refactor(schema): 重构数据集和文档类的命名

- 将 dataset、dataset_item 和 doc 类的首字母大写，以符合 Python 类命名惯例
- 更新相关模块中的导入和引用，以适应新的类名
- 此更改不影响功能，仅提高了代码的一致性和可读性

db/dataset_store.py

@@ -8,7 +8,7 @@ from tinydb.storages import MemoryStorage
 
 # 将项目根目录添加到系统路径中，以便能够导入项目中的其他模块
 sys.path.append(str(Path(__file__).resolve().parent.parent))
-from schema.dataset import dataset, dataset_item, Q_A
+from schema.dataset import Dataset, DatasetItem, Q_A
 
 def get_all_dataset(workdir: str) -> TinyDB:
     """

schema/dataset.py

@@ -2,7 +2,7 @@ from typing import Optional
 from pydantic import BaseModel, Field
 from datetime import datetime, timezone
 
-class doc(BaseModel):
+class Doc(BaseModel):
     id: Optional[int] = Field(default=None, description="文档ID")
     name: str = Field(default="", description="文档名称")
     path: str = Field(default="", description="文档路径")
@@ -13,18 +13,18 @@ class Q_A(BaseModel):
     question: str = Field(default="", min_length=1,description="问题")
     answer: str = Field(default="", min_length=1, description="答案")
 
-class dataset_item(BaseModel):
+class DatasetItem(BaseModel):
     id: Optional[int] = Field(default=None, description="数据集项ID")
     message: list[Q_A] = Field(description="数据集项内容")
 
-class dataset(BaseModel):
+class Dataset(BaseModel):
     id: Optional[int] = Field(default=None, description="数据集ID")
     name: str = Field(default="", description="数据集名称")
     model_id: Optional[list[str]] = Field(default=None, description="数据集使用的模型ID")
-    source_doc: Optional[doc] = Field(default=None, description="数据集来源文档")
+    source_doc: Optional[Doc] = Field(default=None, description="数据集来源文档")
     description: Optional[str] = Field(default="", description="数据集描述")
     created_at: datetime = Field(
         default_factory=lambda: datetime.now(timezone.utc),
         description="记录创建时间"
     )
-    dataset_items: list[dataset_item] = Field(default_factory=list, description="数据集项列表")
+    dataset_items: list[DatasetItem] = Field(default_factory=list, description="数据集项列表")

tools/convert_json_to_dataset.py

@@ -1,19 +1,19 @@
 from typing import List
-from schema.dataset import dataset, dataset_item, Q_A
+from schema.dataset import Dataset, DatasetItem, Q_A
 import json
 
-def convert_json_to_dataset(json_data: List[dict]) -> dataset:
+def convert_json_to_dataset(json_data: List[dict]) -> Dataset:
     # 将JSON数据转换为dataset格式
     dataset_items = []
     item_id = 1  # 自增ID计数器
     for item in json_data:
         qa = Q_A(question=item["question"], answer=item["answer"])
-        dataset_item_obj = dataset_item(id=item_id, message=[qa])
+        dataset_item_obj = DatasetItem(id=item_id, message=[qa])
         dataset_items.append(dataset_item_obj)
         item_id += 1  # ID自增
     
     # 创建dataset对象
-    result_dataset = dataset(
+    result_dataset = Dataset(
         name="Converted Dataset",
         model_id=None,
         description="Dataset converted from JSON",

tools/document.py

@@ -4,7 +4,7 @@ from pathlib import Path
 
 # 添加项目根目录到sys.path
 sys.path.append(str(Path(__file__).resolve().parent.parent))
-from schema import doc
+from schema import Doc
 
 def scan_docs_directory(workdir: str):
     docs_dir = os.path.join(workdir, "docs")
@@ -21,7 +21,7 @@ def scan_docs_directory(workdir: str):
                 for file in files:
                     if file.endswith(".md"):
                         markdown_files.append(os.path.join(root, file))
-            to_return.append(doc(name=doc_name, path=doc_path, markdown_files=markdown_files))
+            to_return.append(Doc(name=doc_name, path=doc_path, markdown_files=markdown_files))
                     
     return to_return
 

tools/json_example.py

@@ -61,7 +61,7 @@ if __name__ == "__main__":
     from pathlib import Path
     # 添加项目根目录到sys.path
     sys.path.append(str(Path(__file__).resolve().parent.parent))
-    from schema import dataset
+    from schema import Dataset
 
     print("示例 JSON:")
-    print(generate_example_json(dataset))
+    print(generate_example_json(Dataset))

tools/reasoning.py

@@ -96,7 +96,7 @@ if __name__ == "__main__":
     from json_example import generate_example_json
     from sqlmodel import Session, select
     from global_var import get_sql_engine, init_global_var
-    from schema import dataset_item
+    from schema import DatasetItem
 
     init_global_var("workdir")
     api_state = "1 deepseek-chat"
@@ -105,7 +105,7 @@ if __name__ == "__main__":
     llm_request = LLMRequest(
         prompt="测试，随便说点什么",
         api_provider=api_provider,
-        format=generate_example_json(dataset_item)
+        format=generate_example_json(DatasetItem)
     )
 
     # # 单次调用示例