Update docs for a better experience. (#16419)

2026-08-30 17:23:03 +08:00 · 2025-09-08 17:38:54 +08:00
parent f6ef577f44
commit 2cf629dbe6
37 changed files with 340 additions and 94 deletions
@@ -9,7 +9,7 @@ English | [简体中文](./readme/README_cn.md) | [繁體中文](./readme/README
 [![arXiv](https://img.shields.io/badge/arXiv-2507.05595-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2507.05595)
 [![PyPI Downloads](https://static.pepy.tech/badge/paddleocr/month)](https://pepy.tech/project/paddleocr)
 [![PyPI Downloads](https://static.pepy.tech/badge/paddleocr)](https://pepy.tech/project/paddleocr)
-[![Used by](https://img.shields.io/badge/Used%20by-5.8k%2B%20repositories-blue)](https://github.com/PaddlePaddle/PaddleOCR/network/dependents)
+[![Used by](https://img.shields.io/badge/Used%20by-5.9k%2B%20repositories-blue)](https://github.com/PaddlePaddle/PaddleOCR/network/dependents)

 ![python](https://img.shields.io/badge/python-3.8~3.12-aff.svg)
 ![os](https://img.shields.io/badge/os-linux%2C%20win%2C%20mac-pink.svg)
@@ -368,7 +368,7 @@ print(chat_result)
 - [Huawei Ascend](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/other_devices_support/paddlepaddle_install_NPU.html)
 - [KUNLUNXIN](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/other_devices_support/paddlepaddle_install_XPU.html)

-## More Features
+## 🧩 More Features

 - Convert models to ONNX format: [Obtaining ONNX Models](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/obtaining_onnx_models.html).
 - Accelerate inference using engines like OpenVINO, ONNX Runtime, TensorRT, or perform inference using ONNX format models: [High-Performance Inference](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/high_performance_inference.html).
@@ -394,16 +394,32 @@ print(chat_result)
  </p>
 </div>

+
+## ✨ Stay Tuned
+
+⭐ **Star this repository to keep up with exciting updates and new releases, including powerful OCR and document parsing capabilities!** ⭐
+
+<div align="center">
+  <p>
+       <img width="1200" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/star_paddleocr.en.gif" alt="Star-Project">
+  </p>
+</div>
+
 ## 👩‍👩‍👧‍👦 Community

+<div align="center">
+
 | 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"> |
+</div>


 ## 😃 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!

+<div align="center">
+
 | Project Name | Description |
 | ------------ | ----------- |
 | [RAGFlow](https://github.com/infiniflow/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.|
@@ -414,17 +430,23 @@ PaddleOCR wouldn't be where it is today without its incredible community! 💗 A
 | [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit) <a href="https://github.com/opendatalab/PDF-Extract-Kit"><img src="https://img.shields.io/github/stars/opendatalab/PDF-Extract-Kit"></a>|A powerful open-source toolkit designed to efficiently extract high-quality content from complex and diverse PDF documents.|
 | [Dango-Translator](https://github.com/PantsuDango/Dango-Translator)<a href="https://github.com/PantsuDango/Dango-Translator"><img src="https://img.shields.io/github/stars/PantsuDango/Dango-Translator"></a> |Recognize text on the screen, translate it and show the translation results in real time.|
 | [Learn more projects](./awesome_projects.md) | [More projects based on PaddleOCR](./awesome_projects.md)|
+</div>

 ## 👩‍👩‍👧‍👦 Contributors

+<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>

 ## 🌟 Star

-[![Star History Chart](https://api.star-history.com/svg?repos=PaddlePaddle/PaddleOCR&type=Date)](https://star-history.com/#PaddlePaddle/PaddleOCR&Date)
+<div align="center">
+  <p>
+      <img width="800" src="https://api.star-history.com/svg?repos=PaddlePaddle/PaddleOCR&type=Date" alt="Star-history">
+  </p>
+</div>


 ## 📄 License
@@ -22,7 +22,7 @@ Since GPU installation requires specific CUDA versions, the following example is
 python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
 ```

-**Please note that PaddleOCR depends on PaddlePaddle version `3.0` or above.**
+**Please note that PaddleOCR 3.x depends on PaddlePaddle version `3.0` or above.**

 #### 2. Install `paddleocr`

@@ -20,7 +20,7 @@ GPU端安装，由于GPU端需要根据具体CUDA版本来对应安装使用，
 python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
 ```

-**请注意，PaddleOCR 依赖于 `3.0` 及以上版本的飞桨框架。**
+**请注意，PaddleOCR 3.x版本 依赖于 `3.0` 及以上版本的飞桨框架。**

 #### 2. 安装`paddleocr`

@@ -1507,22 +1507,33 @@ The serving inference test is based on the NVIDIA A100 + Intel Xeon Platinum 835

 # FAQ

-1. What is the default configuration? How to get higher accuracy, faster speed, or smaller GPU memory?
+**Q: What is the default model configuration? If I need higher accuracy, faster speed, or lower GPU memory usage, which parameters should I adjust or which models should I switch to? How significant is the impact on results?**

-When using mobile OCR models + PP-FormulaNet_plus-M, and max length of text detection set to 1200, if set use_chart_recognition to False and dont not load the chart recognition model, the GPU memory would be reduced. 
+**A:** By default, the largest models for each module are used. Section 3.3 demonstrates how different model selections affect GPU memory consumption and inference speed. You can choose an appropriate model based on your device capabilities and the complexity of your samples. Additionally, in the Python API or CLI, you can set the device parameter as `<device_type>:<device_id1>,<device_id2>...` (e.g., `gpu:0,1,2,3`) to enable multi-GPU parallel inference. If the built-in multi-GPU parallel inference does not meet your speed requirements, you may refer to the example code for multi-process parallel inference and further optimize it for your specific scenario: [Multi-process Parallel Inference](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/instructions/parallel_inference.html).

-On the V100, the peak and average GPU memory would be reduced from 8776.0 MB and 8680.8 MB to 6118.0 MB and 6016.7 MB, respectively; On the A100, the peak and average GPU memory would be reduced from 11716.0 MB and 11453.9 MB to 9850.0 MB and 9593.5 MB, respectively.
+---

-You can using multi-gpus by setting `device` to `gpu:<no.>,<no.>`, such as `gpu:0,1,2,3`. And about multi-process parallel inference, you can refer: [Multi-Process Parallel Inference](https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/pipeline_usage/instructions/parallel_inference.en.md#example-of-multi-process-parallel-inference).
+**Q: Can PP-StructureV3 run on CPU?**

-2. About serving deployment
+**A:** While PP-StructureV3 is recommended to run on GPU for optimal performance, it also supports CPU inference. Thanks to a variety of configuration options and sufficient optimization for lightweight models, users can refer to section 3.3 to select lightweight configurations for CPU-only environments. For example, on an Intel 8350C CPU, the inference time per image is about 3.74 seconds.

