PaddleOCR — LLM-ready OCR & Document Parsing (PaddleOCR‑VL‑1.6) | PaddlePaddle/PaddleOCR

#4dailyJun 5, 2026OpenAI

Open on GitHub README URL

Summary

PaddleOCR — LLM-ready OCR & Document Parsing (PaddleOCR‑VL‑1.6)

The generated summary body for the selected provider.

OpenAImodel: gpt-5-mini

Highlights

1PaddleOCR‑VL‑1.6: 96.3% on OmniDocBench v1.6
2Structure-aware JSON/Markdown outputs + DOCX export
3PP-OCRv5: fast multilingual text spotting (100+ languages)

ocr vision-language document-parsing multilingual paddlepaddle rag

Overview

PaddleOCR is a production-grade OCR and document AI toolkit that converts PDFs and images into structured, LLM-ready outputs (JSON/Markdown) and DOCX. The project bundles a family of models and tools: the new PaddleOCR‑VL‑1.6 (0.9B) VLM for document parsing, PP-StructureV3 for fine-grained structure extraction (table cell and text coordinates), and PP-OCRv5 for high-speed scene text recognition. It supports 100+ languages (readme references 109–111 language coverage across releases), offers browser inference via PaddleOCR.js, and provides one-click deployment across CPU/GPU/XPU/NPU backends.

Translation

Translated body generated separately from the summary.

No translation available yet.

README

PaddlePaddle/PaddleOCR

Captured original README content.

<div align="center"> <p> <img width="800" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/Banner.png" alt="Star-history"> </p> <h3>Global Leading OCR Toolkit & Document AI Engine</h3>

</div> <div align="center"> <p> <img width="100%" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/Arch.jpg" alt="PaddleOCR Architecture"> </p> </div> <details> <summary><strong>2026.04.21: Release of PaddleOCR 3.5.0</strong></summary> </details> <details> <summary><strong>2026.01.29: Release of PaddleOCR 3.4.0</strong></summary> </details> <details> <summary><strong>2025.10.16: Release of PaddleOCR 3.3.0</strong></summary> </details> <details> <summary><strong>2025.08.21: Release of PaddleOCR 3.2.0</strong></summary> </details> <div align="center"> <p> <img width="100%" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/PP-OCRv5_demo.gif" alt="PP-OCRv5 Demo"> </p> </div> <div align="center"> <p> <img width="100%" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/PP-StructureV3_demo.gif" alt="PP-StructureV3 Demo"> </p> </div> <div align="center"> <p> <img width="100%" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/PaddleOCR-VL_demo.gif" alt="PP-StructureV3 Demo"> </p> </div> <div align="center"> <p> <img width="1200" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/star_paddleocr2.en.gif" alt="Star-Project"> </p> </div> <div align="center"> </div> <div align="center"> </div> <div align="center"> <a href="https://github.com/PaddlePaddle/PaddleOCR/graphs/contributors"> <img src="https://contrib.rocks/image?repo=PaddlePaddle/PaddleOCR&max=400&columns=20" width="800"/> </a> </div> <div align="center"> <p> <img width="800" src="https://api.star-history.com/svg?repos=PaddlePaddle/PaddleOCR&type=Date" alt="Star-history"> </p> </div>

ML engineers and researchers building RAG (retrieval-augmented generation) pipelines and document-centric LLM agents.
Product teams needing robust, multilingual document parsing (tables, formulas, seals, charts) and exportable structured outputs.
Developers targeting edge/cloud deployment who need resource-efficient VLMs and hardware-accelerated inference.

PaddleOCR is trending now due to the 2026.05.28 3.6.0 release that ships PaddleOCR‑VL‑1.6 with new SOTA results (96.3% on OmniDocBench v1.6) and broad capability upgrades for tables, ancient/rare characters, seals, and charts. The repo is seeing heavy activity (79,911 stars total, 141 stars today) and is tightly integrated with the AI agent ecosystem (Dify, RAGFlow, Pathway, Cherry Studio). Concrete practical wins include structure-aware JSON/Markdown outputs, DOCX export for parsed results, HuggingFace-hosted models, a Transformer inference backend option, and improved PP-OCRv5 accuracy and multilingual coverage—making it a turnkey solution for turning messy documents into high-quality training or RAG inputs.

