refactor: replace logging with maxkb_logger for consistent logging across modules

liuruibin · liuruibin · commit a73e0b10f987 · 2025-06-25T17:00:18.000+08:00
diff --git a/apps/application/chat_pipeline/step/chat_step/impl/base_chat_step.py b/apps/application/chat_pipeline/step/chat_step/impl/base_chat_step.py
@@ -26,6 +26,7 @@
 from application.chat_pipeline.step.chat_step.i_chat_step import IChatStep, PostResponseHandler
 from application.flow.tools import Reasoning
 from application.models import ApplicationChatUserStats, ChatUserType
+from common.utils.logger import maxkb_logger
 from models_provider.tools import get_model_instance_by_model_workspace_id
 
 
@@ -135,7 +136,7 @@ def event_content(response,
                                                                       'node_type': 'ai-chat-node'})
         add_access_num(client_id, client_type, manage.context.get('application_id'))
     except Exception as e:
-        logging.getLogger("max_kb_error").error(f'{str(e)}:{traceback.format_exc()}')
+        maxkb_logger.error(f'{str(e)}:{traceback.format_exc()}')
         all_text = 'Exception:' + str(e)
         write_context(step, manage, 0, 0, all_text)
         post_response_handler.handler(chat_id, chat_record_id, paragraph_list, problem_text,
diff --git a/apps/common/event/listener_manage.py b/apps/common/event/listener_manage.py
@@ -21,7 +21,7 @@
 from common.db.search import native_search, get_dynamics_model, native_update
 from common.utils.common import get_file_content
 from common.utils.lock import try_lock, un_lock
-from common.utils.logger import maxkb_logger, maxkb_error_logger
+from common.utils.logger import maxkb_logger
 from common.utils.page_utils import page_desc
 from knowledge.models import Paragraph, Status, Document, ProblemParagraphMapping, TaskType, State,SourceType, SearchMode
 from maxkb.conf import (PROJECT_DIR)
@@ -86,7 +86,7 @@ def embedding_by_paragraph_list(paragraph_id_list, embedding_model: Embeddings):
             ListenerManagement.embedding_by_paragraph_data_list(data_list, paragraph_id_list=paragraph_id_list,
                                                                 embedding_model=embedding_model)
         except Exception as e:
-            maxkb_error_logger.error(_('Query vector data: {paragraph_id_list} error {error} {traceback}').format(
+            maxkb_logger.error(_('Query vector data: {paragraph_id_list} error {error} {traceback}').format(
                 paragraph_id_list=paragraph_id_list, error=str(e), traceback=traceback.format_exc()))
 
     @staticmethod
@@ -103,7 +103,7 @@ def is_save_function():
             # 批量向量化
             VectorStore.get_embedding_vector().batch_save(data_list, embedding_model, is_save_function)
         except Exception as e:
-            maxkb_error_logger.error(_('Vectorized paragraph: {paragraph_id_list} error {error} {traceback}').format(
+            maxkb_logger.error(_('Vectorized paragraph: {paragraph_id_list} error {error} {traceback}').format(
                 paragraph_id_list=paragraph_id_list, error=str(e), traceback=traceback.format_exc()))
             status = Status.error
         finally:
@@ -143,7 +143,7 @@ def is_the_task_interrupted():
             ListenerManagement.update_status(QuerySet(Paragraph).filter(id=paragraph_id), TaskType.EMBEDDING,
                                              State.SUCCESS)
         except Exception as e:
-            maxkb_error_logger.error(_('Vectorized paragraph: {paragraph_id} error {error} {traceback}').format(
+            maxkb_logger.error(_('Vectorized paragraph: {paragraph_id} error {error} {traceback}').format(
                 paragraph_id=paragraph_id, error=str(e), traceback=traceback.format_exc()))
             ListenerManagement.update_status(QuerySet(Paragraph).filter(id=paragraph_id), TaskType.EMBEDDING,
                                              State.FAILURE)
@@ -284,7 +284,7 @@ def is_the_task_interrupted():
                                                                            document_id)),
                       is_the_task_interrupted)
         except Exception as e:
-            maxkb_error_logger.error(_('Vectorized document: {document_id} error {error} {traceback}').format(
+            maxkb_logger.error(_('Vectorized document: {document_id} error {error} {traceback}').format(
                 document_id=document_id, error=str(e), traceback=traceback.format_exc()))
         finally:
             ListenerManagement.post_update_document_status(document_id, TaskType.EMBEDDING)
@@ -308,7 +308,7 @@ def embedding_by_knowledge(knowledge_id, embedding_model: Embeddings):
             for document in document_list:
                 ListenerManagement.embedding_by_document(document.id, embedding_model=embedding_model)
         except Exception as e:
-            maxkb_error_logger.error(_('Vectorized knowledge: {knowledge_id} error {error} {traceback}').format(
+            maxkb_logger.error(_('Vectorized knowledge: {knowledge_id} error {error} {traceback}').format(
                 knowledge_id=knowledge_id, error=str(e), traceback=traceback.format_exc()))
         finally:
             maxkb_logger.info(_('End--->Embedding knowledge: {knowledge_id}').format(knowledge_id=knowledge_id))
diff --git a/apps/common/exception/handle_exception.py b/apps/common/exception/handle_exception.py
@@ -17,6 +17,8 @@
 