-(1) Can the service handle requests concurrently?
+---

-For the basic serving deployment solution, the service processes only one request at a time. This plan is mainly used for rapid verification, to establish the development chain, or for scenarios where concurrent requests are not required.
+**Q: How can I integrate PP-StructureV3 into my own project?**

-For high-stability serving deployment solution, the service process only one request at a time by default, but you can refer to the related docs to adjust achieve scaling.
+**A:**  
+- For Python projects, you can directly integrate using the PaddleOCR Python API.  
+- For projects in other programming languages, it is recommended to use service-based deployment. PaddleOCR supports client-side integration in multiple languages, including C++, C#, Java, Go, and PHP. Please refer to the [official documentation](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/PP-StructureV3.html#3-development-integration-deployment) for details.  
+- If you need to interact with large language models, PaddleOCR also provides the MCP service. For more information, please refer to the [MCP Server documentation](https://www.paddleocr.ai/latest/en/version3.x/deployment/mcp_server.html).

-（2）How to reduce latency and improve throughput?
+---

-Use the High-performance inference plugin, and deploy multi instances.
+**Q: Can the serving handle concurrent requests?**
+
+**A:** In the basic service deployment solution, the service processes only one request at a time, which is mainly intended for quick validation, development pipeline integration, or scenarios that do not require concurrent processing. In the high-stability serving solution, the service also processes one request at a time by default, but users can achieve horizontal scaling and concurrent processing by adjusting the configuration as outlined in the service deployment guide.
+
+---
+
+**Q: How can I reduce latency and increase throughput in serving?**
+
+**A:** PaddleOCR offers two types of service deployment solutions. Regardless of the solution used, enabling high-performance inference plugins can accelerate model inference and thus reduce latency. For the high-stability deployment solution, throughput can be further increased by adjusting the service configuration to run multiple instances, making full use of your hardware resources. Please refer to the [documentation](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_deploy/serving.html#22-adjust-configurations) for more details on configuring high-stability serving.
@@ -1,11 +1,13 @@
 # 一、PP-StructureV3 简介
-**PP-StructureV3** 产线在通用版面解析v1产线的基础上，强化了版面区域检测、表格识别、公式识别的能力，增加了图表理解和多栏阅读顺序的恢复能力、结果转换 Markdown 文件的能力，在多种文档数据中，表现优异，可以处理较复杂的文档数据。本产线同时提供了灵活的服务化部署方式，支持在多种硬件上使用多种编程语言调用。不仅如此，本产线也提供了二次开发的能力，您可以基于本产线在您自己的数据集上训练调优，训练后的模型也可以无缝集成。
+PP-StructureV3 能够将文档图像和 PDF 文件高效转换为结构化内容（如 Markdown 格式），并具备版面区域检测、表格识别、公式识别、图表理解以及多栏阅读顺序恢复等强大功能。该工具在多种文档类型下均表现优异，能够处理复杂的文档数据。PP-StructureV3 支持灵活的服务化部署，兼容多种硬件环境，并可通过多种编程语言进行调用。同时，支持二次开发，用户可以基于自有数据集进行模型训练和优化，训练后的模型可实现无缝集成。

 <div align="center">
-<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr/PP-StructureV3/algorithm_ppstructurev3.png" width="600"/>
+<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr/PP-StructureV3/algorithm_ppstructurev3.png" width="800"/>
 </div>

 # 二、关键指标
+
+<div align="center">
 <table>
  <thead>
    <tr>
@@ -296,6 +298,7 @@
  </tr> 
 </tbody>
 </table>
+</div>

 以上部分数据出自：
 * <a href="https://github.com/opendatalab/OmniDocBench">OmniDocBench</a>
@@ -1492,27 +1495,39 @@

 <div align="center">
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr/PP-StructureV3/algorithm_ppstructurev3_demo.png" width="600"/>
-</div>
+</div> 

 <a href="https://paddle-model-ecology.bj.bcebos.com/paddlex%2FPaddleX3.0%2Fdoc_images%2FPP-StructureV3%2Falgorithm_ppstructurev3_demo.pdf">更多示例</a>

 # 五、使用方法和常见问题

-1. 默认模型是什么配置，如果需要更高精度、更快速度、或者更小显存，应该调哪些参数或者更换哪些模型，对结果影响大概有多大？
+**Q:默认模型是什么配置，如果需要更高精度、更快速度、或者更小显存，应该调哪些参数或者更换哪些模型，对结果影响大概有多大？**

-在“使用轻量OCR模型+轻量公式模型，文本检测max 1200”的基础上，将产线配置文件中的use_chart_recognition设置为False，不加载图表识别模型，可以进一步减少显存用量。在V100测试环境中，峰值和平均显存用量分别从8776.0 MB和8680.8 MB降低到6118.0 MB和6016.7 MB；在A100测试环境中，峰值和平均显存用量分别从11716.0 MB和11453.9 MB降低到9850.0 MB和9593.5 MB。
-在Python API或CLI设置device为<设备类型>:<设备编号1>,<设备编号2>...（例如gpu:0,1,2,3）可实现多卡并行推理。如果内置的多卡并行推理功能提速效果仍不满足预期，可参考多进程并行推理示例代码，结合具体场景进行进一步优化：[多进程并行推理](https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/pipeline_usage/instructions/parallel_inference.md#%E5%A4%9A%E8%BF%9B%E7%A8%8B%E5%B9%B6%E8%A1%8C%E6%8E%A8%E7%90%86%E7%A4%BA%E4%BE%8B)。
+**A:** 默认模型均采用了了各个模块参数量最大的模型，3.3 章节中展示了不同的模型选择对于显存和推理速度的影响。可以根据设备情况和样本难易程度选择合适的模型。另外，在 Python API 或 CLI 设置 device 为<设备类型>:<设备编号1>,<设备编号2>...（例如gpu:0,1,2,3）可实现多卡并行推理。如果内置的多卡并行推理功能提速效果仍不满足预期，可参考多进程并行推理示例代码，结合具体场景进行进一步优化：[多进程并行推理](https://www.paddleocr.ai/latest/version3.x/pipeline_usage/instructions/parallel_inference.html)。

-2. 服务化部署的常见问题
+---

-（1）服务可以并发处理请求吗？
+**Q: PP-StructureV3 是否可以在 CPU 上运行？**

-对于基础服务化部署方案，服务同一时间只处理一个请求，该方案主要用于快速验证、打通开发链路，或者用在不需要并发请求的场景；
+**A:** PP-StructureV3 虽然更推荐在 GPU 环境下进行推理，但也支持在 CPU 上运行。得益于多种配置选项及对轻量级模型的充分优化，在仅有 CPU 环境时，用户可以参考 3.3 节选择轻量化配置进行推理。例如，在 Intel 8350C CPU 上，每张图片的推理时间约为 3.74 秒。

