feat: update v2.0.0

.github/env/custom_config_rule.json

@@ -1,24 +1,16 @@
 {
     "input_path": "test/data/test_local_json.json",
-    "log_level": "DEBUG",
     "dataset": {
         "source": "local",
-        "format": "json",
-        "field": {
-            "content": "prediction"
-        }
-    },
-    "executor": {
-        "rule_list": ["RuleSpecialCharacter", "RuleWatermark"]
+        "format": "json"
     },
-    "evaluator": {
-        "rule_config": {
-            "RuleSpecialCharacter": {
-                "pattern": "[�^□]|\\{\\/U\\}"
-            },
-            "RuleWatermark": {
-                "key_list": ["谢邀", "Architecture of dingo"]
-            }
+    "evaluator": [
+        {
+            "fields": {"content": "prediction"},
+            "evals": [
+                {"name": "RuleSpecialCharacter", "config": {"pattern": "[�^□]|\\{\\/U\\}"}},
+                {"name": "RuleWatermark", "config": {"key_list": ["谢邀", "Architecture of dingo"]}}
+            ]
         }
-    }
+    ]
 }

.github/env/hf_json.json

@@ -2,13 +2,14 @@
     "input_path": "chupei/format-json",
     "dataset": {
         "source": "hugging_face",
-        "format": "json",
-        "field": {
-            "prompt": "origin_prompt",
-            "content": "prediction"
-        }
+        "format": "json"
     },
-    "executor": {
-        "eval_group": "default"
-    }
+    "evaluator": [
+        {
+            "fields": {"prompt": "origin_prompt", "content": "prediction"},
+            "evals": [
+                {"name": "RuleColonEnd"}
+            ]
+        }
+    ]
 }

.github/env/hf_jsonl.json

@@ -2,12 +2,14 @@
     "input_path": "chupei/format-jsonl",
     "dataset": {
         "source": "hugging_face",
-        "format": "jsonl",
-        "field": {
-            "content": "content"
-        }
+        "format": "jsonl"
     },
-    "executor": {
-        "eval_group": "default"
-    }
+    "evaluator": [
+        {
+            "fields": {"content": "content"},
+            "evals": [
+                {"name": "RuleColonEnd"}
+            ]
+        }
+    ]
 }

.github/env/hf_listjson.json

@@ -2,13 +2,14 @@
     "input_path": "chupei/format-listjson",
     "dataset": {
         "source": "hugging_face",
-        "format": "listjson",
-        "field": {
-            "prompt": "instruction",
-            "content": "output"
-        }
+        "format": "listjson"
     },
-    "executor": {
-        "eval_group": "default"
-    }
+    "evaluator": [
+        {
+            "fields": {"prompt": "instruction", "content": "output"},
+            "evals": [
+                {"name": "RuleColonEnd"}
+            ]
+        }
+    ]
 }

.github/env/hf_plaintext.json

@@ -2,12 +2,13 @@
     "input_path": "chupei/format-text",
     "dataset": {
         "source": "hugging_face",
-        "format": "plaintext",
-        "field": {
-            "content": "text"
-        }
+        "format": "plaintext"
     },
-    "executor": {
-        "eval_group": "default"
-    }
+    "evaluator": [
+        {
+            "evals": [
+                {"name": "RuleColonEnd"}
+            ]
+        }
+    ]
 }

.github/env/local_json.json

@@ -2,12 +2,14 @@
     "input_path": "test/data/test_local_json.json",
     "dataset": {
         "source": "local",
-        "format": "json",
-        "field": {
-            "content": "prediction"
-        }
+        "format": "json"
     },
-    "executor": {
-        "eval_group": "default"
-    }
+    "evaluator": [
+        {
+            "fields": {"content": "prediction"},
+            "evals": [
+                {"name": "RuleColonEnd"}
+            ]
+        }
+    ]
 }

.github/env/local_jsonl.json

@@ -2,12 +2,14 @@
     "input_path": "test/data/test_local_jsonl.jsonl",
     "dataset": {
         "source": "local",
-        "format": "jsonl",
-        "field": {
-            "content": "content"
-        }
+        "format": "jsonl"
     },
-    "executor": {
-        "eval_group": "default"
-    }
+    "evaluator": [
+        {
+            "fields": {"content": "content"},
+            "evals": [
+                {"name": "RuleColonEnd"}
+            ]
+        }
+    ]
 }

.github/env/local_listjson.json

@@ -2,12 +2,14 @@
     "input_path": "test/data/test_local_listjson.json",
     "dataset": {
         "source": "local",
-        "format": "listjson",
-        "field": {
-            "content": "output"
-        }
+        "format": "listjson"
     },
-    "executor": {
-        "eval_group": "default"
-    }
+    "evaluator": [
+        {
+            "fields": {"content": "output"},
+            "evals": [
+                {"name": "RuleColonEnd"}
+            ]
+        }
+    ]
 }

.github/env/local_plaintext.json

@@ -4,7 +4,11 @@
         "source": "local",
         "format": "plaintext"
     },
-    "executor": {
-        "eval_group": "default"
-    }
+    "evaluator": [
+        {
+            "evals": [
+                {"name": "RuleColonEnd"}
+            ]
+        }
+    ]
 }