 from django.utils.translation import gettext_lazy as _
 
+from common.utils.logger import maxkb_logger
+
 
 def to_result(key, args, parent_key=None):
     """
@@ -96,6 +98,6 @@ def handle_exception(exc, context):
     if issubclass(exception_class, APIException):
         return result.error(exc.detail)
     if response is None:
-        logging.getLogger("max_kb_error").error(f'{str(exc)}:{traceback.format_exc()}')
+        maxkb_logger.error(f'{str(exc)}:{traceback.format_exc()}')
         return result.error(str(exc))
     return response
diff --git a/apps/common/handle/handle_exception.py b/apps/common/handle/handle_exception.py
@@ -17,6 +17,7 @@
 from django.utils.translation import gettext_lazy as _
 
 from common.result import result
+from common.utils.logger import maxkb_logger
 
 
 def to_result(key, args, parent_key=None):
@@ -89,6 +90,6 @@ def handle_exception(exc, context):
     if issubclass(exception_class, APIException):
         return result.error(exc.detail)
     if response is None:
-        logging.getLogger("max_kb_error").error(f'{str(exc)}:{traceback.format_exc()}')
+        maxkb_logger.error(f'{str(exc)}:{traceback.format_exc()}')
         return result.error(str(exc))
     return response
diff --git a/apps/common/handle/impl/common_handle.py b/apps/common/handle/impl/common_handle.py
@@ -21,6 +21,7 @@
 from openpyxl.xml.constants import SHEET_DRAWING_NS, REL_NS, SHEET_MAIN_NS
 
 from common.handle.base_parse_qa_handle import get_title_row_index_dict, get_row_value
+from common.utils.logger import maxkb_logger
 from knowledge.models import File
 
 
@@ -75,7 +76,7 @@ def handle_images(deps, archive: ZipFile) -> []:
             image_io = archive.read(dep.target)
             image = openpyxl_Image(BytesIO(image_io))
         except Exception as e:
-            logging.getLogger("max_kb_error").error(f"Error reading image {dep.target}: {e}")
+            maxkb_logger.error(f"Error reading image {dep.target}: {e}")
             continue
         image.embed = dep.id  # 文件rId
         image.target = dep.target  # 文件地址
diff --git a/apps/common/handle/impl/table/csv_parse_table_handle.py b/apps/common/handle/impl/table/csv_parse_table_handle.py
@@ -4,7 +4,7 @@
 from charset_normalizer import detect
 
 from common.handle.base_parse_table_handle import BaseParseTableHandle
-from common.utils.logger import maxkb_logger, maxkb_error_logger
+from common.utils.logger import maxkb_logger
 
 
 class CsvParseTableHandle(BaseParseTableHandle):
@@ -39,5 +39,5 @@ def get_content(self, file, save_image):
         try:
             return buffer.decode(detect(buffer)['encoding'])
         except BaseException as e:
-            maxkb_error_logger.error(f'csv split handle error: {e}')
+            maxkb_logger.error(f'csv split handle error: {e}')
             return f'error: {e}'
diff --git a/apps/common/handle/impl/table/xls_parse_table_handle.py b/apps/common/handle/impl/table/xls_parse_table_handle.py
@@ -4,7 +4,7 @@
 import xlrd
 
 from common.handle.base_parse_table_handle import BaseParseTableHandle
-from common.utils.logger import maxkb_error_logger
+from common.utils.logger import maxkb_logger
 
 
 class XlsParseTableHandle(BaseParseTableHandle):
@@ -55,7 +55,7 @@ def handle(self, file, get_buffer, save_image):
                 result.append({'name': sheet.name, 'paragraphs': paragraphs})
 
         except BaseException as e:
-            maxkb_error_logger.error(f'excel split handle error: {e}')
+            maxkb_logger.error(f'excel split handle error: {e}')
             return [{'name': file.name, 'paragraphs': []}]
         return result
 