-对于高稳定性服务化部署方案，服务默认在同一时间只处理一个请求，但用户可以参考服务化部署指南，通过调整配置实现水平扩展，以使服务同时处理多个请求。
+---

-（2）如何降低时延、提升吞吐？
+**Q: 如何将 PP-StructureV3 集成到自己的项目中？**

-无论使用哪一种服务化部署方案，都可以通过启用高性能推理插件提升模型推理速度，从而降低处理时延。
+**A:**  
+- 对于 Python 项目，可以直接使用 PaddleOCR 的 Python API 完成集成。  
+- 对于其他编程语言，建议通过服务化部署方式集成。PaddleOCR 支持包括 C++、C#、Java、Go、PHP 等多种语言的客户端调用方式，具体集成方法可参考 [官方文档](https://www.paddleocr.ai/latest/version3.x/pipeline_usage/PP-StructureV3.html#3)。  
+- 如果需要与大模型进行交互，PaddleOCR 还提供了 MCP 服务，详细说明可参考 [MCP 服务器](https://www.paddleocr.ai/latest/version3.x/deployment/mcp_server.html)。

-此外，对于高稳定性服务化部署方案，通过调整服务配置，设置多个实例，也可以充分利用部署机器的资源，有效提升吞吐。
+---
+
+**Q:服务化部署可以并发处理请求吗？**
+
+**A:** 对于基础服务化部署方案，服务同一时间只处理一个请求，该方案主要用于快速验证、打通开发链路，或者用在不需要并发请求的场景；对于高稳定性服务化部署方案，服务默认在同一时间只处理一个请求，但用户可以参考服务化部署指南，通过调整配置实现水平扩展，以使服务同时处理多个请求。
+
+---
+
+**Q: 服务化部署如何降低时延、提升吞吐？**
+
+**A:** PaddleOCR 提供的2种服务化部署方案，无论使用哪一种方案，都可以通过启用高性能推理插件提升模型推理速度，从而降低处理时延。此外，对于高稳定性服务化部署方案，通过调整服务配置，设置多个实例，也可以充分利用部署机器的资源，有效提升吞吐。高稳定性服务化部署方案调整配置可以参考[文档](https://paddlepaddle.github.io/PaddleX/latest/pipeline_deploy/serving.html#22)。
@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # High-Performance Inference

 In real-world production environments, many applications have stringent performance requirements for deployment strategies, particularly regarding response speed, to ensure efficient system operation and a smooth user experience. PaddleOCR provides high-performance inference capabilities, allowing users to enhance model inference speed with a single click without worrying about complex configurations or underlying details. Specifically, PaddleOCR's high-performance inference functionality can:
@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # 高性能推理

 在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。PaddleOCR 提供高性能推理能力，让用户无需关注复杂的配置和底层细节，一键提升模型的推理速度。具体而言，PaddleOCR 的高性能推理功能能够：
@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # PaddleOCR MCP Server

 [![PaddleOCR](https://img.shields.io/badge/OCR-PaddleOCR-orange)](https://github.com/PaddlePaddle/PaddleOCR)
@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # PaddleOCR MCP 服务器

 [![PaddleOCR](https://img.shields.io/badge/OCR-PaddleOCR-orange)](https://github.com/PaddlePaddle/PaddleOCR)
@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # Obtaining ONNX Models

 PaddleOCR provides a rich collection of pre-trained models, all stored in PaddlePaddle's static graph format. To use these models in ONNX format during deployment, you can convert them using the Paddle2ONNX plugin provided by PaddleX. For more information about PaddleX and its relationship with PaddleOCR, refer to [Differences and Connections Between PaddleOCR and PaddleX](../paddleocr_and_paddlex.en.md#1-Differences-and-Connections-Between-PaddleOCR-and-PaddleX).
@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # 获取 ONNX 模型

 PaddleOCR 提供了丰富的预训练模型，这些模型均采用飞桨的静态图格式进行存储。若需在部署阶段使用 ONNX 格式的模型，可借助 PaddleX 提供的 Paddle2ONNX 插件进行转换。关于 PaddleX 及其与 PaddleOCR 之间的关系，请参考 [PaddleOCR 与 PaddleX 的区别与联系](../paddleocr_and_paddlex.md#1-paddleocr-与-paddlex-的区别与联系)。
@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # OCR On-Device Deployment Demo Usage Guide

 - [Quick Start](#quick-start)
@@ -343,7 +347,7 @@ For detailed instructions on converting `.nb` models using the Python script met
 **Notes**

 - For detailed information about the model optimization tool `opt`, refer to Paddle-Lite's [Model Optimization Tool opt](https://www.paddlepaddle.org.cn/lite/v2.12/user_guides/model_optimize_tool.html).
- Currently, only static graph models in `.pdmodel` format can be converted to `.nb` format.
+- Currently, only static graph models in `.pdmodel` format can be converted to `.nb` format. In PaddlePaddle version 3.0 and above, the default exported model format is `.json`. If you want to export the model in `.pdmodel` format, simply add `-o Global.export_with_pir=False` during export.

 ### Updating Models, Label Files, and Prediction Images

@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # OCR 端侧部署 demo 使用指南

 - [快速开始](#快速开始)
@@ -343,7 +347,7 @@ OCR 文字识别 demo 由三个模型一起完成 OCR 文字识别功能，对
 **注意**

 - 有关模型优化工具 opt 的详细介绍，可参考 Paddle-Lite 仓库的[模型优化工具 opt](https://www.paddlepaddle.org.cn/lite/v2.12/user_guides/model_optimize_tool.html)
- 目前仅支持将 `.pdmodel` 格式的静态图模型转换为 `.nb` 格式。
+- 目前仅支持将 `.pdmodel` 格式的静态图模型转换为 `.nb` 格式。在 PaddlePaddle 3.0 以上的版本，默认导出为 `.json` 的模型，如果希望导出为 `.pdmodel` 格式的模型，导出时加上 `-o Global.export_with_pir=False` 即可。

 ### 更新模型、标签文件和预测图片

@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # Package PaddleOCR Projects

 This guide applies to packaging PaddleOCR projects using PyInstaller.
@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # 打包PaddleOCR项目

 本说明适用于通过PyInstaller打包PaddleOCR项目。
@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # Serving

 Serving is a common deployment method in real-world production environments. By encapsulating inference capabilities as services, clients can access these services via network requests to obtain inference results. **The client-side code can be written in different programming languages and does not need to match the server-side code.** PaddleOCR recommends using [PaddleX](https://github.com/PaddlePaddle/PaddleX) for serving. Please refer to [Differences and Connections between PaddleOCR and PaddleX](../paddleocr_and_paddlex.en.md#1-Differences-and-Connections-Between-PaddleOCR-and-PaddleX) to understand the relationship between PaddleOCR and PaddleX.
@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # 服务化部署

 服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。**客户端代码可以由不同的编程语言编写，而不必与服务端代码保持一致。** PaddleOCR 推荐用户使用 [PaddleX](https://github.com/PaddlePaddle/PaddleX) 进行服务化部署。请阅读 [PaddleOCR 与 PaddleX 的区别与联系](../paddleocr_and_paddlex.md#1-paddleocr-与-paddlex-的区别与联系) 了解 PaddleOCR 与 PaddleX 的关系。
@@ -138,7 +138,7 @@ To perform model training, exporting, etc., first clone the repository to your l
 git clone https://github.com/PaddlePaddle/PaddleOCR

