Fix serving docs and update formula recognition schema (#3483)

docs/pipeline_usage/tutorials/cv_pipelines/face_recognition.en.md

@@ -881,25 +881,25 @@ Below is the API reference for basic service deployment and multi-language servi
 <tr>
 <td><code>detThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>det_threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to description of the <code>det_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>recThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>rec_threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to description of the <code>rec_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>hammingRadius</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>hamming_radius</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>hamming_radius</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>topk</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>Refer to the <code>topk</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to description of the <code>topk</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/face_recognition.md

@@ -877,25 +877,25 @@ data_root             # 数据集根目录，目录名称可以改变
 <tr>
 <td><code>detThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>det_threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>det_threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>recThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>rec_threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>rec_threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>hammingRadius</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>hamming_radius</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>hamming_radius</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>topk</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>topk</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>topk</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/general_image_recognition.en.md

@@ -842,25 +842,25 @@ Below is the API reference for basic service deployment and multi-language servi
 <tr>
 <td><code>detThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>det_threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>det_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>recThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>rec_threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>rec_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>hammingRadius</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>hamming_radius</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>hamming_radius</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>topk</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>Refer to the <code>topk</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>topk</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/general_image_recognition.md

@@ -839,25 +839,25 @@ data_root             # 数据集根目录，目录名称可以改变
 <tr>
 <td><code>detThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>det_threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>det_threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>recThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>rec_threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>rec_threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>hammingRadius</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>hamming_radius</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>hamming_radius</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>topk</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>topk</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>topk</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/image_classification.en.md

@@ -1255,7 +1255,7 @@ Below are the API references for basic service deployment and examples of multi-
 <tr>
 <td><code>topk</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>See the <code>topk</code> parameter description in the <code>predict</code> method documentation.</td>
+<td>Pleaser to ription of the <code>topk</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/image_classification.md

@@ -1071,7 +1071,7 @@ for res in output:
 <tr>
 <td><code>topk</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>topk</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>topk</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.en.md

@@ -450,7 +450,7 @@ Below is the API reference for basic service deployment and multi-language servi
 <tr>
 <td><code>threshold</code></td>
 <td><code>number</code> | <code>array</code> | <code>object</code> | <code>null</code></td>
-<td>Refer to the <code>threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md

@@ -446,7 +446,7 @@ for res in output:
 <tr>
 <td><code>threshold</code></td>
 <td><code>number</code> | <code>array</code> | <code>object</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.en.md

@@ -564,7 +564,7 @@ Below are the API references for basic service deployment and examples of multi-
 <tr>
 <td><code>threshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.md

@@ -561,7 +561,7 @@ for res in output:
 <tr>
 <td><code>threshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/object_detection.en.md

@@ -723,7 +723,7 @@ Below is the API reference for basic service deployment and multi-language servi
 <tr>
 <td><code>threshold</code></td>
 <td><code>number</code> | <code>object</code> | <code>null</code></td>
-<td>Refer to the <code>threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tr>

docs/pipeline_usage/tutorials/cv_pipelines/object_detection.md

@@ -738,7 +738,7 @@ for res in output:
 <tr>
 <td><code>threshold</code></td>
 <td><code>number</code> | <code>object</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/pedestrian_attribute_recognition.en.md

@@ -479,13 +479,13 @@ Below are the API references for basic serving deployment and examples of multi-
 <tr>
 <td><code>detThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>det_threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>det_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>clsThreshold</code></td>
 <td><code>number</code> | <code>array</code> | <code>object</code> | <code>null</code></td>
-<td>Refer to the <code>cls_threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>cls_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/pedestrian_attribute_recognition.md

@@ -473,13 +473,13 @@ for res in output:
 <tr>
 <td><code>detThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>det_threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>det_threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>clsThreshold</code></td>
 <td><code>number</code> | <code>array</code> | <code>object</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>cls_threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>cls_threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/rotated_object_detection.en.md

@@ -429,13 +429,13 @@ Below are the API references and multi-language service call examples for basic
 <tr>
 <td><code>detThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>det_threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>det_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>clsThreshold</code></td>
 <td><code>number</code> | <code>array</code> | <code>object</code> | <code>null</code></td>
-<td>Refer to the <code>cls_threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>cls_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/rotated_object_detection.md

@@ -425,7 +425,7 @@ for res in output:
 <tr>
 <td><code>threshold</code></td>
 <td><code>number</code> | <code>object</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation.en.md

@@ -591,7 +591,7 @@ Below are the API references for basic service deployment and examples of multi-
 <tr>
 <td><code>targetSize</code></td>
 <td><code>integer</code> | <code>array</code> | <code>null</code></td>
-<td>Refer to the <code>target_size</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>target_size</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation.md

@@ -593,7 +593,7 @@ for res in output:
 <tr>
 <td><code>targetSize</code></td>
 <td><code>integer</code> | <code>array</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>target_size</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>target_size</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection.en.md

@@ -446,7 +446,7 @@ Below is the API reference for basic service deployment and multi-language servi
 <tr>
 <td><code>threshold</code></td>
 <td><code>number</code> | <code>object</code> | <code>null</code></td>
-<td>Refer to the <code>threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection.md

@@ -444,7 +444,7 @@ for res in output:
 <tr>
 <td><code>threshold</code></td>
 <td><code>number</code> | <code>object</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/vehicle_attribute_recognition.en.md

@@ -460,13 +460,13 @@ Below are the API references for basic serving deployment and multi-language ser
 <tr>
 <td><code>detThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>det_threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>det_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>clsThreshold</code></td>
 <td><code>number</code> | <code>array</code> | <code>object</code> | <code>null</code></td>
-<td>Refer to the <code>cls_threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>cls_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/cv_pipelines/vehicle_attribute_recognition.md

@@ -470,13 +470,13 @@ for res in output:
 <tr>
 <td><code>detThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>det_threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>det_threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>clsThreshold</code></td>
 <td><code>number</code> | <code>array</code> | <code>object</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>cls_threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>cls_threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