diff --git a/apps/common/handle/impl/table/xlsx_parse_table_handle.py b/apps/common/handle/impl/table/xlsx_parse_table_handle.py
@@ -6,7 +6,7 @@
 
 from common.handle.base_parse_table_handle import BaseParseTableHandle
 from common.handle.impl.common_handle import xlsx_embed_cells_images
-from common.utils.logger import maxkb_error_logger
+from common.utils.logger import maxkb_logger
 
 
 class XlsxParseTableHandle(BaseParseTableHandle):
@@ -73,7 +73,7 @@ def handle(self, file, get_buffer, save_image):
                 result.append({'name': sheetname, 'paragraphs': paragraphs})
 
         except BaseException as e:
-            maxkb_error_logger.error(f'excel split handle error: {e}')
+            maxkb_logger.error(f'excel split handle error: {e}')
             return [{'name': file.name, 'paragraphs': []}]
         return result
 
@@ -86,7 +86,7 @@ def get_content(self, file, save_image):
                 if len(image_dict) > 0:
                     save_image(image_dict.values())
             except Exception as e:
-                maxkb_error_logger.error(f'Exception: {e}')
+                maxkb_logger.error(f'Exception: {e}')
                 image_dict = {}
             md_tables = ''
             # 如果未指定 sheet_name，则使用第一个工作表
diff --git a/apps/common/handle/impl/text/doc_split_handle.py b/apps/common/handle/impl/text/doc_split_handle.py
@@ -21,6 +21,7 @@
 from docx.text.paragraph import Paragraph
 
 from common.handle.base_split_handle import BaseSplitHandle
+from common.utils.logger import maxkb_logger
 from common.utils.split_model import SplitModel
 from knowledge.models import File
 
@@ -79,7 +80,7 @@ def get_paragraph_element_txt(paragraph_element, doc: Document, images_list, get
             return paragraph_element.text
         return ""
     except Exception as e:
-        logging.getLogger("max_kb_error").error(f'Error getting paragraph element text: {e}')
+        maxkb_logger.error(f'Error getting paragraph element text: {e}')
     return ""
 
 
diff --git a/apps/common/handle/impl/text/pdf_split_handle.py b/apps/common/handle/impl/text/pdf_split_handle.py
@@ -19,7 +19,7 @@
 from langchain_community.document_loaders import PyPDFLoader
 
 from common.handle.base_split_handle import BaseSplitHandle
-from common.utils.logger import maxkb_error_logger, maxkb_logger
+from common.utils.logger import maxkb_logger
 from common.utils.split_model import SplitModel
 
 default_pattern_list = [re.compile('(?<=^)# .*|(?<=\\n)# .*'),
@@ -72,7 +72,7 @@ def handle(self, file, pattern_list: List, with_filter: bool, limit: int, get_bu
             else:
                 split_model = SplitModel(default_pattern_list, with_filter=with_filter, limit=limit)
         except BaseException as e:
-            maxkb_error_logger.error(f"File: {file.name}, error: {e}")
+            maxkb_logger.error(f"File: {file.name}, error: {e}")
             return {'name': file.name,
                     'content': []}
         finally:
@@ -109,7 +109,7 @@ def handle_pdf_content(file, pdf_document):
                     raise e
                 except BaseException as e:
                     # 当页出错继续进行下一页，防止一个页面出错导致整个文件解析失败
-                    maxkb_error_logger.error(f"File: {file.name}, Page: {page_num + 1}, error: {e}")
+                    maxkb_logger.error(f"File: {file.name}, Page: {page_num + 1}, error: {e}")
                     continue
                 finally:
                     os.remove(page_num_pdf)
@@ -278,7 +278,7 @@ def handle_links(doc, pattern_list, with_filter, limit):
                     pre_toc[i]['content'] = re.sub(r'(?<!。)\n+', '', pre_toc[i]['content'])
                     pre_toc[i]['content'] = re.sub(r'(?<!.)\n+', '', pre_toc[i]['content'])
             except BaseException as e:
-                maxkb_error_logger.error(_('This document has no preface and is treated as ordinary text: {e}').format(e=e))
+                maxkb_logger.error(_('This document has no preface and is treated as ordinary text: {e}').format(e=e))
                 if pattern_list is not None and len(pattern_list) > 0:
                     split_model = SplitModel(pattern_list, with_filter, limit)
                 else:
diff --git a/apps/common/utils/fork.py b/apps/common/utils/fork.py
@@ -10,7 +10,7 @@
 import requests
 from bs4 import BeautifulSoup
 
