PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports
What is PaddleOCR?
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Overview of PaddleOCR
What it is
PaddleOCR is an open-source OCR toolkit and document AI engine that converts PDF documents and images into structured, LLM-ready data in JSON or Markdown format. It has over 70,000 GitHub stars and is used by projects such as Dify, RAGFlow, and Cherry Studio.
Key features
- Intelligent document parsing: Includes PaddleOCR-VL-1.6 (0.9B), a lightweight vision-language model that achieves 96.3% accuracy on OmniDocBench v1.6. PP-StructureV3 converts complex PDFs and images into Markdown or JSON with fine-grained coordinate information.
- Universal text recognition: PP-OCRv6 supports 50 languages with a single unified model (Chinese, English, Japanese, and 46 Latin-script languages). It achieves +4.6% detection and +5.1% recognition accuracy over PP-OCRv5, with 5.2× CPU inference speedup end-to-end.
- Developer ecosystem: Seamlessly integrates with Dify, RAGFlow, Pathway, and Cherry Studio. Supports multiple hardware backends including NVIDIA GPU, Intel CPU, and Kunlunxin XPU.
Use cases
PaddleOCR is designed for building intelligent RAG and Agentic applications. It can be used to extract structured data from scanned documents, invoices, receipts, tables, forms, and natural scene text. It supports over 100 languages and handles complex elements such as tables, formulas, seals, and charts.
Getting started
See the repository README for installation and quick-start instructions.
License and pricing
The project is licensed under Apache-2.0 and is open source.
Based on the project's public README and repository metadata.
