Use consistent log file names, introduced initLogger (#3403)

### What problem does this PR solve?

Use consistent log file names, introduced initLogger

### Type of change

- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [x] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):

agent/canvas.py

@@ -13,13 +13,13 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import json
 from abc import ABC
 from copy import deepcopy
 from functools import partial
 from agent.component import component_class
 from agent.component.base import ComponentBase
-from api.utils.log_utils import logger
 
 class Canvas(ABC):
     """
@@ -187,7 +187,7 @@ class Canvas(ABC):
                 if cpn.component_name == "Answer":
                     self.answer.append(c)
                 else:
-                    logger.debug(f"Canvas.prepare2run: {c}")
+                    logging.debug(f"Canvas.prepare2run: {c}")
                     cpids = cpn.get_dependent_components()
                     if any([c not in self.path[-1] for c in cpids]):
                         continue
@@ -197,7 +197,7 @@ class Canvas(ABC):
 
         prepare2run(self.components[self.path[-2][-1]]["downstream"])
         while 0 <= ran < len(self.path[-1]):
-            logger.debug(f"Canvas.run: {ran} {self.path}")
+            logging.debug(f"Canvas.run: {ran} {self.path}")
             cpn_id = self.path[-1][ran]
             cpn = self.get_component(cpn_id)
             if not cpn["downstream"]: break
@@ -217,7 +217,7 @@ class Canvas(ABC):
                             self.get_component(p)["obj"].set_exception(e)
                             prepare2run([p])
                             break
-                    logger.exception("Canvas.run got exception")
+                    logging.exception("Canvas.run got exception")
                     break
                 continue
 
@@ -229,7 +229,7 @@ class Canvas(ABC):
                         self.get_component(p)["obj"].set_exception(e)
                         prepare2run([p])
                         break
-                logger.exception("Canvas.run got exception")
+                logging.exception("Canvas.run got exception")
                 break
 
         if self.answer:

agent/component/arxiv.py

@@ -13,11 +13,11 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 import arxiv
 import pandas as pd
 from agent.component.base import ComponentBase, ComponentParamBase
-from api.utils.log_utils import logger
 
 class ArXivParam(ComponentParamBase):
     """
@@ -64,5 +64,5 @@ class ArXiv(ComponentBase, ABC):
             return ArXiv.be_output("")
 
         df = pd.DataFrame(arxiv_res)
-        logger.debug(f"df: {str(df)}")
+        logging.debug(f"df: {str(df)}")
         return df

agent/component/baidu.py

@@ -13,12 +13,12 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 import pandas as pd
 import requests
 import re
 from agent.component.base import ComponentBase, ComponentParamBase
-from api.utils.log_utils import logger
 
 
 class BaiduParam(ComponentParamBase):
@@ -62,6 +62,6 @@ class Baidu(ComponentBase, ABC):
             return Baidu.be_output("")
 
         df = pd.DataFrame(baidu_res)
-        logger.debug(f"df: {str(df)}")
+        logging.debug(f"df: {str(df)}")
         return df
 

agent/component/base.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 import builtins
 import json
@@ -23,7 +24,6 @@ from typing import Tuple, Union
 import pandas as pd
 
 from agent import settings
-from api.utils.log_utils import logger
 
 
 _FEEDED_DEPRECATED_PARAMS = "_feeded_deprecated_params"
@@ -361,13 +361,13 @@ class ComponentParamBase(ABC):
 
     def _warn_deprecated_param(self, param_name, descr):
         if self._deprecated_params_set.get(param_name):
-            logger.warning(
+            logging.warning(
                 f"{descr} {param_name} is deprecated and ignored in this version."
             )
 
     def _warn_to_deprecate_param(self, param_name, descr, new_param):
         if self._deprecated_params_set.get(param_name):
-            logger.warning(
+            logging.warning(
                 f"{descr} {param_name} will be deprecated in future release; "
                 f"please use {new_param} instead."
             )
@@ -403,7 +403,7 @@ class ComponentBase(ABC):
         return cpnts
 
     def run(self, history, **kwargs):
-        logger.info("{}, history: {}, kwargs: {}".format(self, json.dumps(history, ensure_ascii=False),
+        logging.debug("{}, history: {}, kwargs: {}".format(self, json.dumps(history, ensure_ascii=False),
                                                               json.dumps(kwargs, ensure_ascii=False)))
         try:
             res = self._run(history, **kwargs)
@@ -476,7 +476,7 @@ class ComponentBase(ABC):
             reversed_cpnts.extend(self._canvas.path[-2])
         reversed_cpnts.extend(self._canvas.path[-1])
 
-        logger.debug(f"{self.component_name} {reversed_cpnts[::-1]}")
+        logging.debug(f"{self.component_name} {reversed_cpnts[::-1]}")
         for u in reversed_cpnts[::-1]:
             if self.get_component_name(u) in ["switch", "concentrator"]: continue
             if self.component_name.lower() == "generate" and self.get_component_name(u) == "retrieval":

agent/component/bing.py

@@ -13,11 +13,11 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 import requests
 import pandas as pd
 from agent.component.base import ComponentBase, ComponentParamBase
-from api.utils.log_utils import logger
 
 class BingParam(ComponentParamBase):
     """
@@ -80,5 +80,5 @@ class Bing(ComponentBase, ABC):
             return Bing.be_output("")
 
         df = pd.DataFrame(bing_res)
-        logger.debug(f"df: {str(df)}")
+        logging.debug(f"df: {str(df)}")
         return df

agent/component/categorize.py

@@ -13,11 +13,11 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 from api.db import LLMType
 from api.db.services.llm_service import LLMBundle
 from agent.component import GenerateParam, Generate
-from api.utils.log_utils import logger
 
 
 class CategorizeParam(GenerateParam):
@@ -77,7 +77,7 @@ class Categorize(Generate, ABC):
         chat_mdl = LLMBundle(self._canvas.get_tenant_id(), LLMType.CHAT, self._param.llm_id)
         ans = chat_mdl.chat(self._param.get_prompt(), [{"role": "user", "content": input}],
                             self._param.gen_conf())
-        logger.debug(f"input: {input}, answer: {str(ans)}")
+        logging.debug(f"input: {input}, answer: {str(ans)}")
         for c in self._param.category_description.keys():
             if ans.lower().find(c.lower()) >= 0:
                 return Categorize.be_output(self._param.category_description[c]["to"])

agent/component/duckduckgo.py

@@ -13,11 +13,11 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 from duckduckgo_search import DDGS
 import pandas as pd
 from agent.component.base import ComponentBase, ComponentParamBase
-from api.utils.log_utils import logger
 
 
 class DuckDuckGoParam(ComponentParamBase):
@@ -62,5 +62,5 @@ class DuckDuckGo(ComponentBase, ABC):
             return DuckDuckGo.be_output("")
 
         df = pd.DataFrame(duck_res)
-        logger.debug("df: {df}")
+        logging.debug("df: {df}")
         return df

agent/component/github.py

@@ -13,11 +13,11 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 import pandas as pd
 import requests
 from agent.component.base import ComponentBase, ComponentParamBase
-from api.utils.log_utils import logger
 
 
 class GitHubParam(ComponentParamBase):
@@ -57,5 +57,5 @@ class GitHub(ComponentBase, ABC):
             return GitHub.be_output("")
 
         df = pd.DataFrame(github_res)
-        logger.debug(f"df: {df}")
+        logging.debug(f"df: {df}")
         return df

agent/component/google.py

@@ -13,11 +13,11 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 from serpapi import GoogleSearch
 import pandas as pd
 from agent.component.base import ComponentBase, ComponentParamBase
-from api.utils.log_utils import logger
 
 
 class GoogleParam(ComponentParamBase):
@@ -92,5 +92,5 @@ class Google(ComponentBase, ABC):
             return Google.be_output("")
 
         df = pd.DataFrame(google_res)
-        logger.debug(f"df: {df}")
+        logging.debug(f"df: {df}")
         return df

agent/component/googlescholar.py

@@ -13,11 +13,11 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 import pandas as pd
 from agent.component.base import ComponentBase, ComponentParamBase
 from scholarly import scholarly
-from api.utils.log_utils import logger
 
 
 class GoogleScholarParam(ComponentParamBase):
@@ -59,12 +59,12 @@ class GoogleScholar(ComponentBase, ABC):
                                                    'bib'].get('abstract', 'no abstract')})
 
             except StopIteration or Exception:
-                logger.exception("GoogleScholar")
+                logging.exception("GoogleScholar")
                 break
 
         if not scholar_res:
             return GoogleScholar.be_output("")
 
         df = pd.DataFrame(scholar_res)
-        logger.debug(f"df: {df}")
+        logging.debug(f"df: {df}")
         return df

agent/component/keyword.py

@@ -13,12 +13,12 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import re
 from abc import ABC
 from api.db import LLMType
 from api.db.services.llm_service import LLMBundle
 from agent.component import GenerateParam, Generate
-from api.utils.log_utils import logger
 
 
 class KeywordExtractParam(GenerateParam):
@@ -58,5 +58,5 @@ class KeywordExtract(Generate, ABC):
                             self._param.gen_conf())
 
         ans = re.sub(r".*keyword:", "", ans).strip()
-        logger.info(f"ans: {ans}")
+        logging.debug(f"ans: {ans}")
         return KeywordExtract.be_output(ans)

agent/component/pubmed.py

@@ -13,13 +13,13 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 from Bio import Entrez
 import re
 import pandas as pd
 import xml.etree.ElementTree as ET
 from agent.component.base import ComponentBase, ComponentParamBase
-from api.utils.log_utils import logger
 
 
 class PubMedParam(ComponentParamBase):
@@ -65,5 +65,5 @@ class PubMed(ComponentBase, ABC):
             return PubMed.be_output("")
 
         df = pd.DataFrame(pubmed_res)
-        logger.debug(f"df: {df}")
+        logging.debug(f"df: {df}")
         return df

agent/component/relevant.py

@@ -13,12 +13,12 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 from api.db import LLMType
 from api.db.services.llm_service import LLMBundle
 from agent.component import GenerateParam, Generate
 from rag.utils import num_tokens_from_string, encoder
-from api.utils.log_utils import logger
 
 
 class RelevantParam(GenerateParam):
@@ -71,7 +71,7 @@ class Relevant(Generate, ABC):
         ans = chat_mdl.chat(self._param.get_prompt(), [{"role": "user", "content": ans}],
                             self._param.gen_conf())
 
-        logger.info(ans)
+        logging.debug(ans)
         if ans.lower().find("yes") >= 0:
             return Relevant.be_output(self._param.yes)
         if ans.lower().find("no") >= 0:

agent/component/retrieval.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 
 import pandas as pd
@@ -22,7 +23,6 @@ from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.db.services.llm_service import LLMBundle
 from api.settings import retrievaler
 from agent.component.base import ComponentBase, ComponentParamBase
-from api.utils.log_utils import logger
 
 
 class RetrievalParam(ComponentParamBase):
@@ -81,7 +81,7 @@ class Retrieval(ComponentBase, ABC):
         df = pd.DataFrame(kbinfos["chunks"])
         df["content"] = df["content_with_weight"]
         del df["content_with_weight"]
-        logger.debug("{} {}".format(query, df))
+        logging.debug("{} {}".format(query, df))
         return df
 
 

agent/component/rewrite.py

@@ -13,11 +13,11 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 from api.db import LLMType
 from api.db.services.llm_service import LLMBundle
 from agent.component import GenerateParam, Generate
-from api.utils.log_utils import logger
 
 
 class RewriteQuestionParam(GenerateParam):
@@ -105,7 +105,7 @@ class RewriteQuestion(Generate, ABC):
         self._canvas.history.pop()
         self._canvas.history.append(("user", ans))
 
-        logger.info(ans)
+        logging.debug(ans)
         return RewriteQuestion.be_output(ans)
 
 

agent/component/wikipedia.py

@@ -13,11 +13,11 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 import wikipedia
 import pandas as pd
 from agent.component.base import ComponentBase, ComponentParamBase
-from api.utils.log_utils import logger
 
 
 class WikipediaParam(ComponentParamBase):
@@ -63,5 +63,5 @@ class Wikipedia(ComponentBase, ABC):
             return Wikipedia.be_output("")
 
         df = pd.DataFrame(wiki_res)
-        logger.debug(f"df: {df}")
+        logging.debug(f"df: {df}")
         return df

agent/component/yahoofinance.py

@@ -13,11 +13,11 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from abc import ABC
 import pandas as pd
 from agent.component.base import ComponentBase, ComponentParamBase
 import yfinance as yf
-from api.utils.log_utils import logger
 
 
 class YahooFinanceParam(ComponentParamBase):
@@ -76,7 +76,7 @@ class YahooFinance(ComponentBase, ABC):
             if self._param.news:
                 yohoo_res.append({"content": "news:\n" + pd.DataFrame(msft.news).to_markdown() + "\n"})
         except Exception:
-            logger.exception("YahooFinance got exception")
+            logging.exception("YahooFinance got exception")
 
         if not yohoo_res:
             return YahooFinance.be_output("")

api/apps/__init__.py

@@ -15,6 +15,7 @@
 #
 import os
 import sys
+import logging
 from importlib.util import module_from_spec, spec_from_file_location
 from pathlib import Path
 from flask import Blueprint, Flask
@@ -32,7 +33,6 @@ from flask_login import LoginManager
 from api.settings import SECRET_KEY
 from api.settings import API_VERSION
 from api.utils.api_utils import server_error_response
-from api.utils.log_utils import logger
 from itsdangerous.url_safe import URLSafeTimedSerializer as Serializer
 
 __all__ = ["app"]
@@ -154,7 +154,7 @@ def load_user(web_request):
             else:
                 return None
         except Exception:
-            logger.exception("load_user got exception")
+            logging.exception("load_user got exception")
             return None
     else:
         return None

api/apps/canvas_app.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import json
 from functools import partial
 from flask import request, Response
@@ -23,7 +24,6 @@ from api.utils import get_uuid
 from api.utils.api_utils import get_json_result, server_error_response, validate_request, get_data_error_result
 from agent.canvas import Canvas
 from peewee import MySQLDatabase, PostgresqlDatabase
-from api.utils.log_utils import logger
 
 
 @manager.route('/templates', methods=['GET'])
@@ -115,7 +115,7 @@ def run():
                 pass
             canvas.add_user_input(req["message"])
         answer = canvas.run(stream=stream)
-        logger.info(canvas)
+        logging.debug(canvas)
     except Exception as e:
         return server_error_response(e)
 

api/apps/llm_app.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import json
 
 from flask import request
@@ -25,7 +26,6 @@ from api.db.db_models import TenantLLM
 from api.utils.api_utils import get_json_result
 from rag.llm import EmbeddingModel, ChatModel, RerankModel, CvModel, TTSModel
 import requests
-from api.utils.log_utils import logger
 
 
 @manager.route('/factories', methods=['GET'])
@@ -90,7 +90,7 @@ def set_api_key():
                 if len(arr) == 0 or tc == 0:
                     raise Exception("Fail")
                 rerank_passed = True
-                logger.info(f'passed model rerank {llm.llm_name}')
+                logging.debug(f'passed model rerank {llm.llm_name}')
             except Exception as e:
                 msg += f"\nFail to access model({llm.llm_name}) using this api key." + str(
                     e)

api/apps/user_app.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import json
 import re
 from datetime import datetime
@@ -54,7 +55,6 @@ from api.settings import (
 from api.db.services.user_service import UserService, TenantService, UserTenantService
 from api.db.services.file_service import FileService
 from api.utils.api_utils import get_json_result, construct_response
-from api.utils.log_utils import logger
 
 
 @manager.route("/login", methods=["POST", "GET"])
@@ -177,7 +177,7 @@ def github_callback():
             try:
                 avatar = download_img(user_info["avatar_url"])
             except Exception as e:
-                logger.exception(e)
+                logging.exception(e)
                 avatar = ""
             users = user_register(
                 user_id,
@@ -202,7 +202,7 @@ def github_callback():
             return redirect("/?auth=%s" % user.get_id())
         except Exception as e:
             rollback_user_registration(user_id)
-            logger.exception(e)
+            logging.exception(e)
             return redirect("/?error=%s" % str(e))
 