-from common.utils.logger import maxkb_error_logger, maxkb_logger
+from common.utils.logger import maxkb_logger
 
 requests.packages.urllib3.disable_warnings()
 
@@ -147,7 +147,7 @@ def get_beautiful_soup(response):
                 try:
                     html_content = response.content.decode(charset)
                 except Exception as e:
-                    maxkb_error_logger.error(f'{e}')
+                    maxkb_logger.error(f'{e}')
                 return BeautifulSoup(html_content, "html.parser")
         return beautiful_soup
 
@@ -161,11 +161,11 @@ def fork(self):
             maxkb_logger.info(f'fork:{self.base_fork_url}')
             response = requests.get(self.base_fork_url, verify=False, headers=headers)
             if response.status_code != 200:
-                maxkb_error_logger.error(f"url: {self.base_fork_url} code:{response.status_code}")
+                maxkb_logger.error(f"url: {self.base_fork_url} code:{response.status_code}")
                 return Fork.Response.error(f"url: {self.base_fork_url} code:{response.status_code}")
             bf = self.get_beautiful_soup(response)
         except Exception as e:
-            maxkb_error_logger.error(f'{str(e)}:{traceback.format_exc()}')
+            maxkb_logger.error(f'{str(e)}:{traceback.format_exc()}')
             return Fork.Response.error(str(e))
         bf = self.reset_beautiful_soup(bf)
         link_list = self.get_child_link_list(bf)
diff --git a/apps/common/utils/logger.py b/apps/common/utils/logger.py
@@ -0,0 +1,3 @@
+import logging
+
+maxkb_logger = logging.getLogger('max_kb')
diff --git a/apps/knowledge/serializers/document.py b/apps/knowledge/serializers/document.py
@@ -42,6 +42,7 @@
 from common.handle.impl.text.zip_split_handle import ZipSplitHandle
 from common.utils.common import post, get_file_content, bulk_create_in_batches, parse_image
 from common.utils.fork import Fork
+from common.utils.logger import maxkb_logger
 from common.utils.split_model import get_split_model, flat_map
 from knowledge.models import Knowledge, Paragraph, Problem, Document, KnowledgeType, ProblemParagraphMapping, State, \
     TaskType, File, FileSourceType
@@ -483,7 +484,7 @@ def sync(self, with_valid=True, with_embedding=True):
                 else:
                     state = State.FAILURE
             except Exception as e:
-                logging.getLogger("max_kb_error").error(f'{str(e)}:{traceback.format_exc()}')
+                maxkb_logger.error(f'{str(e)}:{traceback.format_exc()}')
                 state = State.FAILURE
             ListenerManagement.update_status(
                 QuerySet(Document).filter(id=document_id),
diff --git a/apps/knowledge/serializers/knowledge.py b/apps/knowledge/serializers/knowledge.py
@@ -647,7 +647,7 @@ def handler(child_link: ChildLink, response: Fork.Response):
                                           'selector': knowledge.meta.get('selector')},
                                  'type': KnowledgeType.WEB}, with_valid=True)
                     except Exception as e:
-                        logging.getLogger("max_kb_error").error(f'{str(e)}:{traceback.format_exc()}')
+                        maxkb_logger.error(f'{str(e)}:{traceback.format_exc()}')
 
             return handler
 
diff --git a/apps/knowledge/task/embedding.py b/apps/knowledge/task/embedding.py
@@ -11,15 +11,15 @@
 from common.config.embedding_config import ModelManage
 from common.event import ListenerManagement, UpdateProblemArgs, UpdateEmbeddingKnowledgeIdArgs, \
     UpdateEmbeddingDocumentIdArgs
-from common.utils.logger import maxkb_error_logger, maxkb_logger
+from common.utils.logger import maxkb_logger
 from knowledge.models import Document, TaskType, State
 from models_provider.tools import get_model
 from models_provider.models import Model
 from ops import celery_app
 
 
 
-def get_embedding_model(model_id, exception_handler=lambda e: maxkb_error_logger.error(
+def get_embedding_model(model_id, exception_handler=lambda e: maxkb_logger.error(
     _('Failed to obtain vector model: {error} {traceback}').format(
         error=str(e),
         traceback=traceback.format_exc()
@@ -69,7 +69,7 @@ def embedding_by_document(document_id, model_id, state_list=None):
     def exception_handler(e):
         ListenerManagement.update_status(QuerySet(Document).filter(id=document_id), TaskType.EMBEDDING,
                                          State.FAILURE)
-        maxkb_error_logger.error(
+        maxkb_logger.error(
             _('Failed to obtain vector model: {error} {traceback}').format(
                 error=str(e),
                 traceback=traceback.format_exc()
@@ -111,7 +111,7 @@ def embedding_by_knowledge(knowledge_id, model_id):
             except Exception as e:
                 pass
     except Exception as e:
-        maxkb_error_logger.error(
+        maxkb_logger.error(
             _('Vectorized knowledge: {knowledge_id} error {error} {traceback}'.format(knowledge_id=knowledge_id,
                                                                                       error=str(e),
                                                                                       traceback=traceback.format_exc())))
diff --git a/apps/knowledge/task/generate.py b/apps/knowledge/task/generate.py
@@ -9,7 +9,7 @@
 
