[Docs] Refine deployment documentation (#2222)

* review hpi_performance_deploy.md

* review high_performance_deploy.md and high_performance_deploy_en.md, also change deploy to inference.

* review high_performance_inference.md, lite_deploy.md, service_deploy.md at 202410141420.

* fix some capitalization errors about "high-performance" & "High-Performance".

* del "pipeline" in "Document Scene Information Extraction v3 pipeline".

* rm LaTeX_OCR_rec<br/>

* add models in  Text Recognition.

* fix some tiny mistakes.

* optimize format

* fix chatocrv3 api_reference

* fix chatocrv3 api_reference

* change chatocrv3 api_reference

---------

Co-authored-by: zhang-prog <1506416712@qq.com>
Co-authored-by: zhang-prog <69562787+zhang-prog@users.noreply.github.com>
Co-authored-by: cuicheng01 <45199522+cuicheng01@users.noreply.github.com>

README.md

@@ -56,13 +56,10 @@ PaddleX 3.0 是基于飞桨框架构建的低代码开发工具，它集成了
 
  ## 📊 能力支持
 
-PaddleX的各个产线均支持本地**快速推理**，部分模型支持**在线体验**，您可以快速体验各个产线的预训练模型效果，如果您对产线的预训练模型效果满意，可以直接对产线进行[高性能推理](./docs/pipeline_deploy/high_performance_deploy.md)/[服务化部署](./docs/pipeline_deploy/service_deploy.md)/[端侧部署](./docs/pipeline_deploy/lite_deploy.md)，如果不满意，您也可以使用产线的**二次开发**能力，提升效果。完整的产线开发流程请参考[PaddleX产线使用概览](./docs/pipeline_usage/pipeline_develop_guide.md)或各产线使用[教程](#-文档)。
-
-
+PaddleX的各个产线均支持本地**快速推理**，部分模型支持**在线体验**，您可以快速体验各个产线的预训练模型效果，如果您对产线的预训练模型效果满意，可以直接对产线进行[高性能部署](./docs/pipeline_deploy/high_performance_inference.md)/[服务化部署](./docs/pipeline_deploy/service_deploy.md)/[端侧部署](./docs/pipeline_deploy/lite_deploy.md)，如果不满意，您也可以使用产线的**二次开发**能力，提升效果。完整的产线开发流程请参考[PaddleX产线使用概览](./docs/pipeline_usage/pipeline_develop_guide.md)或各产线使用[教程](#-文档)。
 
 此外，PaddleX 为开发者提供了基于[云端图形化开发界面](https://aistudio.baidu.com/pipeline/mine)的全流程开发工具, 点击【创建产线】，选择对应的任务场景和模型产线，就可以开启全流程开发。详细请参考[教程《零门槛开发产业级AI模型》](https://aistudio.baidu.com/practical/introduce/546656605663301)
 
-
 <table >
     <tr>
         <th>模型产线</th>
@@ -631,7 +628,7 @@ for res in output:
 <details open>
   <summary> <b> 🏗️ 模型产线部署 </b></summary>
 
-  * [🚀 PaddleX 高性能部署指南](./docs/pipeline_deploy/high_performance_deploy.md)
+  * [🚀 PaddleX 高性能推理指南](./docs/pipeline_deploy/high_performance_inference.md)
   * [🖥️ PaddleX 服务化部署指南](./docs/pipeline_deploy/service_deploy.md)
   * [📱 PaddleX 端侧部署指南](./docs/pipeline_deploy/lite_deploy.md)
 

README_en.md

@@ -21,7 +21,6 @@
 
 PaddleX 3.0 is a low-code development tool for AI models built on the PaddlePaddle framework. It integrates numerous **ready-to-use pre-trained models**, enabling **full-process development** from model training to inference, supporting **a variety of mainstream hardware** both domestic and international, and aiding AI developers in industrial practice.
  
-
 |                                                            [**Image Classification**](./docs/pipeline_usage/tutorials/cv_pipelines/image_classification_en.md)                                                            |                                                            [**Multi-label Image Classification**](./docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification_en.md)                                                            |                                                            [**Object Detection**](./docs/pipeline_usage/tutorials/cv_pipelines/object_detection_en.md)                                                            |                                                            [**Instance Segmentation**](./docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation_en.md)                                                            |
 |:--------------------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------:|
 | <img src="https://github.com/PaddlePaddle/PaddleX/assets/142379845/b302cd7e-e027-4ea6-86d0-8a4dd6d61f39" height="126px" width="180px"> | <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/multilabel_cls.png" height="126px" width="180px"> | <img src="https://github.com/PaddlePaddle/PaddleX/assets/142379845/099e2b00-0bbe-4b20-9c5a-96b69e473bd2" height="126px" width="180px"> | <img src="https://github.com/PaddlePaddle/PaddleX/assets/142379845/09f683b4-27df-4c24-b8a7-84da20fdd182" height="126px" width="180px"> |
@@ -36,7 +35,7 @@ PaddleX 3.0 is a low-code development tool for AI models built on the PaddlePadd
 
   🚀 **High Efficiency and Low barrier of entry**: Achieve model **full-process development** based on graphical interfaces and unified commands, creating **8 featured model pipelines** that combine large and small models, semi-supervised learning of large models, and multi-model fusion, greatly reducing the cost of iterating models.
 
-  🌐 **Flexible Deployment in Various Scenarios**: Support various deployment methods such as **high-performance deployment**, **service-oriented deployment**, and **edge deployment** to ensure efficient operation and rapid response of models in different application scenarios.
+  🌐 **Flexible Deployment in Various Scenarios**: Support various deployment methods such as **high-performance inference**, **service deployment**, and **lite deployment** to ensure efficient operation and rapid response of models in different application scenarios.
 
   🔧 **Efficient Support for Mainstream Hardware**: Support seamless switching of various mainstream hardware such as NVIDIA GPUs, Kunlun XPU, Ascend NPU, and Cambricon MLU to ensure efficient operation.
 
@@ -55,7 +54,7 @@ PaddleX is dedicated to achieving pipeline-level model training, inference, and
 
 ## 📊 What can PaddleX do？
 
-All pipelines of PaddleX support **online experience** and local **inference**. You can quickly experience the effects of each pre-trained pipeline. If you are satisfied with the effects of the pre-trained pipeline, you can directly perform [high-performance inference](./docs/pipeline_deploy/high_performance_deploy_en.md) / [Service-Oriented Deployment](./docs/pipeline_deploy/service_deploy_en.md) / [edge deployment](./docs/pipeline_deploy/lite_deploy_en.md) on the pipeline. If not satisfied, you can also **Custom Development** to improve the pipeline effect. For the complete pipeline development process, please refer to the [PaddleX pipeline Development Tool Local Use Tutorial](./docs/pipeline_usage/pipeline_develop_guide_en.md).
+All pipelines of PaddleX support **online experience** and local **fast inference**. You can quickly experience the effects of each pre-trained pipeline. If you are satisfied with the effects of the pre-trained pipeline, you can directly perform [high-performance inference](./docs/pipeline_deploy/high_performance_inference_en.md) / [serving deployment](./docs/pipeline_deploy/service_deploy_en.md) / [edge deployment](./docs/pipeline_deploy/lite_deploy_en.md) on the pipeline. If not satisfied, you can also **Custom Development** to improve the pipeline effect. For the complete pipeline development process, please refer to the [PaddleX pipeline Development Tool Local Use Tutorial](./docs/pipeline_usage/pipeline_develop_guide_en.md).
 
 In addition, PaddleX provides developers with a full-process efficient model training and deployment tool based on a [cloud-based GUI](https://aistudio.baidu.com/pipeline/mine). Developers **do not need code development**, just need to prepare a dataset that meets the pipeline requirements to **quickly start model training**. For details, please refer to the tutorial ["Developing Industrial-level AI Models with Zero Barrier"](https://aistudio.baidu.com/practical/introduce/546656605663301).
 
@@ -92,7 +91,7 @@ In addition, PaddleX provides developers with a full-process efficient model tra
     </tr>
     <tr>
         <td>Table Recognition</td>
-        <td><a href="https://aistudio.baidu.com/community/app/91661?source=appMineRecent">Link</a></td> 
+        <td><a href="https://aistudio.baidu.com/community/app/91661?source=appMineRecent">Link</a></td>
         <td>✅</td>
         <td>✅</td>
         <td>✅</td>
@@ -142,7 +141,7 @@ In addition, PaddleX provides developers with a full-process efficient model tra
     </tr>
     <tr>
         <td>Time Series Forecasting</td>
-        <td><a href="https://aistudio.baidu.com/community/app/105706/webUI?source=appMineRecent">Link</a></td> 
+        <td><a href="https://aistudio.baidu.com/community/app/105706/webUI?source=appMineRecent">Link</a></td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
@@ -152,7 +151,7 @@ In addition, PaddleX provides developers with a full-process efficient model tra
     </tr>
     <tr>
         <td>Time Series Anomaly Detection</td>
-        <td><a href="https://aistudio.baidu.com/community/app/105708/webUI?source=appMineRecent">Link</a></td> 
+        <td><a href="https://aistudio.baidu.com/community/app/105708/webUI?source=appMineRecent">Link</a></td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
@@ -162,7 +161,7 @@ In addition, PaddleX provides developers with a full-process efficient model tra
     </tr>
     <tr>
         <td>Time Series Classification</td>
-        <td><a href="https://aistudio.baidu.com/community/app/105707/webUI?source=appMineRecent">Link</a></td> 
+        <td><a href="https://aistudio.baidu.com/community/app/105707/webUI?source=appMineRecent">Link</a></td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
@@ -357,6 +356,7 @@ In addition, PaddleX provides developers with a full-process efficient model tra
 > ❗Before installing PaddleX, please ensure you have a basic **Python environment** (Note: Currently supports Python 3.8 to Python 3.10, with more Python versions being adapted).
 