PaddleOCR‑VL‑1.6: SOTA document VLM, available on HuggingFace and the project website.
PP-StructureV3: provides cell/text coordinates for precise table and layout extraction.
PP-OCRv5: single-model multilingual recognition with a reported 13% accuracy improvement over prior versions and ultra-small footprints for production.
Recent features: DOCX export, Office→Markdown conversion, browser SDK (PaddleOCR.js), and flexible inference backends (Paddle static/dynamic, Transformers).

PaddleOCR converts PDF documents and images into structured, LLM-ready data (JSON/Markdown) with industry-leading accuracy. With 70k+ Stars and trusted by top-tier projects like Dify, RAGFlow, and Cherry Studio, PaddleOCR is the bedrock for building intelligent RAG and Agentic applications.

📄 Intelligent Document Parsing (LLM-Ready)

Transforming messy visuals into structured data for the LLM era.

SOTA Document VLM: Featuring PaddleOCR-VL-1.6 (0.9B), the industry's leading lightweight vision-language model for document parsing. It achieves 96.3% accuracy on OmniDocBench v1.6, leads in text, formula, and table recognition, and shows significantly enhanced capabilities in ancient documents, rare characters, seals, and charts, with structured outputs in Markdown and JSON formats.
Structure-Aware Conversion: Powered by PP-StructureV3, seamlessly convert complex PDFs and images into Markdown or JSON. Unlike the PaddleOCR-VL series models, it provides more fine-grained coordinate information, including table cell coordinates, text coordinates, and more.
Production-Ready Efficiency: Achieve commercial-grade accuracy with an ultra-small footprint. Outperforms numerous closed-source solutions in public benchmarks while remaining resource-efficient for edge/cloud deployment.

🔍 Universal Text Recognition (Scene OCR)

The global gold standard for high-speed, multilingual text spotting.

100+ Languages Supported: Native recognition for a vast global library. Our PP-OCRv5 single-model solution elegantly handles multilingual mixed documents (Chinese, English, Japanese, Pinyin, etc.).
Complex Element Mastery: Beyond standard text recognition, we support natural scene text spotting across a wide range of environments, including IDs, street views, books, and industrial components
Performance Leap: PP-OCRv5 delivers a 13% accuracy boost over previous versions, maintaining the "Extreme Efficiency" that PaddleOCR is famous for.

🛠️ Developer-Centric Ecosystem

Seamless Integration: The premier choice for the AI Agent ecosystem—deeply integrated with Dify, RAGFlow, Pathway, and Cherry Studio.
LLM Data Flywheel: A complete pipeline to build high-quality datasets, providing a sustainable "Data Engine" for fine-tuning Large Language Models.
One-Click Deployment: Supports various hardware backends (NVIDIA GPU, Intel CPU, Kunlunxin XPU, and diverse AI Accelerators).

🔥 2026.05.28: Release of PaddleOCR 3.6.0

PaddleOCR-VL-1.6 highlights:
- New SOTA Accuracy: Achieves over 96.3% on OmniDocBench v1.6, also sets new SOTA on OmniDocBench v1.5 and Real5-OmniDocBench, leading both open-source and proprietary solutions in text, formula, and table recognition.
- Comprehensive Capability Upgrade: Significant improvements in table, ancient document, and rare character recognition, with notably enhanced seal recognition, spotting, and chart understanding across multiple scenarios.
- Seamless Migration: Model architecture is fully consistent with PaddleOCR-VL-1.5, enabling zero-cost adaptation—swap and go.
- Try it now: Available on HuggingFace or our Official Website.