     # User has already registered, try to log in
@@ -279,7 +279,7 @@ def feishu_callback():
             try:
                 avatar = download_img(user_info["avatar_url"])
             except Exception as e:
-                logger.exception(e)
+                logging.exception(e)
                 avatar = ""
             users = user_register(
                 user_id,
@@ -304,7 +304,7 @@ def feishu_callback():
             return redirect("/?auth=%s" % user.get_id())
         except Exception as e:
             rollback_user_registration(user_id)
-            logger.exception(e)
+            logging.exception(e)
             return redirect("/?error=%s" % str(e))
 
     # User has already registered, try to log in
@@ -436,7 +436,7 @@ def setting_user():
         UserService.update_by_id(current_user.id, update_dict)
         return get_json_result(data=True)
     except Exception as e:
-        logger.exception(e)
+        logging.exception(e)
         return get_json_result(
             data=False, message="Update failure!", code=RetCode.EXCEPTION_ERROR
         )
@@ -621,7 +621,7 @@ def user_add():
         )
     except Exception as e:
         rollback_user_registration(user_id)
-        logger.exception(e)
+        logging.exception(e)
         return get_json_result(
             data=False,
             message=f"User registration failure, error: {str(e)}",

api/db/db_models.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import inspect
 import os
 import sys
@@ -32,7 +33,6 @@ from playhouse.pool import PooledMySQLDatabase, PooledPostgresqlDatabase
 from api.db import SerializedType, ParserType
 from api.settings import DATABASE, SECRET_KEY, DATABASE_TYPE
 from api import utils
-from api.utils.log_utils import logger
 
 def singleton(cls, *args, **kw):
     instances = {}
@@ -285,7 +285,7 @@ class BaseDataBase:
         database_config = DATABASE.copy()
         db_name = database_config.pop("name")
         self.database_connection = PooledDatabase[DATABASE_TYPE.upper()].value(db_name, **database_config)
-        logger.info('init database on cluster mode successfully')
+        logging.info('init database on cluster mode successfully')
 
 class PostgresDatabaseLock:
     def __init__(self, lock_name, timeout=10, db=None):
@@ -393,7 +393,7 @@ def close_connection():
         if DB:
             DB.close_stale(age=30)
     except Exception as e:
-        logger.exception(e)
+        logging.exception(e)
 
 
 class DataBaseModel(BaseModel):
@@ -409,15 +409,15 @@ def init_database_tables(alter_fields=[]):
     for name, obj in members:
         if obj != DataBaseModel and issubclass(obj, DataBaseModel):
             table_objs.append(obj)
-            logger.info(f"start create table {obj.__name__}")
+            logging.debug(f"start create table {obj.__name__}")
             try:
                 obj.create_table()
-                logger.info(f"create table success: {obj.__name__}")
+                logging.debug(f"create table success: {obj.__name__}")
             except Exception as e:
-                logger.exception(e)
+                logging.exception(e)
                 create_failed_list.append(obj.__name__)
     if create_failed_list:
-        logger.info(f"create tables failed: {create_failed_list}")
+        logging.error(f"create tables failed: {create_failed_list}")
         raise Exception(f"create tables failed: {create_failed_list}")
     migrate_db()
 

api/db/init_data.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import base64
 import json
 import os
@@ -30,7 +31,6 @@ from api.db.services.llm_service import LLMFactoriesService, LLMService, TenantL
 from api.db.services.user_service import TenantService, UserTenantService
 from api.settings import CHAT_MDL, EMBEDDING_MDL, ASR_MDL, IMAGE2TEXT_MDL, PARSERS, LLM_FACTORY, API_KEY, LLM_BASE_URL
 from api.utils.file_utils import get_project_base_directory
-from api.utils.log_utils import logger
 
 
 def encode_to_base64(input_string):
@@ -70,26 +70,26 @@ def init_superuser():
              "api_key": API_KEY, "api_base": LLM_BASE_URL})
 
     if not UserService.save(**user_info):
-        logger.info("can't init admin.")
+        logging.error("can't init admin.")
         return
     TenantService.insert(**tenant)
     UserTenantService.insert(**usr_tenant)
     TenantLLMService.insert_many(tenant_llm)
-    logger.info(
-        "Super user initialized. email: admin@ragflow.io, password: admin. Changing the password after logining is strongly recomanded.")
+    logging.info(
+        "Super user initialized. email: admin@ragflow.io, password: admin. Changing the password after login is strongly recommended.")
 
     chat_mdl = LLMBundle(tenant["id"], LLMType.CHAT, tenant["llm_id"])
     msg = chat_mdl.chat(system="", history=[
                         {"role": "user", "content": "Hello!"}], gen_conf={})
     if msg.find("ERROR: ") == 0:
-        logger.error(
+        logging.error(
             "'{}' dosen't work. {}".format(
                 tenant["llm_id"],
                 msg))
     embd_mdl = LLMBundle(tenant["id"], LLMType.EMBEDDING, tenant["embd_id"])
     v, c = embd_mdl.encode(["Hello!"])
     if c == 0:
-        logger.error(
+        logging.error(
             "'{}' dosen't work!".format(
                 tenant["embd_id"]))
 
@@ -172,7 +172,7 @@ def add_graph_templates():
             except:
                 CanvasTemplateService.update_by_id(cnvs["id"], cnvs)
         except Exception:
-            logger.exception("Add graph templates error: ")
+            logging.exception("Add graph templates error: ")
 
 
 def init_web_data():
@@ -183,7 +183,7 @@ def init_web_data():
     #    init_superuser()
 
     add_graph_templates()
-    logger.info("init web data success:{}".format(time.time() - start_time))
+    logging.info("init web data success:{}".format(time.time() - start_time))
 
 
 if __name__ == '__main__':

api/db/services/dialog_service.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import binascii
 import os
 import json
@@ -31,7 +32,6 @@ from rag.app.resume import forbidden_select_fields4resume
 from rag.nlp.search import index_name
 from rag.utils import rmSpace, num_tokens_from_string, encoder
 from api.utils.file_utils import get_project_base_directory
-from api.utils.log_utils import logger
 
 
 class DialogService(CommonService):
@@ -178,7 +178,7 @@ def chat(dialog, messages, stream=True, **kwargs):
         tts_mdl = LLMBundle(dialog.tenant_id, LLMType.TTS)
     # try to use sql if field mapping is good to go
     if field_map:
-        logger.info("Use SQL to retrieval:{}".format(questions[-1]))
+        logging.debug("Use SQL to retrieval:{}".format(questions[-1]))
         ans = use_sql(questions[-1], field_map, dialog.tenant_id, chat_mdl, prompt_config.get("quote", True))
         if ans:
             yield ans
@@ -220,7 +220,7 @@ def chat(dialog, messages, stream=True, **kwargs):
                                         doc_ids=attachments,
                                         top=dialog.top_k, aggs=False, rerank_mdl=rerank_mdl)
     knowledges = [ck["content_with_weight"] for ck in kbinfos["chunks"]]
-    logger.info(
+    logging.debug(
         "{}->{}".format(" ".join(questions), "\n->".join(knowledges)))
     retrieval_tm = timer()
 
@@ -292,7 +292,7 @@ def chat(dialog, messages, stream=True, **kwargs):
         yield decorate_answer(answer)
     else:
         answer = chat_mdl.chat(prompt, msg[1:], gen_conf)
-        logger.info("User: {}|Assistant: {}".format(
+        logging.debug("User: {}|Assistant: {}".format(
             msg[-1]["content"], answer))
         res = decorate_answer(answer)
         res["audio_binary"] = tts(tts_mdl, answer)
@@ -320,7 +320,7 @@ def use_sql(question, field_map, tenant_id, chat_mdl, quota=True):
         nonlocal sys_prompt, user_promt, question, tried_times
         sql = chat_mdl.chat(sys_prompt, [{"role": "user", "content": user_promt}], {
             "temperature": 0.06})
-        logger.info(f"{question} ==> {user_promt} get SQL: {sql}")
+        logging.debug(f"{question} ==> {user_promt} get SQL: {sql}")
         sql = re.sub(r"[\r\n]+", " ", sql.lower())
         sql = re.sub(r".*select ", "select ", sql.lower())
         sql = re.sub(r" +", " ", sql)
@@ -340,7 +340,7 @@ def use_sql(question, field_map, tenant_id, chat_mdl, quota=True):
                     flds.append(k)
                 sql = "select doc_id,docnm_kwd," + ",".join(flds) + sql[8:]
 
-        logger.info(f"{question} get SQL(refined): {sql}")
+        logging.debug(f"{question} get SQL(refined): {sql}")
         tried_times += 1
         return retrievaler.sql_retrieval(sql, format="json"), sql
 
@@ -369,9 +369,9 @@ def use_sql(question, field_map, tenant_id, chat_mdl, quota=True):
             question, sql, tbl["error"]
         )
         tbl, sql = get_table()
-        logger.info("TRY it again: {}".format(sql))
+        logging.debug("TRY it again: {}".format(sql))
 
-    logger.info("GET table: {}".format(tbl))
+    logging.debug("GET table: {}".format(tbl))
     if tbl.get("error") or len(tbl["rows"]) == 0:
         return None
 
@@ -401,7 +401,7 @@ def use_sql(question, field_map, tenant_id, chat_mdl, quota=True):
     rows = re.sub(r"T[0-9]{2}:[0-9]{2}:[0-9]{2}(\.[0-9]+Z)?\|", "|", rows)
 
     if not docid_idx or not docnm_idx:
-        logger.warning("SQL missing field: " + sql)
+        logging.warning("SQL missing field: " + sql)
         return {
             "answer": "\n".join([clmns, line, rows]),
             "reference": {"chunks": [], "doc_aggs": []},

api/db/services/document_service.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import hashlib
 import json
 import random
@@ -39,7 +40,6 @@ from api.db.services.common_service import CommonService
 from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.db import StatusEnum
 from rag.utils.redis_conn import REDIS_CONN
-from api.utils.log_utils import logger
 
 
 class DocumentService(CommonService):
@@ -387,7 +387,7 @@ class DocumentService(CommonService):
                 cls.update_by_id(d["id"], info)
             except Exception as e:
                 if str(e).find("'0'") < 0:
-                    logger.exception("fetch task exception")
+                    logging.exception("fetch task exception")
 
     @classmethod
     @DB.connection_context()
@@ -544,7 +544,7 @@ def doc_upload_and_parse(conversation_id, file_objs, user_id):
                     "knowledge_graph_kwd": "mind_map"
                 })
             except Exception as e:
-                logger.exception("Mind map generation error")
+                logging.exception("Mind map generation error")
 
         vects = embedding(doc_id, [c["content_with_weight"] for c in cks])
         assert len(cks) == len(vects)

api/db/services/file_service.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import re
 import os
 from concurrent.futures import ThreadPoolExecutor
@@ -30,7 +31,6 @@ from api.db.services.file2document_service import File2DocumentService
 from api.utils import get_uuid
 from api.utils.file_utils import filename_type, thumbnail_img
 from rag.utils.storage_factory import STORAGE_IMPL
-from api.utils.log_utils import logger
 
 
 class FileService(CommonService):
@@ -276,7 +276,7 @@ class FileService(CommonService):
             return cls.model.delete().where((cls.model.tenant_id == user_id)
                                             & (cls.model.id == folder_id)).execute(),
         except Exception:
-            logger.exception("delete_folder_by_pf_id")
+            logging.exception("delete_folder_by_pf_id")
             raise RuntimeError("Database error (File retrieval)!")
 
     @classmethod
@@ -325,7 +325,7 @@ class FileService(CommonService):
         try:
             cls.filter_update((cls.model.id << file_ids, ), { 'parent_id': folder_id })
         except Exception:
-            logger.exception("move_file")
+            logging.exception("move_file")
             raise RuntimeError("Database error (File move)!")
 
     @classmethod

api/db/services/llm_service.py

@@ -13,13 +13,13 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from api.db.services.user_service import TenantService
 from rag.llm import EmbeddingModel, CvModel, ChatModel, RerankModel, Seq2txtModel, TTSModel
 from api.db import LLMType
 from api.db.db_models import DB
 from api.db.db_models import LLMFactories, LLM, TenantLLM
 from api.db.services.common_service import CommonService
-from api.utils.log_utils import logger
 
 
 class LLMFactoriesService(CommonService):
@@ -209,7 +209,7 @@ class LLMBundle(object):
         emd, used_tokens = self.mdl.encode(texts, batch_size)
         if not TenantLLMService.increase_usage(
                 self.tenant_id, self.llm_type, used_tokens):
-            logger.error(
+            logging.error(
                 "LLMBundle.encode can't update token usage for {}/EMBEDDING used_tokens: {}".format(self.tenant_id, used_tokens))
         return emd, used_tokens
 
@@ -217,7 +217,7 @@ class LLMBundle(object):
         emd, used_tokens = self.mdl.encode_queries(query)
         if not TenantLLMService.increase_usage(
                 self.tenant_id, self.llm_type, used_tokens):
-            logger.error(
+            logging.error(
                 "LLMBundle.encode_queries can't update token usage for {}/EMBEDDING used_tokens: {}".format(self.tenant_id, used_tokens))
         return emd, used_tokens
 
@@ -225,7 +225,7 @@ class LLMBundle(object):
         sim, used_tokens = self.mdl.similarity(query, texts)
         if not TenantLLMService.increase_usage(
                 self.tenant_id, self.llm_type, used_tokens):
-            logger.error(
+            logging.error(
                 "LLMBundle.similarity can't update token usage for {}/RERANK used_tokens: {}".format(self.tenant_id, used_tokens))
         return sim, used_tokens
 
@@ -233,7 +233,7 @@ class LLMBundle(object):
         txt, used_tokens = self.mdl.describe(image, max_tokens)
         if not TenantLLMService.increase_usage(
                 self.tenant_id, self.llm_type, used_tokens):
-            logger.error(
+            logging.error(
                 "LLMBundle.describe can't update token usage for {}/IMAGE2TEXT used_tokens: {}".format(self.tenant_id, used_tokens))
         return txt
 
@@ -241,7 +241,7 @@ class LLMBundle(object):
         txt, used_tokens = self.mdl.transcription(audio)
         if not TenantLLMService.increase_usage(
                 self.tenant_id, self.llm_type, used_tokens):
-            logger.error(
+            logging.error(
                 "LLMBundle.transcription can't update token usage for {}/SEQUENCE2TXT used_tokens: {}".format(self.tenant_id, used_tokens))
         return txt
 
@@ -250,7 +250,7 @@ class LLMBundle(object):
             if isinstance(chunk,int):
                 if not TenantLLMService.increase_usage(
                     self.tenant_id, self.llm_type, chunk, self.llm_name):
-                        logger.error(
+                        logging.error(
                             "LLMBundle.tts can't update token usage for {}/TTS".format(self.tenant_id))
                 return
             yield chunk     
@@ -259,7 +259,7 @@ class LLMBundle(object):
         txt, used_tokens = self.mdl.chat(system, history, gen_conf)
         if isinstance(txt, int) and not TenantLLMService.increase_usage(
                 self.tenant_id, self.llm_type, used_tokens, self.llm_name):
-            logger.error(
+            logging.error(
                 "LLMBundle.chat can't update token usage for {}/CHAT llm_name: {}, used_tokens: {}".format(self.tenant_id, self.llm_name, used_tokens))
         return txt
 
@@ -268,7 +268,7 @@ class LLMBundle(object):
             if isinstance(txt, int):
                 if not TenantLLMService.increase_usage(
                         self.tenant_id, self.llm_type, txt, self.llm_name):
-                    logger.error(
+                    logging.error(
                         "LLMBundle.chat_streamly can't update token usage for {}/CHAT llm_name: {}, content: {}".format(self.tenant_id, self.llm_name, txt))
                 return
             yield txt

api/ragflow_server.py

@@ -15,6 +15,17 @@
 #
 
 import logging
+import inspect
+from api.utils.log_utils import initRootLogger
+initRootLogger(inspect.getfile(inspect.currentframe()))
+for module in ["pdfminer"]:
+    module_logger = logging.getLogger(module)
+    module_logger.setLevel(logging.WARNING)
+for module in ["peewee"]:
+    module_logger = logging.getLogger(module)
+    module_logger.handlers.clear()
+    module_logger.propagate = True
+
 import os
 import signal
 import sys
@@ -22,7 +33,6 @@ import time
 import traceback
 from concurrent.futures import ThreadPoolExecutor
 
