1', doctag_output) doctag_output = re.sub(r'(<loc_500>)(?!.*<loc_500>)<[^>]+>', r'\1', doctag_output)
doc = DoclingDocument(name="Document") doc = DoclingDocument(name="Document")
doctags_doc = DocTagsDocument.from_doctags_and_image_pairs([doctag_output], images) doctags_doc = DocTagsDocument.from_doctags_and_image_pairs([doctag_output], images)
doc.load_from_doctags(doctags_doc) doc.load_from_doctags(doctags_doc)
final_output += "\n\n**MD Output:**\n\n" + doc.export_to_markdown() yield f"**MD Output:**\n\n{doc.export_to_markdown()}"
# Yield the final combined output only once
yield final_output
if any(tag in doctag_output for tag in ["<doctag>", "<otsl>", "<code>", "<chart>", "<formula>"]): if any(tag in doctag_output for tag in ["<doctag>", "<otsl>", "<code>", "<chart>", "<formula>"]):