 # (Optional) Switch to a specific branch
-git checkout release/3.0
+git checkout release/3.2

 # If you encounter network issues preventing successful cloning, you can also use the repository on Gitee:
 git clone https://gitee.com/paddlepaddle/PaddleOCR
@@ -135,7 +135,7 @@ python -m pip install "paddleocr@git+https://github.com/PaddlePaddle/PaddleOCR.g
 git clone https://github.com/PaddlePaddle/PaddleOCR

 # （可选）切换到指定分支
-git checkout release/3.0
+git checkout release/3.2

 # 如果因为网络问题无法克隆成功，也可选择使用码云上的仓库：
 git clone https://gitee.com/paddlepaddle/PaddleOCR
@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # Logging

 This document mainly introduces how to configure the logging system for the PaddleOCR inference package. It's important to note that PaddleOCR's inference package uses a different logging system than the training scripts, and this document does not cover the configuration of the logging system used in the training scripts.
@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # 日志

 本文档主要介绍如何配置 PaddleOCR 推理包的日志系统。需要注意的是，PaddleOCR 推理包与训练脚本使用的是不同的日志系统，本文档不涉及训练脚本所使用的日志系统的配置方法。
@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # PaddleOCR and PaddleX

 [PaddleX](https://github.com/PaddlePaddle/PaddleX) is a low-code development tool built on the PaddlePaddle framework. It integrates numerous out-of-the-box pre-trained models, supports the full-pipeline development from model training to inference, and is compatible with various mainstream hardware both domestically and internationally, empowering AI developers to efficiently deploy solutions in industrial practices.
@@ -1,3 +1,7 @@
+---
+comments: true
+---
+
 # PaddleOCR 与 PaddleX

 [PaddleX](https://github.com/PaddlePaddle/PaddleX) 是一款基于飞桨框架构建的低代码开发工具，集成了众多开箱即用的预训练模型，支持模型从训练到推理的全流程开发，兼容多款国内外主流硬件，助力 AI 开发者在产业实践中高效落地。
@@ -1,3 +1,9 @@
+---
+comments: true
+hide:
+  - toc
+---
+
 ## 1. Introduction to All-in-One Development

 The All-in-One development tool [PaddleX](https://github.com/PaddlePaddle/PaddleX/tree/release/3.0-beta1), based on the advanced technology of PaddleOCR, supports **low-code full-process** development capabilities in the OCR field. Through low-code development, simple and efficient model use, combination, and customization can be achieved. This will significantly **reduce the time consumption** of model development, **lower its development difficulty**, and greatly accelerate the application and promotion speed of models in the industry. Features include:
@@ -1,27 +1,41 @@
+---
+comments: true
+hide:
+  - toc
+---
+
 # ⏭️ Quick Start

+> **Note:**
+
+>* The low-code development tool [PaddleX](https://github.com/PaddlePaddle/PaddleX) by PaddlePaddle leverages the advanced technology of PaddleOCR to support **end-to-end low-code development** capabilities in the OCR field. With low-code development, users can achieve simple and efficient model usage, combination, and customization.
+
+>* PaddleX is dedicated to enabling production-level model training, inference, and deployment. A model pipeline refers to a series of predefined development processes for specific AI tasks, including combinations of single models (single-function modules) that can independently accomplish certain tasks. This document provides quick inference usage for **OCR-related pipelines**. For quick usage of single-function modules and more features, please refer to the relevant sections in [Low-Code End-to-End Development with PaddleOCR](https://www.paddleocr.ai/latest/version3.x/paddlex/overview.html).
+
+>* For information about the relationship between PaddleOCR and PaddleX, please refer to the [Introduction to the Relationship between PaddleOCR and PaddleX](https://www.paddleocr.ai/latest/version3.x/paddleocr_and_paddlex.html).
+
 ## 🛠️ Installation

-> ❗Before installing PaddleX, please ensure you have a basic **Python runtime environment** (Note: Currently supports running under Python 3.8 to Python 3.10, with more Python versions under adaptation). The PaddlePaddle version required by PaddleX
+> ❗Before installing PaddleX, please make sure you have a basic **Python runtime environment** (Note: Currently, Python 3.8 to Python 3.12 are supported). PaddleX version 3.2 requires PaddlePaddle version 3.0.0 or higher as a dependency.

 * **Installing PaddlePaddle**

 ```bash
 # CPU
-python -m pip install paddlepaddle==3.0.0rc0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
+python -m pip install paddlepaddle==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/

 # gpu，requires GPU driver version ≥450.80.02 (Linux) or ≥452.39 (Windows)
-python -m pip install paddlepaddle-gpu==3.0.0rc0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
+python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/

-# gpu，requires GPU driver version ≥545.23.06 (Linux) or ≥545.84 (Windows)
-python -m pip install paddlepaddle-gpu==3.0.0rc0 -i https://www.paddlepaddle.org.cn/packages/stable/cu123/
+# gpu，requires GPU driver version ≥550.54.14 (Linux) or ≥550.54.14 (Windows)
+python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
 ```
 > ❗No need to focus on the CUDA version on the physical machine, only the GPU driver version needs attention. For more information on PaddlePaddle Wheel versions, please refer to the [PaddlePaddle Official Website](https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation./docs/en/install/pip/linux-pip.html).

 * **Installing PaddleX**

 ```bash
-pip install https://paddle-model-ecology.bj.bcebos.com/paddlex/whl/paddlex-3.0.0rc0-py3-none-any.whl
+pip install "paddlex[ocr]"
 ```

 > ❗For more installation methods, refer to the [PaddleX Installation Guide](https://paddlepaddle.github.io/PaddleX/latest/en/installation/installation.html).
@@ -81,7 +95,7 @@ To use the command line for other pipelines, simply adjust the `pipeline` parame
 | Formula Recognition              | `paddlex --pipeline formula_recognition --input https://paddle-model-ecology.bj.bcebos.com/paddlex/demo_image/general_formula_recognition.png --use_layout_detection True --use_doc_orientation_classify False --use_doc_unwarping False --layout_threshold 0.5 --layout_nms True --layout_unclip_ratio  1.0 --layout_merge_bboxes_mode large --save_path ./output --device gpu:0`                                      |
 | Seal Recognition            | `paddlex --pipeline seal_recognition --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/seal_text_det.png --use_doc_orientation_classify False --use_doc_unwarping False --device gpu:0 --save_path ./output`                                      |
 | Layout Parsing           | `paddlex --pipeline layout_parsing --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/demo_paper.png --use_doc_orientation_classify False --use_doc_unwarping False --use_textline_orientation False --save_path ./output --device gpu:0`                      |
-| Layout Parsing v2        | `paddlex --pipeline layout_parsing_v2 --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/layout_parsing_v2_demo.png --use_doc_orientation_classify False --use_doc_unwarping False --use_textline_orientation False --save_path ./output --device gpu:0`                      |
+| PP-StructureV3        | `paddlex --pipeline PP-StructureV3 --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/pp_structure_v3_demo.png --use_doc_orientation_classify False --use_doc_unwarping False --use_textline_orientation False --save_path ./output --device gpu:0`                      |