Flexible inference backends: Seamlessly switch between Paddle static graph, Paddle dynamic graph, or Transformers. PaddleOCR is now deeply integrated with the Hugging Face ecosystem, and 20 major models support Transformers as the inference backend.
Office documents to Markdown: Convert common document formats such as Word, Excel, and PowerPoint into Markdown.
DOCX export for parsed results: The PaddleOCR-VL series, PP-StructureV3, and PP-DocTranslation now support exporting parsed results to DOCX for convenient viewing and editing in Microsoft Word.
Official browser inference SDK: Released PaddleOCR.js, the official browser inference SDK that supports running PP-OCRv5 directly in the browser.

PaddleOCR-VL-1.5 (SOTA 0.9B VLM): Our latest flagship model for document parsing is now live!
- 94.5% Accuracy on OmniDocBench: Surpassing top-tier general large models and specialized document parsers.
- Real-World Robustness: First to introduce the PP-DocLayoutV3 algorithm for irregular shape positioning, mastering 5 tough scenarios: Skew, Warping, Scanning, Illumination, and Screen Photography.
- Capability Expansion: Now supports Seal Recognition, Text Spotting, and expands to 111 languages (including China’s Tibetan script and Bengali).
- Long Document Mastery: Supports automatic cross-page table merging and hierarchical heading identification.
- Try it now: Available on HuggingFace or our Official Website.

Released PaddleOCR-VL:
- Model Introduction:
  - PaddleOCR-VL is a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic resolution visual encoder with the ERNIE-4.5-0.3B language model to enable accurate element recognition. This innovative model efficiently supports 109 languages and excels in recognizing complex elements (e.g., text, tables, formulas, and charts), while maintaining minimal resource consumption. Through comprehensive evaluations on widely used public benchmarks and in-house benchmarks, PaddleOCR-VL achieves SOTA performance in both page-level document parsing and element-level recognition. It significantly outperforms existing solutions, exhibits strong competitiveness against top-tier VLMs, and delivers fast inference speeds. These strengths make it highly suitable for practical deployment in real-world scenarios. The model has been released on HuggingFace. Everyone is welcome to download and use it! More introduction information can be found in PaddleOCR-VL.
- Core Features:
  - Compact yet Powerful VLM Architecture: We present a novel vision-language model that is specifically designed for resource-efficient inference, achieving outstanding performance in element recognition. By integrating a NaViT-style dynamic high-resolution visual encoder with the lightweight ERNIE-4.5-0.3B language model, we significantly enhance the model’s recognition capabilities and decoding efficiency. This integration maintains high accuracy while reducing computational demands, making it well-suited for efficient and practical document processing applications.
  - SOTA Performance on Document Parsing: PaddleOCR-VL achieves state-of-the-art performance in both page-level document parsing and element-level recognition. It significantly outperforms existing pipeline-based solutions and exhibiting strong competitiveness against leading vision-language models (VLMs) in document parsing. Moreover, it excels in recognizing complex document elements, such as text, tables, formulas, and charts, making it suitable for a wide range of challenging content types, including handwritten text and historical documents. This makes it highly versatile and suitable for a wide range of document types and scenarios.
  - Multilingual Support: PaddleOCR-VL Supports 109 languages, covering major global languages, including but not limited to Chinese, English, Japanese, Latin, and Korean, as well as languages with different scripts and structures, such as Russian (Cyrillic script), Arabic, Hindi (Devanagari script), and Thai. This broad language coverage substantially enhances the applicability of our system to multilingual and globalized document processing scenarios.
Released PP-OCRv5 Multilingual Recognition Model:
- Improved the accuracy and coverage of Latin script recognition; added support for Cyrillic, Arabic, Devanagari, Telugu, Tamil, and other language systems, covering recognition of 109 languages. The model has only 2M parameters, and the accuracy of some models has increased by over 40% compared to the previous generation.

