PaddleOCR
PaddleOCR是支持100+语言的开源OCR工具包,可将PDF、图片等文档转换为结构化数据,适配大模型相关应用的搭建需求。
这个项目值得继续研究吗?
PaddleOCR是支持100+语言的开源OCR工具包,可将PDF、图片等文档转换为结构化数据,适配大模型相关应用的搭建需求。
- 解决什么问题
- 企业日常经营中存在大量扫描件、图片、PDF格式的非结构化文档,手动提取信息效率低、差错率高,现有解析工具对多语言、复杂版式、生僻内容识别效果不佳,也难直接对接大模型应用。
- 适合什么团队
- 需要开展文档数字化、知识库建设、RAG(检索增强生成,一种将外部知识库接入大模型的技术)应用搭建的企业业务、AI开发团队均可使用。
- 使用前注意
- 项目采用Apache-2.0开源许可,可免费商用;支持多操作系统与硬件部署,具体配置要求需参考对应版本的官方文档。
本页用于缩短初步筛选时间,不构成技术、采购或法律结论。 正式使用前请在真实业务数据上验证,并以官方说明与许可证为准。
从官方资料看清能力、部署与采用边界
以下内容依据项目公开 README 或模型卡翻译整理,代码、命令和产品名保持原样。
PaddleOCR项目导读
1. 项目定位
PaddleOCR是开源OCR工具包与文档AI引擎,核心能力是将PDF、图片等非结构化视觉文档转换为大模型可用的结构化数据(支持JSON、Markdown格式),目前已被Dify、RAGFlow等主流AI项目集成,是搭建RAG、智能Agent应用的基础工具。
2. 核心能力
2.1 智能文档解析
搭载VLM(视觉语言模型,可同时处理图像和文本信息的人工智能模型)系列能力:
- PaddleOCR-VL-1.6为0.9B参数量的轻量文档解析视觉语言模型,在OmniDocBench v1.6上准确率达96.3%,支持文本、公式、表格、古籍、生僻字、印章、图表识别,可直接输出Markdown和JSON格式结果。
- PP-StructureV3可实现复杂PDF、图片的结构化转换,相比VLM系列额外提供细粒度坐标信息,包括表格单元格坐标、文本坐标等。
2.2 通用场景文本识别
支持100+语言的文本识别:
- PP-OCRv6单模型即可覆盖中文、英文、日文及46种拉丁系语言共50种语言,无需切换模型即可识别多语言混合文档。
- 除普通版式文档外,支持身份证、街景、书籍、工业零部件等自然场景的文字识别,相比上一代版本检测准确率提升4.6%、识别准确率提升5.1%,CPU端端到端推理速度提升5.2倍。
2.3 生态适配能力
已与Dify、RAGFlow、Pathway、Cherry Studio等主流AI Agent生态产品深度集成;提供完整的高质量数据集构建流程,可作为大模型微调的“数据引擎”;支持多硬件环境的一键部署。
3. 典型使用方式
3.1 在线试用
官方网站提供交互式体验中心和API服务,无需部署即可直接体验功能效果。
3.2 本地部署
可根据业务需求选择对应能力分支,参考官方文档完成部署:
- PP-OCR系列能力参考PP-OCR官方文档
- PaddleOCR-VL系列能力参考PaddleOCR-VL官方文档
- PP-StructureV3能力参考PP-StructureV3官方文档
- 其他扩展能力参考官方总览文档
4. 部署要求
- 软件环境:支持Python 3.83.12版本,兼容Linux、Windows、macOS操作系统。
- 硬件支持:适配CPU、GPU、昆仑芯XPU、昇腾NPU等多种硬件设备。
- 模型选型:提供1.5M参数量的tiny版(适配边缘设备)、7.7M参数量的small版(适配移动端)、34.5M参数量的medium版(适配服务端)三个版本,可按需选择。
5. 近期重要更新
- 2026年7月:上线HPD-Parsing轻量视觉语言模型,主打高吞吐文档解析,公开基准测试峰值吞吐量达4752 tokens/s,兼容OpenAI接口规范,也支持基于vLLM的本地部署,适合对推理效率、部署吞吐量要求高的场景。
- 2026年6月:发布3.7.0版本,PP-OCRv6系列模型准确率、推理速度均有明显提升,单模型支持50种语言,提供三个不同参数量版本适配多场景部署。
- 2026年5月:发布3.6.0版本,PaddleOCR-VL-1.6在OmniDocBench v1.6上准确率达96.3%,在多个基准测试中表现优于同类开源及闭源方案,与上一代VLM模型架构完全一致,可零成本迁移适配。
- 2026年4月:发布3.5.0版本,支持多推理后端无缝切换,新增Word、Excel、PowerPoint格式文档转Markdown能力,解析结果支持导出为DOCX格式,同时发布浏览器端SDK PaddleOCR.js,可直接在浏览器中运行OCR能力。
6. 许可证与采用建议
本项目采用Apache-2.0开源许可,可免费商用,二次开发无需公开源码。 如果你的团队有文档数字化、知识库建设、RAG应用搭建等需求,建议先通过官方在线体验中心测试功能匹配度,符合要求后再根据业务场景选择对应模型部署,对接现有业务系统或AI应用。
官方资料与来源
- ai4science
- chineseocr
- document-parsing
- document-translation
- kie
- ocr
- paddleocr-vl
- pdf-extractor-rag
- pdf-parser
- pdf2markdown
- pp-ocr
- pp-structure
## 🚀 Quick Start ### Step 1: Try Online PaddleOCR official website provides interactive **Experience Center** and **APIs**—no setup required, just one click to experience. 👉 [Visit Official Website](https://www.paddleocr.com) ### Step 2: Local Deployment For local usage, please refer to the following documentation based on your needs: - **PP-OCR Series**: See [PP-OCR Documentation](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/OCR.html) - **PaddleOCR-VL Series**: See [PaddleOCR-VL Documentation](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/PaddleOCR-VL.html) - **PP-StructureV3**: See [PP-StructureV3 Documentation](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/PP-StructureV3.html) - **More Capabilities**: See [More Capabilities Documentation](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/pipeline_overview.html)
该片段来自项目 README,仅用于初步判断;实际部署请以官方文档为准。