@@ -110,13 +124,13 @@ To use the Python script for other pipelines, simply adjust the `pipeline` param

 | pipeline Name           | Corresponding Parameter               | Detailed Explanation                                                                                                      |
 |-------------------------------|-------------------------------------|---------------------------------------------------------------------------------------------------------------|
-| OCR | `OCR` | [Instructions for Using the General OCR Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/OCR.html#222-python-script-integration) |
-| Document Image Preprocessing | `doc_preprocessor` | [Instructions for Using the Document Image Preprocessing Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/doc_preprocessor.html#212-python-script-integration) |
-| Table Recognition | `table_recognition` | [Instructions for Using the General Table Recognition Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/table_recognition.html#22-python-script-integration) |
-| Table Recognition v2 | `table_recognition_v2` | [Instructions for Using the General Table Recognition v2 Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/table_recognition_v2.html#22-python-script-integration) |
-| Formula Recognition | `formula_recognition` | [Instructions for Using the Formula Recognition Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.html#22-python-script-integration) |
-| Seal Recognition | `seal_recognition` | [Instructions for Using the Seal Text Recognition Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.html#22-python-script-integration) |
-| Layout Parsing | `layout_parsing` | [Instructions for Using the General Layout Parsing Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.html#22-python-script-integration) |
-| Layout Parsing v2 | `layout_parsing_v2` | [Instructions for Using the General Layout Parsing v2 Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/layout_parsing_v2.html#22-python-script-integration) |
-| PP-ChatOCRv3-doc   | `PP-ChatOCRv3-doc` | [PP-ChatOCRv3-doc Pipeline Python Script Usage Instructions](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.html) |
-| PP-ChatOCRv4-doc | `PP-ChatOCRv4-doc` | [PP-ChatOCRv4-doc Pipeline Python Script Usage Instructions](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v4.html) |
+| OCR | `OCR` | [Instructions for Using the General OCR Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/ocr_pipelines/OCR.html#222-python-script-integration) |
+| Document Image Preprocessing | `doc_preprocessor` | [Instructions for Using the Document Image Preprocessing Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/ocr_pipelines/doc_preprocessor.html#212-python-script-integration) |
+| Table Recognition | `table_recognition` | [Instructions for Using the General Table Recognition Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/ocr_pipelines/table_recognition.html#22-python-script-integration) |
+| Table Recognition v2 | `table_recognition_v2` | [Instructions for Using the General Table Recognition v2 Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/ocr_pipelines/table_recognition_v2.html#22-integration-via-python-script) |
+| Formula Recognition | `formula_recognition` | [Instructions for Using the Formula Recognition Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.html#222-python-script-integration) |
+| Seal Recognition | `seal_recognition` | [Instructions for Using the Seal Text Recognition Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.html#222-python-script-integration) |
+| Layout Parsing | `layout_parsing` | [Instructions for Using the General Layout Parsing Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.html#22-integrating-via-python-script) |
+| PP-StructureV3 | `P-StructureV3` | [Instructions for Using the P-StructureV3 Pipeline Python Script](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/ocr_pipelines/PP-StructureV3.html#22-python-script-integration) |
+| PP-ChatOCRv3-doc   | `PP-ChatOCRv3-doc` | [PP-ChatOCRv3-doc Pipeline Python Script Usage Instructions](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.html#22-local-experience) |
+| PP-ChatOCRv4-doc | `PP-ChatOCRv4-doc` | [PP-ChatOCRv4-doc Pipeline Python Script Usage Instructions](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v4.html#21-local-experience) |
@@ -1,33 +1,41 @@
+---
+comments: true
+hide:
+  - toc
+---
+
 # 快速开始

 >**说明：**

 >* 飞桨低代码开发工具[PaddleX](https://github.com/PaddlePaddle/PaddleX)，依托于PaddleOCR的先进技术，支持了OCR领域的**低代码全流程**开发能力。通过低代码开发，可实现简单且高效的模型使用、组合与定制。

->* PaddleX 致力于实现产线级别的模型训练、推理与部署。模型产线是指一系列预定义好的、针对特定AI任务的开发流程，其中包含能够独立完成某类任务的单模型（单功能模块）组合。本文档提供**OCR相关产线**的快速推理使用，单功能模块的快速使用以及更多功能请参考[PaddleOCR低代码全流程开发](https://paddlepaddle.github.io/PaddleOCR/latest/paddlex/overview.html)中相关章节。
+>* PaddleX 致力于实现产线级别的模型训练、推理与部署。模型产线是指一系列预定义好的、针对特定AI任务的开发流程，其中包含能够独立完成某类任务的单模型（单功能模块）组合。本文档提供**OCR相关产线**的快速推理使用，单功能模块的快速使用以及更多功能请参考[PaddleOCR低代码全流程开发](https://www.paddleocr.ai/latest/version3.x/paddlex/overview.html)中相关章节。
+
+>* 关于 PaddleOCR 和 PaddleX 的关系，可以查看[ PaddleOCR 与 PaddleX 关系介绍](https://www.paddleocr.ai/latest/version3.x/paddleocr_and_paddlex.html)。


 ### 🛠️ 安装

-> ❗在安装 PaddleX 之前，请确保您已具备基本的 **Python 运行环境**（注：目前支持 Python 3.8 至 Python 3.12）。PaddleX 3.0-rc0 版本依赖的 PaddlePaddle 版本为 3.0.0rc0。
+> ❗在安装 PaddleX 之前，请确保您已具备基本的 **Python 运行环境**（注：目前支持 Python 3.8 至 Python 3.12）。PaddleX 3.2 版本依赖的 PaddlePaddle 版本为 3.0.0 以上版本。

 * **安装 PaddlePaddle**
 ```bash
 # CPU 版本
-python -m pip install paddlepaddle==3.0.0rc0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
+python -m pip install paddlepaddle==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/

 # GPU 版本，需显卡驱动程序版本 ≥450.80.02（Linux）或 ≥452.39（Windows）
-python -m pip install paddlepaddle-gpu==3.0.0rc0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
+python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/

-# GPU 版本，需显卡驱动程序版本 ≥545.23.06（Linux）或 ≥545.84（Windows）
-python -m pip install paddlepaddle-gpu==3.0.0rc0 -i https://www.paddlepaddle.org.cn/packages/stable/cu123/
+# GPU 版本，需显卡驱动程序版本 ≥550.54.14（Linux）或 ≥550.54.14（Windows）
+python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
 ```
 > ❗无需关注物理机上的 CUDA 版本，只需关注显卡驱动程序版本。更多飞桨 Wheel 版本信息，请参考[飞桨官网](https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation./docs/zh/install/pip/linux-pip.html)。

 * **安装PaddleX**

 ```bash
-pip install https://paddle-model-ecology.bj.bcebos.com/paddlex/whl/paddlex-3.0.0rc0-py3-none-any.whl
+pip install "paddlex[ocr]"
 ```

