reformat kb_doc_api.py

server/knowledge_base/kb_doc_api.py

@@ -13,7 +13,7 @@ from pydantic import Json
 import json
 from server.knowledge_base.kb_service.base import KBServiceFactory
 from server.db.repository.knowledge_file_repository import get_file_detail
-from typing import List, Dict
+from typing import List
 from langchain.docstore.document import Document
 
 
@@ -21,10 +21,15 @@ class DocumentWithScore(Document):
     score: float = None
 
 
-def search_docs(query: str = Body(..., description="用户输入", examples=["你好"]),
+def search_docs(
+        query: str = Body(..., description="用户输入", examples=["你好"]),
         knowledge_base_name: str = Body(..., description="知识库名称", examples=["samples"]),
         top_k: int = Body(VECTOR_SEARCH_TOP_K, description="匹配向量数"),
-                score_threshold: float = Body(SCORE_THRESHOLD, description="知识库匹配相关度阈值，取值范围在0-1之间，SCORE越小，相关度越高，取到1相当于不筛选，建议设置在0.5左右", ge=0, le=1),
+        score_threshold: float = Body(SCORE_THRESHOLD,
+                                      description="知识库匹配相关度阈值，取值范围在0-1之间，"
+                                                  "SCORE越小，相关度越高，"
+                                                  "取到1相当于不筛选，建议设置在0.5左右",
+                                      ge=0, le=1),
 ) -> List[DocumentWithScore]:
     kb = KBServiceFactory.get_service_by_name(knowledge_base_name)
     if kb is None:
@@ -52,10 +57,11 @@ def list_files(
 def _save_files_in_thread(files: List[UploadFile],
                           knowledge_base_name: str,
                           override: bool):
-    '''
+    """
     通过多线程将上传的文件保存到对应知识库目录内。
     生成器返回保存结果：{"code":200, "msg": "xxx", "data": {"knowledge_base_name":"xxx", "file_name": "xxx"}}
-    '''
+    """
+
     def save_file(file: UploadFile, knowledge_base_name: str, override: bool) -> dict:
         '''
         保存单个文件。
@@ -117,19 +123,21 @@ def _save_files_in_thread(files: List[UploadFile],
 #             yield json.dumps(result, ensure_ascii=False)
 
 
-def upload_docs(files: List[UploadFile] = File(..., description="上传文件，支持多文件"),
+def upload_docs(
+        files: List[UploadFile] = File(..., description="上传文件，支持多文件"),
         knowledge_base_name: str = Form(..., description="知识库名称", examples=["samples"]),
         override: bool = Form(False, description="覆盖已有文件"),
         to_vector_store: bool = Form(True, description="上传文件后是否进行向量化"),
         chunk_size: int = Form(CHUNK_SIZE, description="知识库中单段文本最大长度"),
         chunk_overlap: int = Form(OVERLAP_SIZE, description="知识库中相邻文本重合长度"),
         zh_title_enhance: bool = Form(ZH_TITLE_ENHANCE, description="是否开启中文标题加强"),
-                docs: Json = Form({}, description="自定义的docs，需要转为json字符串", examples=[{"test.txt": [Document(page_content="custom doc")]}]),
+        docs: Json = Form({}, description="自定义的docs，需要转为json字符串",
+                          examples=[{"test.txt": [Document(page_content="custom doc")]}]),
         not_refresh_vs_cache: bool = Form(False, description="暂不保存向量库（用于FAISS）"),
 ) -> BaseResponse:
-    '''
+    """
     API接口：上传文件，并/或向量化
-    '''
+    """
     if not validate_kb_name(knowledge_base_name):
         return BaseResponse(code=403, msg="Don't attack me")
 
@@ -168,7 +176,8 @@ def upload_docs(files: List[UploadFile] = File(..., description="上传文件，
     return BaseResponse(code=200, msg="文件上传与向量化完成", data={"failed_files": failed_files})
 
 
-def delete_docs(knowledge_base_name: str = Body(..., examples=["samples"]),
+def delete_docs(
+        knowledge_base_name: str = Body(..., examples=["samples"]),
         file_names: List[str] = Body(..., examples=[["file_name.md", "test.txt"]]),
         delete_content: bool = Body(False),
         not_refresh_vs_cache: bool = Body(False, description="暂不保存向量库（用于FAISS）"),
@@ -202,7 +211,8 @@ def delete_docs(knowledge_base_name: str = Body(..., examples=["samples"]),
     return BaseResponse(code=200, msg=f"文件删除完成", data={"failed_files": failed_files})
 
 
-def update_info(knowledge_base_name: str = Body(..., description="知识库名称", examples=["samples"]),
+def update_info(
+        knowledge_base_name: str = Body(..., description="知识库名称", examples=["samples"]),
         kb_info: str = Body(..., description="知识库介绍", examples=["这是一个知识库"]),
 ):
     if not validate_kb_name(knowledge_base_name):
@@ -223,12 +233,13 @@ def update_docs(
         chunk_overlap: int = Body(OVERLAP_SIZE, description="知识库中相邻文本重合长度"),
         zh_title_enhance: bool = Body(ZH_TITLE_ENHANCE, description="是否开启中文标题加强"),
         override_custom_docs: bool = Body(False, description="是否覆盖之前自定义的docs"),
-    docs: Json = Body({}, description="自定义的docs，需要转为json字符串", examples=[{"test.txt": [Document(page_content="custom doc")]}]),
+        docs: Json = Body({}, description="自定义的docs，需要转为json字符串",
+                          examples=[{"test.txt": [Document(page_content="custom doc")]}]),
         not_refresh_vs_cache: bool = Body(False, description="暂不保存向量库（用于FAISS）"),
 ) -> BaseResponse:
-    '''
+    """
     更新知识库文档
-    '''
+    """
     if not validate_kb_name(knowledge_base_name):
         return BaseResponse(code=403, msg="Don't attack me")
 
@@ -293,9 +304,9 @@ def download_doc(
         file_name: str = Query(..., description="文件名称", examples=["test.txt"]),
         preview: bool = Query(False, description="是：浏览器内预览；否：下载"),
 ):
-    '''
+    """
     下载知识库文档
-    '''
+    """
     if not validate_kb_name(knowledge_base_name):
         return BaseResponse(code=403, msg="Don't attack me")
 
@@ -338,12 +349,12 @@ def recreate_vector_store(
         zh_title_enhance: bool = Body(ZH_TITLE_ENHANCE, description="是否开启中文标题加强"),
         not_refresh_vs_cache: bool = Body(False, description="暂不保存向量库（用于FAISS）"),
 ):
-    '''
+    """
     recreate vector store from the content.
     this is usefull when user can copy files to content folder directly instead of upload through network.
     by default, get_service_by_name only return knowledge base in the info.db and having document files in it.
     set allow_empty_kb to True make it applied on empty knowledge base which it not in the info.db or having no documents.
-    '''
+    """
 
     def output():
         kb = KBServiceFactory.get_service(knowledge_base_name, vs_type, embed_model)