-import validation
 from werkzeug.serving import run_simple
 from api.apps import app
 from api.db.runtime_config import RuntimeConfig
@@ -31,7 +41,6 @@ from api.settings import (
     HOST, HTTP_PORT
 )
 from api import utils
-from api.utils.log_utils import logger
 
 from api.db.db_models import init_database_tables as init_web_db
 from api.db.init_data import init_web_data
@@ -44,11 +53,11 @@ def update_progress():
         try:
             DocumentService.update_progress()
         except Exception:
-            logger.exception("update_progress exception")
+            logging.exception("update_progress exception")
 
 
 if __name__ == '__main__':
-    logger.info(r"""
+    logging.info(r"""
         ____   ___    ______ ______ __               
        / __ \ /   |  / ____// ____// /____  _      __
       / /_/ // /| | / / __ / /_   / // __ \| | /| / /
@@ -56,10 +65,10 @@ if __name__ == '__main__':
     /_/ |_|/_/  |_|\____//_/    /_/ \____/ |__/|__/                             
 
     """)
-    logger.info(
+    logging.info(
         f'RAGFlow version: {RAGFLOW_VERSION_INFO}'
     )
-    logger.info(
+    logging.info(
         f'project base: {utils.file_utils.get_project_base_directory()}'
     )
 
@@ -83,26 +92,18 @@ if __name__ == '__main__':
 
     RuntimeConfig.DEBUG = args.debug
     if RuntimeConfig.DEBUG:
-        logger.info("run on debug mode")
+        logging.info("run on debug mode")
 
     RuntimeConfig.init_env()
     RuntimeConfig.init_config(JOB_SERVER_HOST=HOST, HTTP_PORT=HTTP_PORT)
 
-    peewee_logger = logging.getLogger("peewee")
-    peewee_logger.propagate = False
-    # rag_arch.common.log.ROpenHandler
-    peewee_logger.addHandler(logger.handlers[0])
-    peewee_logger.setLevel(logger.handlers[0].level)
 
     thr = ThreadPoolExecutor(max_workers=1)
     thr.submit(update_progress)
 
     # start http server
     try:
-        logger.info("RAG Flow http server start...")
-        werkzeug_logger = logging.getLogger("werkzeug")
-        for h in logger.handlers:
-            werkzeug_logger.addHandler(h)
+        logging.info("RAG Flow http server start...")
         run_simple(
             hostname=HOST,
             port=HTTP_PORT,

api/utils/api_utils.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import functools
 import json
 import random
@@ -40,7 +41,6 @@ from api.settings import (
 from api.settings import RetCode
 from api.utils import CustomJSONEncoder, get_uuid
 from api.utils import json_dumps
-from api.utils.log_utils import logger
 
 requests.models.complexjson.dumps = functools.partial(
     json.dumps, cls=CustomJSONEncoder)
@@ -118,7 +118,7 @@ def get_data_error_result(code=RetCode.DATA_ERROR,
 
 
 def server_error_response(e):
-    logger.exception(e)
+    logging.exception(e)
     try:
         if e.code == 401:
             return get_json_result(code=401, message=repr(e))
@@ -259,7 +259,7 @@ def construct_json_result(code=RetCode.SUCCESS, message='success', data=None):
 
 
 def construct_error_response(e):
-    logger.exception(e)
+    logging.exception(e)
     try:
         if e.code == 401:
             return construct_json_result(code=RetCode.UNAUTHORIZED, message=repr(e))

api/utils/log_utils.py

@@ -14,38 +14,41 @@
 #  limitations under the License.
 #
 import os
+import os.path
 import logging
 from logging.handlers import RotatingFileHandler
 
-from api.utils.file_utils import get_project_base_directory
-
-LOG_LEVEL = logging.INFO
-LOG_FILE = os.path.abspath(os.path.join(get_project_base_directory(), "logs", f"ragflow_{os.getpid()}.log"))
-LOG_FORMAT = "%(asctime)-15s %(levelname)-8s %(process)d %(message)s"
-logger = None
-
-def getLogger():
-    global logger
-    if logger is not None:
-        return logger
-
-    print(f"log file path: {LOG_FILE}")
-    os.makedirs(os.path.dirname(LOG_FILE), exist_ok=True)
-    logger = logging.getLogger("ragflow")
-    logger.setLevel(LOG_LEVEL)
-
-    handler1 = RotatingFileHandler(LOG_FILE, maxBytes=10*1024*1024, backupCount=5)
-    handler1.setLevel(LOG_LEVEL)
-    formatter1 = logging.Formatter(LOG_FORMAT)
-    handler1.setFormatter(formatter1)
+def get_project_base_directory():
+    PROJECT_BASE = os.path.abspath(
+        os.path.join(
+            os.path.dirname(os.path.realpath(__file__)),
+            os.pardir,
+            os.pardir,
+        )
+    )
+    return PROJECT_BASE
+
+def initRootLogger(script_path: str, log_level: int = logging.INFO, log_format: str = "%(asctime)-15s %(levelname)-8s %(process)d %(message)s"):
+    logger = logging.getLogger()
+    if logger.hasHandlers():
+        return
+
+    script_name = os.path.basename(script_path)
+    log_path = os.path.abspath(os.path.join(get_project_base_directory(), "logs", f"{os.path.splitext(script_name)[0]}.log"))
+
+    os.makedirs(os.path.dirname(log_path), exist_ok=True)
+    logger.setLevel(log_level)
+    formatter = logging.Formatter(log_format)
+
+    handler1 = RotatingFileHandler(log_path, maxBytes=10*1024*1024, backupCount=5)
+    handler1.setLevel(log_level)
+    handler1.setFormatter(formatter)
     logger.addHandler(handler1)
 
     handler2 = logging.StreamHandler()
-    handler2.setLevel(LOG_LEVEL)
-    formatter2 = logging.Formatter(LOG_FORMAT)
-    handler2.setFormatter(formatter2)
+    handler2.setLevel(log_level)
+    handler2.setFormatter(formatter)
     logger.addHandler(handler2)
 
-    return logger
-
-logger = getLogger()
+    msg = f"{script_name} log path: {log_path}"
+    logger.info(msg)

api/validation.py

@@ -14,20 +14,20 @@
 #  limitations under the License.
 #
 
+import logging
 import sys
-from api.utils.log_utils import logger
 
 
 def python_version_validation():
     # Check python version
     required_python_version = (3, 10)
     if sys.version_info < required_python_version:
-        logger.info(
+        logging.info(
             f"Required Python: >= {required_python_version[0]}.{required_python_version[1]}. Current Python version: {sys.version_info[0]}.{sys.version_info[1]}."
         )
         sys.exit(1)
     else:
-        logger.info(f"Python version: {sys.version_info[0]}.{sys.version_info[1]}")
+        logging.info(f"Python version: {sys.version_info[0]}.{sys.version_info[1]}")
 
 
 python_version_validation()

deepdoc/parser/pdf_parser.py

@@ -11,6 +11,7 @@
 #  limitations under the License.
 #
 
+import logging
 import os
 import random
 
@@ -18,7 +19,6 @@ import xgboost as xgb
 from io import BytesIO
 import re
 import pdfplumber
-import logging
 from PIL import Image
 import numpy as np
 from timeit import default_timer as timer
@@ -26,15 +26,11 @@ from pypdf import PdfReader as pdf2_read
 
 from api.settings import LIGHTEN
 from api.utils.file_utils import get_project_base_directory
-from api.utils.log_utils import logger
 from deepdoc.vision import OCR, Recognizer, LayoutRecognizer, TableStructureRecognizer
 from rag.nlp import rag_tokenizer
 from copy import deepcopy
 from huggingface_hub import snapshot_download
 
-logging.getLogger("pdfminer").setLevel(logging.WARNING)
-
-
 class RAGFlowPdfParser:
     def __init__(self):
         self.ocr = OCR()
@@ -51,7 +47,7 @@ class RAGFlowPdfParser:
                 if torch.cuda.is_available():
                     self.updown_cnt_mdl.set_param({"device": "cuda"})
             except Exception:
-                logger.exception("RAGFlowPdfParser __init__")
+                logging.exception("RAGFlowPdfParser __init__")
         try:
             model_dir = os.path.join(
                 get_project_base_directory(),
@@ -188,7 +184,7 @@ class RAGFlowPdfParser:
         return True
 
     def _table_transformer_job(self, ZM):
-        logger.info("Table processing...")
+        logging.debug("Table processing...")
         imgs, pos = [], []
         tbcnt = [0]
         MARGIN = 10
@@ -426,7 +422,7 @@ class RAGFlowPdfParser:
             detach_feats = [b["x1"] < b_["x0"],
                             b["x0"] > b_["x1"]]
             if (any(feats) and not any(concatting_feats)) or any(detach_feats):
-                logger.info("{} {} {} {}".format(
+                logging.debug("{} {} {} {}".format(
                     b["text"],
                     b_["text"],
                     any(feats),
@@ -727,14 +723,14 @@ class RAGFlowPdfParser:
             #    continue
             if tv < fv and tk:
                 tables[tk].insert(0, c)
-                logger.debug(
+                logging.debug(
                     "TABLE:" +
                     self.boxes[i]["text"] +
                     "; Cap: " +
                     tk)
             elif fk:
                 figures[fk].insert(0, c)
-                logger.debug(
+                logging.debug(
                     "FIGURE:" +
                     self.boxes[i]["text"] +
                     "; Cap: " +
@@ -761,7 +757,7 @@ class RAGFlowPdfParser:
                 if ii is not None:
                     b = louts[ii]
                 else:
-                    logger.warn(
+                    logging.warn(
                         f"Missing layout match: {pn + 1},%s" %
                         (bxs[0].get(
                             "layoutno", "")))
@@ -919,7 +915,7 @@ class RAGFlowPdfParser:
                 if usefull(boxes[0]):
                     dfs(boxes[0], 0)
                 else:
-                    logger.debug("WASTE: " + boxes[0]["text"])
+                    logging.debug("WASTE: " + boxes[0]["text"])
             except Exception:
                 pass
             boxes.pop(0)
@@ -928,7 +924,7 @@ class RAGFlowPdfParser:
                 res.append(
                     "\n".join([c["text"] + self._line_tag(c, ZM) for c in lines]))
             else:
-                logger.debug("REMOVED: " +
+                logging.debug("REMOVED: " +
                               "<<".join([c["text"] for c in lines]))
 
         return "\n\n".join(res)
@@ -940,7 +936,7 @@ class RAGFlowPdfParser:
                 fnm) if not binary else pdfplumber.open(BytesIO(binary))
             return len(pdf.pages)
         except Exception:
-            logger.exception("total_page_number")
+            logging.exception("total_page_number")
 
     def __images__(self, fnm, zoomin=3, page_from=0,
                    page_to=299, callback=None):
@@ -964,7 +960,7 @@ class RAGFlowPdfParser:
                                self.pdf.pages[page_from:page_to]]
             self.total_page = len(self.pdf.pages)
         except Exception:
-            logger.exception("RAGFlowPdfParser __images__")
+            logging.exception("RAGFlowPdfParser __images__")
 
         self.outlines = []
         try:
@@ -980,11 +976,11 @@ class RAGFlowPdfParser:
 
             dfs(outlines, 0)
         except Exception as e:
-            logger.warning(f"Outlines exception: {e}")
+            logging.warning(f"Outlines exception: {e}")
         if not self.outlines:
-            logger.warning("Miss outlines")
+            logging.warning("Miss outlines")
 
-        logger.info("Images converted.")
+        logging.debug("Images converted.")
         self.is_english = [re.search(r"[a-zA-Z0-9,/¸;:'\[\]\(\)!@#$%^&*\"?<>._-]{30,}", "".join(
             random.choices([c["text"] for c in self.page_chars[i]], k=min(100, len(self.page_chars[i]))))) for i in
                            range(len(self.page_chars))]
@@ -1024,7 +1020,7 @@ class RAGFlowPdfParser:
             self.is_english = re.search(r"[\na-zA-Z0-9,/¸;:'\[\]\(\)!@#$%^&*\"?<>._-]{30,}",
                                         "".join([b["text"] for b in random.choices(bxes, k=min(30, len(bxes)))]))
 
-        logger.info("Is it English:", self.is_english)
+        logging.debug("Is it English:", self.is_english)
 
         self.page_cum_height = np.cumsum(self.page_cum_height)
         assert len(self.page_cum_height) == len(self.page_images) + 1
@@ -1164,9 +1160,9 @@ class PlainParser(object):
 
             dfs(outlines, 0)
         except Exception:
-            logger.exception("Outlines exception")
+            logging.exception("Outlines exception")
         if not self.outlines:
-            logger.warning("Miss outlines")
+            logging.warning("Miss outlines")
 
         return [(l, "") for l in lines], []
 

deepdoc/parser/resume/entities/corporations.py

@@ -11,13 +11,13 @@
 #  limitations under the License.
 #
 
+import logging
 import re
 import json
 import os
 import pandas as pd
 from rag.nlp import rag_tokenizer
 from . import regions
-from api.utils.log_utils import logger
 
 
 current_file_path = os.path.dirname(os.path.abspath(__file__))
@@ -71,7 +71,7 @@ GOOD_CORP = set([corpNorm(rmNoise(c), False) for c in GOOD_CORP])
 for c,v in CORP_TAG.items():
     cc = corpNorm(rmNoise(c), False)
     if not cc:
-        logger.info(c)
+        logging.debug(c)
 CORP_TAG = {corpNorm(rmNoise(c), False):v for c,v in CORP_TAG.items()}
 
 def is_good(nm):

deepdoc/parser/resume/step_two.py

@@ -10,7 +10,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-
+import logging
 import re
 import copy
 import time
@@ -23,7 +23,6 @@ from deepdoc.parser.resume.entities import degrees, schools, corporations
 from rag.nlp import rag_tokenizer, surname
 from xpinyin import Pinyin
 from contextlib import contextmanager
-from api.utils.log_utils import logger
 
 
 class TimeoutException(Exception): pass
@@ -164,7 +163,7 @@ def forEdu(cv):
             y, m, d = getYMD(edu_end_dt)
             cv["work_exp_flt"] = min(int(str(datetime.date.today())[0:4]) - int(y), cv.get("work_exp_flt", 1000))
         except Exception as e:
-            logger.exception("forEdu {} {} {}".format(e, edu_end_dt, cv.get("work_exp_flt")))
+            logging.exception("forEdu {} {} {}".format(e, edu_end_dt, cv.get("work_exp_flt")))
     if sch:
         cv["school_name_kwd"] = sch
         if (len(cv.get("degree_kwd", [])) >= 1 and "本科" in cv["degree_kwd"]) \
@@ -276,7 +275,7 @@ def forWork(cv):
         try:
             duas.append((datetime.datetime.strptime(ed, "%Y-%m-%d") - datetime.datetime.strptime(st, "%Y-%m-%d")).days)
         except Exception:
-            logger.exception("forWork {} {}".format(n.get("start_time"), n.get("end_time")))
+            logging.exception("forWork {} {}".format(n.get("start_time"), n.get("end_time")))
 
         if n.get("scale"):
             r = re.search(r"^([0-9]+)", str(n["scale"]))
@@ -333,7 +332,7 @@ def forWork(cv):
             y, m, d = getYMD(work_st_tm)
             cv["work_exp_flt"] = min(int(str(datetime.date.today())[0:4]) - int(y), cv.get("work_exp_flt", 1000))
         except Exception as e:
-            logger.exception("forWork {} {} {}".format(e, work_st_tm, cv.get("work_exp_flt")))
+            logging.exception("forWork {} {} {}".format(e, work_st_tm, cv.get("work_exp_flt")))
 
     cv["job_num_int"] = 0
     if duas:
@@ -464,7 +463,7 @@ def parse(cv):
                     cv[f"{t}_kwd"] = nms
                     cv[f"{t}_tks"] = rag_tokenizer.tokenize(" ".join(nms))
             except Exception:
-                logger.exception("parse {} {}".format(str(traceback.format_exc()), cv[k]))
+                logging.exception("parse {} {}".format(str(traceback.format_exc()), cv[k]))
                 cv[k] = []
 