 * **Installing PaddlePaddle**
+
 ```bash
 # cpu
 python -m pip install paddlepaddle==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
@@ -492,7 +492,7 @@ For other pipelines in Python scripts, just adjust the `pipeline` parameter of t
 ## 📖 Documentation
 <details>
   <summary> <b> ⬇️ Installation </b></summary>
-  
+
   * [📦 PaddlePaddle Installation](./docs/installation/paddlepaddle_install_en.md)
   * [📦 PaddleX Installation](./docs/installation/installation_en.md) 
 
@@ -529,7 +529,7 @@ For other pipelines in Python scripts, just adjust the `pipeline` parameter of t
    * [🔍 Small Object Detection pipeline Tutorial](./docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection_en.md)
    * [🖼️ Image Anomaly Detection pipeline Tutorial](./docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection_en.md)
   </details>
-  
+
 * <details open>
     <summary> <b> ⏱️ Time Series Analysis</b> </summary>
 
@@ -544,7 +544,7 @@ For other pipelines in Python scripts, just adjust the `pipeline` parameter of t
    * [🖥️ PaddleX pipeline Command Line Instruction](./docs/pipeline_usage/instructions/pipeline_CLI_usage_en.md)
    * [📝 PaddleX pipeline Python Script Instruction](./docs/pipeline_usage/instructions/pipeline_python_API_en.md)
   </details>
-  
+
 </details>
 
 <details open>
@@ -607,7 +607,7 @@ For other pipelines in Python scripts, just adjust the `pipeline` parameter of t
   * [🚨 Time Series Anomaly Detection Module Tutorial](./docs/module_usage/tutorials/time_series_modules/time_series_anomaly_detection.md)
   * [🕒 Time Series Classification Module Tutorial](./docs/module_usage/tutorials/ts_modules/time_series_classification_en.md)
   </details>
-    
+
 * <details open>
   <summary> <b> 📄 Related Instructions </b></summary>
 
@@ -621,9 +621,9 @@ For other pipelines in Python scripts, just adjust the `pipeline` parameter of t
 <details open>
   <summary> <b> 🏗️ Pipeline Deployment </b></summary>
 
-  * [🚀 PaddleX High-Performance Inference Tutorial](./docs/pipeline_deploy/high_performance_deploy_en.md)
-  * [🖥️ PaddleX Service-Oriented Deployment Tutorial](./docs/pipeline_deploy/service_deploy_en.md)
-  * [📱 PaddleX Edge Deployment Tutorial](./docs/pipeline_deploy/lite_deploy_en.md)
+  * [🚀 PaddleX High-Performance Inference Guide](./docs/pipeline_deploy/high_performance_inference_en.md)
+  * [🖥️ PaddleX Service Deployment Guide](./docs/pipeline_deploy/service_deploy_en.md)
+  * [📱 PaddleX Edge Deployment Guide](./docs/pipeline_deploy/lite_deploy_en.md)
 
 </details>
 <details open>
@@ -667,9 +667,3 @@ We warmly welcome and encourage community members to raise questions, share idea
 ## 📄 License
 
 The release of this project is licensed under the [Apache 2.0 license](https://github.com/PaddlePaddle/PaddleX/blob/release/3.0-beta/LICENSE).
-
-
-
-
-
-

docs/FAQ_en.md

@@ -8,7 +8,7 @@ A: PaddleX is a low-code development tool featuring selected models and pipeline
 
 ## Q: What is a Pipeline? What is a Module? What is the relationship between them?
 
-A: In PaddleX, a module is defined as the smallest unit that implements basic functions, meaning each module undertakes a specific task, such as text detection. Within this framework, a pipeline is the actual functionality achieved by one or more modules working together, often forming more complex application scenarios, such as Optical Character Recognition (OCR) technology. Therefore, the relationship between modules and pipelines can be understood as the relationship between basics and applications. Modules, as the smallest units, provide the foundation for construction, while pipelines demonstrate the practical application effects of these foundational modules after reasonable combination and configuration. This design approach allows users to flexibly select and combine different modules to achieve the functions they need, significantly enhancing development flexibility and efficiency. The official pipelines also support users with high-performance deployment, service-oriented deployment, and other deployment capabilities.
+A: In PaddleX, a module is defined as the smallest unit that implements basic functions, meaning each module undertakes a specific task, such as text detection. Within this framework, a pipeline is the actual functionality achieved by one or more modules working together, often forming more complex application scenarios, such as Optical Character Recognition (OCR) technology. Therefore, the relationship between modules and pipelines can be understood as the relationship between basics and applications. Modules, as the smallest units, provide the foundation for construction, while pipelines demonstrate the practical application effects of these foundational modules after reasonable combination and configuration. This design approach allows users to flexibly select and combine different modules to achieve the functions they need, significantly enhancing development flexibility and efficiency. The official pipelines also support users with high-performance inference, service-oriented deployment, and other deployment capabilities.
 
 ## Q: How to choose between the Wheel package installation mode and the plugin installation mode?
 

docs/module_usage/tutorials/cv_modules/anomaly_detection_en.md

@@ -185,7 +185,7 @@ The model can be directly integrated into the PaddleX pipeline or into your own
 
 1. **Pipeline Integration**
 
-The unsupervised anomaly detection module can be integrated into PaddleX pipelines such as [Image_anomaly_detection](../../../pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection_en.md). Simply replace the model path to update the unsupervised anomaly detection module of the relevant pipeline. In pipeline integration, you can use high-performance deployment and service-oriented deployment to deploy your model.
+The unsupervised anomaly detection module can be integrated into PaddleX pipelines such as [Image_anomaly_detection](../../../pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection_en.md). Simply replace the model path to update the unsupervised anomaly detection module of the relevant pipeline. In pipeline integration, you can use high-performance inference and service-oriented deployment to deploy your model.
 
 2. **Module Integration**
 

docs/module_usage/tutorials/cv_modules/face_detection_en.md

@@ -242,7 +242,7 @@ The model can be directly integrated into the PaddleX pipeline or into your own
 
 1. **Pipeline Integration**
 
-The face detection module can be integrated into PaddleX pipelines such as **Face Recognition** (coming soon). Simply replace the model path to update the face detection module of the relevant pipeline. In pipeline integration, you can use high-performance deployment and service-oriented deployment to deploy your model.
+The face detection module can be integrated into PaddleX pipelines such as **Face Recognition** (coming soon). Simply replace the model path to update the face detection module of the relevant pipeline. In pipeline integration, you can use high-performance inference and service-oriented deployment to deploy your model.
 
 2. **Module Integration**
 

docs/module_usage/tutorials/cv_modules/image_classification_en.md

@@ -814,7 +814,7 @@ The model can be directly integrated into the PaddleX pipelines or directly into
 
 1.**Pipeline Integration**
 
-The image classification module can be integrated into the [General Image Classification Pipeline](../../../pipeline_usage/tutorials/cv_pipelines/image_classification_en.md) of PaddleX. Simply replace the model path to update the image classification module of the relevant pipeline. In pipeline integration, you can use high-performance deployment and service-oriented deployment to deploy your obtained model.
+The image classification module can be integrated into the [General Image Classification Pipeline](../../../pipeline_usage/tutorials/cv_pipelines/image_classification_en.md) of PaddleX. Simply replace the model path to update the image classification module of the relevant pipeline. In pipeline integration, you can use high-performance inference and service-oriented deployment to deploy your obtained model.
 
 2.**Module Integration**
 

docs/module_usage/tutorials/cv_modules/mainbody_detection_en.md

@@ -257,7 +257,7 @@ The model can be directly integrated into the PaddleX pipeline or directly into
 
 1. **Pipeline Integration**
 
-The main body detection module can be integrated into PaddleX pipelines such as **General Object Detection** (comming soon). Simply replace the model path to update the main body detection module of the relevant pipeline. In pipeline integration, you can use high-performance deployment and service-oriented deployment to deploy your trained model.
+The main body detection module can be integrated into PaddleX pipelines such as **General Object Detection** (comming soon). Simply replace the model path to update the main body detection module of the relevant pipeline. In pipeline integration, you can use high-performance inference and service-oriented deployment to deploy your trained model.
 
 2. **Module Integration**
 

docs/module_usage/tutorials/cv_modules/ml_classification_en.md

@@ -327,7 +327,7 @@ The model can be directly integrated into the PaddleX pipeline or directly into
 
 1.**Pipeline Integration**
 
-The image multi-label classification module can be integrated into the [General Image Multi-label Classification Pipeline](../../../pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification_en.md) of PaddleX. Simply replace the model path to update the image multi-label classification module of the relevant pipeline. In pipeline integration, you can use high-performance deployment and service-oriented deployment to deploy your model.
+The image multi-label classification module can be integrated into the [General Image Multi-label Classification Pipeline](../../../pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification_en.md) of PaddleX. Simply replace the model path to update the image multi-label classification module of the relevant pipeline. In pipeline integration, you can use high-performance inference and service-oriented deployment to deploy your model.
 
 2.**Module Integration**
 

docs/module_usage/tutorials/cv_modules/object_detection_en.md

@@ -593,7 +593,7 @@ The model can be directly integrated into the PaddleX pipelines or directly into
 
 1.**Pipeline Integration**
 
-The object detection module can be integrated into the [General Object Detection Pipeline](../../../pipeline_usage/tutorials/cv_pipelines/object_detection_en.md) of PaddleX. Simply replace the model path to update the object detection module of the relevant pipeline. In pipeline integration, you can use high-performance deployment and service-oriented deployment to deploy your model.
+The object detection module can be integrated into the [General Object Detection Pipeline](../../../pipeline_usage/tutorials/cv_pipelines/object_detection_en.md) of PaddleX. Simply replace the model path to update the object detection module of the relevant pipeline. In pipeline integration, you can use high-performance inference and service-oriented deployment to deploy your model.
 
 2.**Module Integration**
 

docs/module_usage/tutorials/cv_modules/pedestrian_attribute_recognition_en.md

@@ -272,7 +272,7 @@ The model can be directly integrated into the PaddleX pipeline or directly into
 
 1.**Pipeline Integration**
 
-The pedestrian attribute recognition module can be integrated into the [General Image Multi-label Classification Pipeline](../../../pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification_en.md) of PaddleX. Simply replace the model path to update the pedestrian attribute recognition module of the relevant pipeline. In pipeline integration, you can use high-performance deployment and service-oriented deployment to deploy your model.
+The pedestrian attribute recognition module can be integrated into the [General Image Multi-label Classification Pipeline](../../../pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification_en.md) of PaddleX. Simply replace the model path to update the pedestrian attribute recognition module of the relevant pipeline. In pipeline integration, you can use high-performance inference and service-oriented deployment to deploy your model.
 
 2.**Module Integration**
 

docs/module_usage/tutorials/cv_modules/small_object_detection_en.md

@@ -308,7 +308,7 @@ The model can be directly integrated into the PaddleX pipelines or directly into
 
 1. **Pipeline Integration**
 
-The small object detection module can be integrated into the [Small Object Detection Pipeline](../../../pipeline_usage/tutorials/cv_pipelines/small_object_detection_en.md) of PaddleX. Simply replace the model path to update the small object detection module of the relevant pipeline. In pipeline integration, you can use high-performance deployment and service-oriented deployment to deploy your obtained model.
+The small object detection module can be integrated into the [Small Object Detection Pipeline](../../../pipeline_usage/tutorials/cv_pipelines/small_object_detection_en.md) of PaddleX. Simply replace the model path to update the small object detection module of the relevant pipeline. In pipeline integration, you can use high-performance inference and service-oriented deployment to deploy your obtained model.
 
 2. **Module Integration**
 

docs/module_usage/tutorials/cv_modules/vehicle_attribute_recognition_en.md

@@ -255,7 +255,7 @@ The model can be directly integrated into the PaddleX pipeline or directly into
 
 1.**Pipeline Integration**
 
-The vehicle attribute recognition module can be integrated into the [General Image Multi-label Classification Pipeline](../../../pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification_en.md) of PaddleX. Simply replace the model path to update the vehicle attribute recognition module of the relevant pipeline. In pipeline integration, you can use high-performance deployment and service-oriented deployment to deploy your model.
+The vehicle attribute recognition module can be integrated into the [General Image Multi-label Classification Pipeline](../../../pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification_en.md) of PaddleX. Simply replace the model path to update the vehicle attribute recognition module of the relevant pipeline. In pipeline integration, you can use high-performance inference and service-oriented deployment to deploy your model.
 
 2.**Module Integration**
 

docs/module_usage/tutorials/cv_modules/vehicle_detection_en.md

@@ -246,7 +246,7 @@ The model can be directly integrated into the PaddleX pipeline or into your own
 
 1. **Pipeline Integration**
 
-The object detection module can be integrated into the [General Object Detection Pipeline](../../../pipeline_usage/tutorials/cv_pipelines/object_detection_en.md) of PaddleX. Simply replace the model path to update the object detection module of the relevant pipeline. In pipeline integration, you can use high-performance deployment and service-oriented deployment to deploy your trained model.
+The object detection module can be integrated into the [General Object Detection Pipeline](../../../pipeline_usage/tutorials/cv_pipelines/object_detection_en.md) of PaddleX. Simply replace the model path to update the object detection module of the relevant pipeline. In pipeline integration, you can use high-performance inference and service-oriented deployment to deploy your trained model.
 
 2. **Module Integration**
 

docs/module_usage/tutorials/ocr_modules/layout_detection_en.md

@@ -249,7 +249,7 @@ Other related parameters can be set by modifying the fields under `Global` and `
 The model can be directly integrated into PaddleX pipelines or into your own projects.
 
 1. **Pipeline Integration**
-The structure analysis module can be integrated into PaddleX pipelines such as the [General Table Recognition Pipeline](../../../pipeline_usage/tutorials/ocr_pipelines/table_recognition_en.md) and the [Document Scene Information Extraction Pipeline v3 (PP-ChatOCRv3)](../../../pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction_en.md). Simply replace the model path to update the layout area localization module. In pipeline integration, you can use high-performance deployment and service-oriented deployment to deploy your model.
+The structure analysis module can be integrated into PaddleX pipelines such as the [General Table Recognition Pipeline](../../../pipeline_usage/tutorials/ocr_pipelines/table_recognition_en.md) and the [Document Scene Information Extraction Pipeline v3 (PP-ChatOCRv3)](../../..//pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction_en.md). Simply replace the model path to update the layout area localization module. In pipeline integration, you can use high-performance inference and service-oriented deployment to deploy your model.
 
 1. **Module Integration**
 The weights you produce can be directly integrated into the layout area localization module. You can refer to the Python example code in the [Quick Integration](#quick) section, simply replacing the model with the path to your trained model.

docs/module_usage/tutorials/ocr_modules/table_structure_recognition_en.md

@@ -268,7 +268,7 @@ The model can be directly integrated into the PaddleX pipeline or directly into
 
 1.**Pipeline Integration**
 
-The table structure recognition module can be integrated into PaddleX pipelines such as the [General Table Recognition Pipeline](../../../pipeline_usage/tutorials/ocr_pipelines/table_recognition_en.md) and the [Document Scene Information Extraction Pipeline v3 (PP-ChatOCRv3)](../../../pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction_en.md). Simply replace the model path to update the table structure recognition module in the relevant pipelines. For pipeline integration, you can deploy your obtained model using high-performance deployment and service-oriented deployment.
+The table structure recognition module can be integrated into PaddleX pipelines such as the [General Table Recognition Pipeline](../../../pipeline_usage/tutorials/ocr_pipelines/table_recognition_en.md) and the [Document Scene Information Extraction Pipeline v3 (PP-ChatOCRv3)](../../../pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction_en.md). Simply replace the model path to update the table structure recognition module in the relevant pipelines. For pipeline integration, you can deploy your obtained model using high-performance inference and service-oriented deployment.
 
 2.**Module Integration**
 

docs/pipeline_deploy/high_performance_deploy.md → docs/pipeline_deploy/high_performance_inference.md

@@ -1,6 +1,6 @@
-简体中文 | [English](high_performance_deploy_en.md)
+简体中文 | [English](high_performance_inference_en.md)
 
-# PaddleX 高性能部署指南
+# PaddleX 高性能推理指南
 
 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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速。本文档将首先介绍高性能推理插件的安装和使用方式，然后列举目前支持使用高性能推理插件的产线与模型。
 
@@ -69,12 +69,12 @@
 使用序列号完成激活后，即可使用高性能推理插件。PaddleX 提供离线激活和在线激活两种方式（均只支持 Linux 系统）：
 
 * 联网激活：在使用推理 API 或 CLI 时，通过参数指定序列号及联网激活，使程序自动完成激活。
-* 离线激活：按照序列号管理界面中的指引（点击“操作”中的“离线激活”），获取机器的设备指纹，并将序列号与设备指纹绑定以获取证书，完成激活。使用这种激活方式，需要手动将证书存放在机器的${HOME}/.baidu/paddlex/licenses目录中（如果目录不存在，需要创建目录），并在使用推理 API 或 CLI 时指定序列号。
+* 离线激活：按照序列号管理界面中的指引（点击“操作”中的“离线激活”），获取机器的设备指纹，并将序列号与设备指纹绑定以获取证书，完成激活。使用这种激活方式，需要手动将证书存放在机器的 `${HOME}/.baidu/paddlex/licenses` 目录中（如果目录不存在，需要创建目录），并在使用推理 API 或 CLI 时指定序列号。
 请注意：每个序列号只能绑定到唯一的设备指纹，且只能绑定一次。这意味着用户如果使用不同的机器部署模型，则必须为每台机器准备单独的序列号。
 
 ### 1.3 启用高性能推理插件
 
-在启用高性能插件前，请确保当前环境的`LD_LIBRARY_PATH`没有指定 TensorRT 目录，因为插件中已经集成了 TensorRT，避免 TensorRT 版本冲突导致插件无法正常使用。
+在启用高性能插件前，请确保当前环境的 `LD_LIBRARY_PATH` 没有指定 TensorRT 的共享库目录，因为插件中已经集成了 TensorRT，避免 TensorRT 版本冲突导致插件无法正常使用。
 
 对于 PaddleX CLI，指定 `--use_hpip`，并设置序列号，即可启用高性能推理插件。如果希望进行联网激活，在第一次使用序列号时，需指定 `--update_license`，以通用图像分类产线为例：
 
@@ -107,7 +107,7 @@ pipeline = create_pipeline(
 +   serial_number="{序列号}",
 )
 
- output = pipeline.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg")
+output = pipeline.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg")
 ```
 
