docling-project / docling-project/docling
Refine the format of markdown parsing from raw document
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 84
Description
### Requested feature
I use docling to parsing documents(docx and pdf) and show the output(mardown) to user for comfirmation and other activates. sometime the format of raw document is not good enought that makes the bad format of output markdown. so I wonder if docling could add new feature to fix the format of the output markdown file.
### Alternatives
...
Contributor guide
Research direction
No source file, test, or entry point is named. Start by reproducing the reported output-format problem with DOCX and PDF inputs, then trace how Docling generates Markdown from the raw documents. Done means the generated Markdown has a reliably improved format, but the desired formatting rules still need to be defined.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- backend
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100