         # tokenize fields
@@ -565,7 +564,7 @@ def parse(cv):
                 cv["work_start_dt"] = "%s-%02d-%02d 00:00:00" % (y, int(m), int(d))
                 cv["work_exp_flt"] = int(str(datetime.date.today())[0:4]) - int(y)
     except Exception as e:
-        logger.exception("parse {} ==> {}".format(e, cv.get("work_start_time")))
+        logging.exception("parse {} ==> {}".format(e, cv.get("work_start_time")))
     if "work_exp_flt" not in cv and cv.get("work_experience", 0): cv["work_exp_flt"] = int(cv["work_experience"]) / 12.
 
     keys = list(cv.keys())
@@ -580,7 +579,7 @@ def parse(cv):
 
     cv["tob_resume_id"] = str(cv["tob_resume_id"])
     cv["id"] = cv["tob_resume_id"]
-    logger.info("CCCCCCCCCCCCCCC")
+    logging.debug("CCCCCCCCCCCCCCC")
 
     return dealWithInt64(cv)
 

deepdoc/vision/operators.py

@@ -14,13 +14,13 @@
 #  limitations under the License.
 #
 
+import logging
 import sys
 import six
 import cv2
 import numpy as np
 import math
 from PIL import Image
-from api.utils.log_utils import logger
 
 
 class DecodeImage(object):
@@ -403,7 +403,7 @@ class DetResizeForTest(object):
                 return None, (None, None)
             img = cv2.resize(img, (int(resize_w), int(resize_h)))
         except BaseException:
-            logger.exception("{} {} {}".format(img.shape, resize_w, resize_h))
+            logging.exception("{} {} {}".format(img.shape, resize_w, resize_h))
             sys.exit(0)
         ratio_h = resize_h / float(h)
         ratio_w = resize_w / float(w)

deepdoc/vision/recognizer.py

@@ -11,6 +11,7 @@
 #  limitations under the License.
 #
 
+import logging
 import os
 from copy import deepcopy
 
@@ -19,7 +20,6 @@ from huggingface_hub import snapshot_download
 
 from api.utils.file_utils import get_project_base_directory
 from .operators import *
-from api.utils.log_utils import logger
 
 
 class Recognizer(object):
@@ -440,7 +440,7 @@ class Recognizer(object):
             end_index = min((i + 1) * batch_size, len(imgs))
             batch_image_list = imgs[start_index:end_index]
             inputs = self.preprocess(batch_image_list)
-            logger.info("preprocess")
+            logging.debug("preprocess")
             for ins in inputs:
                 bb = self.postprocess(self.ort_sess.run(None, {k:v for k,v in ins.items() if k in self.input_names})[0], ins, thr)
                 res.append(bb)

deepdoc/vision/seeit.py

@@ -11,10 +11,10 @@
 #  limitations under the License.
 #
 
+import logging
 import os
 import PIL
 from PIL import ImageDraw
-from api.utils.log_utils import logger
 
 
 def save_results(image_list, results, labels, output_dir='output/', threshold=0.5):
@@ -25,7 +25,7 @@ def save_results(image_list, results, labels, output_dir='output/', threshold=0.
 
         out_path = os.path.join(output_dir, f"{idx}.jpg")
         im.save(out_path, quality=95)
-        logger.info("save result to: " + out_path)
+        logging.debug("save result to: " + out_path)
 
 
 def draw_box(im, result, lables, threshold=0.5):

deepdoc/vision/t_recognizer.py

@@ -10,9 +10,9 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import os
 import sys
-from api.utils.log_utils import logger
 
 sys.path.insert(
     0,
@@ -59,7 +59,7 @@ def main(args):
             } for t in lyt]
         img = draw_box(images[i], lyt, labels, float(args.threshold))
         img.save(outputs[i], quality=95)
-        logger.info("save result to: " + outputs[i])
+        logging.info("save result to: " + outputs[i])
 
 
 def get_table_html(img, tb_cpns, ocr):

deepdoc/vision/table_structure_recognizer.py

@@ -38,7 +38,7 @@ class TableStructureRecognizer(Recognizer):
             super().__init__(self.labels, "tsr", os.path.join(
                     get_project_base_directory(),
                     "rag/res/deepdoc"))
-        except Exception as e:
+        except Exception:
             super().__init__(self.labels, "tsr", snapshot_download(repo_id="InfiniFlow/deepdoc",
                                               local_dir=os.path.join(get_project_base_directory(), "rag/res/deepdoc"),
                                               local_dir_use_symlinks=False))

graphrag/claim_extractor.py

@@ -5,6 +5,7 @@ Reference:
  - [graphrag](https://github.com/microsoft/graphrag)
 """
 
+import logging
 import argparse
 import json
 import re
@@ -17,7 +18,6 @@ import tiktoken
 from graphrag.claim_prompt import CLAIM_EXTRACTION_PROMPT, CONTINUE_PROMPT, LOOP_PROMPT
 from rag.llm.chat_model import Base as CompletionLLM
 from graphrag.utils import ErrorHandlerFn, perform_variable_replacements
-from api.utils.log_utils import logger
 
 DEFAULT_TUPLE_DELIMITER = "<|>"
 DEFAULT_RECORD_DELIMITER = "##"
@@ -126,7 +126,7 @@ class ClaimExtractor:
                 ]
                 source_doc_map[document_id] = text
             except Exception as e:
-                logger.exception("error extracting claim")
+                logging.exception("error extracting claim")
                 self._on_error(
                     e,
                     traceback.format_exc(),
@@ -265,4 +265,4 @@ if __name__ == "__main__":
         "claim_description": ""
     }
     claim = ex(info)
-    logger.info(json.dumps(claim.output, ensure_ascii=False, indent=2))
+    logging.info(json.dumps(claim.output, ensure_ascii=False, indent=2))

graphrag/community_reports_extractor.py

@@ -5,6 +5,7 @@ Reference:
  - [graphrag](https://github.com/microsoft/graphrag)
 """
 
+import logging
 import json
 import re
 import traceback
@@ -19,7 +20,6 @@ from rag.llm.chat_model import Base as CompletionLLM
 from graphrag.utils import ErrorHandlerFn, perform_variable_replacements, dict_has_keys_with_types
 from rag.utils import num_tokens_from_string
 from timeit import default_timer as timer
-from api.utils.log_utils import logger
 
 
 @dataclass
@@ -80,7 +80,7 @@ class CommunityReportsExtractor:
                     response = re.sub(r"[^\}]*$", "", response)
                     response = re.sub(r"\{\{", "{", response)
                     response = re.sub(r"\}\}", "}", response)
-                    logger.info(response)
+                    logging.debug(response)
                     response = json.loads(response)
                     if not dict_has_keys_with_types(response, [
                                 ("title", str),
@@ -92,7 +92,7 @@ class CommunityReportsExtractor:
                     response["weight"] = weight
                     response["entities"] = ents
                 except Exception as e:
-                    logger.exception("CommunityReportsExtractor got exception")
+                    logging.exception("CommunityReportsExtractor got exception")
                     self._on_error(e, traceback.format_exc(), None)
                     continue
 

graphrag/description_summary.py

@@ -5,19 +5,11 @@ Reference:
  - [graphrag](https://github.com/microsoft/graphrag)
 """
 
-import argparse
-import html
 import json
-import logging
-import numbers
-import re
-import traceback
-from collections.abc import Callable
 from dataclasses import dataclass
 
 from graphrag.utils import ErrorHandlerFn, perform_variable_replacements
 from rag.llm.chat_model import Base as CompletionLLM
-import networkx as nx
 
 from rag.utils import num_tokens_from_string
 

graphrag/entity_resolution.py

@@ -13,8 +13,8 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-import itertools
 import logging
+import itertools
 import re
 import traceback
 from dataclasses import dataclass

graphrag/index.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import os
 from concurrent.futures import ThreadPoolExecutor
 import json
@@ -28,7 +29,6 @@ from graphrag.graph_extractor import GraphExtractor, DEFAULT_ENTITY_TYPES
 from graphrag.mind_map_extractor import MindMapExtractor
 from rag.nlp import rag_tokenizer
 from rag.utils import num_tokens_from_string
-from api.utils.log_utils import logger
 
 
 def graph_merge(g1, g2):
@@ -95,7 +95,7 @@ def build_knowledge_graph_chunks(tenant_id: str, chunks: List[str], callback, en
     chunks = []
     for n, attr in graph.nodes(data=True):
         if attr.get("rank", 0) == 0:
-            logger.info(f"Ignore entity: {n}")
+            logging.debug(f"Ignore entity: {n}")
             continue
         chunk = {
             "name_kwd": n,
@@ -137,7 +137,7 @@ def build_knowledge_graph_chunks(tenant_id: str, chunks: List[str], callback, en
     mg = mindmap(_chunks).output
     if not len(mg.keys()): return chunks
 
-    logger.info(json.dumps(mg, ensure_ascii=False, indent=2))
+    logging.debug(json.dumps(mg, ensure_ascii=False, indent=2))
     chunks.append(
         {
             "content_with_weight": json.dumps(mg, ensure_ascii=False, indent=2),

graphrag/leiden.py

@@ -14,8 +14,6 @@ from graspologic.utils import largest_connected_component
 import networkx as nx
 from networkx import is_empty
 
-log = logging.getLogger(__name__)
-
 
 def _stabilize_graph(graph: nx.Graph) -> nx.Graph:
     """Ensure an undirected graph with the same relationships will always be read the same way."""
@@ -99,7 +97,7 @@ def run(graph: nx.Graph, args: dict[str, Any]) -> dict[int, dict[str, dict]]:
     max_cluster_size = args.get("max_cluster_size", 12)
     use_lcc = args.get("use_lcc", True)
     if args.get("verbose", False):
-        log.info(
+        logging.debug(
             "Running leiden with max_cluster_size=%s, lcc=%s", max_cluster_size, use_lcc
         )
     if not graph.nodes(): return {}

graphrag/mind_map_extractor.py

@@ -14,8 +14,8 @@
 #  limitations under the License.
 #
 
-import collections
 import logging
+import collections
 import os
 import re
 import traceback
@@ -29,7 +29,6 @@ from rag.llm.chat_model import Base as CompletionLLM
 import markdown_to_json
 from functools import reduce
 from rag.utils import num_tokens_from_string
-from api.utils.log_utils import logger
 
 
 @dataclass
@@ -193,6 +192,6 @@ class MindMapExtractor:
         gen_conf = {"temperature": 0.5}
         response = self._llm.chat(text, [{"role": "user", "content": "Output:"}], gen_conf)
         response = re.sub(r"```[^\n]*", "", response)
-        logger.info(response)
-        logger.info(self._todict(markdown_to_json.dictify(response)))
+        logging.debug(response)
+        logging.debug(self._todict(markdown_to_json.dictify(response)))
         return self._todict(markdown_to_json.dictify(response))

intergrations/chatgpt-on-wechat/plugins/ragflow_chat.py

@@ -1,8 +1,8 @@
+import logging
 import requests
 from bridge.context import ContextType  # Import Context, ContextType
 from bridge.reply import Reply, ReplyType  # Import Reply, ReplyType
 from bridge import *
-from api.utils.log_utils import logger
 from plugins import Plugin, register  # Import Plugin and register
 from plugins.event import Event, EventContext, EventAction  # Import event-related classes
 
@@ -16,7 +16,7 @@ class RAGFlowChat(Plugin):
         self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
         # Store conversation_id for each user
         self.conversations = {}
-        logger.info("[RAGFlowChat] Plugin initialized")
+        logging.info("[RAGFlowChat] Plugin initialized")
 
     def on_handle_context(self, e_context: EventContext):
         context = e_context['context']
@@ -45,7 +45,7 @@ class RAGFlowChat(Plugin):
         user_id = session_id  # Use session_id as user_id
 
         if not api_key or not host_address:
-            logger.error("[RAGFlowChat] Missing configuration")
+            logging.error("[RAGFlowChat] Missing configuration")
             return "The plugin configuration is incomplete. Please check the configuration."
 
         headers = {
@@ -63,20 +63,20 @@ class RAGFlowChat(Plugin):
             }
             try:
                 response = requests.get(url_new_conversation, headers=headers, params=params_new_conversation)
-                logger.debug(f"[RAGFlowChat] New conversation response: {response.text}")
+                logging.debug(f"[RAGFlowChat] New conversation response: {response.text}")
                 if response.status_code == 200:
                     data = response.json()
                     if data.get("code") == 0:
                         conversation_id = data["data"]["id"]
                         self.conversations[user_id] = conversation_id
                     else:
-                        logger.error(f"[RAGFlowChat] Failed to create conversation: {data.get('message')}")
+                        logging.error(f"[RAGFlowChat] Failed to create conversation: {data.get('message')}")
                         return f"Sorry, unable to create a conversation: {data.get('message')}"
                 else:
-                    logger.error(f"[RAGFlowChat] HTTP error when creating conversation: {response.status_code}")
+                    logging.error(f"[RAGFlowChat] HTTP error when creating conversation: {response.status_code}")
                     return f"Sorry, unable to connect to RAGFlow API (create conversation). HTTP status code: {response.status_code}"
             except Exception as e:
-                logger.exception("[RAGFlowChat] Exception when creating conversation")
+                logging.exception("[RAGFlowChat] Exception when creating conversation")
                 return f"Sorry, an internal error occurred: {str(e)}"
 
         # Step 2: Send the message and get a reply
@@ -95,18 +95,18 @@ class RAGFlowChat(Plugin):
 
         try:
             response = requests.post(url_completion, headers=headers, json=payload_completion)
-            logger.debug(f"[RAGFlowChat] Completion response: {response.text}")
+            logging.debug(f"[RAGFlowChat] Completion response: {response.text}")
             if response.status_code == 200:
                 data = response.json()
                 if data.get("code") == 0:
                     answer = data["data"]["answer"]
                     return answer
                 else:
-                    logger.error(f"[RAGFlowChat] Failed to get answer: {data.get('message')}")
+                    logging.error(f"[RAGFlowChat] Failed to get answer: {data.get('message')}")
                     return f"Sorry, unable to get a reply: {data.get('message')}"
             else:
-                logger.error(f"[RAGFlowChat] HTTP error when getting answer: {response.status_code}")
+                logging.error(f"[RAGFlowChat] HTTP error when getting answer: {response.status_code}")
                 return f"Sorry, unable to connect to RAGFlow API (get reply). HTTP status code: {response.status_code}"
         except Exception as e:
-            logger.exception("[RAGFlowChat] Exception when getting answer")
+            logging.exception("[RAGFlowChat] Exception when getting answer")
             return f"Sorry, an internal error occurred: {str(e)}"

rag/app/book.py

@@ -10,6 +10,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from tika import parser
 import re
 from io import BytesIO
@@ -20,7 +21,6 @@ from rag.nlp import bullets_category, is_english,remove_contents_table, \
     tokenize_chunks
 from rag.nlp import rag_tokenizer
 from deepdoc.parser import PdfParser, DocxParser, PlainParser, HtmlParser
-from api.utils.log_utils import logger
 
 
 class Pdf(PdfParser):
@@ -39,7 +39,7 @@ class Pdf(PdfParser):
         start = timer()
         self._layouts_rec(zoomin)
         callback(0.67, "Layout analysis finished")
-        logger.info("layouts: {}".format(timer() - start))
+        logging.debug("layouts: {}".format(timer() - start))
         self._table_transformer_job(zoomin)
         callback(0.68, "Table analysis finished")
         self._text_merge()

rag/app/email.py

@@ -11,6 +11,7 @@
 #  limitations under the License.
 #
 
+import logging
 from email import policy
 from email.parser import BytesParser
 from rag.app.naive import chunk as naive_chunk
@@ -18,7 +19,6 @@ import re
 from rag.nlp import rag_tokenizer, naive_merge, tokenize_chunks
 from deepdoc.parser import HtmlParser, TxtParser
 from timeit import default_timer as timer
-from api.utils.log_utils import logger
 import io
 
