Apppublic

adelevett/docling_pp_layout_demo

sourceHugging Facemitupdated 7mo agoView on Hugging Face

0likes

App README

PDF Layout Detection with PP-DocLayoutV3

Upload any PDF and get a structured breakdown of every element on the page — titles, body text, tables, figures, formulas, headers, footers, footnotes, and more — powered by PaddlePaddle's PP-DocLayoutV3 model via the docling-pp-doc-layout plugin.

Results are displayed as interactive JSON in the browser and can be downloaded as a .json file with one click.

How to use

1.Click Source Document and upload a PDF.
2.Click Run Layout Detection.
3.Inspect the extracted elements in the JSON panel.
4.Click Download JSON to save the results.

Output format

Each detected region is returned as an object with two fields:

json

{
  "type": "SectionHeaderItem",
  "content": "Introduction"
}

type reflects the docling document-model class. The table below maps the model's raw labels to the types you will see:

Detected region	Output type
`doc_title`	`TitleItem`
`paragraph_title`	`SectionHeaderItem`
`text`, `content`, `abstract`, `aside_text`	`TextItem`
`table`	`TableItem`
`image`, `chart`, `seal`	`PictureItem`
`formula`	`TextItem` (formula)
`footnote`, `vision_footnote`	`TextItem` (footnote)
`header`	`TextItem` (page header)
`footer`	`TextItem` (page footer)
`reference`, `reference_content`	`TextItem`
`algorithm`	`TextItem` (code)

Infrastructure

Component	Detail
Hardware	ZeroGPU — NVIDIA H200 (70 GB VRAM, shared)
Layout model	`PaddlePaddle/PP-DocLayoutV3_safetensors`
Pipeline	docling ≥ 2.73 + docling-pp-doc-layout
SDK	Gradio 6.9.0, Python 3.10