 启用高性能推理插件得到的推理结果与未启用插件时一致。对于部分模型，在首次启用高性能推理插件时，可能需要花费较长时间完成推理引擎的构建。PaddleX 将在推理引擎的第一次构建完成后将相关信息缓存在模型目录，并在后续复用缓存中的内容以提升初始化速度。
@@ -116,7 +116,7 @@ pipeline = create_pipeline(
 
 PaddleX 为每个模型提供默认的高性能推理配置，并将其存储在模型的配置文件中。由于实际部署环境的多样性，使用默认配置可能无法在特定环境中获取理想的性能，甚至可能出现推理失败的情况。对于默认配置无法满足要求的情形，可以通过如下方式，尝试更换模型的推理后端：
 
-1. 找到模型目录中的 `inference.yml` 文件，定位到其中的Hpi字段；
+1. 找到模型目录中的 `inference.yml` 文件，定位到其中的 `Hpi` 字段；
 2. 修改 `selected_backends` 的值。具体而言，`selected_backends` 可能被设置如下：
 
     ```
@@ -129,7 +129,7 @@ PaddleX 为每个模型提供默认的高性能推理配置，并将其存储在
     目前所有可选的推理后端如下：
 
     * `paddle_infer`：标准的 Paddle Inference 推理引擎。支持 CPU 和 GPU。
-    * `paddle_tensorrt`：[Paddle-TensorRT](https://www.paddlepaddle.org.cn/lite/v2.10/optimize/paddle_trt.html)，Paddle 官方出品的高性能深度学习推理库，采用子图的形式对 TensorRT 进行了集成，以实现进一步优化加速。仅支持 GPU。
+    * `paddle_tensorrt`：[Paddle-TensorRT](https://www.paddlepaddle.org.cn/lite/v2.10/optimize/paddle_trt.html)，Paddle 官方出品的高性能深度学习推理库，采用子图的形式对 TensorRT 进行了集成，以实现进一步优化加速。仅支持 GPU。
     * `openvino`：[OpenVINO](https://github.com/openvinotoolkit/openvino)，Intel 提供的深度学习推理工具，优化了多种 Intel 硬件上的模型推理性能。仅支持 CPU。
     * `onnx_runtime`：[ONNX Runtime](https://onnxruntime.ai/)，跨平台、高性能的推理引擎。支持 CPU 和 GPU。
     * `tensorrt`：[TensorRT](https://developer.nvidia.com/tensorrt)，NVIDIA 提供的高性能深度学习推理库，针对 NVIDIA GPU 进行优化以提升速度。仅支持 GPU。
@@ -186,7 +186,7 @@ PaddleX 为每个模型提供默认的高性能推理配置，并将其存储在
 
   <tr>
     <td>文本识别</td>
-    <td>PP-OCRv4_server_rec<br/>PP-OCRv4_mobile_rec<br/>LaTeX_OCR_rec<br/>ch_RepSVTR_rec<br/>ch_SVTRv2_rec</td>
+    <td>PP-OCRv4_server_rec<br/>PP-OCRv4_mobile_rec<br/>ch_RepSVTR_rec<br/>ch_SVTRv2_rec</td>
   </tr>
 
   <tr>
@@ -211,11 +211,11 @@ PaddleX 为每个模型提供默认的高性能推理配置，并将其存储在
 
   <tr>
     <td>文本识别</td>
-    <td>PP-OCRv4_server_rec<br/>PP-OCRv4_mobile_rec</td>
+    <td>PP-OCRv4_server_rec<br/>PP-OCRv4_mobile_rec<br/>ch_RepSVTR_rec<br/>ch_SVTRv2_rec</td>
   </tr>
 
   <tr>
-    <td rowspan="15">文档场景信息抽取v3产线</td>
+    <td rowspan="15">文档场景信息抽取v3</td>
     <td rowspan="2">表格识别</td>
     <td>SLANet</td>
   </tr>

docs/pipeline_deploy/high_performance_deploy_en.md → docs/pipeline_deploy/high_performance_inference_en.md

@@ -1,6 +1,6 @@
-[简体中文](high_performance_deploy.md) | English
+[简体中文](high_performance_inference.md) | English
 
-# PaddleX High-Performance Deployment Guide
+# PaddleX High-Performance Inference Guide
 
 In real-world production environments, many applications have stringent standards for deployment strategy performance metrics, particularly response speed, to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins designed to deeply optimize model inference and pre/post-processing, achieving significant speedups in the end-to-end process. This document will first introduce the installation and usage of the high-performance inference plugins, followed by a list of pipelines and models currently supporting the use of these plugins.
 
@@ -117,7 +117,7 @@ The inference results obtained with the high-performance inference plugin enable
 
 PaddleX provides default high-performance inference configurations for each model and stores them in the model's configuration file. Due to the diversity of actual deployment environments, using the default configurations may not achieve ideal performance in specific environments or may even result in inference failures. For situations where the default configurations cannot meet requirements, you can try changing the model's inference backend as follows:
 
-1. Locate the `inference.yml` file in the model directory and find the Hpi field.
+1. Locate the `inference.yml` file in the model directory and find the `Hpi` field.
 