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

@@ -1254,103 +1254,103 @@ Below are the API references for basic serving and multi-language service invoca
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>use_doc_orientation_classify</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>use_doc_orientation_classify</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>use_doc_unwarping</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>use_doc_unwarping</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useGeneralOcr</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>use_general_ocr</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>use_general_ocr</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useSealRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>use_seal_recognition</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>use_seal_recognition</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useTableRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>use_table_recognition</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>use_table_recognition</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_det_limit_side_len</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_limit_side_len</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_det_limit_type</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_limit_type</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_det_thresh</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_thresh</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_det_box_thresh</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_box_thresh</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_det_unclip_ratio</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_unclip_ratio</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_rec_score_thresh</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>text_rec_score_thresh</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>seal_det_limit_side_len</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>seal_det_limit_side_len</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>seal_det_limit_type</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>seal_det_limit_type</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>seal_det_thresh</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>seal_det_thresh</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>seal_det_box_thresh</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>seal_det_box_thresh</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>seal_det_unclip_ratio</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>seal_det_unclip_ratio</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>seal_rec_score_thresh</code> in the pipeline's <code>visual_predict</code> method.</td>
+<td>Please refer to the description of the <code>seal_rec_score_thresh</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>
@@ -1397,12 +1397,12 @@ Below are the API references for basic serving and multi-language service invoca
 <tr>
 <td><code>prunedResult</code></td>
 <td><code>object</code></td>
-<td>A simplified version of the <code>res</code> field in the JSON representation of the results generated by the pipeline's <code>predict</code> method, with the <code>input_path</code> field removed.</td>
+<td>A simplified version of the <code>res</code> field in the JSON representation of the results generated by the pipeline's <code>visual_predict</code> method, with the <code>input_path</code> field removed.</td>
 </tr>
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>img</code> in the pipeline's visual prediction results.</td>
+<td>Refer to the description of <code>img</code> attribute of the pipeline's visual prediction result.</td>
 </tr>
 <tr>
 <td><code>inputImage</code></td>
@@ -1444,13 +1444,13 @@ Below are the API references for basic serving and multi-language service invoca
 <tr>
 <td><code>blockSize</code></td>
 <td><code>int</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>block_size</code> in the pipeline's <code>build_vector</code> method.</td>
+<td>Please refer to the description of the <code>block_size</code> parameter of the pipeline object's <code>build_vector</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>retrieverConfig</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>retriever_config</code> in the pipeline's <code>build_vector</code> method.</td>
+<td>Please refer to the description of the <code>retriever_config</code> parameter of the pipeline object's <code>build_vector</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>
@@ -1495,7 +1495,7 @@ Below are the API references for basic serving and multi-language service invoca
 <tr>
 <td><code>keyList</code></td>
 <td><code>array</code></td>
-<td>List of keywords.</td>
+<td>List of keys.</td>
 <td>Yes</td>
 </tr>
 <tr>
@@ -1507,7 +1507,7 @@ Below are the API references for basic serving and multi-language service invoca
 <tr>
 <td><code>useVectorRetrieval</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>use_vector_retrieval</code> in the pipeline's <code>chat</code> method.</td>
+<td>Please refer to the description of the <code>use_vector_retrieval</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
@@ -1525,73 +1525,73 @@ Below are the API references for basic serving and multi-language service invoca
 <tr>
 <td><code>textTaskDescription</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_task_description</code> in the pipeline's <code>chat</code> method.</td>
+<td>Please refer to the description of the <code>text_task_description</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textOutputFormat</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_output_format</code> in the pipeline's <code>chat</code> method.</td>
+<td>Please refer to the description of the <code>text_output_format</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textRulesStr</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_rules_str</code> in the pipeline's <code>chat</code> method.</td>
+<td>Please refer to the description of the <code>text_rules_str</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textFewShotDemoTextContent</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_few_shot_demo_text_content</code> in the pipeline's <code>chat</code> method.</td>
+<td>Please refer to the description of the <code>text_few_shot_demo_text_content</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textFewShotDemoKeyValueList</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_few_shot_demo_key_value_list</code> in the pipeline's <code>chat</code> method.</td>
+<td>Please refer to the description of the <code>text_few_shot_demo_key_value_list</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>tableTaskDescription</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>table_task_description</code> in the pipeline's <code>chat</code> method.</td>
+<td>Please refer to the description of the <code>table_task_description</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>tableOutputFormat</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>table_output_format</code> in the pipeline's <code>chat</code> method.</td>
+<td>Please refer to the description of the <code>table_output_format</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>tableRulesStr</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>table_rules_str</code> in the pipeline's <code>chat</code> method.</td>
+<td>Please refer to the description of the <code>table_rules_str</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>tableFewShotDemoTextContent</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>table_few_shot_demo_text_content</code> in the pipeline's <code>chat</code> method.</td>
+<td>Please refer to the description of the <code>table_few_shot_demo_text_content</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>tableFewShotDemoKeyValueList</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>table_few_shot_demo_key_value_list</code> in the pipeline's <code>chat</code> method.</td>
+<td>Please refer to the description of the <code>table_few_shot_demo_key_value_list</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>chatBotConfig</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>chat_bot_config</code> in the pipeline's <code>chat</code> method.</td>
+<td>Please refer to the description of the <code>chat_bot_config</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>retrieverConfig</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>retriever_config</code> in the pipeline's <code>chat</code> method.</td>
+<td>Please refer to the description of the <code>retriever_config</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.md

@@ -1258,103 +1258,103 @@ for res in visual_predict_res:
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>use_doc_orientation_classify</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>use_doc_orientation_classify</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>use_doc_unwarping</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>use_doc_unwarping</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useGeneralOcr</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>use_general_ocr</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>use_general_ocr</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useSealRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>use_seal_recognition</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>use_seal_recognition</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useTableRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>use_table_recognition</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>use_table_recognition</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>text_det_limit_side_len</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>text_det_limit_side_len</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>text_det_limit_type</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>text_det_limit_type</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>text_det_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>text_det_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>text_det_box_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>text_det_box_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>text_det_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>text_det_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>text_rec_score_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>text_rec_score_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>seal_det_limit_side_len</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>seal_det_limit_side_len</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>seal_det_limit_type</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>seal_det_limit_type</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>seal_det_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>seal_det_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>seal_det_box_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>seal_det_box_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>seal_det_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>seal_det_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>seal_rec_score_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>seal_rec_score_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>
@@ -1401,12 +1401,12 @@ for res in visual_predict_res:
 <tr>
 <td><code>prunedResult</code></td>
 <td><code>object</code></td>
-<td>产线对象的 <code>predict</code> 方法生成结果的 JSON 表示中 <code>res</code> 字段的简化版本，其中去除了 <code>input_path</code> 字段</td>
+<td>产线对象的 <code>visual_predict</code> 方法生成结果的 JSON 表示中 <code>res</code> 字段的简化版本，其中去除了 <code>input_path</code> 字段</td>
 </tr>
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线视觉预测结果中的 <code>img</code> 参数说明。</td>
+<td>参见产线视觉预测结果的 <code>img</code> 属性说明。</td>
 </tr>
 <tr>
 <td><code>inputImage</code></td>
@@ -1448,13 +1448,13 @@ for res in visual_predict_res:
 <tr>
 <td><code>blockSize</code></td>
 <td><code>int</code> | <code>null</code></td>
-<td>参见产线 <code>build_vector</code> 方法中的 <code>block_size</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>build_vector</code> 方法的 <code>block_size</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>retrieverConfig</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线 <code>build_vector</code> 方法中的 <code>retriever_config</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>build_vector</code> 方法的 <code>retriever_config</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>
@@ -1499,7 +1499,7 @@ for res in visual_predict_res:
 <tr>
 <td><code>keyList</code></td>
 <td><code>array</code></td>
-<td>关键词列表。</td>
+<td>键列表。</td>
 <td>是</td>
 </tr>
 <tr>
@@ -1511,7 +1511,7 @@ for res in visual_predict_res:
 <tr>
 <td><code>useVectorRetrieval</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>use_vector_retrieval</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>use_vector_retrieval</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
@@ -1529,73 +1529,73 @@ for res in visual_predict_res:
 <tr>
 <td><code>textTaskDescription</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>text_task_description</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>text_task_description</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textOutputFormat</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>text_output_format</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>text_output_format</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textRulesStr</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>text_rules_str</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>text_rules_str</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textFewShotDemoTextContent</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>text_few_shot_demo_text_content</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>text_few_shot_demo_text_content</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textFewShotDemoKeyValueList</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>text_few_shot_demo_key_value_list</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>text_few_shot_demo_key_value_list</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>tableTaskDescription</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>table_task_description</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>table_task_description</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>tableOutputFormat</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>table_output_format</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>table_output_format</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>tableRulesStr</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>table_rules_str</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>table_rules_str</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>tableFewShotDemoTextContent</code></td>
 <td><code>string</code> | <code>null</code></td>
 <td></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>table_few_shot_demo_text_content</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>table_few_shot_demo_text_content</code> 参数相关说明。</td>
 </tr>
 <tr>
 <td><code>tableFewShotDemoKeyValueList</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>table_few_shot_demo_key_value_list</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>table_few_shot_demo_key_value_list</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>chatBotConfig</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>chat_bot_config</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>chat_bot_config</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>retrieverConfig</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>retriever_config</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>retriever_config</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