 
@@ -86,7 +86,7 @@ def chunk(
     )
 
     main_res.extend(tokenize_chunks(chunks, doc, eng, None))
-    logger.info("naive_merge({}): {}".format(filename, timer() - st))
+    logging.debug("naive_merge({}): {}".format(filename, timer() - st))
     # get the attachment info
     for part in msg.iter_attachments():
         content_disposition = part.get("Content-Disposition")

rag/app/laws.py

@@ -21,7 +21,6 @@ from rag.nlp import bullets_category, remove_contents_table, hierarchical_merge,
     make_colon_as_title, tokenize_chunks, docx_question_level
 from rag.nlp import rag_tokenizer
 from deepdoc.parser import PdfParser, DocxParser, PlainParser, HtmlParser
-from api.utils.log_utils import logger
 
 
 class Docx(DocxParser):
@@ -122,7 +121,7 @@ class Pdf(PdfParser):
         start = timer()
         self._layouts_rec(zoomin)
         callback(0.67, "Layout analysis finished")
-        logger.info("layouts:".format(
+        logging.debug("layouts:".format(
             ))
         self._naive_vertical_merge()
 

rag/app/manual.py

@@ -14,6 +14,7 @@
 #  limitations under the License.
 #
 
+import logging
 import copy
 import re
 
@@ -24,7 +25,6 @@ from rag.utils import num_tokens_from_string
 from deepdoc.parser import PdfParser, PlainParser, DocxParser
 from docx import Document
 from PIL import Image
-from api.utils.log_utils import logger
 
 
 class Pdf(PdfParser):
@@ -48,11 +48,11 @@ class Pdf(PdfParser):
         # for bb in self.boxes:
         #    for b in bb:
         #        print(b)
-        logger.info("OCR: {}".format(timer() - start))
+        logging.debug("OCR: {}".format(timer() - start))
 
         self._layouts_rec(zoomin)
         callback(0.65, "Layout analysis finished.")
-        logger.info("layouts: {}".format(timer() - start))
+        logging.debug("layouts: {}".format(timer() - start))
         self._table_transformer_job(zoomin)
         callback(0.67, "Table analysis finished.")
         self._text_merge()

rag/app/naive.py

@@ -10,6 +10,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from tika import parser
 from io import BytesIO
 from docx import Document
@@ -19,7 +20,6 @@ from deepdoc.parser.pdf_parser import PlainParser
 from rag.nlp import rag_tokenizer, naive_merge, tokenize_table, tokenize_chunks, find_codec, concat_img, \
     naive_merge_docx, tokenize_chunks_docx
 from deepdoc.parser import PdfParser, ExcelParser, DocxParser, HtmlParser, JsonParser, MarkdownParser, TxtParser
-from api.utils.log_utils import logger
 from rag.utils import num_tokens_from_string
 from PIL import Image
 from functools import reduce
@@ -41,13 +41,13 @@ class Docx(DocxParser):
         try:
             image_blob = related_part.image.blob
         except UnrecognizedImageError:
-            logger.info("Unrecognized image format. Skipping image.")
+            logging.info("Unrecognized image format. Skipping image.")
             return None
         except UnexpectedEndOfFileError:
-            logger.info("EOF was unexpectedly encountered while reading an image stream. Skipping image.")
+            logging.info("EOF was unexpectedly encountered while reading an image stream. Skipping image.")
             return None
         except InvalidImageStreamError:
-            logger.info("The recognized image stream appears to be corrupted. Skipping image.")
+            logging.info("The recognized image stream appears to be corrupted. Skipping image.")
             return None
         try:
             image = Image.open(BytesIO(image_blob)).convert('RGB')
@@ -133,7 +133,7 @@ class Pdf(PdfParser):
             callback
         )
         callback(msg="OCR finished")
-        logger.info("OCR({}~{}): {}".format(from_page, to_page, timer() - start))
+        logging.info("OCR({}~{}): {}".format(from_page, to_page, timer() - start))
 
         start = timer()
         self._layouts_rec(zoomin)
@@ -147,7 +147,7 @@ class Pdf(PdfParser):
         self._concat_downward()
         # self._filter_forpages()
 
-        logger.info("layouts cost: {}s".format(timer() - start))
+        logging.info("layouts cost: {}s".format(timer() - start))
         return [(b["text"], self._line_tag(b, zoomin))
                 for b in self.boxes], tbls
 
@@ -216,7 +216,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
             return chunks
 
         res.extend(tokenize_chunks_docx(chunks, doc, eng, images))
-        logger.info("naive_merge({}): {}".format(filename, timer() - st))
+        logging.info("naive_merge({}): {}".format(filename, timer() - st))
         return res
 
     elif re.search(r"\.pdf$", filename, re.IGNORECASE):
@@ -280,7 +280,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
         return chunks
 
     res.extend(tokenize_chunks(chunks, doc, eng, pdf_parser))
-    logger.info("naive_merge({}): {}".format(filename, timer() - st))
+    logging.info("naive_merge({}): {}".format(filename, timer() - st))
     return res
 
 

rag/app/one.py

@@ -10,6 +10,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 from tika import parser
 from io import BytesIO
 import re
@@ -18,7 +19,6 @@ from deepdoc.parser.utils import get_text
 from rag.app import laws
 from rag.nlp import rag_tokenizer, tokenize
 from deepdoc.parser import PdfParser, ExcelParser, PlainParser, HtmlParser
-from api.utils.log_utils import logger
 
 
 class Pdf(PdfParser):
@@ -38,7 +38,7 @@ class Pdf(PdfParser):
         start = timer()
         self._layouts_rec(zoomin, drop=False)
         callback(0.63, "Layout analysis finished.")
-        logger.info("layouts cost: {}s".format(timer() - start))
+        logging.debug("layouts cost: {}s".format(timer() - start))
         self._table_transformer_job(zoomin)
         callback(0.65, "Table analysis finished.")
         self._text_merge()

rag/app/paper.py

@@ -10,6 +10,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import copy
 import re
 
@@ -17,7 +18,6 @@ from api.db import ParserType
 from rag.nlp import rag_tokenizer, tokenize, tokenize_table, add_positions, bullets_category, title_frequency, tokenize_chunks
 from deepdoc.parser import PdfParser, PlainParser
 import numpy as np
-from api.utils.log_utils import logger
 
 
 class Pdf(PdfParser):
@@ -41,7 +41,7 @@ class Pdf(PdfParser):
         start = timer()
         self._layouts_rec(zoomin)
         callback(0.63, "Layout analysis finished")
-        logger.info(f"layouts cost: {timer() - start}s")
+        logging.debug(f"layouts cost: {timer() - start}s")
         self._table_transformer_job(zoomin)
         callback(0.68, "Table analysis finished")
         self._text_merge()
@@ -53,7 +53,7 @@ class Pdf(PdfParser):
 
         # clean mess
         if column_width < self.page_images[0].size[0] / zoomin / 2:
-            logger.info("two_column................... {} {}".format(column_width,
+            logging.debug("two_column................... {} {}".format(column_width,
                   self.page_images[0].size[0] / zoomin / 2))
             self.boxes = self.sort_X_by_page(self.boxes, column_width / 2)
         for b in self.boxes:
@@ -115,8 +115,8 @@ class Pdf(PdfParser):
                 from_page, min(
                     to_page, self.total_page)))
         for b in self.boxes:
-            logger.info("{} {}".format(b["text"], b.get("layoutno")))
-        logger.info("{}".format(tbls))
+            logging.debug("{} {}".format(b["text"], b.get("layoutno")))
+        logging.debug("{}".format(tbls))
 
         return {
             "title": title,
@@ -157,7 +157,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
     doc["authors_sm_tks"] = rag_tokenizer.fine_grained_tokenize(doc["authors_tks"])
     # is it English
     eng = lang.lower() == "english"  # pdf_parser.is_english
-    logger.info("It's English.....{}".format(eng))
+    logging.debug("It's English.....{}".format(eng))
 
     res = tokenize_table(paper["tables"], doc, eng)
 
@@ -184,7 +184,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
         if lvl <= most_level and i > 0 and lvl != levels[i - 1]:
             sid += 1
         sec_ids.append(sid)
-        logger.info("{} {} {} {}".format(lvl, sorted_sections[i][0], most_level, sid))
+        logging.debug("{} {} {} {}".format(lvl, sorted_sections[i][0], most_level, sid))
 
     chunks = []
     last_sid = -2

rag/app/qa.py

@@ -10,6 +10,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import re
 from copy import deepcopy
 from io import BytesIO
@@ -19,7 +20,6 @@ from openpyxl import load_workbook
 from deepdoc.parser.utils import get_text
 from rag.nlp import is_english, random_choices, qbullets_category, add_positions, has_qbullet, docx_question_level
 from rag.nlp import rag_tokenizer, tokenize_table, concat_img
-from api.utils.log_utils import logger
 from deepdoc.parser import PdfParser, ExcelParser, DocxParser
 from docx import Document
 from PIL import Image
@@ -82,7 +82,7 @@ class Pdf(PdfParser):
             callback
         )
         callback(msg="OCR finished")
-        logger.info("OCR({}~{}): {}".format(from_page, to_page, timer() - start))
+        logging.debug("OCR({}~{}): {}".format(from_page, to_page, timer() - start))
         start = timer()
         self._layouts_rec(zoomin, drop=False)
         callback(0.63, "Layout analysis finished.")
@@ -94,7 +94,7 @@ class Pdf(PdfParser):
         #self._naive_vertical_merge()
         # self._concat_downward()
         #self._filter_forpages()
-        logger.info("layouts: {}".format(timer() - start))
+        logging.debug("layouts: {}".format(timer() - start))
         sections = [b["text"] for b in self.boxes]
         bull_x0_list = []
         q_bull, reg = qbullets_category(sections)

rag/app/resume.py

@@ -10,6 +10,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import base64
 import datetime
 import json
@@ -20,7 +21,6 @@ from api.db.services.knowledgebase_service import KnowledgebaseService
 from rag.nlp import rag_tokenizer
 from deepdoc.parser.resume import refactor
 from deepdoc.parser.resume import step_one, step_two
-from api.utils.log_utils import logger
 from rag.utils import rmSpace
 
 forbidden_select_fields4resume = [
@@ -64,7 +64,7 @@ def remote_call(filename, binary):
             resume = step_two.parse(resume)
             return resume
         except Exception:
-            logger.exception("Resume parser error")
+            logging.exception("Resume parser error")
     return {}
 
 
@@ -86,7 +86,7 @@ def chunk(filename, binary=None, callback=None, **kwargs):
         callback(-1, "Resume is not successfully parsed.")
         raise Exception("Resume parser remote call fail!")
     callback(0.6, "Done parsing. Chunking...")
-    logger.info("chunking resume: " + json.dumps(resume, ensure_ascii=False, indent=2))
+    logging.debug("chunking resume: " + json.dumps(resume, ensure_ascii=False, indent=2))
 
     field_map = {
         "name_kwd": "姓名/名字",
@@ -158,7 +158,7 @@ def chunk(filename, binary=None, callback=None, **kwargs):
             resume[n] = rag_tokenizer.fine_grained_tokenize(resume[n])
         doc[n] = resume[n]
 
-    logger.info("chunked resume to " + str(doc))
+    logging.debug("chunked resume to " + str(doc))
     KnowledgebaseService.update_parser_config(
         kwargs["kb_id"], {"field_map": field_map})
     return [doc]

rag/llm/embedding_model.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import re
 from typing import Optional
 import threading
@@ -32,7 +33,6 @@ from api.utils.file_utils import get_home_cache_dir
 from rag.utils import num_tokens_from_string, truncate
 import google.generativeai as genai 
 import json
-from api.utils.log_utils import logger
 
 class Base(ABC):
     def __init__(self, key, model_name):
@@ -297,7 +297,7 @@ class YoudaoEmbed(Base):
         if not LIGHTEN and not YoudaoEmbed._client:
             from BCEmbedding import EmbeddingModel as qanthing
             try:
-                logger.info("LOADING BCE...")
+                logging.info("LOADING BCE...")
                 YoudaoEmbed._client = qanthing(model_name_or_path=os.path.join(
                     get_home_cache_dir(),
                     "bce-embedding-base_v1"))

rag/llm/rerank_model.py

@@ -27,7 +27,6 @@ from api.settings import LIGHTEN
 from api.utils.file_utils import get_home_cache_dir
 from rag.utils import num_tokens_from_string, truncate
 import json
-from api.utils.log_utils import logger
 
 
 def sigmoid(x):
@@ -127,7 +126,7 @@ class YoudaoRerank(DefaultRerank):
             with YoudaoRerank._model_lock:
                 if not YoudaoRerank._model:
                     try:
-                        logger.info("LOADING BCE...")
+                        logging.info("LOADING BCE...")
                         YoudaoRerank._model = RerankerModel(model_name_or_path=os.path.join(
                             get_home_cache_dir(),
                             re.sub(r"^[a-zA-Z0-9]+/", "", model_name)))

rag/nlp/__init__.py

@@ -14,6 +14,7 @@
 #  limitations under the License.
 #
 
+import logging
 import random
 from collections import Counter
 
@@ -26,7 +27,6 @@ from word2number import w2n
 from cn2an import cn2an
 from PIL import Image
 import json
-from api.utils.log_utils import logger
 
 all_codecs = [
     'utf-8', 'gb2312', 'gbk', 'utf_16', 'ascii', 'big5', 'big5hkscs',
@@ -236,7 +236,7 @@ def tokenize_chunks(chunks, doc, eng, pdf_parser=None):
     # wrap up as es documents
     for ck in chunks:
         if len(ck.strip()) == 0:continue
-        logger.debug("-- {}".format(ck))
+        logging.debug("-- {}".format(ck))
         d = copy.deepcopy(doc)
         if pdf_parser:
             try:
@@ -255,7 +255,7 @@ def tokenize_chunks_docx(chunks, doc, eng, images):
     # wrap up as es documents
     for ck, image in zip(chunks, images):
         if len(ck.strip()) == 0:continue
-        logger.debug("-- {}".format(ck))
+        logging.debug("-- {}".format(ck))
         d = copy.deepcopy(doc)
         d["image"] = image
         tokenize(d, ck, eng)
@@ -458,7 +458,7 @@ def hierarchical_merge(bull, sections, depth):
 
     for i in range(len(cks)):
         cks[i] = [sections[j] for j in cks[i][::-1]]
-        logger.info("\n* ".join(cks[i]))
+        logging.debug("\n* ".join(cks[i]))
 
     res = [[]]
     num = [0]

rag/nlp/query.py

@@ -14,9 +14,9 @@
 #  limitations under the License.
 #
 
+import logging
 import json
 import re
-import logging
 from rag.utils.doc_store_conn import MatchTextExpr
 
 from rag.nlp import rag_tokenizer, term_weight, synonym
@@ -88,7 +88,7 @@ class FulltextQueryer:
                 syn = ["\"{}\"^{:.4f}".format(s, w / 4.) for s in syn]
                 syns.append(" ".join(syn))
 
