docling-project / docling-project/docling

[Bee]Table cell structure and reading order issue

Open
#1,474 1 comment 0 reactions 0 assignees View on GitHub
bug
Dominant language
Python
Stars
66.4k
Forks
4.8k
Avg merge
3d 4h
Merged PRs (30d)
95

Description

### Bug
Table cell structure and reading order issue when testing the latest TF accurate model.

Not including the input document due to sensitive nature. Can share the document privately upon request.
...

### Steps to reproduce
Run REDP-5027-00_IBM_SAN_Volume_Controller_and_IBM_FlashSystem_820__Best_Practices_and_Performance_Capabilities.pdf through TF and observe the output.
...

### Docling version
Latest TableFomer Accurate
...

### Python version
3.11
...

Contributor guide

Open the contributing guide

Research direction

Start by reproducing the reported output from REDP-5027-00_IBM_SAN_Volume_Controller_and_IBM_FlashSystem_820__Best_Practices_and_Performance_Capabilities.pdf with the latest TableFormer Accurate model, obtaining the sensitive document privately if needed. Compare the extracted table cell structure and reading order with the source document; done means the problematic output is corrected and verified on that document.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
data
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.