 > ❗ 更多安装方式参考 [PaddleX 安装教程](https://paddlepaddle.github.io/PaddleX/latest/installation/installation.html)
@@ -87,7 +95,7 @@ paddlex --pipeline OCR \
 | 公式识别       | `paddlex --pipeline formula_recognition --input https://paddle-model-ecology.bj.bcebos.com/paddlex/demo_image/general_formula_recognition.png --use_layout_detection True --use_doc_orientation_classify False --use_doc_unwarping False --layout_threshold 0.5 --layout_nms True --layout_unclip_ratio  1.0 --layout_merge_bboxes_mode large --save_path ./output --device gpu:0`                                      |
 | 印章文本识别       | `paddlex --pipeline seal_recognition --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/seal_text_det.png --use_doc_orientation_classify False --use_doc_unwarping False --device gpu:0 --save_path ./output`                                      |
 | 通用版面解析       | `paddlex --pipeline layout_parsing --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/demo_paper.png --use_doc_orientation_classify False --use_doc_unwarping False --use_textline_orientation False --save_path ./output --device gpu:0`                                      |
-| 通用版面解析v2       | `paddlex --pipeline layout_parsing_v2 --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/layout_parsing_v2_demo.png --use_doc_orientation_classify False --use_doc_unwarping False --use_textline_orientation False --save_path ./output --device gpu:0`                                      |
+| 通用版面解析v3       | `paddlex --pipeline PP-StructureV3 --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/pp_structure_v3_demo.png --use_doc_orientation_classify False --use_doc_unwarping False --use_textline_orientation False --save_path ./output --device gpu:0`                                      |


 ### 📝 Python 脚本使用
@@ -115,13 +123,13 @@ for res in output:

 | 产线名称           | 对应参数                           | 详细说明                                                                                                                                                         |
 |--------------------|------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| 通用OCR            | `OCR`                              | [通用OCR产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/OCR.html#222-python脚本方式集成)                                                     |
-| 文档图像预处理            | `doc_preprocessor`                              | [文档图像预处理产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/doc_preprocessor.html#212-python脚本方式集成)                       |
-| 通用表格识别       | `table_recognition`                | [通用表格识别产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/table_recognition.html#22-python脚本方式集成)                                   |
-| 通用表格识别v2      | `table_recognition_v2`                | [通用表格识别v2产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/table_recognition_v2.html#22-python脚本方式集成)                                   |
-| 公式识别       | `formula_recognition`                | [公式识别产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.html#22-python脚本方式集成)                                   |
-| 印章文本识别       | `seal_recognition`                | [印章文本识别产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.html#22-python脚本方式集成)                                   |
-| 通用版面解析       | `layout_parsing`                | [通用版面解析产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.html#22-python脚本方式集成)                                   |
-| 通用版面解析v2      | `layout_parsing_v2`                | [通用版面解析v2产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/layout_parsing_v2.html#22-python脚本方式集成)                                   |
-| 文档场景信息抽取v3   | `PP-ChatOCRv3-doc`                 | [文档场景信息抽取v3产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.html#22-本地体验) |
-| 文档场景信息抽取v4   | `PP-ChatOCRv4-doc`                 | [文档场景信息抽取v4产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v4.html#22-本地体验) |
+| 通用OCR            | `OCR`                              | [通用OCR产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/OCR.html#222-python)                                                     |
+| 文档图像预处理            | `doc_preprocessor`                              | [文档图像预处理产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/doc_preprocessor.html#212-python脚)                       |
+| 通用表格识别       | `table_recognition`                | [通用表格识别产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/table_recognition.html#22-python脚)                                   |
+| 通用表格识别v2      | `table_recognition_v2`                | [通用表格识别v2产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/table_recognition_v2.html#22-python脚)                                   |
+| 公式识别       | `formula_recognition`                | [公式识别产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.html#222-python)                                   |
+| 印章文本识别       | `seal_recognition`                | [印章文本识别产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.html#222-python)                                   |
+| 通用版面解析       | `layout_parsing`                | [通用版面解析产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.html#22-python)                                   |
+| 通用版面解析v3      | `PP-StructureV3`                | [通用版面解析v3产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/PP-StructureV3.html#22-python)                                   |
+| 文档场景信息抽取v3   | `PP-ChatOCRv3-doc`                 | [文档场景信息抽取v3产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.html#22) |
+| 文档场景信息抽取v4   | `PP-ChatOCRv4-doc`                 | [文档场景信息抽取v4产线Python脚本使用说明](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v4.html#21) |
@@ -1,3 +1,16 @@
-See [Docs](https://paddlepaddle.github.io/PaddleOCR/latest/en/ppstructure/overview.html) for details.

-请移步[Docs](https://paddlepaddle.github.io/PaddleOCR/latest/ppstructure/overview.html)查看。
+## PP-Structure Upgrade Considerations
+
+Since its launch in 2021, the PP-Structure series models have undergone three generations of updates and iterations. Currently, the latest version is the third generation (PP-StructureV3). All the code and documentation on this page are based on the second generation (PP-StructureV2). **This directory will be removed at an appropriate time in the future, and maintenance for the second generation will be discontinued.**
+
+The third generation, PP-StructureV3, offers more powerful document analysis capabilities, and we strongly recommend users to use this version via the integrated wheel package. For a detailed introduction to PP-StructureV3, please refer to the [PP-StructureV3 Introduction Document](https://www.paddleocr.ai/latest/en/version3.x/algorithm/PP-StructureV3/PP-StructureV3.html); for specific usage instructions, please see the [PP-StructureV3 Usage Guide](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/PP-StructureV3.html).
+
+In addition, we will discontinue maintenance of the KIE capability provided in the second generation. We recommend that you use the PP-ChatOCRv4 model in PaddleOCR 3.x, which offers more accurate key information extraction. For a detailed introduction to PP-ChatOCRv4, please refer to the [PP-ChatOCRv4 Introduction Document](https://www.paddleocr.ai/latest/en/version3.x/algorithm/PP-ChatOCRv4/PP-ChatOCRv4.html); for specific usage instructions, please see the [PP-ChatOCRv4 Usage Document](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/PP-ChatOCRv4.html).
+
+## PP-Structure 升级事项
+
+PP-Structure 系列模型自 2021 年推出以来，已经历三代版本的更新迭代。目前，最新版本为第三代（PP-StructureV3）。本页面的所有代码与文档均基于第二代（PP-StructureV2），**后续将在适当时机删除本目录，并停止对第二代的维护。**
+
+第三代 PP-StructureV3 提供了更为强大的文档解析能力，我们更推荐用户通过集成 wheel 包来使用该版本。关于 PP-StructureV3 的详细介绍，请参考[PP-StructureV3 介绍文档](https://www.paddleocr.ai/latest/version3.x/algorithm/PP-StructureV3/PP-StructureV3.html)；具体的使用方法可参见[PP-StructureV3 使用文档](https://www.paddleocr.ai/latest/version3.x/pipeline_usage/PP-StructureV3.html)。
+
+另外，在第二代提供的 KIE 能力，我们也将停止维护，推荐大家使用 PaddleOCR 3.x 版本的 PP-ChatOCRv4 模型方案，关键信息抽取更准确。关于 PP-ChatOCRv4 的详细介绍，请参考[PP-ChatOCRv4 介绍文档](https://www.paddleocr.ai/latest/version3.x/algorithm/PP-ChatOCRv4/PP-ChatOCRv4.html)；具体的使用方法可参见[PP-ChatOCRv4 使用文档](https://www.paddleocr.ai/latest/version3.x/pipeline_usage/PP-ChatOCRv4.html)。
@@ -8,10 +8,10 @@ name = "paddleocr"
 dynamic = ["version"]
 description = "Awesome multilingual OCR and document parsing toolkits based on PaddlePaddle"
 authors = [
-    {name = "PaddlePaddle", email = "Paddle-better@baidu.com"},
+    {name = "PaddlePaddle", email = "paddleocr@baidu.com"},
 ]
 maintainers = [
-    {name = "PaddlePaddle", email = "Paddle-better@baidu.com"},
+    {name = "PaddlePaddle", email = "paddleocr@baidu.com"},
 ]
 readme = "README.md"
 requires-python = ">=3.8"
@@ -20,15 +20,15 @@ keywords = [
    "textdetection",
    "textrecognition",
    "paddleocr",
-    "crnn",
-    "east",
-    "star-net",
-    "rosetta",
-    "ocrlite",
-    "db",
    "chineseocr",
-    "chinesetextdetection",
-    "chinesetextrecognition",
+    "pp-ocr",
+    "pp-structure",
+    "document-parsing",
+    "pdf2markdown",
+    "kie",
+    "pp-chatocr",
+    "document-translation",
+    "rag"
 ]
 license = {text = "Apache License 2.0"}
 classifiers = [
@@ -486,7 +486,17 @@ print(chat_result)
    <img width="100%" src="../docs/images/blue_v3.gif" alt="PP-StructureV3 Demo">
 </p>

