Merge pull request #282 from shijinpjlab/dev_main

feat: merge main

Author: e06084

README.md

@@ -445,9 +445,9 @@ If you find this project useful, please consider citing our tool:
 
 ```
 @misc{dingo,
-  title={Dingo: A Comprehensive Data Quality Evaluation Tool for Large Models},
+  title={Dingo: A Comprehensive AI Data Quality Evaluation Tool for Large Models},
   author={Dingo Contributors},
-  howpublished={\url{https://github.com/DataEval/dingo}},
+  howpublished={\url{https://github.com/MigoXLab/dingo}},
   year={2024}
 }
 ```

README_ja.md

@@ -438,9 +438,9 @@ result = executor.execute()
 
 ```
 @misc{dingo,
-  title={Dingo: A Comprehensive Data Quality Evaluation Tool for Large Models},
+  title={Dingo: A Comprehensive AI Data Quality Evaluation Tool for Large Models},
   author={Dingo Contributors},
-  howpublished={\url{https://github.com/DataEval/dingo}},
+  howpublished={\url{https://github.com/MigoXLab/dingo}},
   year={2024}
 }
 ```

README_zh-CN.md

@@ -444,9 +444,9 @@ If you find this project useful, please consider citing our tool:
 
 ```
 @misc{dingo,
-  title={Dingo: A Comprehensive Data Quality Evaluation Tool for Large Models},
+  title={Dingo: A Comprehensive AI Data Quality Evaluation Tool for Large Models},
   author={Dingo Contributors},
-  howpublished={\url{https://github.com/DataEval/dingo}},
+  howpublished={\url{https://github.com/MigoXLab/dingo}},
   year={2024}
 }
 ```

app_gradio/app.py

@@ -369,7 +369,7 @@ def get_data_column_mapping():
                             visible=False
                         )
                         column_content = gr.Textbox(
-                            value="",
+                            value="content",
                             placeholder="Column name of content in the input file. If exists multiple levels, use '.' separate",
                             label="column_content",
                             visible=False
@@ -388,7 +388,7 @@ def get_data_column_mapping():
                 # 修改输出组件部分，使用Tabs
                 with gr.Tabs():
                     with gr.Tab("Result Summary"):
-                        summary_output = gr.Textbox(label="summary", max_lines=50)
+                        summary_output = gr.JSON(label="summary", max_height=800)
                     with gr.Tab("Result Detail"):
                         detail_output = gr.JSON(label="detail", max_height=800)  # 使用JSON组件来更好地展示结构化数据
 

docs/assets/wechat.jpg

@@ -9,7 +9,7 @@ huggingface_hub
 jieba
 jsonlines
 langid
-openai==1.56.2
+openai>=1.56.2
 opencv-python
 packaging>=24.1
 pandas

requirements/runtime.txt

@@ -26,7 +26,7 @@ def get_data_files(directory):
 
 setup(
     name="dingo-python",
-    version="1.11.0",
+    version="1.11.1",
     author="Dingo",
     description="A Comprehensive AI Data Quality Evaluation Tool for Large Models",
     long_description=long_description,