docling-project / docling-project/docling

Refine the format of markdown parsing from raw document

Open
#4,080 1 comment 0 reactions 0 assignees View on GitHub
enhancement
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

Open the contributing 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.