 from common.config.embedding_config import ModelManage
 from common.event import ListenerManagement
-from common.utils.logger import maxkb_error_logger, maxkb_logger
+from common.utils.logger import maxkb_logger
 from common.utils.page_utils import page, page_desc
 from knowledge.models import Paragraph, Document, Status, TaskType, State
 from knowledge.task.handler import save_problem
@@ -100,8 +100,8 @@ def generate_related_by_document_id(document_id, model_id, prompt, state_list=No
         ).filter(task_type_status__in=state_list, document_id=document_id)
         page_desc(query_set, 10, generate_problem, is_the_task_interrupted)
     except Exception as e:
-        maxkb_error_logger.error(f'根据文档生成问题:{document_id}出现错误{str(e)}{traceback.format_exc()}')
-        maxkb_error_logger.error(_('Generate issue based on document: {document_id} error {error}{traceback}').format(
+        maxkb_logger.error(f'根据文档生成问题:{document_id}出现错误{str(e)}{traceback.format_exc()}')
+        maxkb_logger.error(_('Generate issue based on document: {document_id} error {error}{traceback}').format(
             document_id=document_id, error=str(e), traceback=traceback.format_exc()))
     finally:
         ListenerManagement.post_update_document_status(document_id, TaskType.GENERATE_PROBLEM)
diff --git a/apps/knowledge/task/handler.py b/apps/knowledge/task/handler.py
@@ -9,7 +9,7 @@
 from django.utils.translation import gettext_lazy as _
 
 from common.utils.fork import ChildLink, Fork
-from common.utils.logger import maxkb_error_logger
+from common.utils.logger import maxkb_logger
 from common.utils.split_model import get_split_model
 from knowledge.models.knowledge import KnowledgeType, Document, Knowledge, Status
 
@@ -32,7 +32,7 @@ def handler(child_link: ChildLink, response: Fork.Response):
                     'type': KnowledgeType.WEB
                 }, with_valid=True)
             except Exception as e:
-                logging.getLogger("max_kb_error").error(f'{str(e)}:{traceback.format_exc()}')
+                maxkb_logger.error(f'{str(e)}:{traceback.format_exc()}')
 
     return handler
 
@@ -64,7 +64,7 @@ def handler(child_link: ChildLink, response: Fork.Response):
                         'type': KnowledgeType.WEB
                     }, with_valid=True)
             except Exception as e:
-                logging.getLogger("max_kb_error").error(f'{str(e)}:{traceback.format_exc()}')
+                maxkb_logger.error(f'{str(e)}:{traceback.format_exc()}')
 
     return handler
 
@@ -82,7 +82,7 @@ def handler(source_url: str, selector, response: Fork.Response):
                      'meta': {'source_url': source_url, 'selector': selector},
                      'type': KnowledgeType.WEB}, with_valid=True)
             except Exception as e:
-                logging.getLogger("max_kb_error").error(f'{str(e)}:{traceback.format_exc()}')
+                maxkb_logger.error(f'{str(e)}:{traceback.format_exc()}')
         else:
             Document(name=source_url[0:128],
                      knowledge_id=knowledge_id,
@@ -116,4 +116,4 @@ def save_problem(knowledge_id, document_id, paragraph_id, problem):
             }
         ).save(instance={"content": problem}, with_valid=True)
     except Exception as e:
-        maxkb_error_logger.error(_('Association problem failed {error}').format(error=str(e)))
+        maxkb_logger.error(_('Association problem failed {error}').format(error=str(e)))
diff --git a/apps/knowledge/task/sync.py b/apps/knowledge/task/sync.py
diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/tti.py b/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/tti.py
diff --git a/apps/models_provider/impl/tencent_model_provider/model/tti.py b/apps/models_provider/impl/tencent_model_provider/model/tti.py
diff --git a/apps/models_provider/impl/volcanic_engine_model_provider/model/stt.py b/apps/models_provider/impl/volcanic_engine_model_provider/model/stt.py