 2. Modify the value of `selected_backends`. Specifically, `selected_backends` may be set as follows:
 
@@ -143,7 +143,7 @@ PaddleX provides default high-performance inference configurations for each mode
     * GPU: NVIDIA Tesla T4
     * CUDA Version: 11.8
     * cuDNN Version: 8.6
-    * Docker
+    * Docker：registry.baidubce.com/paddlepaddle/paddle:latest-dev-cuda11.8-cudnn8.6-trt8.5-gcc82
 
 ## 2. Pipelines and Models Supporting High-Performance Inference Plugins
 
@@ -188,7 +188,7 @@ PaddleX provides default high-performance inference configurations for each mode
 
   <tr>
     <td>Text Recognition</td>
-    <td>PP-OCRv4_server_rec<br/>PP-OCRv4_mobile_rec<br/>LaTeX_OCR_rec<br/>ch_RepSVTR_rec<br/>ch_SVTRv2_rec</td>
+    <td>PP-OCRv4_server_rec<br/>PP-OCRv4_mobile_rec<br/>ch_RepSVTR_rec<br/>ch_SVTRv2_rec</td>
   </tr>
 
   <tr>
@@ -213,11 +213,11 @@ PaddleX provides default high-performance inference configurations for each mode
 
   <tr>
     <td>Text Recognition</td>
-    <td>PP-OCRv4_server_rec<br/>PP-OCRv4_mobile_rec</td>
+    <td>PP-OCRv4_server_rec<br/>PP-OCRv4_mobile_rec<br/>ch_RepSVTR_rec<br/>ch_SVTRv2_rec</td>
   </tr>
 
   <tr>
-    <td rowspan="15">Document Scene Information Extraction v3 Pipeline</td>
+    <td rowspan="15">Document Scene Information Extraction v3</td>
     <td rowspan="2">Table Recognition</td>
     <td>SLANet</td>
   </tr>

docs/pipeline_deploy/lite_deploy_en.md

@@ -182,7 +182,7 @@ This guide applies to 8 models across 6 modules:
 
 3. Switch the working directory to `PaddleX_Lite_Deploy/{Task_Name}/android/shell/cxx/{Demo_Name}`, run the `build.sh` script to complete the compilation and execution of the executable file.
 
-4. Switch the working directory to `PaddleX-Lite-Deploy/{Task_Name}/android/shell/cxx/{Demo_Name}`, run the `run.sh` script to complete the prediction on the edge side.
+4. Switch the working directory to `PaddleX-Lite-Deploy/{Task_Name}/android/shell/cxx/{Demo_Name}`, run the `run.sh` script to complete the prediction on the edge.
 
     **Note**:
     - `{Pipeline_Name}` and `{Demo_Name}` are placeholders. Refer to the table at the end of this section for specific values.
@@ -302,11 +302,11 @@ This section describes the deployment steps applicable to the demos listed in th
 </table>
 
 **Note**
-- Currently, there is no demo for deploying the Layout Area Detection module on the edge side, so the `picodet_detection` demo is reused to deploy the `PicoDet_layout_1x` model.
+- Currently, there is no demo for deploying the Layout Area Detection module on the edge, so the `picodet_detection` demo is reused to deploy the `PicoDet_layout_1x` model.
 
 ## Reference Materials
 
-This guide only introduces the basic installation and usage process of the edge-side deployment demo. If you want to learn more detailed information, such as code introduction, code explanation, updating models, updating input and output preprocessing, updating prediction libraries, etc., please refer to the following documents:
+This guide only introduces the basic installation and usage process of the edge deployment demo. If you want to learn more detailed information, such as code introduction, code explanation, updating models, updating input and output preprocessing, updating prediction libraries, etc., please refer to the following documents:
 
 - [Object Detection](https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/feature/paddle-x/object_detection/android/shell/cxx/picodet_detection)
 - [Semantic Segmentation](https://github.com/PaddlePaddle/Paddle-Lite-Demo/blob/feature/paddle-x/semantic_segmentation/android/shell/cxx/semantic_segmentation/README.md)
@@ -315,4 +315,4 @@ This guide only introduces the basic installation and usage process of the edge-
 
 ## Feedback Section
 
-The edge-side deployment capabilities are continuously optimized. Welcome to submit [issue](https://github.com/PaddlePaddle/PaddleX/issues/new/choose) to report problems and needs, and we will follow up promptly.
+The edge deployment capabilities are continuously optimized. Welcome to submit [issue](https://github.com/PaddlePaddle/PaddleX/issues/new/choose) to report problems and needs, and we will follow up promptly.

docs/pipeline_deploy/service_deploy.md

@@ -50,11 +50,11 @@ INFO:     Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)
 | 名称             | 说明                                                                                                                                                        |
 |------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | `--pipeline`       | 产线名称或产线配置文件路径。                                                                                                                                |
-| `--device`         | 产线部署设备。默认为 `cpu`（如机器不支持 `GPU`）或 `gpu`（如机器支持 `GPU`）。                                                                                       |
+| `--device`         | 产线部署设备。默认为 `cpu`（如 GPU 不可用）或 `gpu`（如 GPU 可用）。                                                                                       |
 | `--host`           | 服务器绑定的主机名或 IP 地址。默认为0.0.0.0。                                                                                                               |
 | `--port`           | 服务器监听的端口号。默认为8080。                                                                                                                            |
 | `--use_hpip`       | 如果指定，则启用高性能推理插件。                                                                                                                            |
-| `--serial_number`  | 高性能推理插件使用的序列号。只在启用高性能推理插件时生效。 请注意，并非所有产线、模型都支持使用高性能推理插件，详细的支持情况请参考[PaddleX 高性能部署指南](./high_performance_deploy.md)。 |
+| `--serial_number`  | 高性能推理插件使用的序列号。只在启用高性能推理插件时生效。 请注意，并非所有产线、模型都支持使用高性能推理插件，详细的支持情况请参考[PaddleX 高性能推理指南](./high_performance_inference.md)。 |
 | `--update_license` | 如果指定，则进行联网激活。只在启用高性能推理插件时生效。                                                                                                    |
 
 </table>
@@ -72,8 +72,8 @@ INFO:     Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)
 | 通用图像多标签分类产线 | [通用图像多标签分类产线使用教程](../pipeline_usage/tutorials/cv_pipelines/image_multi_label_lassification.md) |
 | 小目标检测产线         | [小目标检测产线使用教程](../pipeline_usage/tutorials/cv_pipelines/small_object_detection.md)         |
 | 图像异常检测产线       | [图像异常检测产线使用教程](../pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.md)       |
-| 通用OCR产线            | [通用OCR产线使用教程](../pipeline_usage/tutorials/ocr_pipelies/OCR.md)            |
-| 通用表格识别产线       | [通用表格识别产线使用教程](../pipeline_usage/tutorials/ocr_pipelies/table_recognition.md)       |
+| 通用OCR产线            | [通用OCR产线使用教程](../pipeline_usage/tutorials/ocr_pipelines/OCR.md)            |
+| 通用表格识别产线       | [通用表格识别产线使用教程](../pipeline_usage/tutorials/ocr_pipelines/table_recognition.md)       |
 | 时序预测产线           | [时序预测产线使用教程](../pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting.md)           |
 | 时序异常检测产线       | [时序异常检测产线使用教程](../pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection.md)       |
 | 时序分类产线           | [时序分类产线使用教程](../pipeline_usage/tutorials/time_series_pipelines/time_series_classification.md)           |
@@ -87,7 +87,7 @@ INFO:     Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)
 
 在对于服务响应时间要求较严格的应用场景中，可以使用 PaddleX 高性能推理插件对模型推理及前后处理进行加速，从而降低响应时间、提升吞吐量。
 
-使用 PaddleX 高性能推理插件，请参考[PaddleX 高性能部署指南](./high_performance_deploy.md)中安装高性能推理插件、获取序列号与激活部分完成插件的安装与序列号的申请。同时，不是所有的产线、模型和环境都支持使用高性能推理插件，支持的详细情况请参考支持使用高性能推理插件的产线与模型部分。
+使用 PaddleX 高性能推理插件，请参考[PaddleX 高性能推理指南](./high_performance_inference.md)中安装高性能推理插件、获取序列号与激活部分完成插件的安装与序列号的申请。同时，不是所有的产线、模型和环境都支持使用高性能推理插件，支持的详细情况请参考支持使用高性能推理插件的产线与模型部分。
 
 在启动 PaddleX 产线服务时，可以通过指定 `--use_hpip` 及序列号以使用高性能推理插件。如果希望进行联网激活 需指定 `--update_license`。使用示例：
 

docs/pipeline_deploy/service_deploy_en.md

@@ -5,7 +5,7 @@
 Serving deployment is a common form of deployment in real-world production environments. By encapsulating inference capabilities as services, clients can access these services through network requests to obtain inference results. PaddleX enables users to achieve low-cost serving deployment for production lines. This document will first introduce the basic process of serving deployment using PaddleX, followed by considerations and potential operations when using the service in a production environment.
 
 **Note**
-- **Serving deployment provides services for model production lines, not specific to individual production line modules.**
+- **Serving deployment provides services for model pipelines, not specific to individual pipeline modules.**
 
 Serving Deployment Example Diagram:
 
@@ -51,16 +51,16 @@ Command-line options related to serving deployment are as follows:
 | Name             | Description                                                                                                                                                   |
 |------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | `--pipeline`       | Pipeline name or pipeline configuration file path.                                                                                                             |
-| `--device`         | Deployment device for the pipeline. Defaults to `cpu` (if the machine does not support `GPU`) or `gpu` (if the machine supports `GPU`).                                |
+| `--device`         | Deployment device for the pipeline. Defaults to `cpu` (If GPU is unavailable) or `gpu` (If GPU is available).                                |
 | `--host`           | Hostname or IP address bound to the server. Defaults to 0.0.0.0.                                                                                                |
 | `--port`           | Port number listened to by the server. Defaults to 8080.                                                                                                       |
 | `--use_hpip`       | Enables the high-performance inference plugin if specified.                                                                                                    |
-| `--serial_number`  | Serial number used by the high-performance inference plugin. Only valid when the high-performance inference plugin is enabled. Note that not all pipelines and models support the use of the high-performance inference plugin. For detailed support, please refer to the [PaddleX High-Performance Deployment Guide](./high_performance_deploy_en.md). |
+| `--serial_number`  | Serial number used by the high-performance inference plugin. Only valid when the high-performance inference plugin is enabled. Note that not all pipelines and models support the use of the high-performance inference plugin. For detailed support, please refer to the [PaddleX High-Performance Inference Guide](./high_performance_inference_en.md). |
 | `--update_license` | Activates the license online if specified. Only valid when the high-performance inference plugin is enabled.                                                      |
 
 </table>
 
-### 1.3 Calling the Service
+### 1.3 Call the Service
 
 Please refer to the **"Development Integration/Deployment"** section in the usage tutorials for each pipeline.
 
@@ -78,17 +78,17 @@ Please refer to the **"Development Integration/Deployment"** section in the usag
 | Time Series Forecasting Pipeline | [Tutorial for Using the Time Series Forecasting Pipeline](../pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting_en.md) |
 | Time Series Anomaly Detection Pipeline | [Tutorial for Using the Time Series Anomaly Detection Pipeline](../pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection_en.md) |
 | Time Series Classification Pipeline | [Tutorial for Using the Time Series Classification Pipeline](../pipeline_usage/tutorials/time_series_pipelines/time_series_classification_en.md) |
-| Document Scene Information Extraction v3 Pipeline | [Tutorial for Using the Document Scene Information Extraction v3 Pipeline](../pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_en.md) |
+| Document Scene Information Extraction v3 Pipeline | [Tutorial for Using the Document Scene Information Extraction v3 Pipeline](../pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction_en.md) |
 
-## 2. Deploying Services for Production
+## 2. Deploy Services for Production
 
 When deploying services into production environments, the stability, efficiency, and security of the services are of paramount importance. Below are some recommendations for deploying services into production.
 
