MigoXLab · e06084 · Jun 11, 2025 · Jun 11, 2025 · Jun 11, 2025 · Jun 11, 2025
diff --git a/.github/workflows/IntegrationTest.yml b/.github/workflows/IntegrationTest.yml
@@ -1,7 +1,7 @@
 # This workflow will install Python dependencies, run tests and lint with a single version of Python
 # For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
 
-name: Python application
+name: Test
 
 on:
   push:
@@ -12,28 +12,21 @@ on:
 
 
 jobs:
-  build:
-
+  test:
     runs-on: ubuntu-latest
-
     steps:
     - uses: actions/checkout@v4
-    - name: Set up Python 3.10
-      uses: actions/setup-python@v3
+    - name: Set up Python
+      uses: actions/setup-python@v4
       with:
         python-version: "3.10"
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install flake8 pytest
+        pip install pytest
         if [ -f requirements/runtime.txt ]; then pip install -r requirements/runtime.txt; fi
         pip install -e .
-    - name: Lint with flake8
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+
     - name: Integration Test(local plaintext)
       run: |
         python -m dingo.run.cli --input_path test/data/test_local_plaintext.txt --dataset local -e default --data_format plaintext
@@ -62,6 +55,6 @@ jobs:
     - name: Integration Test(custom config)
       run: |
         python -m dingo.run.cli --input_path test/data/test_local_json.json --dataset local -e test --data_format json --column_content prediction --custom_config test/config/config_rule.json --log_level=DEBUG
-    - name: Run unit tests with pytest
+    - name: Run unit tests
       run: |
         pytest test/scripts --ignore=test/scripts/data
diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
@@ -1,4 +1,4 @@
-name: lint
+name: Lint
 
 on: [push, pull_request]
 
@@ -9,19 +9,13 @@ concurrency:
 jobs:
   lint:
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version: [3.10.15]
     steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python ${{ matrix.python-version }}
+      - uses: actions/checkout@v4
+      - name: Set up Python
         uses: actions/setup-python@v4
         with:
-          python-version: ${{ matrix.python-version }}
-      - name: Install pre-commit hook
+          python-version: "3.10"
+      - name: Run pre-commit
         run: |
           pip install pre-commit==3.8.0
-          pre-commit install
-      - name: Linting
-        run: |
           pre-commit run --all-files
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -13,8 +13,8 @@ repos:
     hooks:
     -   id: isort
 -   repo: https://github.com/PyCQA/flake8
-    rev: 5.0.4
+    rev: 6.1.0
     hooks:
     -   id: flake8
-        args: [ "--max-line-length=2200", "--ignore=E121,E131,E125,W503,W504,W604,E203,E231,E702,E128,F541" ]
-        exclude: 'app/|examples/|test/|dingo/run/vsl.py'
+        args: [ "--max-line-length=2200", "--ignore=E121,E131,E125,W503,W504,W604,E203,E231,E702,E128,F541,F401" ]
+        exclude: 'app/'
diff --git a/examples/classify/sdk_3h_evaluation.py b/examples/classify/sdk_3h_evaluation.py
@@ -12,23 +12,21 @@ def classify_3H():
         "data_format": "jsonl",
         "column_prompt": "input",
         "column_content": "response",
-        "custom_config":
-            {
-                "prompt_list": ["PromptTextHarmless"], # options:['PromptIsHelpful', 'PromptIsHonest']
-                "llm_config":
-                    {
-                        "LLMText3HHarmless":
-                            {
-                                "key": "",
-                                "api_url": ""
-                            }
-                    }
+        "custom_config": {
+            "prompt_list": ["PromptTextHarmless"],  # options:['PromptIsHelpful', 'PromptIsHonest']
+            "llm_config": {
+                "LLMText3HHarmless": {
+                    "key": "",
+                    "api_url": ""
+                }
             }
+        }
     }
     input_args = InputArgs(**input_data)
     executor = Executor.exec_map["local"](input_args)
     result = executor.execute()
     print(result)
 