-            q = ["({}^{:.4f}".format(tk, w) + " %s)".format(syn) for (tk, w), syn in zip(tks_w, syns)]
+            q = ["({}^{:.4f}".format(tk, w) + " %s)".format() for (tk, w), syn in zip(tks_w, syns)]
             for i in range(1, len(tks_w)):
                 q.append(
                     '"%s %s"^%.4f'
@@ -121,7 +121,7 @@ class FulltextQueryer:
             twts = self.tw.weights([tt])
             syns = self.syn.lookup(tt)
             if syns: keywords.extend(syns)
-            logging.info(json.dumps(twts, ensure_ascii=False))
+            logging.debug(json.dumps(twts, ensure_ascii=False))
             tms = []
             for tk, w in sorted(twts, key=lambda x: x[1] * -1):
                 sm = (

rag/nlp/rag_tokenizer.py

@@ -14,6 +14,7 @@
 #  limitations under the License.
 #
 
+import logging
 import copy
 import datrie
 import math
@@ -25,7 +26,6 @@ from hanziconv import HanziConv
 from nltk import word_tokenize
 from nltk.stem import PorterStemmer, WordNetLemmatizer
 from api.utils.file_utils import get_project_base_directory
-from api.utils.log_utils import logger
 
 
 class RagTokenizer:
@@ -36,7 +36,7 @@ class RagTokenizer:
         return str(("DD" + (line[::-1].lower())).encode("utf-8"))[2:-1]
 
     def loadDict_(self, fnm):
-        logger.info(f"[HUQIE]:Build trie {fnm}")
+        logging.info(f"[HUQIE]:Build trie {fnm}")
         try:
             of = open(fnm, "r", encoding='utf-8')
             while True:
@@ -53,7 +53,7 @@ class RagTokenizer:
             self.trie_.save(fnm + ".trie")
             of.close()
         except Exception:
-            logger.exception(f"[HUQIE]:Build trie {fnm} failed")
+            logging.exception(f"[HUQIE]:Build trie {fnm} failed")
 
     def __init__(self, debug=False):
         self.DEBUG = debug
@@ -69,7 +69,7 @@ class RagTokenizer:
             self.trie_ = datrie.Trie.load(self.DIR_ + ".txt.trie")
             return
         except Exception:
-            logger.exception("[HUQIE]:Build default trie")
+            logging.exception("[HUQIE]:Build default trie")
             self.trie_ = datrie.Trie(string.printable)
 
         self.loadDict_(self.DIR_ + ".txt")
@@ -173,7 +173,7 @@ class RagTokenizer:
             tks.append(tk)
         F /= len(tks)
         L /= len(tks)
-        logger.debug("[SC] {} {} {} {} {}".format(tks, len(tks), L, F, B / len(tks) + L + F))
+        logging.debug("[SC] {} {} {} {} {}".format(tks, len(tks), L, F, B / len(tks) + L + F))
         return tks, B / len(tks) + L + F
 
     def sortTks_(self, tkslist):
@@ -277,8 +277,8 @@ class RagTokenizer:
             tks, s = self.maxForward_(L)
             tks1, s1 = self.maxBackward_(L)
             if self.DEBUG:
-                logger.debug("[FW] {} {}".format(tks, s))
-                logger.debug("[BW] {} {}".format(tks1, s1))
+                logging.debug("[FW] {} {}".format(tks, s))
+                logging.debug("[BW] {} {}".format(tks1, s1))
 
             i, j, _i, _j = 0, 0, 0, 0
             same = 0
@@ -325,7 +325,7 @@ class RagTokenizer:
                 res.append(" ".join(self.sortTks_(tkslist)[0][0]))
 
         res = " ".join(self.english_normalize_(res))
-        logger.debug("[TKS] {}".format(self.merge_(res)))
+        logging.debug("[TKS] {}".format(self.merge_(res)))
         return self.merge_(res)
 
     def fine_grained_tokenize(self, tks):
@@ -416,30 +416,30 @@ if __name__ == '__main__':
     # huqie.addUserDict("/tmp/tmp.new.tks.dict")
     tks = tknzr.tokenize(
         "哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈")
-    logger.info(tknzr.fine_grained_tokenize(tks))
+    logging.info(tknzr.fine_grained_tokenize(tks))
     tks = tknzr.tokenize(
         "公开征求意见稿提出，境外投资者可使用自有人民币或外汇投资。使用外汇投资的，可通过债券持有人在香港人民币业务清算行及香港地区经批准可进入境内银行间外汇市场进行交易的境外人民币业务参加行（以下统称香港结算行）办理外汇资金兑换。香港结算行由此所产生的头寸可到境内银行间外汇市场平盘。使用外汇投资的，在其投资的债券到期或卖出后，原则上应兑换回外汇。")
-    logger.info(tknzr.fine_grained_tokenize(tks))
+    logging.info(tknzr.fine_grained_tokenize(tks))
     tks = tknzr.tokenize(
         "多校划片就是一个小区对应多个小学初中，让买了学区房的家庭也不确定到底能上哪个学校。目的是通过这种方式为学区房降温，把就近入学落到实处。南京市长江大桥")
-    logger.info(tknzr.fine_grained_tokenize(tks))
+    logging.info(tknzr.fine_grained_tokenize(tks))
     tks = tknzr.tokenize(
         "实际上当时他们已经将业务中心偏移到安全部门和针对政府企业的部门 Scripts are compiled and cached aaaaaaaaa")
-    logger.info(tknzr.fine_grained_tokenize(tks))
+    logging.info(tknzr.fine_grained_tokenize(tks))
     tks = tknzr.tokenize("虽然我不怎么玩")
-    logger.info(tknzr.fine_grained_tokenize(tks))
+    logging.info(tknzr.fine_grained_tokenize(tks))
     tks = tknzr.tokenize("蓝月亮如何在外资夹击中生存,那是全宇宙最有意思的")
-    logger.info(tknzr.fine_grained_tokenize(tks))
+    logging.info(tknzr.fine_grained_tokenize(tks))
     tks = tknzr.tokenize(
         "涡轮增压发动机num最大功率,不像别的共享买车锁电子化的手段,我们接过来是否有意义,黄黄爱美食,不过，今天阿奇要讲到的这家农贸市场，说实话，还真蛮有特色的！不仅环境好，还打出了")
-    logger.info(tknzr.fine_grained_tokenize(tks))
+    logging.info(tknzr.fine_grained_tokenize(tks))
     tks = tknzr.tokenize("这周日你去吗？这周日你有空吗？")
-    logger.info(tknzr.fine_grained_tokenize(tks))
+    logging.info(tknzr.fine_grained_tokenize(tks))
     tks = tknzr.tokenize("Unity3D开发经验 测试开发工程师 c++双11双11 985 211 ")
-    logger.info(tknzr.fine_grained_tokenize(tks))
+    logging.info(tknzr.fine_grained_tokenize(tks))
     tks = tknzr.tokenize(
         "数据分析项目经理|数据分析挖掘|数据分析方向|商品数据分析|搜索数据分析 sql python hive tableau Cocos2d-")
-    logger.info(tknzr.fine_grained_tokenize(tks))
+    logging.info(tknzr.fine_grained_tokenize(tks))
     if len(sys.argv) < 2:
         sys.exit()
     tknzr.DEBUG = False
@@ -449,5 +449,5 @@ if __name__ == '__main__':
         line = of.readline()
         if not line:
             break
-        logger.info(tknzr.tokenize(line))
+        logging.info(tknzr.tokenize(line))
     of.close()

rag/nlp/search.py

@@ -14,12 +14,12 @@
 #  limitations under the License.
 #
 
+import logging
 import re
 import json
 from typing import List, Optional, Dict, Union
 from dataclasses import dataclass
 
-from api.utils.log_utils import logger
 from rag.utils import rmSpace
 from rag.nlp import rag_tokenizer, query
 import numpy as np
@@ -83,7 +83,7 @@ class Dealer:
                 orderBy.desc("create_timestamp_flt")
             res = self.dataStore.search(src, [], filters, [], orderBy, offset, limit, idx_names, kb_ids)
             total=self.dataStore.getTotal(res)
-            logger.info("Dealer.search TOTAL: {}".format(total))
+            logging.debug("Dealer.search TOTAL: {}".format(total))
         else:
             highlightFields = ["content_ltks", "title_tks"] if highlight else []
             matchText, keywords = self.qryr.question(qst, min_match=0.3)
@@ -91,7 +91,7 @@ class Dealer:
                 matchExprs = [matchText]
                 res = self.dataStore.search(src, highlightFields, filters, matchExprs, orderBy, offset, limit, idx_names, kb_ids)
                 total=self.dataStore.getTotal(res)
-                logger.info("Dealer.search TOTAL: {}".format(total))
+                logging.debug("Dealer.search TOTAL: {}".format(total))
             else:
                 matchDense = self.get_vector(qst, emb_mdl, topk, req.get("similarity", 0.1))
                 q_vec = matchDense.embedding_data
@@ -102,7 +102,7 @@ class Dealer:
 
                 res = self.dataStore.search(src, highlightFields, filters, matchExprs, orderBy, offset, limit, idx_names, kb_ids)
                 total=self.dataStore.getTotal(res)
-                logger.info("Dealer.search TOTAL: {}".format(total))
+                logging.debug("Dealer.search TOTAL: {}".format(total))
 
                 # If result is empty, try again with lower min_match
                 if total == 0:
@@ -112,7 +112,7 @@ class Dealer:
                     matchDense.extra_options["similarity"] = 0.17
                     res = self.dataStore.search(src, highlightFields, filters, [matchText, matchDense, fusionExpr], orderBy, offset, limit, idx_names, kb_ids)
                     total=self.dataStore.getTotal(res)
-                    logger.info("Dealer.search 2 TOTAL: {}".format(total))
+                    logging.debug("Dealer.search 2 TOTAL: {}".format(total))
 
             for k in keywords:
                 kwds.add(k)
@@ -123,7 +123,7 @@ class Dealer:
                         continue
                     kwds.add(kk)
 
-        logger.info(f"TOTAL: {total}")
+        logging.debug(f"TOTAL: {total}")
         ids=self.dataStore.getChunkIds(res)
         keywords=list(kwds)
         highlight = self.dataStore.getHighlight(res, keywords, "content_with_weight")
@@ -180,7 +180,7 @@ class Dealer:
                 continue
             idx.append(i)
             pieces_.append(t)
-        logger.info("{} => {}".format(answer, pieces_))
+        logging.debug("{} => {}".format(answer, pieces_))
         if not pieces_:
             return answer, set([])
 
@@ -201,7 +201,7 @@ class Dealer:
                                                                 chunks_tks,
                                                                 tkweight, vtweight)
                 mx = np.max(sim) * 0.99
-                logger.info("{} SIM: {}".format(pieces_[i], mx))
+                logging.debug("{} SIM: {}".format(pieces_[i], mx))
                 if mx < thr:
                     continue
                 cites[idx[i]] = list(

rag/nlp/synonym.py

@@ -14,13 +14,13 @@
 #  limitations under the License.
 #
 
+import logging
 import json
 import os
 import time
 import re
 from nltk.corpus import wordnet
 from api.utils.file_utils import get_project_base_directory
-from api.utils.log_utils import logger
 
 
 class Dealer:
@@ -33,14 +33,14 @@ class Dealer:
         try:
             self.dictionary = json.load(open(path, 'r'))
         except Exception:
-            logger.warn("Missing synonym.json")
+            logging.warn("Missing synonym.json")
             self.dictionary = {}
 
         if not redis:
-            logger.warning(
+            logging.warning(
                 "Realtime synonym is disabled, since no redis connection.")
         if not len(self.dictionary.keys()):
-            logger.warning("Fail to load synonym")
+            logging.warning("Fail to load synonym")
 
         self.redis = redis
         self.load()
@@ -64,7 +64,7 @@ class Dealer:
             d = json.loads(d)
             self.dictionary = d
         except Exception as e:
-            logger.error("Fail to load synonym!" + str(e))
+            logging.error("Fail to load synonym!" + str(e))
 
     def lookup(self, tk):
         if re.match(r"[a-z]+$", tk):

rag/nlp/term_weight.py

@@ -14,6 +14,7 @@
 #  limitations under the License.
 #
 
+import logging
 import math
 import json
 import re
@@ -21,7 +22,6 @@ import os
 import numpy as np
 from rag.nlp import rag_tokenizer
 from api.utils.file_utils import get_project_base_directory
-from api.utils.log_utils import logger
 
 
 class Dealer:
@@ -83,11 +83,11 @@ class Dealer:
         try:
             self.ne = json.load(open(os.path.join(fnm, "ner.json"), "r"))
         except Exception:
-            logger.warning("Load ner.json FAIL!")
+            logging.warning("Load ner.json FAIL!")
         try:
             self.df = load_dict(os.path.join(fnm, "term.freq"))
         except Exception:
-            logger.warning("Load term.freq FAIL!")
+            logging.warning("Load term.freq FAIL!")
 
     def pretoken(self, txt, num=False, stpwd=True):
         patt = [

rag/raptor.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import re
 from concurrent.futures import ThreadPoolExecutor, ALL_COMPLETED, wait
 from threading import Lock
@@ -22,7 +23,6 @@ import numpy as np
 from sklearn.mixture import GaussianMixture
 
 from rag.utils import truncate
-from api.utils.log_utils import logger
 
 
 class RecursiveAbstractiveProcessing4TreeOrganizedRetrieval:
@@ -62,13 +62,13 @@ class RecursiveAbstractiveProcessing4TreeOrganizedRetrieval:
                                              {"temperature": 0.3, "max_tokens": self._max_token}
                                              )
                 cnt = re.sub("(······\n由于长度的原因，回答被截断了，要继续吗？|For the content length reason, it stopped, continue?)", "", cnt)
-                logger.info(f"SUM: {cnt}")
+                logging.debug(f"SUM: {cnt}")
                 embds, _ = self._embd_model.encode([cnt])
                 with lock:
                     if not len(embds[0]): return
                     chunks.append((cnt, embds[0]))
             except Exception as e:
-                logger.exception("summarize got exception")
+                logging.exception("summarize got exception")
                 return e
 
         labels = []
@@ -104,7 +104,7 @@ class RecursiveAbstractiveProcessing4TreeOrganizedRetrieval:
                     ck_idx = [i+start for i in range(len(lbls)) if lbls[i] == c]
                     threads.append(executor.submit(summarize, ck_idx, lock))
                 wait(threads, return_when=ALL_COMPLETED)
-                logger.info(str([t.result() for t in threads]))
+                logging.debug(str([t.result() for t in threads]))
 
             assert len(chunks) - end == n_clusters, "{} vs. {}".format(len(chunks) - end, n_clusters)
             labels.extend(lbls)

rag/svr/cache_file_svr.py

@@ -13,19 +13,19 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import time
 import traceback
 
 from api.db.db_models import close_connection
 from api.db.services.task_service import TaskService
-from api.utils.log_utils import logger
 from rag.utils.storage_factory import STORAGE_IMPL
 from rag.utils.redis_conn import REDIS_CONN
 
 
 def collect():
     doc_locations = TaskService.get_ongoing_doc_name()
-    logger.info(doc_locations)
+    logging.debug(doc_locations)
     if len(doc_locations) == 0:
         time.sleep(1)
         return
@@ -34,7 +34,7 @@ def collect():
 def main():
     locations = collect()
     if not locations:return
-    logger.info(f"TASKS: {len(locations)}")
+    logging.info(f"TASKS: {len(locations)}")
     for kb_id, loc in locations:
         try:
             if REDIS_CONN.is_alive():
@@ -43,7 +43,7 @@ def main():
                     if REDIS_CONN.exist(key):continue
                     file_bin = STORAGE_IMPL.get(kb_id, loc)
                     REDIS_CONN.transaction(key, file_bin, 12 * 60)
-                    logger.info("CACHE: {}".format(loc))
+                    logging.info("CACHE: {}".format(loc))
                 except Exception as e:
                     traceback.print_stack(e)
         except Exception as e:

rag/svr/discord_svr.py

@@ -13,11 +13,11 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import discord
 import requests
 import base64
 import asyncio
-from api.utils.log_utils import logger
 
 URL = '{YOUR_IP_ADDRESS:PORT}/v1/api/completion_aibotk' # Default: https://demo.ragflow.io/v1/api/completion_aibotk
 
@@ -37,7 +37,7 @@ client = discord.Client(intents=intents)
 
 @client.event
 async def on_ready():
-    logger.info(f'We have logged in as {client.user}')
+    logging.info(f'We have logged in as {client.user}')
 