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

@@ -1295,7 +1295,7 @@ Below are the API references for basic serving and multi-language service invoca
 <ul>
 <li>The HTTP request method is POST.</li>
 <li>Both the request body and response body are JSON data (JSON objects).</li>
-<li>When the request is successfully processed, the response status code is <code>200</code>, and the response body has the following attributes:</li>
+<li>When the request is successfully processed, the response status code is <code>200</code>, and the response body has the following properties:</li>
 </ul>
 <table>
 <thead>
@@ -1329,7 +1329,7 @@ Below are the API references for basic serving and multi-language service invoca
 </tbody>
 </table>
 <ul>
-<li>When the request is not successfully processed, the response body has the following attributes:</li>
+<li>When the request is not successfully processed, the response body has the following properties:</li>
 </ul>
 <table>
 <thead>
@@ -1364,7 +1364,7 @@ Below are the API references for basic serving and multi-language service invoca
 <p>Uses computer vision models to analyze images, obtain OCR, table recognition results, etc., and extract key information from the images.</p>
 <p><code>POST /chatocr-visual</code></p>
 <ul>
-<li>Attributes of the request body:</li>
+<li>Properties of the request body:</li>
 </ul>
 <table>
 <thead>
@@ -1384,122 +1384,117 @@ Below are the API references for basic serving and multi-language service invoca
 </tr>
 <tr>
 <td><code>fileType</code></td>
-<td><code>integer</code></td>
-<td>File type. <code>0</code> represents a PDF file, <code>1</code> represents an image file. If this attribute is not present in the request body, the file type will be inferred based on the URL.</td>
+<td><code>integer</code> | <code>null</code></td>
+<td>File type. <code>0</code> represents a PDF file, <code>1</code> represents an image file. If this property is not present in the request body, the file type will be inferred based on the URL.</td>
 <td>No</td>
 </tr>
 <tr>
-<td><code>useImgOrientationCls</code></td>
-<td><code>boolean</code></td>
-<td>Whether to enable document image orientation classification. This feature is enabled by default.</td>
+<td><code>useDocOrientationClassify</code></td>
+<td><code>boolean</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>use_doc_orientation_classify</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
-<td><code>useImgUnwarping</code></td>
-<td><code>boolean</code></td>
-<td>Whether to enable text image correction. This feature is enabled by default.</td>
+<td><code>useDocUnwarping</code></td>
+<td><code>boolean</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>use_doc_unwarping</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
-<td><code>useSealTextDet</code></td>
-<td><code>boolean</code></td>
-<td>Whether to enable seal text detection. This feature is enabled by default.</td>
+<td><code>useGeneralOcr</code></td>
+<td><code>boolean</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>use_general_ocr</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
-<td><code>inferenceParams</code></td>
-<td><code>object</code></td>
-<td>Inference parameters.</td>
+<td><code>useSealRecognition</code></td>
+<td><code>boolean</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>use_seal_recognition</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
-</tbody>
-</table>
-<p>Attributes of <code>inferenceParams</code>:</p>
-<table>
-<thead>
 <tr>
-<th>Name</th>
-<th>Type</th>
-<th>Meaning</th>
-<th>Required</th>
+<td><code>useTableRecognition</code></td>
+<td><code>boolean</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>use_table_recognition</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
+<td>No</td>
 </tr>
-</thead>
-<tbody>
 <tr>
-<td><code>maxLongSide</code></td>
-<td><code>integer</code></td>
-<td>During inference, if the length of the longer side of the input image to the text detection model is greater than <code>maxLongSide</code>, the image will be scaled so that the length of its longer side equals <code>maxLongSide</code>.</td>
+<td><code>textDetLimitSideLen</code></td>
+<td><code>integer</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>text_det_limit_side_len</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
 <td>No</td>
 </tr>
-</tbody>
-</table>
-<ul>
-<li>When the request is successfully processed, the <code>result</code> of the response body has the following attributes:</li>
-</ul>
-<table>
-<thead>
 <tr>
-<th>Name</th>
-<th>Type</th>
-<th>Meaning</th>
+<td><code>textDetLimitType</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>text_det_limit_type</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
+<td>No</td>
 </tr>
-</thead>
-<tbody>
 <tr>
-<td><code>visualResults</code></td>
-<td><code>array</code></td>
-<td>Analysis results obtained using computer vision models. The array length is 1 (for image input) or the smaller value between 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.</td>
+<td><code>textDetThresh</code></td>
+<td><code>number</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>text_det_thresh</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
+<td>No</td>
 </tr>
 <tr>
-<td><code>visualInfo</code></td>
-<td><code>object</code></td>
-<td>Key information in the image, which can be used as input for other operations.</td>
+<td><code>textDetBoxThresh</code></td>
+<td><code>number</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>text_det_box_thresh</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
+<td>No</td>
 </tr>
 <tr>
-<td><code>dataInfo</code></td>
-<td><code>object</code></td>
-<td>Input data information.</td>
+<td><code>textDetUnclipRatio</code></td>
+<td><code>number</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>text_det_unclip_ratio</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
+<td>No</td>
 </tr>
-</tbody>
-</table>
-<p>Each element in <code>visualResults</code> is an <code>object</code> with the following attributes:</p>
-<table>
-<thead>
 <tr>
-<th>Name</th>
-<th>Type</th>
-<th>Meaning</th>
+<td><code>textRecScoreThresh</code></td>
+<td><code>number</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>text_rec_score_thresh</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
+<td>No</td>
 </tr>
-</thead>
-<tbody>
 <tr>
-<td><code>texts</code></td>
-<td><code>array</code></td>
-<td>Text positions, contents, and scores.</td>
+<td><code>sealDetLimitSideLen</code></td>
+<td><code>integer</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>seal_det_limit_side_len</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
+<td>No</td>
 </tr>
 <tr>
-<td><code>tables</code></td>
-<td><code>array</code></td>
-<td>Table positions and contents.</td>
+<td><code>sealDetLimitType</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>seal_det_limit_type</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
+<td>No</td>
 </tr>
 <tr>
-<td><code>inputImage</code></td>
-<td><code>string</code></td>
-<td>Input image. The image is in JPEG format and encoded using Base64.</td>
+<td><code>sealDetThresh</code></td>
+<td><code>number</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>seal_det_thresh</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
+<td>No</td>
 </tr>
 <tr>
-<td><code>layoutImage</code></td>
-<td><code>string</code></td>
-<td>Detection result image of the layout area. The image is in JPEG format and encoded using Base64.</td>
+<td><code>sealDetBoxThresh</code></td>
+<td><code>number</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>seal_det_box_thresh</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
+<td>No</td>
 </tr>
 <tr>
-<td><code>ocrImage</code></td>
-<td><code>string</code></td>
-<td>OCR result image. The image is in JPEG format and encoded using Base64.</td>
+<td><code>sealDetUnclipRatio</code></td>
+<td><code>number</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>seal_det_unclip_ratio</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
+<td>No</td>
+</tr>
+<tr>
+<td><code>sealRecScoreThresh</code></td>
+<td><code>number</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>seal_rec_score_thresh</code> parameter of the pipeline object's <code>visual_predict</code> method.</td>
+<td>No</td>
 </tr>
 </tbody>
 </table>
-<p>Each element in <code>texts</code> is an <code>object</code> with the following attributes:</p>
+<ul>
+<li>When the request is successfully processed, the <code>result</code> of the response body has the following properties:</li>
+</ul>
 <table>
 <thead>
 <tr>
@@ -1510,23 +1505,23 @@ Below are the API references for basic serving and multi-language service invoca
 </thead>
 <tbody>
 <tr>
-<td><code>poly</code></td>
+<td><code>layoutParsingResults</code></td>
 <td><code>array</code></td>
-<td>Text position. The elements in the array are the vertex coordinates of the polygon enclosing the text in sequence.</td>
+<td>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 in sequence.</td>
 </tr>
 <tr>
-<td><code>text</code></td>
-<td><code>string</code></td>
-<td>Text content.</td>
+<td><code>visualInfo</code></td>
+<td><code>array</code></td>
+<td>Key information in the image, which can be used as input for other operations.</td>
 </tr>
 <tr>
-<td><code>score</code></td>
-<td><code>number</code></td>
-<td>Text recognition score.</td>
+<td><code>dataInfo</code></td>
+<td><code>object</code></td>
+<td>Input data information.</td>
 </tr>
 </tbody>
 </table>
-<p>Each element in <code>tables</code> is an <code>object</code> with the following attributes:</p>
+<p>Each element in <code>layoutParsingResults</code> is an <code>object</code> with the following properties:</p>
 <table>
 <thead>
 <tr>
@@ -1537,14 +1532,19 @@ Below are the API references for basic serving and multi-language service invoca
 </thead>
 <tbody>
 <tr>
-<td><code>bbox</code></td>
-<td><code>array</code></td>
-<td>Table position. 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.</td>
+<td><code>prunedResult</code></td>
+<td><code>object</code></td>
+<td>A simplified version of the <code>res</code> field in the JSON representation of the results generated by the pipeline's <code>visual_predict</code> method, with the <code>input_path</code> field removed.</td>
 </tr>
 <tr>
-<td><code>html</code></td>
-<td><code>string</code></td>
-<td>Table recognition result in HTML format.</td>
+<td><code>outputImages</code></td>
+<td><code>object</code> | <code>null</code></td>
+<td>Refer to the description of <code>img</code> attribute of the pipeline's visual prediction result.</td>
+</tr>
+<tr>
+<td><code>inputImage</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Input image. The image is in JPEG format and encoded using Base64.</td>
 </tr>
 </tbody>
 </table>
@@ -1554,7 +1554,7 @@ Below are the API references for basic serving and multi-language service invoca
 <p>Builds a vector database.</p>
 <p><code>POST /chatocr-vector</code></p>
 <ul>
-<li>Attributes of the request body:</li>
+<li>Properties of the request body:</li>
 </ul>
 <table>
 <thead>
@@ -1568,50 +1568,32 @@ Below are the API references for basic serving and multi-language service invoca
 <tbody>
 <tr>
 <td><code>visualInfo</code></td>
-<td><code>object</code></td>
+<td><code>array</code></td>
 <td>Key information in the image. Provided by the <code>analyzeImages</code> operation.</td>
 <td>Yes</td>
 </tr>
 <tr>
-<td><code>minChars</code></td>
-<td><code>integer</code></td>
+<td><code>minCharacters</code></td>
+<td><code>integer</code> | <code>null</code></td>
 <td>Minimum data length to enable the vector database.</td>