+
 if __name__ == '__main__':
     classify_3H()
diff --git a/examples/classify/sdk_QR_classification.py b/examples/classify/sdk_QR_classification.py
@@ -14,20 +14,19 @@ def classify_QR():
         "column_content": "content",
         "custom_config": {
             "prompt_list": ["PromptClassifyQR"],
-            "llm_config":
-                {
-                    "LLMClassifyQR":
-                        {
-                            "key": "",
-                            "api_url": "",
-                        }
+            "llm_config": {
+                "LLMClassifyQR": {
+                    "key": "",
+                    "api_url": "",
                 }
+            }
         }
     }
     input_args = InputArgs(**input_data)
     executor = Executor.exec_map["local"](input_args)
     result = executor.execute()
     print(result)
 
+
 if __name__ == '__main__':
     classify_QR()
diff --git a/examples/classify/sdk_topic_classifcation.py b/examples/classify/sdk_topic_classifcation.py
@@ -13,20 +13,19 @@ def classify_topic():
         "column_content": "question",
         "custom_config": {
             "prompt_list": ["PromptClassifyTopic"],
-            "llm_config":
-                {
-                    "LLMClassifyTopic":
-                        {
-                            "key": "",
-                            "api_url": "",
-                        }
+            "llm_config": {
+                "LLMClassifyTopic": {
+                    "key": "",
+                    "api_url": "",
                 }
+            }
         }
     }
     input_args = InputArgs(**input_data)
     executor = Executor.exec_map["local"](input_args)
     result = executor.execute()
     print(result)
 
+
 if __name__ == '__main__':
     classify_topic()
diff --git a/examples/compare/compare_content.py b/examples/compare/compare_content.py
@@ -15,14 +15,12 @@
     "custom_config":
         {
             "prompt_list": ["PromptHtmlAbstract"],
-            "llm_config":
-                {
-                    "LLMHtmlAbstract":
-                        {
-                            "key": "",
-                            "api_url": ""
-                        }
+            "llm_config": {
+                "LLMHtmlAbstract": {
+                    "key": "",
+                    "api_url": ""
                 }
+            }
         },
     "log_level": "INFO"
 }

diff --git a/examples/continue/continue.py b/examples/continue/continue.py
@@ -20,6 +20,7 @@ def exec_first():
     result = executor.execute()
     print(result)
 
+
 def exec_second():
     input_data = {
         "eval_group": "sft",
@@ -38,6 +39,7 @@ def exec_second():
     result = executor.execute()
     print(result)
 
+
 if __name__ == '__main__':
     exec_first()
     exec_second()
diff --git a/examples/core/score.py b/examples/core/score.py
@@ -19,6 +19,7 @@ def llm():
     res = LLMTextQualityModelBase.eval(data)
     print(res)
 
+
 def rule():
     data = Data(
         data_id='123',
@@ -29,6 +30,7 @@ def rule():
     res = RuleEnterAndSpace().eval(data)
     print(res)
 
+
 if __name__ == "__main__":
     llm()
     rule()
diff --git a/examples/custom/sdk_custom_llm.py b/examples/custom/sdk_custom_llm.py
@@ -8,18 +8,15 @@
     "dataset": "local",
     "data_format": "jsonl",
     "column_content": "content",
-    "custom_config":
-        {
-            "prompt_list": ["PromptRepeat"],
-            "llm_config":
-                {
-                    "LLMTextQualityPromptBase":
-                        {
-                            "key": "",
-                            "api_url": "",
-                        }
-                }
+    "custom_config": {
+        "prompt_list": ["PromptRepeat"],
+        "llm_config": {
+            "LLMTextQualityPromptBase": {
+                "key": "",
+                "api_url": "",
+            }
         }
+    }
 }
 input_args = InputArgs(**input_data)
 executor = Executor.exec_map["local"](input_args)

