docling-project / docling-project/docling

Smoldocling inserts "The Book of the Dead" on blank pdf pages

Open
#1,468 1 comment 0 reactions 1 assignee Claimed by @nassarofficial View on GitHub
bug smoldocling triage/close-stale
Dominant language
Python
Stars
66.4k
Forks
4.8k
Avg merge
2d 21h
Merged PRs (30d)
84

Description

### Bug

When processing a pdf with smoldocling mlx locally on my silicon mac, the docling document json output contains a series of "The book of the dead" text entries within parsed blank pages. These appear in doc tag output as well.

### Steps to reproduce

Running smoldocling test scripts as well as docling using vlm with smoldocling, processing a short pdf with some totally blank pages.

### Docling version

Docling version: 2.30.0
Docling Core version: 2.26.4
Docling IBM Models version: 3.4.1
Docling Parse version: 4.0.1
Python: cpython-311 (3.11.11)
Platform: macOS-15.1.1-arm64-arm-64bit

### Python version

Python 3.11.11

[book_of_dead.md](https://github.com/user-attachments/files/19930976/book_of_dead.md)

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.