 <td>No</td>
 </tr>
 <tr>
-<td><code>llmRequestInterval</code></td>
-<td><code>number</code></td>
-<td>Interval time for calling the large language model API.</td>
+<td><code>blockSize</code></td>
+<td><code>int</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>block_size</code> parameter of the pipeline object's <code>build_vector</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
-<td><code>llmName</code></td>
-<td><code>string</code></td>
-<td>Name of the large language model.</td>
-<td>No</td>
-</tr>
-<tr>
-<td><code>llmParams</code></td>
-<td><code>object</code></td>
-<td>Parameters for the large language model API.</td>
+<td><code>retrieverConfig</code></td>
+<td><code>object</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>retriever_config</code> parameter of the pipeline object's <code>build_vector</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>
 </table>
-<p>Currently, <code>llmParams</code> can take one of the following forms:</p>
-<pre><code class="language-json">{
-&quot;apiType&quot;: &quot;qianfan&quot;,
-&quot;apiKey&quot;: &quot;{API key of Qianfan Platform}&quot;,
-&quot;secretKey&quot;: &quot;{Secret key of Qianfan Platform}&quot;
-}
-</code></pre>
-<pre><code class="language-json">{
-&quot;apiType&quot;: &quot;aistudio&quot;,
-&quot;accessToken&quot;: &quot;{Access token of Baidu AIStudio Community}&quot;
-}
-</code></pre>
 <ul>
-<li>When the request is successfully processed, the <code>result</code> of the response body has the following attribute:</li>
+<li>When the request is successfully processed, the <code>result</code> of the response body has the following properties:</li>
 </ul>
 <table>
 <thead>
@@ -1623,19 +1605,18 @@ Below are the API references for basic serving and multi-language service invoca
 </thead>
 <tbody>
 <tr>
-<td><code>vectorStore</code></td>
-<td><code>string</code></td>
+<td><code>vectorInfo</code></td>
+<td><code>object</code></td>
 <td>Serialized result of the vector database, which can be used as input for other operations.</td>
 </tr>
 </tbody>
 </table>
-<ul>
-<li><b><code>retrieveKnowledge</code></b></li>
+<li><b><code>invokeMLLM</code></b></li>
 </ul>
-<p>Performs knowledge retrieval.</p>
-<p><code>POST /chatocr-retrieval</code></p>
+<p>Invoke the MLLM.</p>
+<p><code>POST /chatocr-mllm</code></p>
 <ul>
-<li>Attributes of the request body:</li>
+<li>Properties of the request body:</li>
 </ul>
 <table>
 <thead>
@@ -1648,45 +1629,27 @@ Below are the API references for basic serving and multi-language service invoca
 </thead>
 <tbody>
 <tr>
-<td><code>keys</code></td>
-<td><code>array</code></td>
-<td>List of keywords.</td>
-<td>Yes</td>
-</tr>
-<tr>
-<td><code>vectorStore</code></td>
+<td><code>image</code></td>
 <td><code>string</code></td>
-<td>Serialized result of the vector database. Provided by the <code>buildVectorStore</code> operation.</td>
+<td>URL of an image file accessible by the server or the Base64-encoded content of the image file.</td>
 <td>Yes</td>
 </tr>
 <tr>
-<td><code>llmName</code></td>
-<td><code>string</code></td>
-<td>Name of the large language model.</td>
-<td>No</td>
+<td><code>keyList</code></td>
+<td><code>array</code></td>
+<td>List of keys.</td>
+<td>Yes</td>
 </tr>
 <tr>
-<td><code>llmParams</code></td>
-<td><code>object</code></td>
-<td>Parameters for the large language model API.</td>
+<td><code>mllmChatBotConfig</code></td>
+<td><code>object</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>mllm_chat_bot_config</code> parameter of the pipeline object's <code>mllm_pred</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>
 </table>
-<p>Currently, <code>llmParams</code> can take one of the following forms:</p>
-<pre><code class="language-json">{
-&quot;apiType&quot;: &quot;qianfan&quot;,
-&quot;apiKey&quot;: &quot;{API key of Qianfan Platform}&quot;,
-&quot;secretKey&quot;: &quot;{Secret key of Qianfan Platform}&quot;
-}
-</code></pre>
-<pre><code class="language-json">{
-&quot;apiType&quot;: &quot;aistudio&quot;,
-&quot;accessToken&quot;: &quot;{Access token of Baidu AIStudio Community}&quot;
-}
-</code></pre>
 <ul>
-<li>When the request is successfully processed, the <code>result</code> of the response body has the following attribute:</li>
+<li>When the request is successfully processed, the <code>result</code> of the response body has the following property:</li>
 </ul>
 <table>
 <thead>
@@ -1698,19 +1661,19 @@ Below are the API references for basic serving and multi-language service invoca
 </thead>
 <tbody>
 <tr>
-<td><code>retrievalResult</code></td>
-<td><code>string</code></td>
-<td>Knowledge retrieval result, which can be used as input for other operations.</td>
+<td><code>mllmPredictInfo</code></td>
+<td><code>object</code></td>
+<td>MLLM invocation result.</td>
 </tr>
 </tbody>
 </table>
 <ul>
 <li><b><code>chat</code></b></li>
 </ul>
-<p>Interacts with the large language model to extract key information using it.</p>
+<p>Interacts with large language models to extract key information using them.</p>
 <p><code>POST /chatocr-chat</code></p>
 <ul>
-<li>Attributes of the request body:</li>
+<li>Properties of the request body:</li>
 </ul>
 <table>
 <thead>
@@ -1723,9 +1686,9 @@ Below are the API references for basic serving and multi-language service invoca
 </thead>
 <tbody>
 <tr>
-<td><code>keys</code></td>
+<td><code>keyList</code></td>
 <td><code>array</code></td>
-<td>List of keywords.</td>
+<td>List of keys.</td>
 <td>Yes</td>
 </tr>
 <tr>
@@ -1735,92 +1698,112 @@ Below are the API references for basic serving and multi-language service invoca
 <td>Yes</td>
 </tr>
 <tr>
-<td><code>vectorStore</code></td>
-<td><code>string</code></td>
+<td><code>useVectorRetrieval</code></td>
+<td><code>boolean</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>use_vector_retrieval</code> parameter of the pipeline object's <code>chat</code> method.</td>
+<td>No</td>
+</tr>
+<tr>
+<td><code>vectorInfo</code></td>
+<td><code>object</code> | <code>null</code></td>
 <td>Serialized result of the vector database. Provided by the <code>buildVectorStore</code> operation.</td>
 <td>No</td>
 </tr>
 <tr>
-<td><code>retrievalResult</code></td>
-<td><code>string</code></td>
-<td>Knowledge retrieval result. Provided by the <code>retrieveKnowledge</code> operation.</td>
+<td><code>minCharacters</code></td>
+<td><code>integer</code></td>
+<td>Minimum data length to enable the vector database.</td>
 <td>No</td>
 </tr>
 <tr>
-<td><code>taskDescription</code></td>
-<td><code>string</code></td>
-<td>Task description for prompts.</td>
+<td><code>textTaskDescription</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>text_task_description</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
-<td><code>rules</code></td>
-<td><code>string</code></td>
-<td>Prompt rules. Used to customize information extraction rules, such as specifying the output format.</td>
+<td><code>textOutputFormat</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>text_output_format</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
-<td><code>fewShot</code></td>
-<td><code>string</code></td>
-<td>Prompt examples.</td>
+<td><code>textRulesStr</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>text_rules_str</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
-<td><code>llmName</code></td>
-<td><code>string</code></td>
-<td>Name of the large language model.</td>
+<td><code>textFewShotDemoTextContent</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>text_few_shot_demo_text_content</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
-<td><code>llmParams</code></td>
-<td><code>object</code></td>
-<td>Parameters for the large language model API.</td>
+<td><code>textFewShotDemoKeyValueList</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>text_few_shot_demo_key_value_list</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
-<td><code>returnPrompts</code></td>
-<td><code>boolean</code></td>
-<td>Whether to return the used prompts. Disabled by default.</td>
+<td><code>tableTaskDescription</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>table_task_description</code> parameter of the pipeline object's <code>chat</code> method.</td>
 <td>No</td>
 </tr>
-</tbody>
-</table>
-<p>Currently, <code>llmParams</code> can take one of the following forms:</p>
-<pre><code class="language-json">{
-&quot;apiType&quot;: &quot;qianfan&quot;,
-&quot;apiKey&quot;: &quot;{API key of Qianfan Platform}&quot;,
-&quot;secretKey&quot;: &quot;{Secret key of Qianfan Platform}&quot;
-}
-</code></pre>
-<pre><code class="language-json">{
-&quot;apiType&quot;: &quot;aistudio&quot;,
-&quot;accessToken&quot;: &quot;{Access token of Baidu AIStudio Community}&quot;
-}
-</code></pre>
-<ul>
-<li>When the request is successfully processed, the <code>result</code> of the response body has the following attributes:</li>
-</ul>
-<table>
-<thead>
 <tr>
-<th>Name</th>
-<th>Type</th>
-<th>Meaning</th>
+<td><code>tableOutputFormat</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>table_output_format</code> parameter of the pipeline object's <code>chat</code> method.</td>
+<td>No</td>
 </tr>
-</thead>
-<tbody>
 <tr>
-<td><code>chatResult</code></td>
-<td><code>object</code></td>
-<td>Key information extraction result.</td>
+<td><code>tableRulesStr</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>table_rules_str</code> parameter of the pipeline object's <code>chat</code> method.</td>
+<td>No</td>
 </tr>
 <tr>
-<td><code>prompts</code></td>
-<td><code>object</code></td>
-<td>Used prompts.</td>
+<td><code>tableFewShotDemoTextContent</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>table_few_shot_demo_text_content</code> parameter of the pipeline object's <code>chat</code> method.</td>
+<td>No</td>
+</tr>
+<tr>
+<td><code>tableFewShotDemoKeyValueList</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>table_few_shot_demo_key_value_list</code> parameter of the pipeline object's <code>chat</code> method.</td>
+<td>No</td>
+</tr>
+<tr>
+<td><code>mllmPredictInfo</code></td>
+<td><code>object</code> | <code>null</code></td>
+<td>MLLM invocation result. Provided by the <code>invokeMllm</code> operation.</td>
+<td>No</td>
+</tr>
+<tr>
+<td><code>mllmIntegrationStrategy</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>mllm_integration_strategy</code> parameter of the pipeline object's <code>chat</code> method.</td>
+<td>No</td>
+</tr>
+<tr>
+<td><code>chatBotConfig</code></td>
+<td><code>object</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>chat_bot_config</code> parameter of the pipeline object's <code>chat</code> method.</td>
+<td>No</td>
+</tr>
+<tr>
+<td><code>retrieverConfig</code></td>
+<td><code>object</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>retriever_config</code> parameter of the pipeline object's <code>chat</code> method.</td>
+<td>No</td>
 </tr>
 </tbody>
 </table>
-<p>Attributes of <code>prompts</code>:</p>
+<ul>
+<li>When the request is successfully processed, the <code>result</code> of the response body has the following properties:</li>
+</ul>
 <table>
 <thead>
 <tr>
@@ -1831,19 +1814,9 @@ Below are the API references for basic serving and multi-language service invoca
 </thead>
 <tbody>
 <tr>
-<td><code>ocr</code></td>
-<td><code>array</code></td>
-<td>OCR prompts.</td>
-</tr>
-<tr>
-<td><code>table</code></td>
-<td><code>array</code></td>
-<td>Table prompts.</td>
-</tr>
-<tr>
-<td><code>html</code></td>
-<td><code>array</code></td>
-<td>HTML prompts.</td>
+<td><code>chatResult</code></td>
+<td><code>object</code></td>
+<td>Key information extraction result.</td>
 </tr>
 </tbody>
 </table>

