refine log format (#312)

### What problem does this PR solve?

Issue link:#264
### Type of change


- [x] Documentation Update
- [x] Refactoring

README.md

@@ -65,7 +65,7 @@
 
 - CPU >= 2 cores
 - RAM >= 8 GB
-- Docker >= 24.0.0
+- Docker >= 24.0.0 & Docker Compose >= v2.26.1
   > If you have not installed Docker on your local machine (Windows, Mac, or Linux), see [Install Docker Engine](https://docs.docker.com/engine/install/).
 
 ### 🚀 Start up the server

README_ja.md

@@ -65,7 +65,7 @@
 
 - CPU >= 2 cores
 - RAM >= 8 GB
-- Docker >= 24.0.0
+- Docker >= 24.0.0 & Docker Compose >= v2.26.1
   > ローカルマシン（Windows、Mac、または Linux）に Docker をインストールしていない場合は、[Docker Engine のインストール](https://docs.docker.com/engine/install/) を参照してください。
 
 ### 🚀 サーバーを起動

README_zh.md

@@ -65,7 +65,7 @@
 
 - CPU >= 2 核
 - RAM >= 8 GB
-- Docker >= 24.0.0
+- Docker >= 24.0.0 & Docker Compose >= v2.26.1
   > 如果你并没有在本机安装 Docker（Windows、Mac，或者 Linux）, 可以参考文档 [Install Docker Engine](https://docs.docker.com/engine/install/) 自行安装。
 
 ### 🚀 启动服务器

api/db/db_models.py

@@ -695,7 +695,7 @@ class Dialog(DataBaseModel):
     language = CharField(
         max_length=32,
         null=True,
-        default="English",
+        default="Chinese",
         help_text="English|Chinese")
     llm_id = CharField(max_length=32, null=False, help_text="default llm ID")
     llm_setting = JSONField(null=False, default={"temperature": 0.1, "top_p": 0.3, "frequency_penalty": 0.7,

api/settings.py

@@ -13,15 +13,8 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-import logging
-
-from rag.utils import ELASTICSEARCH
-from rag.nlp import search
 import os
-
 from enum import IntEnum, Enum
-
-from api.utils import get_base_config, decrypt_database_config
 from api.utils.file_utils import get_project_base_directory
 from api.utils.log_utils import LoggerFactory, getLogger
 
@@ -32,13 +25,16 @@ LoggerFactory.set_directory(
         "logs",
         "api"))
 # {CRITICAL: 50, FATAL:50, ERROR:40, WARNING:30, WARN:30, INFO:20, DEBUG:10, NOTSET:0}
-LoggerFactory.LEVEL = 10
+LoggerFactory.LEVEL = 30
 
 stat_logger = getLogger("stat")
 access_logger = getLogger("access")
 database_logger = getLogger("database")
 chat_logger = getLogger("chat")
-database_logger.setLevel(logging.WARNING)
+
+from rag.utils import ELASTICSEARCH
+from rag.nlp import search
+from api.utils import get_base_config, decrypt_database_config
 
 API_VERSION = "v1"
 RAG_FLOW_SERVICE_NAME = "ragflow"
@@ -79,7 +75,7 @@ default_llm = {
         "image2text_model": "glm-4v",
         "asr_model": "",
     },
-    "Local": {
+    "Ollama": {
         "chat_model": "qwen-14B-chat",
         "embedding_model": "flag-embedding",
         "image2text_model": "",

api/utils/log_utils.py

@@ -26,7 +26,8 @@ from api.utils import file_utils
 
 class LoggerFactory(object):
     TYPE = "FILE"
-    LOG_FORMAT = "[%(levelname)s] [%(asctime)s] [jobId] [%(process)s:%(thread)s] - [%(module)s.%(funcName)s] [line:%(lineno)d]: %(message)s"
+    LOG_FORMAT = "[%(levelname)s] [%(asctime)s] [%(module)s.%(funcName)s] [line:%(lineno)d]: %(message)s"
+    logging.basicConfig(format=LOG_FORMAT)
     LEVEL = logging.DEBUG
     logger_dict = {}
     global_handler_dict = {}

rag/app/book.py

@@ -110,7 +110,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
         [t for t in random_choices([t for t, _ in sections], k=100)])
     if bull >= 0:
         chunks = ["\n".join(ck)
-                  for ck in hierarchical_merge(bull, sections, 3)]
+                  for ck in hierarchical_merge(bull, sections, 5)]
     else:
         sections = [s.split("@") for s, _ in sections]
         sections = [(pr[0], "@" + pr[1]) for pr in sections if len(pr) == 2]

rag/app/laws.py

@@ -133,7 +133,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
 
     make_colon_as_title(sections)
     bull = bullets_category(sections)
-    chunks = hierarchical_merge(bull, sections, 3)
+    chunks = hierarchical_merge(bull, sections, 5)
     if not chunks:
         callback(0.99, "No chunk parsed out.")
 

rag/llm/chat_model.py

@@ -98,7 +98,7 @@ class QWenChat(Base):
         tk_count = 0
         if response.status_code == HTTPStatus.OK:
             ans += response.output.choices[0]['message']['content']
-            tk_count += response.usage.output_tokens
+            tk_count += response.usage.total_tokens
             if response.output.choices[0].get("finish_reason", "") == "length":
                 ans += "...\nFor the content length reason, it stopped, continue?" if is_english(
                     [ans]) else "······\n由于长度的原因，回答被截断了，要继续吗？"