-### 2.1 Utilizing PaddleX High-Performance Inference Plugin
+### 2.1 Utilize PaddleX high-performance inference Plugin
 
-In scenarios where strict response time requirements are imposed on applications, the PaddleX High-Performance Inference Plugin can be used to accelerate model inference and pre/post-processing, thereby reducing response time and increasing throughput.
+In scenarios where strict response time requirements are imposed on applications, the PaddleX high-performance inference Plugin can be used to accelerate model inference and pre/post-processing, thereby reducing response time and increasing throughput.
 
-To use the PaddleX High-Performance Inference Plugin, please refer to the [PaddleX High-Performance Deployment Guide](./high_performance_deploy_en.md) for installing the high-performance inference plugin, obtaining serial numbers, and activating the plugin. Additionally, not all pipelines, models, and environments support the use of the high-performance inference plugin. For detailed support information, please refer to the section on pipelines and models that support the high-performance inference plugin.
+To use the PaddleX high-performance inference Plugin, please refer to the [PaddleX High-Performance Inference Guide](./high_performance_inference_en.md) for installing the high-performance inference plugin, obtaining serial numbers, and activating the plugin. Additionally, not all pipelines, models, and environments support the use of the high-performance inference plugin. For detailed support information, please refer to the section on pipelines and models that support the high-performance inference plugin.
 
 When starting the PaddleX pipeline service, you can specify `--use_hpip` along with the serial number to use the high-performance inference plugin. If you wish to perform online activation, you should also specify `--update_license`. Example usage:
 
@@ -99,6 +99,6 @@ paddlex --serve --pipeline image_classification --use_hpip --serial_number {seri
 paddlex --serve --pipeline image_classification --use_hpip --serial_number {serial_number} --update_license
 ```
 
-### 2.2 Considering Security
+### 2.2 Consider Security
 
 A typical scenario involves an application accepting inputs from the network, with the PaddleX pipeline service acting as a module within the application, interacting with other modules through APIs. In this case, the position of the PaddleX pipeline service within the application is crucial. The service-oriented deployment solution provided by PaddleX focuses on efficiency and ease of use but does not perform sufficient security checks on request bodies. Malicious requests from the network, such as excessively large images or carefully crafted data, can lead to severe consequences like service crashes. Therefore, it is recommended to place the PaddleX pipeline service within the application's internal network, avoiding direct processing of external inputs, and ensuring it only processes trustworthy requests. Appropriate protective measures, such as input validation and authentication, should be added at the application's outer layer.

docs/pipeline_usage/pipeline_develop_guide.md

@@ -182,7 +182,7 @@ Pipeline:
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考[PaddleX高性能部署指南](../pipeline_deploy/high_performance_deploy.md)。
+🚀 **高性能部署**：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考[PaddleX高性能部署指南](../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../pipeline_deploy/service_deploy.md)。
 

docs/pipeline_usage/pipeline_develop_guide_en.md

@@ -178,7 +178,7 @@ If you need to apply the pipeline directly in your Python project, you can refer
 In addition, PaddleX also provides three other deployment methods, with detailed instructions as follows:
 
 
-🚀 **High-Performance Deployment**: In actual production environments, many applications have stringent standards for the performance metrics (especially response speed) of deployment strategies to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins that aim to deeply optimize model inference and pre/post-processing for significant speedups in the end-to-end process. Refer to the [PaddleX High-Performance Deployment Guide](../pipeline_deploy/high_performance_deploy_en.md) for detailed high-performance deployment procedures.
+🚀 **high-performance inference**: In actual production environments, many applications have stringent standards for the performance metrics (especially response speed) of deployment strategies to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins that aim to deeply optimize model inference and pre/post-processing for significant speedups in the end-to-end process. Refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference_en.md) for detailed high-performance inference procedures.
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving low-cost service-oriented deployment of pipelines. Refer to the [PaddleX Service-Oriented Deployment Guide](../pipeline_deploy/service_deploy_en.md) for detailed service-oriented deployment procedures.
 

docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.md

@@ -136,7 +136,7 @@ for res in output:
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_deploy.md)。
+🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../../../pipeline_deploy/service_deploy.md)。
 

docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection_en.md

@@ -137,7 +137,7 @@ If you need to apply the pipeline directly in your Python project, refer to the
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
-🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing to significantly speed up the end-to-end process. For detailed High-Performance Inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_deploy_en.md).
+🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing to significantly speed up the end-to-end process. For detailed high-performance inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference_en.md).
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving low-cost service-oriented deployment of pipelines. For detailed service-oriented deployment procedures, refer to the [PaddleX Service-Oriented Deployment Guide](../../../pipeline_deploy/service_deploy_en.md).
 

docs/pipeline_usage/tutorials/cv_pipelines/image_classification.md

@@ -737,7 +737,7 @@ for res in output:
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_deploy.md)。
+🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../../../pipeline_deploy/service_deploy.md)。
 

docs/pipeline_usage/tutorials/cv_pipelines/image_classification_en.md

@@ -738,7 +738,7 @@ If you need to apply the pipeline directly in your Python project, refer to the
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
-🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end speedups. For detailed High-Performance Inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_deploy_en.md).
+🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end speedups. For detailed high-performance inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference_en.md).
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving low-cost service-oriented deployment of pipelines. For detailed service-oriented deployment procedures, refer to the [PaddleX Service-Oriented Deployment Guide](../../../pipeline_deploy/service_deploy_en.md).
 

docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md

@@ -146,7 +146,7 @@ for res in output:
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_deploy.md)。
+🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../../../pipeline_deploy/service_deploy.md)。
 

docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification_en.md

@@ -144,7 +144,7 @@ If you need to directly apply the pipeline in your Python project, refer to the
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
-🚀 **High-Performance Inference**: In actual production environments, many applications have strict standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins that aim to deeply optimize model inference and pre/post-processing to significantly speed up the end-to-end process. For detailed High-Performance Inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_deploy_en.md).
+🚀 **High-Performance Inference**: In actual production environments, many applications have strict standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins that aim to deeply optimize model inference and pre/post-processing to significantly speed up the end-to-end process. For detailed high-performance inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference_en.md).
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving low-cost service-oriented deployment of pipelines. For detailed service-oriented deployment procedures, refer to the [PaddleX Service-Oriented Deployment Guide](../../../pipeline_deploy/service_deploy_en.md).
 

docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.md

@@ -160,7 +160,7 @@ for res in output:
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_deploy.md)。
+🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../../../pipeline_deploy/service_deploy.md)。
 

docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation_en.md

@@ -167,7 +167,7 @@ If you need to directly apply the pipeline in your Python project, you can refer
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
-🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins that aim to deeply optimize model inference and pre/post-processing for significant speedups in the end-to-end process. For detailed High-Performance Inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_deploy_en.md).
+🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins that aim to deeply optimize model inference and pre/post-processing for significant speedups in the end-to-end process. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference_en.md).
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving low-cost service-oriented deployment of pipelines. For detailed service-oriented deployment procedures, please refer to the [PaddleX Service-Oriented Deployment Guide](../../../pipeline_deploy/service_deploy_en.md).
 

docs/pipeline_usage/tutorials/cv_pipelines/object_detection.md

@@ -454,7 +454,7 @@ for res in output:
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_deploy.md)。
+🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../../../pipeline_deploy/service_deploy.md)。
 

docs/pipeline_usage/tutorials/cv_pipelines/object_detection_en.md

@@ -455,7 +455,7 @@ If you need to directly apply the pipeline in your Python project, refer to the
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
-🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies, especially response speed, to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing to significantly speed up the end-to-end process. Refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_deploy.md) for detailed High-Performance Inference procedures.
+🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies, especially response speed, to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing to significantly speed up the end-to-end process. Refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.md) for detailed high-performance inference procedures.
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving low-cost service-oriented deployment of pipelines. Refer to the [PaddleX Service-Oriented Deployment Guide](../../../pipeline_deploy/service_deploy.md) for detailed service-oriented deployment procedures.
 

docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation.md

@@ -167,7 +167,7 @@ for res in output:
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_deploy.md)。
+🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../../../pipeline_deploy/service_deploy.md)。
 

docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation_en.md

@@ -172,7 +172,7 @@ If you need to directly apply the pipeline in your Python project, refer to the
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
-🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins that aim to deeply optimize model inference and pre/post-processing for significant end-to-end speedups. For detailed High-Performance Inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_deploy_en.md).
+🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins that aim to deeply optimize model inference and pre/post-processing for significant end-to-end speedups. For detailed high-performance inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference_en.md).
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving low-cost service-oriented deployment of pipelines. For detailed service-oriented deployment procedures, refer to the [PaddleX Service-Oriented Deployment Guide](../../../pipeline_deploy/service_deploy_en.md).
 

docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection.md

@@ -143,7 +143,7 @@ for res in output:
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_deploy.md)。
+🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../../../pipeline_deploy/service_deploy.md)。
 

docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection_en.md

@@ -144,7 +144,7 @@ If you need to apply the pipeline directly in your Python project, refer to the
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
-🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end speedups. For detailed High-Performance Inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_deploy_en.md).
+🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end speedups. For detailed high-performance inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference_en.md).
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving low-cost service-oriented deployment of pipelines. For detailed service-oriented deployment procedures, refer to the [PaddleX Service-Oriented Deployment Guide](../../../pipeline_deploy/service_deploy_en.md).
 

docs/pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction.md

@@ -331,7 +331,7 @@ chat_result.print()
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_deploy.md)。
+🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../../../pipeline_deploy/service_deploy.md)。
 
@@ -432,7 +432,7 @@ chat_result.print()
         |`llmName`|`string`|大语言模型名称。|否|
         |`llmParams`|`object`|大语言模型API参数。|否|
 
-        当前，`llmParams`可以采用如下两种形式之一：
+        当前，`llmParams` 可以采用如下形式：
 
         ```json
         {
@@ -442,13 +442,6 @@ chat_result.print()
         }
         ```
 
-        ```json
-        {
-          "apiType": "{aistudio}",
-          "accessToken": "{AI Studio访问令牌}"
-        }
-        ```
-
     - 请求处理成功时，响应体的`result`具有如下属性：
 
         |名称|类型|含义|
@@ -470,7 +463,7 @@ chat_result.print()
         |`llmName`|`string`|大语言模型名称。|否|
         |`llmParams`|`object`|大语言模型API参数。|否|
 
-        当前，`llmParams`可以采用如下两种形式之一：
+        当前，`llmParams` 可以采用如下形式：
 
         ```json
         {
@@ -480,13 +473,6 @@ chat_result.print()
         }
         ```
 
-        ```json
-        {
-          "apiType": "{aistudio}",
-          "accessToken": "{AI Studio访问令牌}"
-        }
-        ```
-
     - 请求处理成功时，响应体的`result`具有如下属性：
 
         |名称|类型|含义|
@@ -514,7 +500,7 @@ chat_result.print()
         |`llmName`|`string`|大语言模型名称。|否|
         |`llmParams`|`object`|大语言模型API参数。|否|
 
-        当前，`llmParams`可以采用如下两种形式之一：
+        当前，`llmParams` 可以采用如下形式：
 
         ```json
         {
@@ -524,13 +510,6 @@ chat_result.print()
         }
         ```
 