Significant Model Additions:
- Introduced training, inference, and deployment for PP-OCRv5 recognition models in English, Thai, and Greek. The PP-OCRv5 English model delivers an 11% improvement in English scenarios compared to the main PP-OCRv5 model, with the Thai and Greek recognition models achieving accuracies of 82.68% and 89.28%, respectively.
Deployment Capability Upgrades:
- Full support for PaddlePaddle framework versions 3.1.0 and 3.1.1.
- Comprehensive upgrade of the PP-OCRv5 C++ local deployment solution, now supporting both Linux and Windows, with feature parity and identical accuracy to the Python implementation.
- High-performance inference now supports CUDA 12, and inference can be performed using either the Paddle Inference or ONNX Runtime backends.
- The high-stability service-oriented deployment solution is now fully open-sourced, allowing users to customize Docker images and SDKs as required.
- The high-stability service-oriented deployment solution also supports invocation via manually constructed HTTP requests, enabling client-side code development in any programming language.
Benchmark Support:
- All production lines now support fine-grained benchmarking, enabling measurement of end-to-end inference time as well as per-layer and per-module latency data to assist with performance analysis. Here's how to set up and use the benchmark feature.
- Documentation has been updated to include key metrics for commonly used configurations on mainstream hardware, such as inference latency and memory usage, providing deployment references for users.
Bug Fixes:
- Resolved the issue of failed log saving during model training.
- Upgraded the data augmentation component for formula models for compatibility with newer versions of the albumentations dependency, and fixed deadlock warnings when using the tokenizers package in multi-process scenarios.
- Fixed inconsistencies in switch behaviors (e.g., use_chart_parsing) in the PP-StructureV3 configuration files compared to other pipelines.
Other Enhancements:
- Separated core and optional dependencies. Only minimal core dependencies are required for basic text recognition; additional dependencies for document parsing and information extraction can be installed as needed.
- Enabled support for NVIDIA RTX 50 series graphics cards on Windows; users can refer to the installation guide for the corresponding PaddlePaddle framework versions.
- PP-OCR series models now support returning single-character coordinates.
- Added AIStudio, ModelScope, and other model download sources, allowing users to specify the source for model downloads.
- Added support for chart-to-table conversion via the PP-Chart2Table module.
- Optimized documentation descriptions to improve usability.

PaddleOCR official website provides interactive Experience Center and APIs—no setup required, just one click to experience.

Step 2: Local Deployment

For local usage, please refer to the following documentation based on your needs:

PP-OCR Series: See PP-OCR Documentation
PaddleOCR-VL Series: See PaddleOCR-VL Documentation
PP-StructureV3: See PP-StructureV3 Documentation
More Capabilities: See More Capabilities Documentation

Convert models to ONNX format: Obtaining ONNX Models.
Accelerate inference using engines like OpenVINO, ONNX Runtime, TensorRT, or perform inference using ONNX format models: High-Performance Inference.
Accelerate inference using multi-GPU and multi-process: Parallel Inference for Pipelines.
Integrate PaddleOCR into applications written in C++, C#, Java, etc.: Serving.

🔄 Quick Overview of Execution Results

⭐ Star this repository to keep up with exciting updates and new releases, including powerful OCR and document parsing capabilities! ⭐

👩‍👩‍👧‍👦 Community

PaddlePaddle WeChat official account	Join the tech discussion group
<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr/README/qrcode_for_paddlepaddle_official_account.jpg" width="150">	<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr/README/qr_code_for_the_questionnaire.jpg" width="150">

😃 Awesome Projects Leveraging PaddleOCR

PaddleOCR wouldn't be where it is today without its incredible community! 💗 A massive thank you to all our longtime partners, new collaborators, and everyone who's poured their passion into PaddleOCR — whether we've named you or not. Your support fuels our fire!