核对上游原始说明节选
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.
Global Leading OCR Toolkit & Document AI Engine
English | 简体中文 | 繁體中文 | 日本語 | 한국어 | Français | Русский | Español | العربية
PyPI Downloads Used by python os hardware
AI Studio Ask DeepWiki License
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.
🚀 Key Features
📄 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. PP-OCRv6 supports 50 languages with a single unified model (Chinese, English, Japanese, and 46 Latin-script languages) — no model switching needed for multilingual documents.
- 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-OCRv6 achieves +4.6% detection and +5.1% recognition accuracy over PP-OCRv5, surpassing mainstream Vision-Language Models. 5.2× CPU inference speedup end-to-end.
🛠️ 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).
📣 Recent updates
🔥 2026.07.22: HPD-Parsing is now available
- HPD-Parsing is a lightweight vision-language model designed for high-throughput document parsing. It adopts a hierarchical parallel decoding paradigm and Progressive Multi-Token Prediction (P-MTP), achieving a peak throughput of 4,752 tokens/s on public benchmarks while maintaining competitive parsing accuracy.
- HPD-Parsing supports both OpenAI-compatible serving and local inference through a customized vLLM runtime, making it suitable for document parsing scenarios with high demands on inference efficiency and deployment throughput.
- See the HPD-Parsing usage tutorial for environment setup, serving, and local inference instructions.
2026.06.11: Release of PaddleOCR 3.7.0
- PP-OCRv6 highlights:
- Accuracy boost: Medium tier achieves +4.6% detection and +5.1% recognition over PP-OCRv5server, surpassing mainstream VLMs (Qwen3-VL-235B, GPT-5.5) with only 34.5M parameters.
- 50 languages unified: Single model covers Chinese, English, Japanese, and 46 Latin-script languages — no model switching needed.
- Specialized scenarios: Major improvements in digital displays, dot-matrix characters, tire prints, and industrial text recognition.
- Faster inference: 5.2× CPU speedup (OpenVINO), 6.1× on Apple M4 (tiny), 0.13s on A100 GPU.
- Three tiers for all scenarios: tiny (1.5M) / small (7.7M) / medium (34.5M) for edge, mobile, and server deployment.
- Model availability: All models are available on HuggingFace and ModelScope.
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.
2026.04.21: Release of PaddleOCR 3.5.0
- 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.
2026.01.29: Release of PaddleOCR 3.4.0
- 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 algor
上游文档较长,此处为节选。完整内容见官方项目。