-        ```json
-        {
-          "apiType": "{aistudio}",
-          "accessToken": "{AI Studio访问令牌}"
-        }
-        ```
-
     - 请求处理成功时，响应体的`result`具有如下属性：
 
         |名称|类型|含义|
@@ -724,4 +703,3 @@ pipeline = create_pipeline(
     )    
 ```
 若您想在更多种类的硬件上使用通用文档场景信息抽取产线，请参考[PaddleX多硬件使用指南](../../../other_devices_support/multi_devices_use_guide.md)。
-

docs/pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction_en.md

@@ -232,12 +232,12 @@ In the above Python script, the following steps are executed:
 
 | Parameter | Type | Default | Description |
 |-|-|-|-|
-|`input`|Python Var|无|Support to pass Python variables directly, such as `numpy.ndarray` representing image data;|
-|`input`|str|无|Support to pass the path of the file to be predicted, such as the local path of an image file: `/root/data/img.jpg`;|
-|`input`|str|无|Support to pass the URL of the file to be predicted, such as: `https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/contract.pdf`;|
-|`input`|str|无|Support to pass the local directory, which should contain files to be predicted, such as: `/root/data/`;|
-|`input`|dict|无|Support to pass a dictionary, where the key needs to correspond to the specific pipeline, such as: `{"img": "/root/data1"}`；|
-|`input`|list|无|Support to pass a list, where the elements must be of the above types of data, such as: `[numpy.ndarray, numpy.ndarray]`，`["/root/data/img1.jpg", "/root/data/img2.jpg"]`，`["/root/data1", "/root/data2"]`，`[{"img": "/root/data1"}, {"img": "/root/data2/img.jpg"}]`；|
+|`input`|Python Var|-|Support to pass Python variables directly, such as `numpy.ndarray` representing image data;|
+|`input`|str|-|Support to pass the path of the file to be predicted, such as the local path of an image file: `/root/data/img.jpg`;|
+|`input`|str|-|Support to pass the URL of the file to be predicted, such as: `https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/contract.pdf`;|
+|`input`|str|-|Support to pass the local directory, which should contain files to be predicted, such as: `/root/data/`;|
+|`input`|dict|-|Support to pass a dictionary, where the key needs to correspond to the specific pipeline, such as: `{"img": "/root/data1"}`；|
+|`input`|list|-|Support to pass a list, where the elements must be of the above types of data, such as: `[numpy.ndarray, numpy.ndarray]`，`["/root/data/img1.jpg", "/root/data/img2.jpg"]`，`["/root/data1", "/root/data2"]`，`[{"img": "/root/data1"}, {"img": "/root/data2/img.jpg"}]`；|
 |`use_doc_image_ori_cls_model`|bool|`True`|Whether or not to use the orientation classification model;|
 |`use_doc_image_unwarp_model`|bool|`True`|Whether or not to use the unwarp model;|
 |`use_seal_text_det_model`|bool|`True`|Whether or not to use the seal text detection model;|
@@ -338,7 +338,7 @@ If you need to directly apply the pipeline in your Python project, you can refer
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
-🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics (especially response speed) of deployment strategies to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing to significantly speed up the end-to-end process. For detailed High-Performance Inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_deploy_en.md).
+🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics (especially response speed) of deployment strategies to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing to significantly speed up the end-to-end process. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference_en.md).
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving low-cost service-oriented deployment of pipelines. For detailed service-oriented deployment procedures, please refer to the [PaddleX Service-Oriented Deployment Guide](../../../pipeline_deploy/service_deploy_en.md).
 
@@ -370,95 +370,167 @@ Operations provided by the service are as follows:
 
 - **`analyzeImage`**
 
-    Analyzes images using computer vision models to obtain OCR, table recognition results, etc., and extracts key information from the images.
+    Analyze images using computer vision models to obtain OCR, table recognition results, and extract key information from the images.
 
     `POST /chatocr-vision`
 
     - Request body properties:
 
         | Name | Type | Description | Required |
-        |------|------|-------------|----------|
-        | `image` | `string` | The URL of an image file or PDF file accessible by the service, or the Base64 encoded result of the content of the above-mentioned file types. For PDF files with more than 10 pages, only the content of the first 10 pages will be used. | Yes |
-        | `fileType` | `integer` | File type. `0` indicates a PDF file, `1` indicates an image file. If this property is not present in the request body, the service will attempt to automatically infer the file type based on the URL. | No |
-        | `useOricls` | `boolean` | Whether to enable document image orientation classification. This feature is enabled by default. | No |
-        | `useCurve` | `boolean` | Whether to enable seal text detection. This feature is enabled by default. | No |
-        | `useUvdoc` | `boolean` | Whether to enable text image correction. This feature is enabled by default. | No |
-        | `inferenceParams` | `object` | Inference parameters. | No |
+        |-|-|-|-|
+        |`image`|`string`|The URL of an accessible image file or PDF file, or the Base64 encoded content of the above file types. For PDF files with more than 10 pages, only the first 10 pages will be used. | Yes |
+        |`fileType`|`integer`|File type. `0` represents PDF files, `1` represents image files. If this property is not present in the request body, the service will attempt to infer the file type automatically based on the URL. | No |
+        |`useOricls`|`boolean`|Whether to enable document image orientation classification. This feature is enabled by default. | No |
+        |`useCurve`|`boolean`|Whether to enable seal text detection. This feature is enabled by default. | No |
+        |`useUvdoc`|`boolean`|Whether to enable text image correction. This feature is enabled by default. | No |
+        |`inferenceParams`|`object`|Inference parameters. | No |
 
         Properties of `inferenceParams`:
 
         | Name | Type | Description | Required |
-        |------|------|-------------|----------|
-        | `maxLongSide` | `integer` | During inference, if the length of the longer side of the input image for the text detection model is greater than `maxLongSide`, the image will be scaled so that the length of the longer side equals `maxLongSide`. | No |
+        |-|-|-|-|
+        |`maxLongSide`|`integer`|During inference, if the length of the longer side of the input image for the text detection model is greater than `maxLongSide`, the image will be scaled so that the length of the longer side equals `maxLongSide`. | No |
 
-    - When the request is processed successfully, the `result` of the response body has the following properties:
+    - When the request is processed successfully, the `result` in the response body has the following properties:
 
         | Name | Type | Description |
-        |------|------|-------------|
-        | `visionResults` | `array` | Analysis results obtained using computer vision models. The array length is 1 (for image input) or the smaller of the number of document pages and 10 (for PDF input). For PDF input, each element in the array represents the processing result of each page in the PDF file. |
-        | `visionInfo` | `object` | Key information in the image, which can be used as input for other operations. |
+        |-|-|-|
+        |`visionResults`|`array`|Analysis results obtained using the computer vision model. The array length is 1 (for image input) or the smaller of the number of document pages and 10 (for PDF input). For PDF input, each element in the array represents the processing result of each page in the PDF file in sequence. |
+        |`visionInfo`|`object`|Key information in the image, which can be used as input for other operations. |
 
         Each element in `visionResults` is an `object` with the following properties:
 
         | Name | Type | Description |
-        |------|------|-------------|
-        | `texts` | `array` | Text positions, contents, and scores. |
-        | `tables` | `array` | Table positions and contents. |
-        | `inputImage` | `string` | Input image. The image is in JPEG format and encoded using Base64. |
-        | `ocrImage` | `string` | OCR result image. The image is in JPEG format and encoded using Base64. |
-        | `layoutImage` | `string` | Layout area detection result image. The image is in JPEG format and encoded using Base64. |
+        |-|-|-|
+        |`texts`|`array`|Text locations, contents, and scores. |
+        |`tables`|`array`|Table locations and contents. |
+        |`inputImage`|`string`|Input image. The image is in JPEG format and encoded in Base64. |
+        |`ocrImage`|`string`|OCR result image. The image is in JPEG format and encoded in Base64. |
+        |`layoutImage`|`string`|Layout area detection result image. The image is in JPEG format and encoded in Base64. |
 
         Each element in `texts` is an `object` with the following properties:
 
         | Name | Type | Description |
-        |------|------|-------------|
-        | `poly` | `array` | Text position. The elements in the array are the vertex coordinates of the polygon enclosing the text in```markdown
-### chat
-
-Interact with large language models to extract key information.
-
-`POST /chatocr-vision`
-
-- Request body properties:
-
-    | Name | Type | Description | Required |
-    |------|------|-------------|----------|
-    |`keys`|`array`|List of keywords.|Yes|
-    |`visionInfo`|`object`|Key information from the image. Provided by the `analyzeImage` operation.|Yes|
-    |`taskDescription`|`string`|Task prompt.|No|
-    |`rules`|`string`|Extraction rules. Used to customize the information extraction rules, e.g., to specify output formats.|No|
-    |`fewShot`|`string`|Example prompts.|No|
-    |`useVectorStore`|`boolean`|Whether to enable the vector database. Enabled by default.|No|
-    |`vectorStore`|`object`|Serialized result of the vector database. Provided by the `buildVectorStore` operation.|No|
-    |`retrievalResult`|`string`|Knowledge retrieval result. Provided by the `retrieveKnowledge` operation.|No|
-    |`returnPrompts`|`boolean`|Whether to return the prompts used. Enabled by default.|No|
-    |`llmName`|`string`|Name of the large language model.|No|
-    |`llmParams`|`object`|API parameters for the large language model.|No|
-
-    Currently, `llmParams` can take the following form:
-
-    ```json
-    {
-      "apiType": "qianfan",
-      "apiKey": "{Qianfan Platform API key}",
-      "secretKey": "{Qianfan Platform secret key}"
-    }
-    ```
+        |-|-|-|
+        |`poly`|`array`|Text location. The elements in the array are the vertex coordinates of the polygon enclosing the text in sequence. |
+        |`text`|`string`|Text content. |
+        |`score`|`number`|Text recognition score. |
 
-- On successful request processing, the `result` in the response body has the following properties:
+        Each element in `tables` is an `object` with the following properties:
 
-    | Name | Type | Description |
-    |------|------|-------------|
-    |`chatResult`|`string`|Extracted key information result.|
-    |`prompts`|`object`|Prompts used.|
+        | Name | Type | Description |
+        |-|-|-|
+        |`bbox`|`array`|Table location. The elements in the array are the x-coordinate of the top-left corner, the y-coordinate of the top-left corner, the x-coordinate of the bottom-right corner, and the y-coordinate of the bottom-right corner of the bounding box in sequence. |
+        |`html`|`string`|Table recognition result in HTML format. |
 