Project Name	Description
Dify <a href="https://github.com/langgenius/dify"><img src="https://img.shields.io/github/stars/langgenius/dify"></a>	Production-ready platform for agentic workflow development.
RAGFlow <a href="https://github.com/infiniflow/ragflow"><img src="https://img.shields.io/github/stars/infiniflow/ragflow"></a>	RAG engine based on deep document understanding.
pathway <a href="https://github.com/pathwaycom/pathway"><img src="https://img.shields.io/github/stars/pathwaycom/pathway"></a>	Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.
MinerU <a href="https://github.com/opendatalab/MinerU"><img src="https://img.shields.io/github/stars/opendatalab/MinerU"></a>	Multi-type Document to Markdown Conversion Tool
Umi-OCR <a href="https://github.com/hiroi-sora/Umi-OCR"><img src="https://img.shields.io/github/stars/hiroi-sora/Umi-OCR"></a>	Free, Open-source, Batch Offline OCR Software.
cherry-studio <a href="https://github.com/CherryHQ/cherry-studio"><img src="https://img.shields.io/github/stars/CherryHQ/cherry-studio"></a>	A desktop client that supports for multiple LLM providers.
haystack<a href="https://github.com/deepset-ai/haystack"><img src="https://img.shields.io/github/stars/deepset-ai/haystack"></a>	AI orchestration framework to build customizable, production-ready LLM applications.
OmniParser<a href="https://github.com/microsoft/OmniParser"><img src="https://img.shields.io/github/stars/microsoft/OmniParser"></a>	OmniParser: Screen Parsing tool for Pure Vision Based GUI Agent.
QAnything<a href="https://github.com/netease-youdao/QAnything"><img src="https://img.shields.io/github/stars/netease-youdao/QAnything"></a>	Question and Answer based on Anything.
Learn more projects	More projects based on PaddleOCR

👩‍👩‍👧‍👦 Contributors

This project is released under the Apache 2.0 license.

@misc{cui2025paddleocr30technicalreport,
      title={PaddleOCR 3.0 Technical Report}, 
      author={Cheng Cui and Ting Sun and Manhui Lin and Tingquan Gao and Yubo Zhang and Jiaxuan Liu and Xueqing Wang and Zelun Zhang and Changda Zhou and Hongen Liu and Yue Zhang and Wenyu Lv and Kui Huang and Yichao Zhang and Jing Zhang and Jun Zhang and Yi Liu and Dianhai Yu and Yanjun Ma},
      year={2025},
      eprint={2507.05595},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2507.05595}, 
}

@misc{cui2025paddleocrvlboostingmultilingualdocument,
      title={PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model}, 
      author={Cheng Cui and Ting Sun and Suyin Liang and Tingquan Gao and Zelun Zhang and Jiaxuan Liu and Xueqing Wang and Changda Zhou and Hongen Liu and Manhui Lin and Yue Zhang and Yubo Zhang and Handong Zheng and Jing Zhang and Jun Zhang and Yi Liu and Dianhai Yu and Yanjun Ma},
      year={2025},
      eprint={2510.14528},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2510.14528}, 
}

@misc{cui2026paddleocrvl15multitask09bvlm,
      title={PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing}, 
      author={Cheng Cui and Ting Sun and Suyin Liang and Tingquan Gao and Zelun Zhang and Jiaxuan Liu and Xueqing Wang and Changda Zhou and Hongen Liu and Manhui Lin and Yue Zhang and Yubo Zhang and Yi Liu and Dianhai Yu and Yanjun Ma},
      year={2026},
      eprint={2601.21957},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2601.21957}, 
}

@misc{zhang2026paddleocrvl16expandingfrontierdocument,
      title={PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training}, 
      author={Zelun Zhang and Hongen Liu and Suyin Liang and Yubo Zhang and Yiqing Xiang and Jiaxuan Liu and Ting Sun and Manhui Lin and Yue Zhang and Changda Zhou and Tingquan Gao and Cheng Cui and Yi Liu and Dianhai Yu and Yanjun Ma},
      year={2026},
      eprint={2606.03264},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2606.03264}, 
}

Who it's for

Why It Matters

Notable specifics

🚀 Key Features

📄 Intelligent Document Parsing (LLM-Ready)

🔍 Universal Text Recognition (Scene OCR)

🛠️ Developer-Centric Ecosystem

📣 Recent updates

🔥 2026.05.28: Release of PaddleOCR 3.6.0

🚀 Quick Start

Step 1: Try Online

Step 2: Local Deployment

🧩 More Features

🔄 Quick Overview of Execution Results

PP-OCRv5

PP-StructureV3

PaddleOCR-VL

✨ Stay Tuned

👩‍👩‍👧‍👦 Community

😃 Awesome Projects Leveraging PaddleOCR

👩‍👩‍👧‍👦 Contributors

🌟 Star

📄 License

🎓 Citation