-### 6. المزيد من الميزات
+## 🌟 لا تفوت أحدث الأخبار
+
+⭐ **ضع نجمة لهذا المستودع لتكون على اطلاع دائم بأحدث التحديثات والإصدارات الجديدة المثيرة، بما في ذلك ميزات التعرف الضوئي على الحروف (OCR) وتحليل المستندات القوية!** ⭐
+
+<div align="center">
+  <p>
+       <img width="1200" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/star_paddleocr.en.gif" alt="Star-Project">
+  </p>
+</div>
+
+## 🧩 المزيد من الميزات

 - تحويل النماذج إلى صيغة ONNX: [الحصول على نماذج ONNX](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/obtaining_onnx_models.html).
 - تسريع الاستدلال باستخدام محركات مثل OpenVINO و ONNX Runtime و TensorRT، أو إجراء الاستدلال باستخدام نماذج صيغة ONNX: [الاستدلال عالي الأداء](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/high_performance_inference.html).
@@ -11,7 +11,7 @@
 [![arXiv](https://img.shields.io/badge/arXiv-2409.18839-b31b1b.svg?logo=arXiv)](https://arxiv.org/pdf/2507.05595)
 [![PyPI Downloads](https://static.pepy.tech/badge/paddleocr/month)](https://pepy.tech/projectsproject/paddleocr)
 [![PyPI Downloads](https://static.pepy.tech/badge/paddleocr)](https://pepy.tech/projects/paddleocr)
-[![Used by](https://img.shields.io/badge/Used%20by-5.8k%2B%20repositories-blue)](https://github.com/PaddlePaddle/PaddleOCR/network/dependents)
+[![Used by](https://img.shields.io/badge/Used%20by-5.9k%2B%20repositories-blue)](https://github.com/PaddlePaddle/PaddleOCR/network/dependents)

 ![python](https://img.shields.io/badge/python-3.8~3.12-aff.svg)
 ![os](https://img.shields.io/badge/os-linux%2C%20win%2C%20mac-pink.svg)
@@ -372,7 +372,7 @@ print(chat_result)
 - [昆仑芯安装指南](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/other_devices_support/paddlepaddle_install_XPU.html)
 - [昇腾安装指南](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/other_devices_support/paddlepaddle_install_NPU.html)

-## 更多特性
+## 🧩 更多特性

 - 将模型转换为 ONNX 格式：[获取 ONNX 模型](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/deployment/obtaining_onnx_models.html)。
 - 使用 OpenVINO、ONNX Runtime、TensorRT等引擎加速推理，或使用 ONNX 格式模型执行推理：[高性能推理](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/deployment/high_performance_inference.html)。
@@ -398,13 +398,31 @@ print(chat_result)
  </p>
 </div>

+## 🌟 关注项目
+
+⭐ **点击右上角的 Star 关注 PaddleOCR，第一时间获取 OCR 和文档解析等重磅能力的最新动态！** ⭐
+
+<div align="center">
+  <p>
+       <img width="1200" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/star_paddleocr.gif" alt="Star-Project">
+  </p>
+</div>
+
+
+
 ## 👩‍👩‍👧‍👦 开发者社区

+<div align="center">
+
 | 扫码关注飞桨公众号 | 扫码加入技术交流群 |
 | :---: | :---: |
 | <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"> |
+</div>

 ## 🏆 使用 PaddleOCR 的优秀项目
+
+<div align="center">
+
 PaddleOCR 的发展离不开社区贡献！💗衷心感谢所有开发者、合作伙伴与贡献者！
 | 项目名称 | 简介 |
 | ------------ | ----------- |
@@ -416,18 +434,23 @@ PaddleOCR 的发展离不开社区贡献！💗衷心感谢所有开发者、合
 | [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit) <a href="https://github.com/opendatalab/PDF-Extract-Kit"><img src="https://img.shields.io/github/stars/opendatalab/PDF-Extract-Kit"></a>|高效复杂PDF文档提取工具包|
 | [Dango-Translator](https://github.com/PantsuDango/Dango-Translator)<a href="https://github.com/PantsuDango/Dango-Translator"><img src="https://img.shields.io/github/stars/PantsuDango/Dango-Translator"></a> |屏幕实时翻译工具|
 | [更多项目](../awesome_projects.md) |  [更多基于PaddleOCR的项目](../awesome_projects.md) |
+</div>

 ## 👩‍👩‍👧‍👦 贡献者

+<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>

 ## 🌟 Star

-[![Star History Chart](https://api.star-history.com/svg?repos=PaddlePaddle/PaddleOCR&type=Date)](https://star-history.com/#PaddlePaddle/PaddleOCR&Date)
-
+<div align="center">
+  <p>
+      <img width="800" src="https://api.star-history.com/svg?repos=PaddlePaddle/PaddleOCR&type=Date" alt="Star-history">
+  </p>
+</div>

 ## 📄 许可协议
 本项目的发布受[Apache 2.0 license](LICENSE)许可认证。
@@ -336,7 +336,7 @@ print(chat_result)

 </details>

-## Más funciones
+## 🧩 Más funciones

 - Convertir modelos al formato ONNX: [Obtener modelos ONNX](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/obtaining_onnx_models.html).
 - Acelerar la inferencia usando motores como OpenVINO, ONNX Runtime, TensorRT, o realizar inferencia usando modelos en formato ONNX: [Inferencia de alto rendimiento](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/high_performance_inference.html).
@@ -362,6 +362,16 @@ print(chat_result)
  </p>
 </div>