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v4.md

@@ -1593,103 +1593,103 @@ for res in visual_predict_res:
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>use_doc_orientation_classify</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>use_doc_orientation_classify</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>use_doc_unwarping</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>use_doc_unwarping</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useGeneralOcr</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>use_general_ocr</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>use_general_ocr</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useSealRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>use_seal_recognition</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>use_seal_recognition</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useTableRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>use_table_recognition</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>use_table_recognition</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>text_det_limit_side_len</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>text_det_limit_side_len</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>text_det_limit_type</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>text_det_limit_type</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>text_det_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>text_det_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>text_det_box_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>text_det_box_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>text_det_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>text_det_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>text_rec_score_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>text_rec_score_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>seal_det_limit_side_len</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>seal_det_limit_side_len</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>seal_det_limit_type</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>seal_det_limit_type</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>seal_det_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>seal_det_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>seal_det_box_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>seal_det_box_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>seal_det_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>seal_det_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>visual_predict</code> 方法中的 <code>seal_rec_score_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>visual_predict</code> 方法的 <code>seal_rec_score_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>
@@ -1736,12 +1736,12 @@ for res in visual_predict_res:
 <tr>
 <td><code>prunedResult</code></td>
 <td><code>object</code></td>
-<td>产线对象的 <code>predict</code> 方法生成结果的 JSON 表示中 <code>res</code> 字段的简化版本，其中去除了 <code>input_path</code> 字段</td>
+<td>产线对象的 <code>visual_predict</code> 方法生成结果的 JSON 表示中 <code>res</code> 字段的简化版本，其中去除了 <code>input_path</code> 字段</td>
 </tr>
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线视觉预测结果中的 <code>img</code> 参数说明。</td>
+<td>参见产线视觉预测结果的 <code>img</code> 属性说明。</td>
 </tr>
 <tr>
 <td><code>inputImage</code></td>
@@ -1783,13 +1783,13 @@ for res in visual_predict_res:
 <tr>
 <td><code>blockSize</code></td>
 <td><code>int</code> | <code>null</code></td>
-<td>参见产线 <code>build_vector</code> 方法中的 <code>block_size</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>build_vector</code> 方法的 <code>block_size</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>retrieverConfig</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线 <code>build_vector</code> 方法中的 <code>retriever_config</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>build_vector</code> 方法的 <code>retriever_config</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>
@@ -1816,7 +1816,7 @@ for res in visual_predict_res:
 <ul>
 <li><b><code>invokeMLLM</code></b></li>
 </ul>
-<p>获取多模态大模型抽取结果。</p>
+<p>调用多模态大模型。</p>
 <p><code>POST /chatocr-mllm</code></p>
 <ul>
 <li>请求体的属性如下：</li>
@@ -1834,19 +1834,19 @@ for res in visual_predict_res:
 <tr>
 <td><code>image</code></td>
 <td><code>string</code></code></td>
-<td>输入图像。</td>
+<td>服务器可访问的图像文件的URL或图像文件内容的Base64编码结果。</td>
 <td>是</td>
 </tr>
 <tr>
 <td><code>keyList</code></td>
 <td><code>array</code></td>
-<td>关键词列表。</td>
+<td>键列表。</td>
 <td>是</td>
 </tr>
 <tr>
 <td><code>mllmChatBotConfig</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线 <code>mllm_pred</code> 方法中的 <code>mllm_chat_bot_config</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>mllm_pred</code> 方法的 <code>mllm_chat_bot_config</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>
@@ -1866,7 +1866,7 @@ for res in visual_predict_res:
 <tr>
 <td><code>mllmPredictInfo</code></td>
 <td><code>object</code></td>
-<td>多模态大模型抽取结果。</td>
+<td>多模态大模型调用结果。</td>
 </tr>
 </tbody>
 </table>
@@ -1891,7 +1891,7 @@ for res in visual_predict_res:
 <tr>
 <td><code>keyList</code></td>
 <td><code>array</code></td>
-<td>关键词列表。</td>
+<td>键列表。</td>
 <td>是</td>
 </tr>
 <tr>
@@ -1903,7 +1903,7 @@ for res in visual_predict_res:
 <tr>
 <td><code>useVectorRetrieval</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>use_vector_retrieval</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>use_vector_retrieval</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
@@ -1921,73 +1921,85 @@ for res in visual_predict_res:
 <tr>
 <td><code>textTaskDescription</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>text_task_description</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>text_task_description</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textOutputFormat</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>text_output_format</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>text_output_format</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textRulesStr</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>text_rules_str</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>text_rules_str</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textFewShotDemoTextContent</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>text_few_shot_demo_text_content</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>text_few_shot_demo_text_content</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textFewShotDemoKeyValueList</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>text_few_shot_demo_key_value_list</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>text_few_shot_demo_key_value_list</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>tableTaskDescription</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>table_task_description</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>table_task_description</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>tableOutputFormat</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>table_output_format</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>table_output_format</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>tableRulesStr</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>table_rules_str</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>table_rules_str</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>tableFewShotDemoTextContent</code></td>
 <td><code>string</code> | <code>null</code></td>
 <td></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>table_few_shot_demo_text_content</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>table_few_shot_demo_text_content</code> 参数相关说明。</td>
 </tr>
 <tr>
 <td><code>tableFewShotDemoKeyValueList</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>table_few_shot_demo_key_value_list</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>table_few_shot_demo_key_value_list</code> 参数相关说明。</td>
+<td>否</td>
+</tr>
+<tr>
+<td><code>mllmPredictInfo</code></td>
+<td><code>object</code> | <code>null</code></td>
+<td>多模态大模型调用结果。由<code>invokeMllm</code>操作提供。</td>
+<td>否</td>
+</tr>
+<tr>
+<td><code>mllmIntegrationStrategy</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>mllm_integration_strategy</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>chatBotConfig</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>chat_bot_config</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>chat_bot_config</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>retrieverConfig</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线 <code>chat</code> 方法中的 <code>retriever_config</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>chat</code> 方法的 <code>retriever_config</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/ocr_pipelines/OCR.en.md