-    Properties of `prompts`:
+- **`buildVectorStore`**
 
-    | Name | Type | Description |
-    |------|------|-------------|
-    |`ocr`|`string`|OCR prompt.|
-    |`table`|`string`|Table prompt.|
-    |`html`|`string`|HTML prompt.|
+    Builds a vector database.
+
+    `POST /chatocr-vector`
+
+    - The request body properties are as follows:
+
+        | Name | Type | Description | Required |
+        |-|-|-|-|
+        |`visionInfo`|`object`|Key information from the image. Provided by the `analyzeImage` operation.|Yes|
+        |`minChars`|`integer`|Minimum data length to enable the vector database.|No|
+        |`llmRequestInterval`|`number`|Interval time for calling the large language model API.|No|
+        |`llmName`|`string`|Name of the large language model.|No|
+        |`llmParams`|`object`|Parameters for the large language model API.|No|
+
+        Currently, `llmParams` can take the following form:
+
+        ```json
+        {
+          "apiType": "qianfan",
+          "apiKey": "{qianfan API key}",
+          "secretKey": "{qianfan secret key}"
+        }
+        ```
+
+    - When the request is processed successfully, the `result` in the response body has the following properties:
+
+        | Name | Type | Description |
+        |-|-|-|
+        |`vectorStore`|`object`|Serialized result of the vector database, which can be used as input for other operations.|
+
+- **`retrieveKnowledge`**
+
+    Perform knowledge retrieval.
+
+    `POST /chatocr-retrieval`
+
+    - The request body properties are as follows:
+
+        | Name | Type | Description | Required |
+        |-|-|-|-|
+        |`keys`|`array`|List of keywords.|Yes|
+        |`vectorStore`|`object`|Serialized result of the vector database. Provided by the `buildVectorStore` operation.|Yes|
+        |`llmName`|`string`|Name of the large language model.|No|
+        |`llmParams`|`object`|API parameters for the large language model.|No|
+
+        Currently, `llmParams` can take the following form:
+
+        ```json
+        {
+          "apiType": "qianfan",
+          "apiKey": "{Qianfan Platform API key}",
+          "secretKey": "{Qianfan Platform secret key}"
+        }
+        ```
+
+    - When the request is processed successfully, the `result` in the response body has the following properties:
+
+        | Name | Type | Description |
+        |-|-|-|
+        |`retrievalResult`|`object`|The result of knowledge retrieval, which can be used as input for other operations.|
+
+- **`chat`**
+
+    Interact with large language models to extract key information.
+
+    `POST /chatocr-vision`
+
+    - Request body properties:
+
+        | Name | Type | Description | Required |
+        |-|-|-|-|
+        |`keys` | `array` | List of keywords. | Yes |
+        |`visionInfo` | `object` | Key information from images. Provided by the `analyzeImage` operation. | Yes |
+        |`taskDescription` | `string` | Task prompt. | No |
+        |`rules` | `string` | Custom extraction rules, e.g., for output formatting. | No |
+        |`fewShot` | `string` | Example prompts. | No |
+        |`vectorStore` | `object` | Serialized result of the vector database. Provided by the `buildVectorStore` operation. | No |
+        |`retrievalResult` | `object` | Results of knowledge retrieval. Provided by the `retrieveKnowledge` operation. | No |
+        |`returnPrompts` | `boolean` | Whether to return the prompts used. Enabled by default. | No |
+        |`llmName` | `string` | Name of the large language model. | No |
+        |`llmParams` | `object` | API parameters for the large language model. | No |
+
+        Currently, `llmParams` can take the following form:
+
+        ```json
+        {
+          "apiType": "qianfan",
+          "apiKey": "{Qianfan Platform API key}",
+          "secretKey": "{Qianfan Platform secret key}"
+        }
+        ```
+
+    - On successful request processing, the `result` in the response body has the following properties:
+
+        | Name | Type | Description |
+        |-|-|-|
+        |`chatResult` | `string` | Extracted key information. |
+        |`prompts` | `object` | Prompts used. |
+
+        Properties of `prompts`:
+
+        | Name | Type | Description |
+        |-|-|-|
+        |`ocr` | `string` | OCR prompt. |
+        |`table` | `string` | Table prompt. |
+        |`html` | `string` | HTML prompt. |
 
 </details>
 
@@ -523,7 +595,6 @@ if __name__ == "__main__":
             f.write(base64.b64decode(res["layoutImage"]))
         print(f"Output images saved at {ocr_img_path} and {layout_img_path}")
         print("")
-    print("="*50 + "\n\n")
 
     payload = {
         "visionInfo": result_vision["visionInfo"],
@@ -540,7 +611,6 @@ if __name__ == "__main__":
         pprint.pp(resp_vector.json())
         sys.exit(1)
     result_vector = resp_vector.json()["result"]
-    print("="*50 + "\n\n")
 
     payload = {
         "keys": keys,
@@ -556,9 +626,6 @@ if __name__ == "__main__":
         pprint.pp(resp_retrieval.json())
         sys.exit(1)
     result_retrieval = resp_retrieval.json()["result"]
-    print("Knowledge retrieval result:")
-    print(result_retrieval["retrievalResult"])
-    print("="*50 + "\n\n")
 
     payload = {
         "keys": keys,
@@ -566,7 +633,6 @@ if __name__ == "__main__":
         "taskDescription": "",
         "rules": "",
         "fewShot": "",
-        "useVectorStore": True,
         "vectorStore": result_vector["vectorStore"],
         "retrievalResult": result_retrieval["retrievalResult"],
         "returnPrompts": True,
@@ -581,33 +647,44 @@ if __name__ == "__main__":
         pprint.pp(resp_chat.json())
         sys.exit(1)
     result_chat = resp_chat.json()["result"]
-    print("Prompts:")
+    print("\nPrompts:")
     pprint.pp(result_chat["prompts"])
     print("Final result:")
     print(len(result_chat["chatResult"]))
 ```
+
 **Note**: Please fill in your API key and secret key at `API_KEY` and `SECRET_KEY`.
+
 </details>
 </details>
 <br/>
 
 📱 **Edge Deployment**: Edge deployment is a method that places computing and data processing functions on user devices themselves, allowing devices to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/lite_deploy_en.md).
+
 ## 4. Custom Development
+
 If the default model weights provided by the PP-ChatOCRv3-doc Pipeline do not meet your requirements in terms of accuracy or speed for your specific scenario, you can attempt to further **fine-tune** the existing models using **your own domain-specific or application-specific data** to enhance the recognition performance of the general table recognition pipeline in your scenario.
 
 ### 4.1 Model Fine-tuning
+
 Since the PP-ChatOCRv3-doc Pipeline comprises six modules, unsatisfactory performance may stem from any of these modules (note that the text image rectification module does not support customization at this time).
 
 You can analyze images with poor recognition results and follow the guidelines below for analysis and model fine-tuning:
 
 * Incorrect table structure detection (e.g., row/column misidentification, cell position errors) may indicate deficiencies in the table structure recognition module. You need to refer to the **Customization** section in the [Table Structure Recognition Module Development Tutorial](../../../module_usage/tutorials/ocr_modules/table_structure_recognition_en.md) and fine-tune the table structure recognition model using your private dataset.
+
 * Misplaced layout elements (e.g., incorrect positioning of tables or seals) may suggest issues with the layout detection module. Consult the **Customization** section in the [Layout Detection Module Development Tutorial](../../../module_usage/tutorials/ocr_modules/layout_detection_en.md) and fine-tune the layout detection model with your private dataset.
+
 * Frequent undetected text (i.e., text leakage) may indicate limitations in the text detection model. Refer to the **Customization** section in the [Text Detection Module Development Tutorial](../../../module_usage/tutorials/ocr_modules/text_detection_en.md) and fine-tune the text detection model using your private dataset.
+
 * High text recognition errors (i.e., recognized text content does not match the actual text) suggest that the text recognition model requires improvement. Follow the **Customization** section in the [Text Recognition Module Development Tutorial](../../../module_usage/tutorials/ocr_modules/text_recognition_en.md) to fine-tune the text recognition model.
+
 * Frequent recognition errors in detected seal text indicate that the seal text detection model needs further refinement. Consult the **Customization** section in the [Seal Text Detection Module Development Tutorials](../../../module_usage/tutorials/ocr_modules/seal_text_detection_en.md) to fine-tune the seal text detection model.
+
 * Frequent misidentifications of document or certificate orientations with text regions suggest that the document image orientation classification model requires improvement. Refer to the **Customization** section in the [Document Image Orientation Classification Module Development Tutorial](../../../module_usage/tutorials/ocr_modules/doc_img_orientation_classification_en.md) to fine-tune the document image orientation classification model.
 
 ### 4.2 Model Deployment
+
 After fine-tuning your models using your private dataset, you will obtain local model weights files.
 
 To use the fine-tuned model weights, simply modify the pipeline configuration file by replacing the local paths of the default model weights with those of your fine-tuned models:
@@ -642,4 +719,5 @@ pipeline = create_pipeline(
     device="npu:0" # gpu:0 --> npu:0
     ) 
 ```
-If you want to use the PP-ChatOCRv3-doc Pipeline on more types of hardware, please refer to the [PaddleX Multi-Device Usage Guide](../../../installation/installation_other_devices_en.md).
+
+If you want to use the PP-ChatOCRv3-doc Pipeline on more types of hardware, please refer to the [PaddleX Multi-Device Usage Guide](../../../installation/multi_devices_use_guide_en.md).

docs/pipeline_usage/tutorials/ocr_pipelines/OCR.md

@@ -225,7 +225,7 @@ for res in output:
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_deploy.md)。
+🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../../../pipeline_deploy/service_deploy.md)。
 

docs/pipeline_usage/tutorials/ocr_pipelines/OCR_en.md

@@ -160,7 +160,7 @@ Among them, `dt_polys` is the detected text box coordinates, `dt_polys` is the d
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/ocr/03.png)
 
-The visualized image not saved by default. You can customize the save path through `--save_path`, and then all results will be saved in the specified path. 
+The visualized image not saved by default. You can customize the save path through `--save_path`, and then all results will be saved in the specified path.
 
 </details>
 
@@ -174,8 +174,8 @@ pipeline = create_pipeline(pipeline="OCR")
 
 output = pipeline.predict("general_ocr_002.png")
 for res in output:
-    res.print() 
-    res.save_to_img("./output/") 
+    res.print()
+    res.save_to_img("./output/")
 ```
 > ❗ The results obtained from running the Python script are the same as those from the command line.
 
@@ -220,7 +220,7 @@ pipeline = create_pipeline(pipeline="./my_path/OCR.yaml")
 output = pipeline.predict("general_ocr_002.png")
 for res in output:
     res.print()
-    res.save_to_img("./output/") 
+    res.save_to_img("./output/")
 ```
 
 ## 3. Development Integration/Deployment
@@ -230,7 +230,7 @@ If you need to apply the general OCR pipeline directly in your Python project, r
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
-🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end speedups. For detailed High-Performance Inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_deploy_en.md).
+🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end speedups. For detailed high-performance inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference_en.md).
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving low-cost service-oriented deployment of pipelines. For detailed service-oriented deployment procedures, refer to the [PaddleX Service-Oriented Deployment Guide](../../../pipeline_deploy/service_deploy_en.md).
 

docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.md

@@ -174,7 +174,7 @@ for res in output:
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_deploy.md)。
+🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../../../pipeline_deploy/service_deploy.md)。
 

docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition_en.md

@@ -174,7 +174,7 @@ If you need to apply the general formula recognition pipeline directly in your P
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
-🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end speedups. For detailed High-Performance Inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_deploy_en.md).
+🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end speedups. For detailed high-performance inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference_en.md).
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving low-cost service-oriented deployment of pipelines. For detailed service-oriented deployment procedures, refer to the [PaddleX Service-Oriented Deployment Guide](../../../pipeline_deploy/service_deploy_en.md).
 

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.md

@@ -246,7 +246,7 @@ for res in output:
 |save_to_xlsx|将结果保存为表格格式的文件|`- save_path`：str类型，保存的文件路径，当为目录时，保存文件命名与输入文件类型命名一致；|
 
 其中，`save_to_img` 能够保存可视化结果（包括OCR结果图片、版面分析结果图片、表格结构识别结果图片）， `save_to_html` 能够将表格直接保存为html文件（包括文本和表格格式），`save_to_xlsx` 能够将表格保存为Excel格式文件（包括文本和格式）。
- 
+
 若您获取了配置文件，即可对表格识别产线各项配置进行自定义，只需要修改 `create_pipeline` 方法中的 `pipeline` 参数值为产线配置文件路径即可。
 
 例如，若您的配置文件保存在 `./my_path/table_recognition.yaml` ，则只需执行：
@@ -268,7 +268,7 @@ for res in output:
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_deploy.md)。
+🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../../../pipeline_deploy/service_deploy.md)。
 

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition_en.md

@@ -127,7 +127,7 @@ After running, the result is:
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/table_recognition/03.png)
 
-The visualized image not saved by default. You can customize the save path through `--save_path`, and then all results will be saved in the specified path. 
+The visualized image not saved by default. You can customize the save path through `--save_path`, and then all results will be saved in the specified path.
 
