[cherry-pick] update ppchatocr doc (#3477)

* fix

* update

* update

* update

Author: zhang-prog

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.en.md

@@ -1614,7 +1614,11 @@ Below are the API references for basic serving and multi-language service invoca
 <td>Key information extraction result.</td>
 </tr>
 </tbody>
-</table></details>
+</table>
+<li><b>Note:</b></li>
+Including sensitive parameters such as API key for large model calls in the request body can be a security risk. If not necessary, set these parameters in the configuration file and do not pass them on request.
+<br/><br/>
+</details>
 <details><summary>Multi-language Service Invocation Examples</summary>
 <details>
 <summary>Python</summary>
@@ -1690,6 +1694,7 @@ print("Final result:")
 print(result_chat["chatResult"])
 </code></pre>
 </details>
+</details>
 <br/>
 
 📱 **Edge Deployment**: Edge deployment is a method where computing and data processing functions are placed on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions on edge deployment, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.md).

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.md

@@ -1618,7 +1618,11 @@ for res in visual_predict_res:
 <td>关键信息抽取结果。</td>
 </tr>
 </tbody>
-</table></details>
+</table>
+<li><b>注意：</b></li>
+在请求体中包含大模型调用的API key等敏感参数可能存在安全风险。如无必要，请在配置文件中设置这些参数，在请求时不传递。
+<br/><br/>
+</details>
 <details><summary>多语言调用服务示例</summary>
 <details>
 <summary>Python</summary>
@@ -1694,6 +1698,7 @@ print("Final result:")
 print(result_chat["chatResult"])
 </code></pre>
 </details>
+</details>
 <br/>
 
 📱 <b>端侧部署</b>：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/edge_deploy.md)。

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v4.en.md

@@ -1846,7 +1846,11 @@ Below are the API references for basic serving and multi-language service invoca
 <td>HTML prompts.</td>
 </tr>
 </tbody>
-</table></details>
+</table>
+<li><b>Note:</b></li>
+Including sensitive parameters such as API key for large model calls in the request body can be a security risk. If not necessary, set these parameters in the configuration file and do not pass them on request.
+<br/><br/>
+</details>
 
 <details><summary>Multi-language Service Invocation Examples</summary>
 

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v4.md

@@ -2010,7 +2010,11 @@ for res in visual_predict_res:
 <td>关键信息抽取结果。</td>
 </tr>
 </tbody>
-</table></details>
+</table>
+<li><b>注意：</b></li>
+在请求体中包含大模型调用的API key等敏感参数可能存在安全风险。如无必要，请在配置文件中设置这些参数，在请求时不传递。
+<br/><br/>
+</details>
 
 <details><summary>多语言调用服务示例</summary>