paddleocr-doc-parsing
paddlepaddle466 installs
Turn complex documents into structured text.
What it does
Extracts structured Markdown and JSON from PDFs and document images while preserving tables, formulas, and reading order.
When to use it
Use for documents containing tables, mathematical formulas, charts, multi-column layouts, or complex structures requiring layout analysis.
How to use it
Give it a document file or URL; it extracts structured content and displays the results in the conversation.
What you provide
- Your files
Uses
PA
Latest review
What you need · 2
Requires the paddleocr CLI to invoke document parsing through its api command.
Requires an access token supplied through the PADDLEOCR_ACCESS_TOKEN environment variable for API authentication.
Access · 1
This skill
PaddleOCR
Write
Sends documents to PaddleOCR