@@ -947,55 +947,55 @@ Below are the API reference and multi-language service invocation examples for t
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_doc_orientation_classify</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_doc_orientation_classify</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_doc_unwarping</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_doc_unwarping</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useTextlineOrientation</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_textline_orientation</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_textline_orientation</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>Refer to the <code>text_det_limit_side_len</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_limit_side_len</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the <code>text_det_limit_type</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_limit_type</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>text_det_thresh</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>text_det_box_thresh</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_box_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>text_det_unclip_ratio</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_unclip_ratio</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>text_rec_score_thresh</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_rec_score_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/ocr_pipelines/OCR.md

@@ -941,56 +941,56 @@ for res in output:
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_orientation_classify</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_orientation_classify</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_unwarping</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_unwarping</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <tr>
 <td><code>useTextlineOrientation</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_textline_orientation</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_textline_orientation</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_limit_side_len</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_limit_side_len</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_limit_type</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_limit_type</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_box_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_box_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_rec_score_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_rec_score_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/ocr_pipelines/doc_preprocessor.en.md

@@ -476,13 +476,13 @@ Additionally, PaddleX offers three other deployment methods, detailed as follows
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_doc_orientation_classify</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_doc_orientation_classify</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_doc_unwarping</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_doc_unwarping</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/ocr_pipelines/doc_preprocessor.md

@@ -477,13 +477,13 @@ for res in output:
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_orientation_classify</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_orientation_classify</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_unwarping</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_unwarping</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.en.md

@@ -760,19 +760,43 @@ Below are the API references for basic service-based deployment and multi-langua
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_doc_orientation_classify</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_doc_orientation_classify</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_doc_unwarping</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_doc_unwarping</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useLayoutDetection</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_layout_detection</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_layout_detection</code> parameter of the pipeline object's <code>predict</code> method.</td>
+<td>No</td>
+</tr>
+<tr>
+<td><code>layoutThreshold</code></td>
+<td><code>number</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>layout_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
+<td>No</td>
+</tr>
+<tr>
+<td><code>layoutNms</code></td>
+<td><code>boolean</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>layout_nms</code> parameter of the pipeline object's <code>predict</code> method.</td>
+<td>No</td>
+</tr>
+<tr>
+<td><code>layoutUnclipRatio</code></td>
+<td><code>number</code> | <code>array</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>layout_unclip_ratio</code> parameter of the pipeline object's <code>predict</code> method.</td>
+<td>No</td>
+</tr>
+<tr>
+<td><code>layoutMergeBboxesMode</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>Please refer to the description of the <code>layout_merge_bboxes_mode</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>
@@ -819,7 +843,7 @@ Below are the API references for basic service-based deployment and multi-langua
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>See the description of the <code>img</code> attribute in the result of the pipeline prediction. The images are in JPEG format and are Base64-encoded.</td>
+<td>See the description of the <code>img</code> attribute of the result of the pipeline prediction. The images are in JPEG format and are Base64-encoded.</td>
 </tr>
 <tr>
 <td><code>inputImage</code> | <code>null</code></td>

docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.md

@@ -759,19 +759,43 @@ for res in output:
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_orientation_classify</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_orientation_classify</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_unwarping</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_unwarping</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useLayoutDetection</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_layout_detection</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_layout_detection</code> 参数相关说明。</td>
+<td>否</td>
+</tr>
+<tr>
+<td><code>layoutThreshold</code></td>
+<td><code>number</code> | <code>null</code></td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_threshold</code> 参数相关说明。</td>
+<td>否</td>
+</tr>
+<tr>
+<td><code>layoutNms</code></td>
+<td><code>boolean</code> | <code>null</code></td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_nms</code> 参数相关说明。</td>
+<td>否</td>
+</tr>
+<tr>
+<td><code>layoutUnclipRatio</code></td>
+<td><code>number</code> | <code>array</code> | <code>null</code></td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_unclip_ratio</code> 参数相关说明。</td>
+<td>否</td>
+</tr>
+<tr>
+<td><code>layoutMergeBboxesMode</code></td>
+<td><code>string</code> | <code>null</code></td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_merge_bboxes_mode</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>
@@ -818,7 +842,7 @@ for res in output:
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线预测结果中的 <code>img</code> 属性说明。图像为JPEG格式，使用Base64编码。</td>
+<td>参见产线预测结果的 <code>img</code> 属性说明。图像为JPEG格式，使用Base64编码。</td>
 </tr>
 <tr>
 <td><code>inputImage</code> | <code>null</code></td>

docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.en.md

@@ -1235,139 +1235,139 @@ Below are the API reference and multi-language service invocation examples for t
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>See the description of the <code>use_doc_orientation_classify</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>use_doc_orientation_classify</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>See the description of the <code>use_doc_unwarping</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>use_doc_unwarping</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useTextlineOrientation</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>See the description of the <code>use_textline_orientation</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>use_textline_orientation</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useGeneralOcr</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>See the description of the <code>use_general_ocr</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>use_general_ocr</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useSealRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>See the description of the <code>use_seal_recognition</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>use_seal_recognition</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useTableRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>See the description of the <code>use_table_recognition</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>use_table_recognition</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useFormulaRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>See the description of the <code>use_formula_recognition</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>use_formula_recognition</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>See the description of the <code>text_det_limit_side_len</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>text_det_limit_side_len</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>See the description of the <code>text_det_limit_type</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>text_det_limit_type</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>See the description of the <code>text_det_thresh</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>text_det_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>See the description of the <code>text_det_box_thresh</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>text_det_box_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>See the description of the <code>text_det_unclip_ratio</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>text_det_unclip_ratio</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>See the description of the <code>text_rec_score_thresh</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>text_rec_score_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>See the description of the <code>seal_det_limit_side_len</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_limit_side_len</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>See the description of the <code>seal_det_limit_type</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_limit_type</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>See the description of the <code>seal_det_thresh</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>See the description of the <code>seal_det_box_thresh</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_box_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>See the description of the <code>seal_det_unclip_ratio</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_unclip_ratio</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>See the description of the <code>seal_rec_score_thresh</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_rec_score_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>See the description of the <code>layout_threshold</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>layout_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutNms</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>See the description of the <code>layout_nms</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>layout_nms</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutUnclipRatio</code></td>
 <td><code>number</code> | <code>array</code> | <code>null</code></td>
-<td>See the description of the <code>layout_unclip_ratio</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>layout_unclip_ratio</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutMergeBboxesMode</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>See the description of the <code>layout_merge_bboxes_mode</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>layout_merge_bboxes_mode</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>
@@ -1414,7 +1414,7 @@ Below are the API reference and multi-language service invocation examples for t
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>See the description of the <code>img</code> attribute in the result of the pipeline prediction. The images are in JPEG format and encoded in Base64.</td>
+<td>See the description of the <code>img</code> attribute of the result of the pipeline prediction. The images are in JPEG format and encoded in Base64.</td>
 </tr>
 <tr>
 <td><code>inputImage</code></td>

docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.md

@@ -1288,139 +1288,139 @@ for res in output:
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_orientation_classify</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_orientation_classify</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_unwarping</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_unwarping</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useTextlineOrientation</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_textline_orientation</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_textline_orientation</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useGeneralOcr</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_general_ocr</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_general_ocr</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useSealRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_seal_recognition</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_seal_recognition</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useTableRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_table_recognition</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_table_recognition</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useFormulaRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_formula_recognition</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_formula_recognition</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_limit_side_len</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_limit_side_len</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_limit_type</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_limit_type</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_box_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_box_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_rec_score_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_rec_score_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_limit_side_len</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_limit_side_len</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_limit_type</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_limit_type</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_box_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_box_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_rec_score_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_rec_score_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutNms</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_nms</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_nms</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutUnclipRatio</code></td>
 <td><code>number</code> | <code>array</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutMergeBboxesMode</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_merge_bboxes_mode</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_merge_bboxes_mode</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>
@@ -1467,7 +1467,7 @@ for res in output:
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线预测结果中的 <code>img</code> 属性说明。图像为JPEG格式，使用Base64编码。</td>
+<td>参见产线预测结果的 <code>img</code> 属性说明。图像为JPEG格式，使用Base64编码。</td>
 </tr>
 <tr>
 <td><code>inputImage</code></td>

docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing_v2.en.md

@@ -1428,139 +1428,139 @@ Below is the API reference for basic serving deployment and examples of service
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_doc_orientation_classify</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_doc_orientation_classify</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_doc_unwarping</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_doc_unwarping</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useTextlineOrientation</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_textline_orientation</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_textline_orientation</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useGeneralOcr</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_general_ocr</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_general_ocr</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useSealRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_seal_recognition</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_seal_recognition</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useTableRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_table_recognition</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_table_recognition</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useFormulaRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>use_formula_recognition</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>use_formula_recognition</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_det_limit_side_len</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>text_det_limit_side_len</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_det_limit_type</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>text_det_limit_type</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_det_thresh</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>text_det_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_det_box_thresh</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>text_det_box_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_det_unclip_ratio</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>text_det_unclip_ratio</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>text_rec_score_thresh</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>text_rec_score_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>seal_det_limit_side_len</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_limit_side_len</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>seal_det_limit_type</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_limit_type</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>seal_det_thresh</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>seal_det_box_thresh</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_box_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>seal_det_unclip_ratio</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_unclip_ratio</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>seal_rec_score_thresh</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_rec_score_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>layout_threshold</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>layout_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutNms</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>layout_nms</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>layout_nms</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutUnclipRatio</code></td>
 <td><code>number</code> | <code>array</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>layout_unclip_ratio</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>layout_unclip_ratio</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutMergeBboxesMode</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the parameter description of <code>layout_merge_bboxes_mode</code> in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>layout_merge_bboxes_mode</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>
@@ -1612,7 +1612,7 @@ Below is the API reference for basic serving deployment and examples of service
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>See the description of the <code>img</code> attribute in the result of the pipeline prediction. The images are in JPEG format and are Base64-encoded.</td>
+<td>See the description of the <code>img</code> attribute of the result of the pipeline prediction. The images are in JPEG format and are Base64-encoded.</td>
 </tr>
 <tr>
 <td><code>inputImage</code></td>

docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing_v2.md

@@ -1325,139 +1325,139 @@ for res in output:
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_orientation_classify</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_orientation_classify</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_unwarping</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_unwarping</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useTextlineOrientation</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_textline_orientation</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_textline_orientation</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useGeneralOcr</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_general_ocr</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_general_ocr</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useSealRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_seal_recognition</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_seal_recognition</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useTableRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_table_recognition</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_table_recognition</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useFormulaRecognition</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_formula_recognition</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_formula_recognition</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_limit_side_len</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_limit_side_len</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_limit_type</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_limit_type</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_box_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_box_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_rec_score_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_rec_score_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_limit_side_len</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_limit_side_len</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_limit_type</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_limit_type</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_box_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_box_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_rec_score_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_rec_score_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutNms</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_nms</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_nms</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutUnclipRatio</code></td>
 <td><code>number</code> | <code>array</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutMergeBboxesMode</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_merge_bboxes_mode</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_merge_bboxes_mode</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>
@@ -1509,7 +1509,7 @@ for res in output:
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线预测结果中的 <code>img</code> 属性说明。图像为JPEG格式，使用Base64编码。</td>
+<td>参见产线预测结果的 <code>img</code> 属性说明。图像为JPEG格式，使用Base64编码。</td>
 </tr>
 <tr>
 <td><code>inputImage</code></td>

docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.en.md

@@ -1104,79 +1104,79 @@ Below are the API references for basic serving deployment and multi-language ser
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the description of the <code>use_doc_orientation_classify</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>use_doc_orientation_classify</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the description of the <code>use_doc_unwarping</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>use_doc_unwarping</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useLayoutDetection</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the description of the <code>use_layout_detection</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>use_layout_detection</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the description of the <code>layout_threshold</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>layout_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutNms</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the description of the <code>layout_nms</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>layout_nms</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutUnclipRatio</code></td>
 <td><code>number</code> | <code>array</code> | <code>null</code></td>
-<td>Refer to the description of the <code>layout_unclip_ratio</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>layout_unclip_ratio</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutMergeBboxesMode</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the description of the <code>layout_merge_bboxes_mode</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>layout_merge_bboxes_mode</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>Refer to the description of the <code>seal_det_limit_side_len</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_limit_side_len</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the description of the <code>seal_det_limit_type</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_limit_type</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the description of the <code>seal_det_thresh</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the description of the <code>seal_det_box_thresh</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_box_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the description of the <code>seal_det_unclip_ratio</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_det_unclip_ratio</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>sealRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the description of the <code>seal_rec_score_thresh</code> parameter in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>seal_rec_score_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>
@@ -1223,7 +1223,7 @@ Below are the API references for basic serving deployment and multi-language ser
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>See the description of the <code>img</code> attribute in the result of the pipeline prediction. The images are in JPEG format and encoded in Base64.</td>
+<td>See the description of the <code>img</code> attribute of the result of the pipeline prediction. The images are in JPEG format and encoded in Base64.</td>
 </tr>
 <tr>
 <td><code>inputImage</code></td>

docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.md

@@ -1121,79 +1121,79 @@ for res in output:
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_orientation_classify</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_orientation_classify</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_unwarping</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_unwarping</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useLayoutDetection</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_layout_detection</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_layout_detection</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutNms</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_nms</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_nms</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutUnclipRatio</code></td>
 <td><code>number</code> | <code>array</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutMergeBboxesMode</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_merge_bboxes_mode</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_merge_bboxes_mode</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_limit_side_len</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_limit_side_len</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_limit_type</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_limit_type</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_box_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_box_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_det_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_det_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>sealRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>seal_rec_score_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>seal_rec_score_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>
@@ -1240,7 +1240,7 @@ for res in output:
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线预测结果中的 <code>img</code> 属性说明。图像为JPEG格式，使用Base64编码。</td>
+<td>参见产线预测结果的 <code>img</code> 属性说明。图像为JPEG格式，使用Base64编码。</td>
 </tr>
 <tr>
 <td><code>inputImage</code></td>

