PaddleOCR plugin provides several capabilities from PaddleOCR, including text recognition, document parsing, and more
PaddleOCR is an industry-leading, production-ready OCR and document AI engine, offering end-to-end solutions from text extraction to intelligent document understanding. This plugin provides several capabilities from PaddleOCR, including text recognition, document parsing, and more.
Open the Plugin Marketplace, search for the PaddleOCR plugin, and install it to integrate it with your application.
Get an AI Studio access token from the AI Studio Access Token page, then enter it in the plugin settings.
The optional Base URL setting is only needed when requests must pass through a custom gateway. Leave it empty to use the official PaddleOCR service.
You can use the PaddleOCR plugin in the following application types.
Both Chatflow and Workflow applications support adding a PaddleOCR tool node.
Add a PaddleOCR tool in the Agent application, and then enter commands to call the tool.
The input supports Dify uploaded image/PDF files directly and submits their contents to the PaddleOCR async job API. For compatibility with existing workflows, URL and base64 string values are still accepted by the runtime.
All tools accept an optional PDF page range such as . Both document parsing tools can skip Markdown image resources when they are not needed and can return an additional DOCX file alongside the Markdown and JSON results.
See the PaddleOCR official API documentation for the hosted service model matrix and request behavior.
This plugin is powered by PaddleOCR.