update docs (#4040)

* fix doc

* update model in structurev3 and chatocrv4 docs

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

@@ -464,7 +464,7 @@ retriever_config = {
 
 mllm_chat_bot_config = {
     "module_name": "chat_bot",
-    "model_name": "PP-DocBee",
+    "model_name": "PP-DocBee2",
     "base_url": "http://172.0.0.1:8080/v1/chat/completions",  # your local mllm service url
     "api_type": "openai",
     "api_key": "api_key",  # your api_key
@@ -1984,7 +1984,7 @@ print(result_chat["chatResult"])
 You can choose an appropriate deployment method for your pipeline based on your needs and proceed with subsequent AI application integration.
 
 ## 4. Custom Development
-If the default model weights provided by the Document Scene Information Extraction v4 Pipeline do not meet your expectations in terms of accuracy or speed in your specific scenario, you can try to further **fine-tune** the existing models using **data from your specific domain or application scenario** to enhance the recognition performance of the General Table Recognition Pipeline in your context.
+If the default model weights provided by the Document Scene Information Extraction v4 Pipeline do not meet your expectations in terms of accuracy or speed in your specific scenario, you can try to further **fine-tune** the existing models using **data from your specific domain or application scenario** to enhance the recognition performance in your context.
 
 ### 4.1 Model Fine-Tuning
 Since the Document Scene Information Extraction v4 Pipeline consists of several modules, suboptimal performance may stem from any of these modules. You can analyze cases with poor extraction results, identify which module is problematic through visual image inspection, and refer to the fine-tuning tutorial links in the table below for model fine-tuning.
@@ -2051,7 +2051,7 @@ To use the fine-tuned model weights, you only need to modify the pipeline config
 SubModules:
     TextDetection:
     module_name: text_detection
-    model_name: PP-OCRv4_server_det
+    model_name: PP-OCRv5_server_det
     model_dir: null # Replace with the path to the fine-tuned text detection model weights
     limit_side_len: 960
     limit_type: max
@@ -2062,7 +2062,7 @@ SubModules:
 
     TextRecognition:
     module_name: text_recognition
-    model_name: PP-OCRv4_server_rec
+    model_name: PP-OCRv5_server_rec
     model_dir: null # Replace with the path to the fine-tuned text recognition model weights
     batch_size: 1
     score_thresh: 0

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v4.md

@@ -635,7 +635,7 @@ retriever_config = {
 
 mllm_chat_bot_config = {
     "module_name": "chat_bot",
-    "model_name": "PP-DocBee",
+    "model_name": "PP-DocBee2",
     "base_url": "http://172.0.0.1:8080/v1/chat/completions",  # your local mllm service url
     "api_type": "openai",
     "api_key": "api_key",  # your api_key
@@ -2189,7 +2189,7 @@ print(result_chat["chatResult"])
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发
-如果文档场景信息抽取v4产线提供的默认模型权重在您的场景中，精度或速度不满意，您可以尝试利用<b>您自己拥有的特定领域或应用场景的数据</b>对现有模型进行进一步的<b>微调</b>，以提升通用表格识别产线的在您的场景中的识别效果。
+如果文档场景信息抽取v4产线提供的默认模型权重在您的场景中，精度或速度不满意，您可以尝试利用<b>您自己拥有的特定领域或应用场景的数据</b>对现有模型进行进一步的<b>微调</b>，以提升在您的场景中的识别效果。
 
 ### 4.1 模型微调
 由于文档场景信息抽取v4产线包含若干模块，模型产线的效果如果不及预期，可能来自于其中任何一个模块。您可以对提取效果差的 case 进行分析，通过可视化图像，确定是哪个模块存在问题，并参考以下表格中对应的微调教程链接进行模型微调。
@@ -2258,7 +2258,7 @@ print(result_chat["chatResult"])
 SubModules:
     TextDetection:
     module_name: text_detection
-    model_name: PP-OCRv4_server_det
+    model_name: PP-OCRv5_server_det
     model_dir: null # 替换为微调后的文本检测模型权重路径
     limit_side_len: 960
     limit_type: max
@@ -2268,7 +2268,7 @@ SubModules:
 
     TextRecognition:
     module_name: text_recognition
-    model_name: PP-OCRv4_server_rec
+    model_name: PP-OCRv5_server_rec
     model_dir: null # 替换为微调后的文本检测模型权重路径
     batch_size: 1
             score_thresh: 0

docs/pipeline_usage/tutorials/ocr_pipelines/PP-StructureV3.en.md

@@ -1906,8 +1906,6 @@ You can choose the appropriate deployment method based on your needs to integrat
 If the default model weights provided by the PP-StructureV3 pipeline do not meet your requirements in terms of accuracy or speed, you can try to <b>fine-tune</b> the existing model using <b>your own domain-specific or application-specific data</b> to improve the recognition performance of the PP-StructureV3 pipeline in your scenario.
 
 ### 4.1 Model Fine-Tuning
-Since the PP-StructureV3 pipeline consists of 7 modules, the unsatisfactory performance of the pipeline may originate from any one of these modules.
-
 Since the PP-StructureV3 pipeline includes several modules, the unsatisfactory performance of the pipeline may originate from any one of these modules. You can analyze the cases with poor extraction results, identify which module is problematic through visualizing the images, and refer to the corresponding fine-tuning tutorial links in the table below to fine-tune the model.
 
 <table>
@@ -1977,7 +1975,7 @@ If you need to use the fine-tuned model weights, simply modify the production co
 SubModules:
   LayoutDetection:
     module_name: layout_detection
-    model_name: PP-DocLayout-L
+    model_name: PP-DocLayout_plus-L
     model_dir: null
 ......
 SubPipelines:
@@ -1989,7 +1987,7 @@ SubPipelines:
     SubModules:
       TextDetection:
         module_name: text_detection
-        model_name: PP-OCRv4_server_rec_doc
+        model_name: PP-OCRv5_server_rec
         model_dir: null
         limit_side_len: 960
         limit_type: max
@@ -2000,7 +1998,7 @@ SubPipelines:
 
       TextRecognition:
         module_name: text_recognition
-        model_name: PP-OCRv4_server_rec
+        model_name: PP-OCRv5_server_rec
         model_dir: null
         batch_size: 1
         score_thresh: 0

docs/pipeline_usage/tutorials/ocr_pipelines/PP-StructureV3.md

@@ -1929,7 +1929,7 @@ for i, res in enumerate(result["layoutParsingResults"]):
 SubModules:
   LayoutDetection:
     module_name: layout_detection
-    model_name: PP-DocLayout-L
+    model_name: PP-DocLayout_plus-L
     model_dir: null # 替换为微调后的版面区域检测模型权重路径
 ......
 SubPipelines:
@@ -1941,7 +1941,7 @@ SubPipelines:
     SubModules:
       TextDetection:
         module_name: text_detection
-        model_name: PP-OCRv4_server_det
+        model_name: PP-OCRv5_server_det
         model_dir: null # 替换为微调后的文本测模型权重路径
         limit_side_len: 960
         limit_type: max
@@ -1952,7 +1952,7 @@ SubPipelines:
 
       TextRecognition:
         module_name: text_recognition
-        model_name: PP-OCRv4_server_rec_doc
+        model_name: PP-OCRv5_server_rec
         model_dir: null # 替换为微调后的文本识别模型权重路径
         batch_size: 1
         score_thresh: 0