diff --git a/examples/dataman/dataman.py b/examples/dataman/dataman.py
@@ -11,14 +11,12 @@
     "custom_config":
         {
             "prompt_list": ["PromptDataManAssessment"],
-            "llm_config":
-                {
-                    "dataman_assessment":
-                        {
-                            "key": "enter your key, such as:EMPTY",
-                            "api_url": "enter your local llm api url, such as:http://127.0.0.1:8080/v1",
-                        }
+            "llm_config": {
+                "dataman_assessment": {
+                    "key": "enter your key, such as:EMPTY",
+                    "api_url": "enter your local llm api url, such as:http://127.0.0.1:8080/v1",
                 }
+            }
         },
     "log_level": "INFO"
 }

diff --git a/examples/dataset/sdk_huggingface.py b/examples/dataset/sdk_huggingface.py
@@ -15,6 +15,7 @@ def huggingface_plaintext():
     result = executor.execute()
     print(result)
 
+
 def huggingface_json():
     input_data = {
         "eval_group": "sft",
@@ -29,6 +30,7 @@ def huggingface_json():
     result = executor.execute()
     print(result)
 
+
 def huggingface_jsonl():
     input_data = {
         "eval_group": "sft",
@@ -42,6 +44,7 @@ def huggingface_jsonl():
     result = executor.execute()
     print(result)
 
+
 def huggingface_listjson():
     input_data = {
         "eval_group": "sft",
@@ -56,6 +59,7 @@ def huggingface_listjson():
     result = executor.execute()
     print(result)
 
+
 if __name__ == '__main__':
     huggingface_plaintext()
     huggingface_json()

diff --git a/examples/dataset/sdk_local.py b/examples/dataset/sdk_local.py
@@ -5,7 +5,7 @@
 def local_plaintext():
     input_data = {
         "eval_group": "sft",
-        "input_path": "../../test/data/test_local_plaintext.txt", # local filesystem dataset
+        "input_path": "../../test/data/test_local_plaintext.txt",  # local filesystem dataset
         "dataset": "local",
         "data_format": "plaintext",
     }
@@ -15,6 +15,7 @@ def local_plaintext():
     result = executor.execute()
     print(result)
 
+
 def local_json():
     input_data = {
         "eval_group": "sft",
@@ -29,6 +30,7 @@ def local_json():
     result = executor.execute()
     print(result)
 
+
 def local_jsonl():
     input_data = {
         "eval_group": "sft",
@@ -43,6 +45,7 @@ def local_jsonl():
     result = executor.execute()
     print(result)
 
+
 def local_listjson():
     input_data = {
         "eval_group": "sft",
@@ -57,6 +60,7 @@ def local_listjson():
     result = executor.execute()
     print(result)
 
+
 if __name__ == '__main__':
     local_plaintext()
     local_json()

diff --git a/examples/image/sdk_image_relevant.py b/examples/image/sdk_image_relevant.py
@@ -15,20 +15,19 @@ def image_relevant():
         "column_content": "url_2",
         "custom_config": {
             "prompt_list": ["PromptImageRelevant"],
-            "llm_config":
-                {
-                    "VLMImageRelevant":
-                        {
-                            "key": "",
-                            "api_url": "",
-                        }
+            "llm_config": {
+                "VLMImageRelevant": {
+                    "key": "",
+                    "api_url": "",
                 }
+            }
         }
     }
     input_args = InputArgs(**input_data)
     executor = Executor.exec_map["local"](input_args)
     result = executor.execute()
     print(result)
 
+
 if __name__ == '__main__':
     image_relevant()
diff --git a/examples/image/sdk_image_repeat.py b/examples/image/sdk_image_repeat.py
@@ -20,5 +20,6 @@ def image_repeat():
     result = executor.execute()
     print(result)
 
+
 if __name__ == '__main__':
     image_repeat()
diff --git a/examples/image/sdk_image_text_similar.py b/examples/image/sdk_image_text_similar.py
@@ -22,5 +22,6 @@ def image_text_similar():
     result = executor.execute()
     print(result)
 
+
 if __name__ == '__main__':
     image_text_similar()