+## 🌟 Mantente Atento
+
+⭐ **Dale una estrella a este repositorio para estar al tanto de emocionantes actualizaciones y nuevos lanzamientos, ¡incluyendo potentes capacidades de OCR y análisis de documentos!** ⭐
+
+<div align="center">
+  <p>
+       <img width="1200" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/star_paddleocr.en.gif" alt="Star-Project">
+  </p>
+</div>
+
 ## 👩‍👩‍👧‍👦 Comunidad

 | Cuenta oficial de PaddlePaddle en WeChat | Únase al grupo de discusión técnica |
@@ -335,7 +335,7 @@ print(chat_result)

 </details>

-## Fonctionnalités supplémentaires
+## 🧩 Fonctionnalités supplémentaires

 - Convertir les modèles au format ONNX : [Obtention des modèles ONNX](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/obtaining_onnx_models.html).
 - Accélérer l'inférence avec des moteurs comme OpenVINO, ONNX Runtime, TensorRT, ou effectuer l'inférence avec des modèles au format ONNX : [Inférence haute performance](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/high_performance_inference.html).
@@ -361,6 +361,16 @@ print(chat_result)
  </p>
 </div>

+## 🌟 Restez à l'écoute
+
+⭐ **Ajoutez une étoile à ce dépôt pour suivre les mises à jour passionnantes et les nouvelles versions, y compris de puissantes fonctionnalités d'OCR et d'analyse de documents !** ⭐
+
+<div align="center">
+  <p>
+       <img width="1200" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/star_paddleocr.en.gif" alt="Star-Project">
+  </p>
+</div>
+
 ## 👩‍👩‍👧‍👦 Communauté

 | Compte officiel WeChat de PaddlePaddle | Rejoignez le groupe de discussion technique |
@@ -333,7 +333,7 @@ print(chat_result)

 </details>

-## その他の機能
+## 🧩 その他の機能

 - モデルをONNX形式に変換：[ONNXモデルの取得](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/obtaining_onnx_models.html)
 - OpenVINO、ONNX Runtime、TensorRTなどのエンジンを使用して推論を高速化、またはONNX形式モデルで推論を実行：[高性能推論](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/high_performance_inference.html)
@@ -359,6 +359,16 @@ print(chat_result)
  </p>
 </div>

+## 🌟 最新情報をお見逃しなく
+
+⭐ **このリポジトリにスターを付けて、強力なOCRやドキュメント解析機能を含む、エキサイティングなアップデートや新リリースに注目しましょう！** ⭐
+
+<div align="center">
+  <p>
+       <img width="1200" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/star_paddleocr.en.gif" alt="Star-Project">
+  </p>
+</div>
+
 ## 👩‍👩‍👧‍👦 コミュニティ

 | PaddlePaddle WeChat公式アカウント |  技術ディスカッショングループへの参加 |
@@ -329,7 +329,7 @@ print(chat_result)

 </details>

-## 추가 기능
+## 🧩 추가 기능

 - 모델을 ONNX 형식으로 변환: [ONNX 모델 얻기](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/obtaining_onnx_models.html)
 - OpenVINO, ONNX Runtime, TensorRT 같은 엔진을 사용하거나 ONNX 형식 모델로 추론 가속: [고성능 추론](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/high_performance_inference.html)
@@ -355,6 +355,16 @@ print(chat_result)
  </p>
 </div>

+## 🌟 최신 소식을 놓치지 마세요
+
+⭐ **이 저장소에 스타를 추가하여 강력한 OCR 및 문서 분석 기능을 포함한 흥미로운 업데이트와 새로운 릴리스를 받아보세요!** ⭐
+
+<div align="center">
+  <p>
+       <img width="1200" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/star_paddleocr.en.gif" alt="Star-Project">
+  </p>
+</div>
+
 ## 👩‍👩‍👧‍👦 커뮤니티

 | PaddlePaddle 위챗(WeChat) 공식 계정 | 기술 토론 그룹 가입 |
@@ -339,7 +339,7 @@ print(chat_result)
 - [Huawei Ascend](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/other_devices_support/paddlepaddle_install_NPU.html)
 - [KUNLUNXIN](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/other_devices_support/paddlepaddle_install_XPU.html)

-## Дополнительные функции
+## 🧩 Дополнительные функции

 - Конвертация моделей в формат ONNX: [Получение моделей ONNX](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/obtaining_onnx_models.html).
 - Ускорение вывода с использованием движков, таких как OpenVINO, ONNX Runtime, TensorRT, или выполнение вывода с моделями в формате ONNX: [Высокопроизводительный вывод](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/deployment/high_performance_inference.html).
@@ -365,6 +365,16 @@ print(chat_result)
  </p>
 </div>

+## 🌟 Не пропустите самые свежие новости
+
+⭐ **Поставьте звезду этому репозиторию, чтобы быть в курсе захватывающих обновлений и новых релизов — включая мощные функции OCR и анализа документов!** ⭐
+
+<div align="center">
+  <p>
+       <img width="1200" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/star_paddleocr.en.gif" alt="Star-Project">
+  </p>
+</div>
+
 ## 👩‍👩‍👧‍👦 Сообщество

 | Официальный аккаунт PaddlePaddle в WeChat | Присоединяйтесь к группе для технических обсуждений |
@@ -338,7 +338,7 @@ print(chat_result)
 - [崑崙芯安裝指南](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/other_devices_support/paddlepaddle_install_XPU.html)
 - [昇騰安裝指南](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/other_devices_support/paddlepaddle_install_NPU.html)

-## 更多特性
+## 🧩 更多特性

 - 將模型轉換為 ONNX 格式：[取得 ONNX 模型](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/deployment/obtaining_onnx_models.html)
 - 使用 OpenVINO、ONNX Runtime、TensorRT 等引擎加速推論，或使用 ONNX 格式模型執行推論：[高效能推論](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/deployment/high_performance_inference.html)
@@ -364,6 +364,16 @@ print(chat_result)
  </p>
 </div>

+## 🌟 不要錯過最新資訊
+
+⭐ **請給這個倉庫加星，以便第一時間獲取包含強大 OCR 及文件分析功能的精彩更新和新版本發布！** ⭐
+
+<div align="center">
+  <p>
+       <img width="1200" src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/paddleocr/README/star_paddleocr.en.gif" alt="Star-Project">
+  </p>
+</div>
+
 ## 👩‍👩‍👧‍👦 開發者社群

 | 掃描 QR Code 關注飛槳官方帳號 | 掃描 QR Code 加入技術交流群組 |
@@ -1,2 +1,2 @@
-# recommended paddle.__version__ == 2.0.0
-python3 -m paddle.distributed.launch --log_dir=./debug/ --gpus '0,1,2,3,4,5,6,7'  tools/train.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml
+# recommended paddle.__version__ == 3.0.0
+python3 -m paddle.distributed.launch --log_dir=./log/ --gpus '0,1,2,3,4,5,6,7'  tools/train.py -c configs/rec/PP-OCRv5/PP-OCRv5_server_rec.yml