 
 @client.event

rag/svr/task_executor.py

@@ -13,9 +13,20 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
+import inspect
+from api.utils.log_utils import initRootLogger
+initRootLogger(inspect.getfile(inspect.currentframe()))
+for module in ["pdfminer"]:
+    module_logger = logging.getLogger(module)
+    module_logger.setLevel(logging.WARNING)
+for module in ["peewee"]:
+    module_logger = logging.getLogger(module)
+    module_logger.handlers.clear()
+    module_logger.propagate = True
+
 import datetime
 import json
-import logging
 import os
 import hashlib
 import copy
@@ -42,7 +53,6 @@ from api.db.db_models import close_connection
 from rag.app import laws, paper, presentation, manual, qa, table, book, resume, picture, naive, one, audio, knowledge_graph, email
 from rag.nlp import search, rag_tokenizer
 from rag.raptor import RecursiveAbstractiveProcessing4TreeOrganizedRetrieval as Raptor
-from api.utils.log_utils import logger, LOG_FILE
 from rag.settings import DOC_MAXIMUM_SIZE, SVR_QUEUE_NAME
 from rag.utils import rmSpace, num_tokens_from_string
 from rag.utils.redis_conn import REDIS_CONN, Payload
@@ -90,7 +100,7 @@ def set_progress(task_id, from_page=0, to_page=-1, prog=None, msg="Processing...
     try:
         TaskService.update_progress(task_id, d)
     except Exception:
-        logger.exception(f"set_progress({task_id}) got exception")
+        logging.exception(f"set_progress({task_id}) got exception")
 
     close_connection()
     if cancel:
@@ -110,7 +120,7 @@ def collect():
             time.sleep(1)
             return pd.DataFrame()
     except Exception:
-        logger.exception("Get task event from queue exception")
+        logging.exception("Get task event from queue exception")
         return pd.DataFrame()
 
     msg = PAYLOAD.get_message()
@@ -118,11 +128,11 @@ def collect():
         return pd.DataFrame()
 
     if TaskService.do_cancel(msg["id"]):
-        logger.info("Task {} has been canceled.".format(msg["id"]))
+        logging.info("Task {} has been canceled.".format(msg["id"]))
         return pd.DataFrame()
     tasks = TaskService.get_tasks(msg["id"])
     if not tasks:
-        logger.warning("{} empty task!".format(msg["id"]))
+        logging.warning("{} empty task!".format(msg["id"]))
         return []
 
     tasks = pd.DataFrame(tasks)
@@ -151,29 +161,29 @@ def build(row):
         st = timer()
         bucket, name = File2DocumentService.get_storage_address(doc_id=row["doc_id"])
         binary = get_storage_binary(bucket, name)
-        logger.info(
+        logging.info(
             "From minio({}) {}/{}".format(timer() - st, row["location"], row["name"]))
     except TimeoutError:
         callback(-1, "Internal server error: Fetch file from minio timeout. Could you try it again.")
-        logger.exception("Minio {}/{} got timeout: Fetch file from minio timeout.".format(row["location"], row["name"]))
+        logging.exception("Minio {}/{} got timeout: Fetch file from minio timeout.".format(row["location"], row["name"]))
         return
     except Exception as e:
         if re.search("(No such file|not found)", str(e)):
             callback(-1, "Can not find file <%s> from minio. Could you try it again?" % row["name"])
         else:
             callback(-1, "Get file from minio: %s" % str(e).replace("'", ""))
-        logger.exception("Chunking {}/{} got exception".format(row["location"], row["name"]))
+        logging.exception("Chunking {}/{} got exception".format(row["location"], row["name"]))
         return
 
     try:
         cks = chunker.chunk(row["name"], binary=binary, from_page=row["from_page"],
                             to_page=row["to_page"], lang=row["language"], callback=callback,
                             kb_id=row["kb_id"], parser_config=row["parser_config"], tenant_id=row["tenant_id"])
-        logger.info("Chunking({}) {}/{} done".format(timer() - st, row["location"], row["name"]))
+        logging.info("Chunking({}) {}/{} done".format(timer() - st, row["location"], row["name"]))
     except Exception as e:
         callback(-1, "Internal server error while chunking: %s" %
                      str(e).replace("'", ""))
-        logger.exception("Chunking {}/{} got exception".format(row["location"], row["name"]))
+        logging.exception("Chunking {}/{} got exception".format(row["location"], row["name"]))
         return
 
     docs = []
@@ -210,12 +220,12 @@ def build(row):
             STORAGE_IMPL.put(row["kb_id"], d["id"], output_buffer.getvalue())
             el += timer() - st
         except Exception:
-            logger.exception("Saving image of chunk {}/{}/{} got exception".format(row["location"], row["name"], d["_id"]))
+            logging.exception("Saving image of chunk {}/{}/{} got exception".format(row["location"], row["name"], d["_id"]))
 
         d["img_id"] = "{}-{}".format(row["kb_id"], d["id"])
         del d["image"]
         docs.append(d)
-    logger.info("MINIO PUT({}):{}".format(row["name"], el))
+    logging.info("MINIO PUT({}):{}".format(row["name"], el))
 
     if row["parser_config"].get("auto_keywords", 0):
         st = timer()
@@ -345,7 +355,7 @@ def main():
             embd_mdl = LLMBundle(r["tenant_id"], LLMType.EMBEDDING, llm_name=r["embd_id"], lang=r["language"])
         except Exception as e:
             callback(-1, msg=str(e))
-            logger.exception("LLMBundle got exception")
+            logging.exception("LLMBundle got exception")
             continue
 
         if r.get("task_type", "") == "raptor":
@@ -354,12 +364,12 @@ def main():
                 cks, tk_count, vector_size = run_raptor(r, chat_mdl, embd_mdl, callback)
             except Exception as e:
                 callback(-1, msg=str(e))
-                logger.exception("run_raptor got exception")
+                logging.exception("run_raptor got exception")
                 continue
         else:
             st = timer()
             cks = build(r)
-            logger.info("Build chunks({}): {}".format(r["name"], timer() - st))
+            logging.info("Build chunks({}): {}".format(r["name"], timer() - st))
             if cks is None:
                 continue
             if not cks:
@@ -375,12 +385,12 @@ def main():
                 tk_count, vector_size = embedding(cks, embd_mdl, r["parser_config"], callback)
             except Exception as e:
                 callback(-1, "Embedding error:{}".format(str(e)))
-                logger.exception("run_rembedding got exception")
+                logging.exception("run_rembedding got exception")
                 tk_count = 0
-            logger.info("Embedding elapsed({}): {:.2f}".format(r["name"], timer() - st))
+            logging.info("Embedding elapsed({}): {:.2f}".format(r["name"], timer() - st))
             callback(msg="Finished embedding (in {:.2f}s)! Start to build index!".format(timer() - st))
 
-        # logger.info(f"task_executor init_kb index {search.index_name(r["tenant_id"])} embd_mdl {embd_mdl.llm_name} vector length {vector_size}")
+        # logging.info(f"task_executor init_kb index {search.index_name(r["tenant_id"])} embd_mdl {embd_mdl.llm_name} vector length {vector_size}")
         init_kb(r, vector_size)
         chunk_count = len(set([c["id"] for c in cks]))
         st = timer()
@@ -391,11 +401,11 @@ def main():
             if b % 128 == 0:
                 callback(prog=0.8 + 0.1 * (b + 1) / len(cks), msg="")
 
-        logger.info("Indexing elapsed({}): {:.2f}".format(r["name"], timer() - st))
+        logging.info("Indexing elapsed({}): {:.2f}".format(r["name"], timer() - st))
         if es_r:
             callback(-1, f"Insert chunk error, detail info please check {LOG_FILE}. Please also check ES status!")
             docStoreConn.delete({"doc_id": r["doc_id"]}, search.index_name(r["tenant_id"]), r["kb_id"])
-            logger.error('Insert chunk error: ' + str(es_r))
+            logging.error('Insert chunk error: ' + str(es_r))
         else:
             if TaskService.do_cancel(r["id"]):
                 docStoreConn.delete({"doc_id": r["doc_id"]}, search.index_name(r["tenant_id"]), r["kb_id"])
@@ -404,7 +414,7 @@ def main():
             callback(1., "Done!")
             DocumentService.increment_chunk_num(
                 r["doc_id"], r["kb_id"], tk_count, chunk_count, 0)
-            logger.info(
+            logging.info(
                 "Chunk doc({}), token({}), chunks({}), elapsed:{:.2f}".format(
                     r["id"], tk_count, len(cks), timer() - st))
 
@@ -421,16 +431,11 @@ def report_status():
             obj[CONSUMER_NAME] = obj[CONSUMER_NAME][-60:]
             REDIS_CONN.set_obj("TASKEXE", obj, 60*2)
         except Exception:
-            logger.exception("report_status got exception")
+            logging.exception("report_status got exception")
         time.sleep(30)
 
 
 if __name__ == "__main__":
-    peewee_logger = logging.getLogger('peewee')
-    peewee_logger.propagate = False
-    peewee_logger.addHandler(logger.handlers[0])
-    peewee_logger.setLevel(logger.handlers[0].level)
-
     exe = ThreadPoolExecutor(max_workers=1)
     exe.submit(report_status)
 

rag/utils/azure_sas_conn.py

@@ -1,3 +1,4 @@
+import logging
 import os
 import time
 from io import BytesIO
@@ -24,7 +25,7 @@ class RAGFlowAzureSasBlob(object):
         try:
             self.conn = ContainerClient.from_container_url(self.container_url + "?" + self.sas_token)
         except Exception:
-            logger.exception("Fail to connect %s " % self.container_url)
+            logging.exception("Fail to connect %s " % self.container_url)
 
     def __close__(self):
         del self.conn
@@ -39,7 +40,7 @@ class RAGFlowAzureSasBlob(object):
             try:
                 return self.conn.upload_blob(name=fnm, data=BytesIO(binary), length=len(binary))
             except Exception:
-                logger.exception(f"Fail put {bucket}/{fnm}")
+                logging.exception(f"Fail put {bucket}/{fnm}")
                 self.__open__()
                 time.sleep(1)
 
@@ -47,7 +48,7 @@ class RAGFlowAzureSasBlob(object):
         try:
             self.conn.delete_blob(fnm)
         except Exception:
-            logger.exception(f"Fail rm {bucket}/{fnm}")
+            logging.exception(f"Fail rm {bucket}/{fnm}")
 
     def get(self, bucket, fnm):
         for _ in range(1):
@@ -55,7 +56,7 @@ class RAGFlowAzureSasBlob(object):
                 r = self.conn.download_blob(fnm)
                 return r.read()
             except Exception:
-                logger.exception(f"fail get {bucket}/{fnm}")
+                logging.exception(f"fail get {bucket}/{fnm}")
                 self.__open__()
                 time.sleep(1)
         return
@@ -64,7 +65,7 @@ class RAGFlowAzureSasBlob(object):
         try:
             return self.conn.get_blob_client(fnm).exists()
         except Exception:
-            logger.exception(f"Fail put {bucket}/{fnm}")
+            logging.exception(f"Fail put {bucket}/{fnm}")
         return False
 
     def get_presigned_url(self, bucket, fnm, expires):
@@ -72,7 +73,7 @@ class RAGFlowAzureSasBlob(object):
             try:
                 return self.conn.get_presigned_url("GET", bucket, fnm, expires)
             except Exception:
-                logger.exception(f"fail get {bucket}/{fnm}")
+                logging.exception(f"fail get {bucket}/{fnm}")
                 self.__open__()
                 time.sleep(1)
         return

rag/utils/azure_spn_conn.py

@@ -1,3 +1,4 @@
+import logging
 import os
 import time
 from rag import settings
@@ -28,7 +29,7 @@ class RAGFlowAzureSpnBlob(object):
             credentials = ClientSecretCredential(tenant_id=self.tenant_id, client_id=self.client_id, client_secret=self.secret, authority=AzureAuthorityHosts.AZURE_CHINA)
             self.conn = FileSystemClient(account_url=self.account_url, file_system_name=self.container_name, credential=credentials)
         except Exception:
-            logger.exception("Fail to connect %s" % self.account_url)
+            logging.exception("Fail to connect %s" % self.account_url)
 
     def __close__(self):
         del self.conn
@@ -47,7 +48,7 @@ class RAGFlowAzureSpnBlob(object):
                 f.append_data(binary, offset=0, length=len(binary))
                 return f.flush_data(len(binary))
             except Exception:
-                logger.exception(f"Fail put {bucket}/{fnm}")
+                logging.exception(f"Fail put {bucket}/{fnm}")
                 self.__open__()
                 time.sleep(1)
 
@@ -55,7 +56,7 @@ class RAGFlowAzureSpnBlob(object):
         try:
             self.conn.delete_file(fnm)
         except Exception:
-            logger.exception(f"Fail rm {bucket}/{fnm}")
+            logging.exception(f"Fail rm {bucket}/{fnm}")
 
     def get(self, bucket, fnm):
         for _ in range(1):
@@ -64,7 +65,7 @@ class RAGFlowAzureSpnBlob(object):
                 r = client.download_file()
                 return r.read()
             except Exception:
-                logger.exception(f"fail get {bucket}/{fnm}")
+                logging.exception(f"fail get {bucket}/{fnm}")
                 self.__open__()
                 time.sleep(1)
         return
@@ -74,7 +75,7 @@ class RAGFlowAzureSpnBlob(object):
             client = self.conn.get_file_client(fnm)
             return client.exists()
         except Exception:
-            logger.exception(f"Fail put {bucket}/{fnm}")
+            logging.exception(f"Fail put {bucket}/{fnm}")
         return False
 
     def get_presigned_url(self, bucket, fnm, expires):
@@ -82,7 +83,7 @@ class RAGFlowAzureSpnBlob(object):
             try:
                 return self.conn.get_presigned_url("GET", bucket, fnm, expires)
             except Exception:
-                logger.exception(f"fail get {bucket}/{fnm}")
+                logging.exception(f"fail get {bucket}/{fnm}")
                 self.__open__()
                 time.sleep(1)
         return

rag/utils/es_conn.py

@@ -1,3 +1,4 @@
+import logging
 import re
 import json
 import time
@@ -8,7 +9,6 @@ import copy
 from elasticsearch import Elasticsearch
 from elasticsearch_dsl import UpdateByQuery, Q, Search, Index
 from elastic_transport import ConnectionTimeout
-from api.utils.log_utils import logger
 from rag import settings
 from rag.utils import singleton
 from api.utils.file_utils import get_project_base_directory
@@ -22,7 +22,7 @@ from rag.nlp import is_english, rag_tokenizer
 class ESConnection(DocStoreConnection):
     def __init__(self):
         self.info = {}
-        logger.info(f"Use Elasticsearch {settings.ES['hosts']} as the doc engine.")
+        logging.info(f"Use Elasticsearch {settings.ES['hosts']} as the doc engine.")
         for _ in range(24):
             try:
                 self.es = Elasticsearch(
@@ -36,25 +36,25 @@ class ESConnection(DocStoreConnection):
                     self.info = self.es.info()
                     break
             except Exception as e:
-                logger.warn(f"{str(e)}. Waiting Elasticsearch {settings.ES['hosts']} to be healthy.")
+                logging.warn(f"{str(e)}. Waiting Elasticsearch {settings.ES['hosts']} to be healthy.")
                 time.sleep(5)
         if not self.es.ping():
             msg = f"Elasticsearch {settings.ES['hosts']} didn't become healthy in 120s."
-            logger.error(msg)
+            logging.error(msg)
             raise Exception(msg)
         v = self.info.get("version", {"number": "8.11.3"})
         v = v["number"].split(".")[0]
         if int(v) < 8:
             msg = f"Elasticsearch version must be greater than or equal to 8, current version: {v}"
-            logger.error(msg)
+            logging.error(msg)
             raise Exception(msg)
         fp_mapping = os.path.join(get_project_base_directory(), "conf", "mapping.json")
         if not os.path.exists(fp_mapping):
             msg = f"Elasticsearch mapping file not found at {fp_mapping}"
-            logger.error(msg)
+            logging.error(msg)
             raise Exception(msg)
         self.mapping = json.load(open(fp_mapping, "r"))
-        logger.info(f"Elasticsearch {settings.ES['hosts']} is healthy.")
+        logging.info(f"Elasticsearch {settings.ES['hosts']} is healthy.")
 