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.en.md

@@ -1161,85 +1161,85 @@ Below are the API references for basic serving deployment and multi-language ser
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>See the description of the <code>use_doc_orientation_classify</code> parameter in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_doc_orientation_classify</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>See the description of the <code>use_doc_unwarping</code> parameter in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_doc_unwarping</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useLayoutDetection</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>See the description of the <code>use_layout_detection</code> parameter in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_layout_detection</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useOcrModel</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>See the description of the <code>use_ocr_model</code> parameter in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_ocr_model</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>See the description of the <code>layout_threshold</code> parameter in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>layout_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutNms</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>See the description of the <code>layout_nms</code> parameter in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>layout_nms</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutUnclipRatio</code></td>
 <td><code>number</code> | <code>array</code> | <code>null</code></td>
-<td>See the description of the <code>layout_unclip_ratio</code> parameter in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>layout_unclip_ratio</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutMergeBboxesMode</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>See the description of the <code>layout_merge_bboxes_mode</code> parameter in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>layout_merge_bboxes_mode</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>See the description of the <code>text_det_limit_side_len</code> parameter in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_limit_side_len</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>See the description of the <code>text_det_limit_type</code> parameter in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_limit_type</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>See the description of the <code>text_det_thresh</code> parameter in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>See the description of the <code>text_det_box_thresh</code> parameter in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_box_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>See the description of the <code>text_det_unclip_ratio</code> parameter in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_unclip_ratio</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>See the description of the <code>text_rec_score_thresh</code> parameter in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_rec_score_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>
@@ -1287,7 +1287,7 @@ Below are the API references for basic serving deployment and multi-language ser
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>Refer to the description of the <code>img</code> attribute in the production prediction results. The image is in JPEG format and encoded in Base64.</td>
+<td>Refer to the description of the <code>img</code> attribute of the production prediction results. The image is in JPEG format and encoded in Base64.</td>
 </tr>
 <tr>
 <td><code>inputImage</code></td>

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.md

@@ -1104,85 +1104,85 @@ for res in output:
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_orientation_classify</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_orientation_classify</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_unwarping</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_unwarping</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useLayoutDetection</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_layout_detection</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_layout_detection</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useOcrModel</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_ocr_model</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_ocr_model</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutNms</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_nms</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_nms</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutUnclipRatio</code></td>
 <td><code>number</code> | <code>array</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutMergeBboxesMode</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_merge_bboxes_mode</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_merge_bboxes_mode</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_limit_side_len</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_limit_side_len</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_limit_type</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_limit_type</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_box_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_box_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_rec_score_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_rec_score_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>
@@ -1229,7 +1229,7 @@ for res in output:
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线预测结果中的 <code>img</code> 属性说明。图像为JPEG格式，使用Base64编码。</td>
+<td>参见产线预测结果的 <code>img</code> 属性说明。图像为JPEG格式，使用Base64编码。</td>
 </tr>
 <tr>
 <td><code>inputImage</code></td>

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition_v2.en.md

@@ -1195,85 +1195,85 @@ Below are the API references for basic serving deployment and multi-language ser
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_doc_orientation_classify</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_doc_orientation_classify</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_doc_unwarping</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_doc_unwarping</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useLayoutDetection</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_layout_detection</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_layout_detection</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>useOcrModel</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>use_ocr_model</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>use_ocr_model</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>layout_threshold</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>layout_threshold</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutNms</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>Refer to the <code>layout_nms</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>layout_nms</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutUnclipRatio</code></td>
 <td><code>number</code> | <code>array</code> | <code>null</code></td>
-<td>Refer to the <code>layout_unclip_ratio</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>layout_unclip_ratio</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>layoutMergeBboxesMode</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the <code>layout_merge_bboxes_mode</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>layout_merge_bboxes_mode</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>Refer to the <code>text_det_limit_side_len</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_limit_side_len</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>Refer to the <code>text_det_limit_type</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_limit_type</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>text_det_thresh</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>text_det_box_thresh</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_box_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>text_det_unclip_ratio</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_det_unclip_ratio</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>textRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>text_rec_score_thresh</code> parameter description in the pipeline <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>text_rec_score_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>
@@ -1296,7 +1296,7 @@ Below are the API references for basic serving deployment and multi-language ser
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>Refer to the <code>img</code> property description in the pipeline prediction results. The images are in JPEG format and are Base64-encoded.</td>
+<td>Refer to the <code>img</code> property description of the pipeline prediction results. The images are in JPEG format and are Base64-encoded.</td>
 </tr>
 <tr>
 <td><code>inputImage</code></td>

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition_v2.md

@@ -1197,85 +1197,85 @@ for res in output:
 <tr>
 <td><code>useDocOrientationClassify</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_orientation_classify</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_orientation_classify</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useDocUnwarping</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_doc_unwarping</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_doc_unwarping</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useLayoutDetection</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_layout_detection</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_layout_detection</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>useOcrModel</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>use_ocr_model</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>use_ocr_model</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutThreshold</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_threshold</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_threshold</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutNms</code></td>
 <td><code>boolean</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_nms</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_nms</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutUnclipRatio</code></td>
 <td><code>number</code> | <code>array</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>layoutMergeBboxesMode</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>layout_merge_bboxes_mode</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_merge_bboxes_mode</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_limit_side_len</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_limit_side_len</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetLimitType</code></td>
 <td><code>string</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_limit_type</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_limit_type</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetBoxThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_box_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_box_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textDetUnclipRatio</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_det_unclip_ratio</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_unclip_ratio</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>textRecScoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>text_rec_score_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_rec_score_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>
@@ -1298,7 +1298,7 @@ for res in output:
 <tr>
 <td><code>outputImages</code></td>
 <td><code>object</code> | <code>null</code></td>
-<td>参见产线预测结果中的 <code>img</code> 属性说明。图像为JPEG格式，使用Base64编码。</td>
+<td>参见产线预测结果的 <code>img</code> 属性说明。图像为JPEG格式，使用Base64编码。</td>
 </tr>
 <tr>
 <td><code>inputImage</code></td>

docs/pipeline_usage/tutorials/video_pipelines/video_classification.en.md

@@ -421,7 +421,7 @@ Below are the API references and multi-language service invocation examples for
 <tr>
 <td><code>topk</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>Refer to the <code>topk</code> parameter description in the <code>predict</code> method of the pipeline.</td>
+<td>Please refer to the description of the <code>topk</code> parameter of the pipeline object's <code>predict</code> mehod.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/video_pipelines/video_classification.md

@@ -420,7 +420,7 @@ for res in output:
 <tr>
 <td><code>topk</code></td>
 <td><code>integer</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>topk</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>topk</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/video_pipelines/video_detection.en.md

@@ -434,13 +434,13 @@ Below are the API references and multi-language service invocation examples for
 <tr>
 <td><code>nmsThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>nms_thresh</code> parameter description in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>nms_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 <tr>
 <td><code>scoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>Refer to the <code>score_thresh</code> parameter description in the production <code>predict</code> method.</td>
+<td>Please refer to the description of the <code>score_thresh</code> parameter of the pipeline object's <code>predict</code> method.</td>
 <td>No</td>
 </tr>
 </tbody>

docs/pipeline_usage/tutorials/video_pipelines/video_detection.md

@@ -436,13 +436,13 @@ for res in output:
 <tr>
 <td><code>nmsThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>nms_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>nms_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 <tr>
 <td><code>scoreThresh</code></td>
 <td><code>number</code> | <code>null</code></td>
-<td>参见产线 <code>predict</code> 方法中的 <code>score_thresh</code> 参数说明。</td>
+<td>请参阅产线对象中 <code>predict</code> 方法的 <code>score_thresh</code> 参数相关说明。</td>
 <td>否</td>
 </tr>
 </tbody>

paddlex/inference/serving/basic_serving/_pipeline_apps/formula_recognition.py

@@ -49,6 +49,10 @@ def create_pipeline_app(pipeline: Any, app_config: AppConfig) -> FastAPI:
             use_layout_detection=request.useLayoutDetection,
             use_doc_orientation_classify=request.useDocOrientationClassify,
             use_doc_unwarping=request.useDocUnwarping,
+            layout_threshold=request.layoutThreshold,
+            layout_nms=request.layoutNms,
+            layout_unclip_ratio=request.layoutUnclipRatio,
+            layout_merge_bboxes_mode=request.layoutMergeBboxesMode,
         )
 
         formula_rec_results: List[Dict[str, Any]] = []

paddlex/inference/serving/schemas/formula_recognition.py

@@ -12,9 +12,10 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from typing import Dict, Final, List, Optional
+from typing import Dict, Final, List, Optional, Union
 
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
+from typing_extensions import Annotated
 
 from ..infra.models import DataInfo, PrimaryOperations
 from .shared import ocr
@@ -34,6 +35,12 @@ class InferRequest(ocr.BaseInferRequest):
     useLayoutDetection: Optional[bool] = None
     useDocOrientationClassify: Optional[bool] = None
     useDocUnwarping: Optional[bool] = None
+    layoutThreshold: Optional[float] = None
+    layoutNms: Optional[bool] = None
+    layoutUnclipRatio: Optional[
+        Union[float, Annotated[List[float], Field(min_length=2, max_length=2)]]
+    ] = None
+    layoutMergeBboxesMode: Optional[str] = None
 
 
 class FormulaRecResult(BaseModel):