Skip to main content
Features Install Cheatsheet Comparison Documentation About GitHub
Privacy

Privacy Policy
paddleocr.dev

What this site collects, which third parties are involved, and what stays on your device.

No uploads

This site has no file upload, account or form. It never sees your images, PDFs or extracted text.

Analytics and fonts

Google Analytics 4 and Google Fonts are loaded, so Google receives standard visit data. Details below.

No ads today

No advertising scripts are loaded. This page will change before any are added.

Introduction

This page explains what data paddleocr.dev processes when you visit it. The site is an independent, static documentation site: it has no accounts, forms, comments or file uploads, and it never receives the images or documents you process with PaddleOCR.

What is collected, and by whom

  • Google Analytics 4 (measurement ID G-2Y98KKZZWL) is loaded on every page. It sets cookies and records pageviews, approximate location derived from IP address, device and browser type and referrer, so we can see which pages are useful. Details: How Google uses data from sites that use its services. You can opt out with the Google Analytics opt-out browser add-on or by blocking analytics in your browser.
  • Google Fonts (Inter and JetBrains Mono) are loaded from fonts.googleapis.com and fonts.gstatic.com, so Google receives your IP address and browser details when a page loads.
  • Hosting: the site is served from Vercel, which keeps standard server logs (IP address, user agent, requested URL, timestamp) for operations and security.
  • Your browser: the site stores your light/dark theme choice in your browser’s localStorage under the key paddleocr_theme. It stays on your device and is not sent anywhere.

Advertising

This site does not currently display advertising and its pages do not load advertising scripts. If that changes, this page will be updated first with the networks involved and how to opt out.

The playground and code generator

The interactive tools on the homepage run entirely in your browser and use only the text and options you type or select. They do not upload files and do not call PaddleOCR; they produce code for you to run yourself.

PaddleOCR itself is separate software

The PaddleOCR library runs on your own computer or server, so images you process with it are not sent to paddleocr.dev. Be aware that PaddleOCR downloads model files from a model hub the first time you use a model, and that optional modes (for example the MCP server with a hosted AI Studio or Qianfan service) send images to that service. Check the documentation of whichever mode you choose.

Your choices and rights

Depending on where you live (for example under the GDPR or UK GDPR) you may have rights to access, correct or delete personal data and to object to its processing. We do not hold personal data ourselves beyond what the providers above process on our behalf, so requests about analytics data are best handled by also using Google’s own controls, such as Google Activity controls.

Children

The site is written for developers and technical readers. We do not knowingly collect personal information from children under 13.

Contact and changes

Questions or corrections about this policy or the site: open an issue at github.com/dencyclopedia/paddleocr/issues. For questions about the PaddleOCR software, use the upstream repository. This policy was last updated on October 7, 2026.