     """
     Database operations
@@ -79,13 +79,13 @@ class ESConnection(DocStoreConnection):
                                                  settings=self.mapping["settings"],
                                                  mappings=self.mapping["mappings"])
         except Exception:
-            logger.exception("ES create index error %s" % (indexName))
+            logging.exception("ES create index error %s" % (indexName))
 
     def deleteIdx(self, indexName: str, knowledgebaseId: str):
         try:
             return self.es.indices.delete(indexName, allow_no_indices=True)
         except Exception:
-            logger.exception("ES delete index error %s" % (indexName))
+            logging.exception("ES delete index error %s" % (indexName))
 
     def indexExist(self, indexName: str, knowledgebaseId: str) -> bool:
         s = Index(indexName, self.es)
@@ -93,7 +93,7 @@ class ESConnection(DocStoreConnection):
             try:
                 return s.exists()
             except Exception as e:
-                logger.exception("ES indexExist")
+                logging.exception("ES indexExist")
                 if str(e).find("Timeout") > 0 or str(e).find("Conflict") > 0:
                     continue
         return False
@@ -178,7 +178,7 @@ class ESConnection(DocStoreConnection):
             s = s[offset:limit]
         q = s.to_dict()
         print(json.dumps(q), flush=True)
-        # logger.info("ESConnection.search [Q]: " + json.dumps(q))
+        logging.debug("ESConnection.search [Q]: " + json.dumps(q))
 
         for i in range(3):
             try:
@@ -190,14 +190,14 @@ class ESConnection(DocStoreConnection):
                                      _source=True)
                 if str(res.get("timed_out", "")).lower() == "true":
                     raise Exception("Es Timeout.")
-                logger.info("ESConnection.search res: " + str(res))
+                logging.debug("ESConnection.search res: " + str(res))
                 return res
             except Exception as e:
-                logger.exception("ES search [Q]: " + str(q))
+                logging.exception("ES search [Q]: " + str(q))
                 if str(e).find("Timeout") > 0:
                     continue
                 raise e
-        logger.error("ES search timeout for 3 times!")
+        logging.error("ES search timeout for 3 times!")
         raise Exception("ES search timeout.")
 
     def get(self, chunkId: str, indexName: str, knowledgebaseIds: list[str]) -> dict | None:
@@ -213,11 +213,11 @@ class ESConnection(DocStoreConnection):
                 chunk["id"] = chunkId
                 return chunk
             except Exception as e:
-                logger.exception(f"ES get({chunkId}) got exception")
+                logging.exception(f"ES get({chunkId}) got exception")
                 if str(e).find("Timeout") > 0:
                     continue
                 raise e
-        logger.error("ES search timeout for 3 times!")
+        logging.error("ES search timeout for 3 times!")
         raise Exception("ES search timeout.")
 
     def insert(self, documents: list[dict], indexName: str, knowledgebaseId: str) -> list[str]:
@@ -247,7 +247,7 @@ class ESConnection(DocStoreConnection):
                             res.append(str(item[action]["_id"]) + ":" + str(item[action]["error"]))
                 return res
             except Exception as e:
-                logger.warning("Fail to bulk: " + str(e))
+                logging.warning("Fail to bulk: " + str(e))
                 if re.search(r"(Timeout|time out)", str(e), re.IGNORECASE):
                     time.sleep(3)
                     continue
@@ -264,7 +264,7 @@ class ESConnection(DocStoreConnection):
                     self.es.update(index=indexName, id=chunkId, doc=doc)
                     return True
                 except Exception as e:
-                    logger.exception(
+                    logging.exception(
                         f"ES failed to update(index={indexName}, id={id}, doc={json.dumps(condition, ensure_ascii=False)})")
                     if str(e).find("Timeout") > 0:
                         continue
@@ -304,7 +304,7 @@ class ESConnection(DocStoreConnection):
                     _ = ubq.execute()
                     return True
                 except Exception as e:
-                    logger.error("ES update exception: " + str(e) + "[Q]:" + str(bqry.to_dict()))
+                    logging.error("ES update exception: " + str(e) + "[Q]:" + str(bqry.to_dict()))
                     if str(e).find("Timeout") > 0 or str(e).find("Conflict") > 0:
                         continue
         return False
@@ -326,7 +326,7 @@ class ESConnection(DocStoreConnection):
                     qry.must.append(Q("term", **{k: v}))
                 else:
                     raise Exception("Condition value must be int, str or list.")
-        logger.info("ESConnection.delete [Q]: " + json.dumps(qry.to_dict()))
+        logging.debug("ESConnection.delete [Q]: " + json.dumps(qry.to_dict()))
         for _ in range(10):
             try:
                 res = self.es.delete_by_query(
@@ -335,7 +335,7 @@ class ESConnection(DocStoreConnection):
                     refresh=True)
                 return res["deleted"]
             except Exception as e:
-                logger.warning("Fail to delete: " + str(filter) + str(e))
+                logging.warning("Fail to delete: " + str(filter) + str(e))
                 if re.search(r"(Timeout|time out)", str(e), re.IGNORECASE):
                     time.sleep(3)
                     continue
@@ -419,7 +419,7 @@ class ESConnection(DocStoreConnection):
     """
 
     def sql(self, sql: str, fetch_size: int, format: str):
-        logger.info(f"ESConnection.sql get sql: {sql}")
+        logging.debug(f"ESConnection.sql get sql: {sql}")
         sql = re.sub(r"[ `]+", " ", sql)
         sql = sql.replace("%", "")
         replaces = []
@@ -436,7 +436,7 @@ class ESConnection(DocStoreConnection):
 
         for p, r in replaces:
             sql = sql.replace(p, r, 1)
-        logger.info(f"ESConnection.sql to es: {sql}")
+        logging.debug(f"ESConnection.sql to es: {sql}")
 
         for i in range(3):
             try:
@@ -444,10 +444,10 @@ class ESConnection(DocStoreConnection):
                                         request_timeout="2s")
                 return res
             except ConnectionTimeout:
-                logger.exception("ESConnection.sql timeout [Q]: " + sql)
+                logging.exception("ESConnection.sql timeout [Q]: " + sql)
                 continue
             except Exception:
-                logger.exception("ESConnection.sql got exception [Q]: " + sql)
+                logging.exception("ESConnection.sql got exception [Q]: " + sql)
                 return None
-        logger.error("ESConnection.sql timeout for 3 times!")
+        logging.error("ESConnection.sql timeout for 3 times!")
         return None

rag/utils/infinity_conn.py

@@ -1,3 +1,4 @@
+import logging
 import os
 import re
 import json
@@ -7,7 +8,6 @@ import infinity
 from infinity.common import ConflictType, InfinityException
 from infinity.index import IndexInfo, IndexType
 from infinity.connection_pool import ConnectionPool
-from api.utils.log_utils import logger
 from rag import settings
 from rag.utils import singleton
 import polars as pl
@@ -56,7 +56,7 @@ class InfinityConnection(DocStoreConnection):
             host, port = infinity_uri.split(":")
             infinity_uri = infinity.common.NetworkAddress(host, int(port))
         self.connPool = None
-        logger.info(f"Use Infinity {infinity_uri} as the doc engine.")
+        logging.info(f"Use Infinity {infinity_uri} as the doc engine.")
         for _ in range(24):
             try:
                 connPool = ConnectionPool(infinity_uri)
@@ -66,13 +66,13 @@ class InfinityConnection(DocStoreConnection):
                 self.connPool = connPool
                 break
             except Exception as e:
-                logger.warn(f"{str(e)}. Waiting Infinity {infinity_uri} to be healthy.")
+                logging.warn(f"{str(e)}. Waiting Infinity {infinity_uri} to be healthy.")
                 time.sleep(5)
         if self.connPool is None:
             msg = f"Infinity {infinity_uri} didn't become healthy in 120s."
-            logger.error(msg)
+            logging.error(msg)
             raise Exception(msg)
-        logger.info(f"Infinity {infinity_uri} is healthy.")
+        logging.info(f"Infinity {infinity_uri} is healthy.")
 
     """
     Database operations
@@ -148,7 +148,7 @@ class InfinityConnection(DocStoreConnection):
                     )
                     break
         self.connPool.release_conn(inf_conn)
-        logger.info(
+        logging.info(
             f"INFINITY created table {table_name}, vector size {vectorSize}"
         )
 
@@ -158,7 +158,7 @@ class InfinityConnection(DocStoreConnection):
         db_instance = inf_conn.get_database(self.dbName)
         db_instance.drop_table(table_name, ConflictType.Ignore)
         self.connPool.release_conn(inf_conn)
-        logger.info(f"INFINITY dropped table {table_name}")
+        logging.info(f"INFINITY dropped table {table_name}")
 
     def indexExist(self, indexName: str, knowledgebaseId: str) -> bool:
         table_name = f"{indexName}_{knowledgebaseId}"
@@ -169,7 +169,7 @@ class InfinityConnection(DocStoreConnection):
             self.connPool.release_conn(inf_conn)
             return True
         except Exception as e:
-            logger.warn(f"INFINITY indexExist {str(e)}")
+            logging.warn(f"INFINITY indexExist {str(e)}")
         return False
 
     """
@@ -216,7 +216,7 @@ class InfinityConnection(DocStoreConnection):
                 )
                 if len(filter_cond) != 0:
                     filter_fulltext = f"({filter_cond}) AND {filter_fulltext}"
-                # logger.info(f"filter_fulltext: {filter_fulltext}")
+                logging.debug(f"filter_fulltext: {filter_fulltext}")
                 minimum_should_match = "0%"
                 if "minimum_should_match" in matchExpr.extra_options:
                     minimum_should_match = (
@@ -279,7 +279,7 @@ class InfinityConnection(DocStoreConnection):
                 df_list.append(kb_res)
         self.connPool.release_conn(inf_conn)
         res = pl.concat(df_list)
-        logger.info("INFINITY search tables: " + str(table_list))
+        logging.debug("INFINITY search tables: " + str(table_list))
         return res
 
     def get(
@@ -334,18 +334,18 @@ class InfinityConnection(DocStoreConnection):
         str_filter = f"id IN ({str_ids})"
         table_instance.delete(str_filter)
         # for doc in documents:
-        #     logger.info(f"insert position_list: {doc['position_list']}")
-        # logger.info(f"InfinityConnection.insert {json.dumps(documents)}")
+        #     logging.info(f"insert position_list: {doc['position_list']}")
+        # logging.info(f"InfinityConnection.insert {json.dumps(documents)}")
         table_instance.insert(documents)
         self.connPool.release_conn(inf_conn)
-        logger.info(f"inserted into {table_name} {str_ids}.")
+        logging.debug(f"inserted into {table_name} {str_ids}.")
         return []
 
     def update(
         self, condition: dict, newValue: dict, indexName: str, knowledgebaseId: str
     ) -> bool:
         # if 'position_list' in newValue:
-        #     logger.info(f"upsert position_list: {newValue['position_list']}")
+        #     logging.info(f"upsert position_list: {newValue['position_list']}")
         inf_conn = self.connPool.get_conn()
         db_instance = inf_conn.get_database(self.dbName)
         table_name = f"{indexName}_{knowledgebaseId}"
@@ -366,7 +366,7 @@ class InfinityConnection(DocStoreConnection):
         try:
             table_instance = db_instance.get_table(table_name)
         except Exception:
-            logger.warning(
+            logging.warning(
                 f"Skipped deleting `{filter}` from table {table_name} since the table doesn't exist."
             )
             return 0

rag/utils/minio_conn.py

@@ -1,9 +1,9 @@
+import logging
 import time
 from minio import Minio
 from io import BytesIO
 from rag import settings
 from rag.utils import singleton
-from api.utils.log_utils import logger
 
 
 @singleton
@@ -26,7 +26,7 @@ class RAGFlowMinio(object):
                               secure=False
                               )
         except Exception:
-            logger.exception(
+            logging.exception(
                 "Fail to connect %s " % settings.MINIO["host"])
 
     def __close__(self):
@@ -55,7 +55,7 @@ class RAGFlowMinio(object):
                                          )
                 return r
             except Exception:
-                logger.exception(f"Fail put {bucket}/{fnm}:")
+                logging.exception(f"Fail put {bucket}/{fnm}:")
                 self.__open__()
                 time.sleep(1)
 
@@ -63,7 +63,7 @@ class RAGFlowMinio(object):
         try:
             self.conn.remove_object(bucket, fnm)
         except Exception:
-            logger.exception(f"Fail put {bucket}/{fnm}:")
+            logging.exception(f"Fail put {bucket}/{fnm}:")
 
     def get(self, bucket, fnm):
         for _ in range(1):
@@ -71,7 +71,7 @@ class RAGFlowMinio(object):
                 r = self.conn.get_object(bucket, fnm)
                 return r.read()
             except Exception:
-                logger.exception(f"Fail put {bucket}/{fnm}:")
+                logging.exception(f"Fail put {bucket}/{fnm}:")
                 self.__open__()
                 time.sleep(1)
         return
@@ -81,7 +81,7 @@ class RAGFlowMinio(object):
             if self.conn.stat_object(bucket, fnm):return True
             return False
         except Exception:
-            logger.exception(f"Fail put {bucket}/{fnm}:")
+            logging.exception(f"Fail put {bucket}/{fnm}:")
         return False
 
 
@@ -90,7 +90,7 @@ class RAGFlowMinio(object):
             try:
                 return self.conn.get_presigned_url("GET", bucket, fnm, expires)
             except Exception:
-                logger.exception(f"Fail put {bucket}/{fnm}:")
+                logging.exception(f"Fail put {bucket}/{fnm}:")
                 self.__open__()
                 time.sleep(1)
         return

rag/utils/redis_conn.py

@@ -1,7 +1,7 @@
+import logging
 import json
 
 import valkey as redis
-import logging
 from rag import settings
 from rag.utils import singleton
 

rag/utils/s3_conn.py

@@ -1,3 +1,4 @@
+import logging
 import boto3
 import os
 from botocore.exceptions import ClientError
@@ -40,7 +41,7 @@ class RAGFlowS3(object):
                 config=config
             )
         except Exception:
-            logger.exception(
+            logging.exception(
                 "Fail to connect %s" % self.endpoint)
 
     def __close__(self):
@@ -49,11 +50,11 @@ class RAGFlowS3(object):
 
     def bucket_exists(self, bucket):
         try:
-            logger.debug(f"head_bucket bucketname {bucket}")
+            logging.debug(f"head_bucket bucketname {bucket}")
             self.conn.head_bucket(Bucket=bucket)
             exists = True
         except ClientError:
-            logger.exception(f"head_bucket error {bucket}")
+            logging.exception(f"head_bucket error {bucket}")
             exists = False
         return exists
 
@@ -62,7 +63,7 @@ class RAGFlowS3(object):
 
         if not self.bucket_exists(bucket):
             self.conn.create_bucket(Bucket=bucket)
-            logger.debug(f"create bucket {bucket} ********")
+            logging.debug(f"create bucket {bucket} ********")
 
         r = self.conn.upload_fileobj(BytesIO(binary), bucket, fnm)
         return r
@@ -74,17 +75,17 @@ class RAGFlowS3(object):
         return []
 
     def put(self, bucket, fnm, binary):
-        logger.debug(f"bucket name {bucket}; filename :{fnm}:")
+        logging.debug(f"bucket name {bucket}; filename :{fnm}:")
         for _ in range(1):
             try:
                 if not self.bucket_exists(bucket):
                     self.conn.create_bucket(Bucket=bucket)
-                    logger.info(f"create bucket {bucket} ********")
+                    logging.info(f"create bucket {bucket} ********")
                 r = self.conn.upload_fileobj(BytesIO(binary), bucket, fnm)
 
                 return r
             except Exception:
-                logger.exception(f"Fail put {bucket}/{fnm}")
+                logging.exception(f"Fail put {bucket}/{fnm}")
                 self.__open__()
                 time.sleep(1)
 
@@ -92,7 +93,7 @@ class RAGFlowS3(object):
         try:
             self.conn.delete_object(Bucket=bucket, Key=fnm)
         except Exception:
-            logger.exception(f"Fail rm {bucket}/{fnm}")
+            logging.exception(f"Fail rm {bucket}/{fnm}")
 
     def get(self, bucket, fnm):
         for _ in range(1):
@@ -101,7 +102,7 @@ class RAGFlowS3(object):
                 object_data = r['Body'].read()
                 return object_data
             except Exception:
-                logger.exception(f"fail get {bucket}/{fnm}")
+                logging.exception(f"fail get {bucket}/{fnm}")
                 self.__open__()
                 time.sleep(1)
         return
@@ -128,7 +129,7 @@ class RAGFlowS3(object):
 
                 return r
             except Exception:
-                logger.exception(f"fail get url {bucket}/{fnm}")
+                logging.exception(f"fail get url {bucket}/{fnm}")
                 self.__open__()
                 time.sleep(1)
         return