.github/env/local_plaintext_save.json

@@ -5,9 +5,15 @@
         "format": "plaintext"
     },
     "executor": {
-        "eval_group": "default",
         "result_save": {
             "bad": true
         }
-    }
+    },
+    "evaluator": [
+        {
+            "evals": [
+                {"name": "RuleColonEnd"}
+            ]
+        }
+    ]
 }

.github/scripts/check_imports.py

@@ -0,0 +1,62 @@
+#!/usr/bin/env python3
+"""检查所有Python文件是否可以成功编译和导入"""
+
+import os
+import py_compile
+import sys
+from pathlib import Path
+
+
+def check_syntax(file_path):
+    """检查Python文件语法"""
+    try:
+        py_compile.compile(file_path, doraise=True)
+        return True, None
+    except py_compile.PyCompileError as e:
+        return False, str(e)
+
+
+def main():
+    """主函数"""
+    project_root = Path(__file__).parent.parent.parent
+    dingo_path = project_root / "dingo"
+
+    if not dingo_path.exists():
+        print(f"❌ 找不到dingo目录: {dingo_path}")
+        sys.exit(1)
+
+    errors = []
+    checked = 0
+
+    print("🔍 检查所有Python文件的语法和导入...")
+    print("-" * 60)
+
+    for py_file in dingo_path.rglob("*.py"):
+        if "__pycache__" in str(py_file):
+            continue
+
+        checked += 1
+        success, error = check_syntax(str(py_file))
+
+        if success:
+            print(f"✓ {py_file.relative_to(project_root)}")
+        else:
+            error_msg = f"✗ {py_file.relative_to(project_root)}: {error}"
+            print(error_msg)
+            errors.append(error_msg)
+
+    print("-" * 60)
+    print(f"📊 检查了 {checked} 个文件")
+
+    if errors:
+        print(f"\n❌ 发现 {len(errors)} 个错误:")
+        for error in errors:
+            print(f"  {error}")
+        sys.exit(1)
+    else:
+        print(f"✅ 所有文件检查通过！")
+        sys.exit(0)
+
+
+if __name__ == "__main__":
+    main()

.github/workflows/IntegrationTest.yml

@@ -25,8 +25,14 @@ jobs:
         python -m pip install --upgrade pip
         pip install pytest
         if [ -f requirements/runtime.txt ]; then pip install -r requirements/runtime.txt; fi
+        pip install pyspark
+        pip install tavily-python
         pip install -e .
 
+    - name: Check Python syntax and imports
+      run: |
+        python .github/scripts/check_imports.py
+
     - name: Integration Test(local plaintext)
       run: |
         python -m dingo.run.cli --input .github/env/local_plaintext.json
@@ -45,7 +51,7 @@ jobs:
         python -m dingo.run.cli --input .github/env/hf_plaintext.json
     - name: Integration Test(huggingface json)
       run: |
-        python -m dingo.run.cli --input .github/env/hf_plaintext.json
+        python -m dingo.run.cli --input .github/env/hf_json.json
     - name: Integration Test(huggingface jsonl)
       run: |
         python -m dingo.run.cli --input .github/env/hf_jsonl.json

.github/workflows/lint.yml

@@ -15,7 +15,47 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: "3.10"
-      - name: Run pre-commit
+
+      - name: Install pre-commit
+        run: pip install pre-commit==3.8.0
+
+      - name: Install package
+        run: |
+          python -m pip install --upgrade pip
+          if [ -f requirements/runtime.txt ]; then pip install -r requirements/runtime.txt; fi
+          pip install -e .
+
+      - name: Check Python syntax and imports
+        run: |
+          python .github/scripts/check_imports.py
+
+      - name: Run pre-commit (auto-fix)
+        id: pre_commit_auto_fix
+        run: |
+          # 运行 pre-commit，允许自动修复，不因修复而失败
+          pre-commit run --all-files || true
+
+      - name: Check for changes
+        id: check_changes
+        run: |
+          if [[ -n $(git status --porcelain) ]]; then
+            echo "changed=true" >> $GITHUB_OUTPUT
+            echo "📝 Files were modified by pre-commit auto-fix"
+          else
+            echo "changed=false" >> $GITHUB_OUTPUT
+            echo "✅ No auto-fix changes"
+          fi
+
+      - name: Commit auto-fix changes
+        if: steps.check_changes.outputs.changed == 'true' && github.event_name == 'push'
+        run: |
+          git config --local user.email "[email protected]"
+          git config --local user.name "GitHub Action"
+          git add -A
+          git commit -m "🎨 Auto-format code with pre-commit"
+          git push
+
+      - name: Run pre-commit (final check)
         run: |
-          pip install pre-commit==3.8.0
+          # 再次运行 pre-commit，这次如果有错误就真的失败
           pre-commit run --all-files

.github/workflows/metrics-validation.yml

@@ -4,12 +4,12 @@ on:
   push:
     branches: [ main, dev ]
     paths:
-      - 'dingo/model/prompt/**'
+      - 'dingo/model/**'
       - 'scripts/generate_metrics.py'
   pull_request:
     branches: [ main ]
     paths:
-      - 'dingo/model/prompt/**'
+      - 'dingo/model/**'
       - 'scripts/generate_metrics.py'
   workflow_dispatch:
 

.pre-commit-config.yaml

@@ -5,6 +5,7 @@ repos:
     rev: v5.0.0
     hooks:
     -   id: trailing-whitespace
+        exclude: '^README.*\.md$'
     -   id: end-of-file-fixer
         exclude: 'docs/metrics\.md'
     -   id: check-yaml