 ### 2.2 Python Script Integration
 A few lines of code are all you need to quickly perform inference with the pipeline. Taking the General Table Recognition pipeline as an example:
@@ -201,7 +201,7 @@ If you need to directly apply the pipeline in your Python project, refer to the
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
-🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins that aim to deeply optimize model inference and pre/post-processing for significant end-to-end process acceleration. For detailed High-Performance Inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_deploy_en.md).
+🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins that aim to deeply optimize model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.md).
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving low-cost service-oriented deployment of pipelines. For detailed service-oriented deployment procedures, refer to the [PaddleX Service-Oriented Deployment Guide](../../../pipeline_deploy/service_deploy_en.md).
 

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection.md

@@ -165,7 +165,7 @@ for res in output:
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_deploy.md)。
+🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../../../pipeline_deploy/service_deploy.md)。
 

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection_en.md

@@ -160,7 +160,7 @@ If you need to directly apply the pipeline in your Python project, refer to the
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
-🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end speedups. For detailed High-Performance Inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_deploy_en.md).
+🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for the performance metrics of deployment strategies (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end speedups. For detailed high-performance inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference_en.md).
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX enables users to achieve low-cost service-oriented deployment of pipelines. For detailed service-oriented deployment procedures, refer to the [PaddleX Service-Oriented Deployment Guide](../../../pipeline_deploy/service_deploy_en.md).
 

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification.md

@@ -147,7 +147,7 @@ for res in output:
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_deploy.md)。
+🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../../../pipeline_deploy/service_deploy.md)。
 

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification_en.md

@@ -151,7 +151,7 @@ If you need to directly apply the pipeline in your Python project, refer to the
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
-🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for deployment performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins that deeply optimize model inference and pre/post-processing to significantly speed up the end-to-end process. Refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_deploy_en.md) for detailed High-Performance Inference procedures.
+🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for deployment performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins that deeply optimize model inference and pre/post-processing to significantly speed up the end-to-end process. Refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference_en.md) for detailed high-performance inference procedures.
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX enables users to achieve low-cost service-oriented deployment of pipelines. Refer to the [PaddleX Service-Oriented Deployment Guide](../../../pipeline_deploy/service_deploy_en.md) for detailed service-oriented deployment procedures.
 

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting.md

@@ -163,7 +163,7 @@ for res in output:
 
 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_deploy.md)。
+🚀 **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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能推理流程请参考[PaddleX高性能推理指南](../../../pipeline_deploy/high_performance_inference.md)。
 
 ☁️ **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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考[PaddleX服务化部署指南](../../../pipeline_deploy/service_deploy.md)。
 

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting_en.md

@@ -162,7 +162,7 @@ If you need to directly apply the pipeline in your Python project, refer to the
 
 Additionally, PaddleX provides three other deployment methods, detailed as follows:
 
-🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed High-Performance Inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_deploy_en.md).
+🚀 **High-Performance Inference**: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference_en.md).
 
 ☁️ **Service-Oriented Deployment**: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving low-cost service-oriented deployment of pipelines. For detailed service-oriented deployment procedures, refer to the [PaddleX Service-Oriented Deployment Guide](../../../pipeline_deploy/service_deploy_en.md).
 

docs/practical_tutorials/image_classification_garbage_tutorial.md

@@ -251,7 +251,7 @@ for res in output:
 
 2. 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-* 高性能部署：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能部署指南](../pipeline_deploy/high_performance_deploy.md)。
+* 高性能部署：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/service_deploy.md)。
 * 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/lite_deploy.md)。
 

docs/practical_tutorials/image_classification_garbage_tutorial_en.md

@@ -254,7 +254,7 @@ For more parameters, please refer to the [General Image Classification Pipeline
 
 2. Additionally, PaddleX offers three other deployment methods, detailed as follows:
 
-* High-Performance Deployment: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance deployment procedures, please refer to the [PaddleX High-Performance Deployment Guide](../pipeline_deploy/high_performance_deploy_en.md).
+* high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugin aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference_en.md).
 * Service-Oriented Deployment: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective service-oriented deployment of production lines. For detailed service-oriented deployment procedures, please refer to the [PaddleX Service-Oriented Deployment Guide](../pipeline_deploy/service_deploy_en.md).
 * Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/lite_deploy_en.md).
 

docs/practical_tutorials/instance_segmentation_remote_sensing_tutorial.md

@@ -249,7 +249,7 @@ for res in output:
 
 2. 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-* 高性能部署：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能部署指南](../pipeline_deploy/high_performance_deploy.md)。
+* 高性能部署：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/service_deploy.md)。
 * 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/lite_deploy.md)。
 

docs/practical_tutorials/instance_segmentation_remote_sensing_tutorial_en.md

@@ -254,7 +254,7 @@ For more parameters, please refer to the [General Instance Segmentation Pipline
 
 2. Additionally, PaddleX offers three other deployment methods, detailed as follows:
 
-* High-Performance Deployment: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance deployment procedures, please refer to the [PaddleX High-Performance Deployment Guide](../pipeline_deploy/high_performance_deploy_en.md).
+* high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference_en.md).
 * Service-Oriented Deployment: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective service-oriented deployment of production lines. For detailed service-oriented deployment procedures, please refer to the [PaddleX Service-Oriented Deployment Guide](../pipeline_deploy/service_deploy_en.md).
 * Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/lite_deploy_en.md).
 

docs/practical_tutorials/object_detection_fall_tutorial.md

@@ -250,7 +250,7 @@ for res in output:
 
 2. 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-* 高性能部署：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能部署指南](../pipeline_deploy/high_performance_deploy.md)。
+* 高性能部署：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/service_deploy.md)。
 * 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/lite_deploy.md)。
 

docs/practical_tutorials/object_detection_fall_tutorial_en.md

@@ -252,7 +252,7 @@ For more parameters, please refer to [General Object Detection Pipeline Usage Tu
 
 2. Additionally, PaddleX offers three other deployment methods, detailed as follows:
 
-* High-Performance Deployment: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance deployment procedures, please refer to the [PaddleX High-Performance Deployment Guide](../pipeline_deploy/high_performance_deploy_en.md).
+* high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference_en.md).
 * Service-Oriented Deployment: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective service-oriented deployment of production lines. For detailed service-oriented deployment procedures, please refer to the [PaddleX Service-Oriented Deployment Guide](../pipeline_deploy/service_deploy_en.md).
 * Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/lite_deploy_en.md).
 

docs/practical_tutorials/object_detection_fashion_pedia_tutorial.md

@@ -251,7 +251,7 @@ for res in output:
 
 2. 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-* 高性能部署：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能部署指南](../pipeline_deploy/high_performance_deploy.md)。
+* 高性能部署：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/service_deploy.md)。
 * 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/lite_deploy.md)。
 

docs/practical_tutorials/object_detection_fashion_pedia_tutorial_en.md

@@ -253,7 +253,7 @@ For more parameters, please refer to [General Object Detection Pipeline Usage Tu
 
 2. Additionally, PaddleX offers three other deployment methods, detailed as follows:
 
-* High-Performance Deployment: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance deployment procedures, please refer to the [PaddleX High-Performance Deployment Guide](../pipeline_deploy/high_performance_deploy_en.md).
+* high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference_en.md).
 * Service-Oriented Deployment: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective service-oriented deployment of production lines. For detailed service-oriented deployment procedures, please refer to the [PaddleX Service-Oriented Deployment Guide](../pipeline_deploy/service_deploy_en.md).
 * Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/lite_deploy_en.md).
 

docs/practical_tutorials/ocr_det_license_tutorial.md

@@ -254,7 +254,7 @@ for res in output:
 
 2. 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-* 高性能部署：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能部署指南](../pipeline_deploy/high_performance_deploy.md)。
+* 高性能部署：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/service_deploy.md)。
 * 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/lite_deploy.md)。
 

docs/practical_tutorials/ocr_det_license_tutorial_en.md

@@ -256,7 +256,7 @@ For more parameters, please refer to the [General OCR Pipeline Usage Tutorial](.
 
 2. Additionally, PaddleX offers three other deployment methods, detailed as follows:
 
-* High-Performance Deployment: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance deployment procedures, please refer to the [PaddleX High-Performance Deployment Guide](../pipeline_deploy/high_performance_deploy_en.md).
+* high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference_en.md).
 * Service-Oriented Deployment: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective service-oriented deployment of production lines. For detailed service-oriented deployment procedures, please refer to the [PaddleX Service-Oriented Deployment Guide](../pipeline_deploy/service_deploy_en.md).
 * Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/lite_deploy_en.md).
 

docs/practical_tutorials/ocr_rec_chinese_tutorial.md

@@ -256,7 +256,7 @@ for res in output:
 
 2. 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-* 高性能部署：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能部署指南](../pipeline_deploy/high_performance_deploy.md)。
+* 高性能部署：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/service_deploy.md)。
 * 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/lite_deploy.md)。
 

docs/practical_tutorials/ocr_rec_chinese_tutorial_en.md

@@ -259,7 +259,7 @@ For more parameters, please refer to the [General OCR Pipeline Usage Tutorial](.
 
 2. Additionally, PaddleX offers three other deployment methods, detailed as follows:
 
-* High-Performance Deployment: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance deployment procedures, please refer to the [PaddleX High-Performance Deployment Guide](../pipeline_deploy/high_performance_deploy_en.md).
+* high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference_en.md).
 * Service-Oriented Deployment: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective service-oriented deployment of production lines. For detailed service-oriented deployment procedures, please refer to the [PaddleX Service-Oriented Deployment Guide](../pipeline_deploy/service_deploy_en.md).
 * Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/lite_deploy_en.md).
 

docs/practical_tutorials/semantic_segmentation_road_tutorial.md

@@ -247,7 +247,7 @@ for res in output:
 
 2. 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 
-* 高性能部署：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能部署指南](../pipeline_deploy/high_performance_deploy.md)。
+* 高性能部署：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。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 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。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/service_deploy.md)。
 * 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/lite_deploy.md)。
 

docs/practical_tutorials/semantic_segmentation_road_tutorial_en.md

@@ -250,7 +250,7 @@ For more parameters, please refer to [General Semantic Segmentation Pipeline Usa
 
 2. Additionally, PaddleX offers three other deployment methods, detailed as follows:
 
-* High-Performance Deployment: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance deployment procedures, please refer to the [PaddleX High-Performance Deployment Guide](../pipeline_deploy/high_performance_deploy_en.md).
+* high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference_en.md).
 * Service-Oriented Deployment: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective service-oriented deployment of production lines. For detailed service-oriented deployment procedures, please refer to the [PaddleX Service-Oriented Deployment Guide](../pipeline_deploy/service_deploy_en.md).
 * Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/lite_deploy_en.md).