Merge branch 'main' of https://github.com/maxkb-dev/maxkb

Author: liqiang-fit2cloud

.github/dependabot.yml

@@ -0,0 +1,9 @@
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+      timezone: "Asia/Shanghai"
+      day: "friday"
+    target-branch: "v2"

README.md

@@ -13,7 +13,7 @@
 MaxKB = Max Knowledge Brain, it is a powerful and easy-to-use AI assistant that integrates Retrieval-Augmented Generation (RAG) pipelines, supports robust workflows, and provides advanced MCP tool-use capabilities. MaxKB is widely applied in scenarios such as intelligent customer service, corporate internal knowledge bases, academic research, and education.
 
 - **RAG Pipeline**: Supports direct uploading of documents / automatic crawling of online documents, with features for automatic text splitting, vectorization. This effectively reduces hallucinations in large models, providing a superior smart Q&A interaction experience.
-- **Flexible Orchestration**: Equipped with a powerful workflow engine, function library and MCP tool-use, enabling the orchestration of AI processes to meet the needs of complex business scenarios. 
+- **Agentic Workflow**: Equipped with a powerful workflow engine, function library and MCP tool-use, enabling the orchestration of AI processes to meet the needs of complex business scenarios. 
 - **Seamless Integration**: Facilitates zero-coding rapid integration into third-party business systems, quickly equipping existing systems with intelligent Q&A capabilities to enhance user satisfaction.
 - **Model-Agnostic**: Supports various large models, including private models (such as DeepSeek, Llama, Qwen, etc.) and public models (like OpenAI, Claude, Gemini, etc.).
 - **Multi Modal**: Native support for input and output text, image, audio and video.

apps/application/flow/step_node/start_node/impl/base_start_node.py

@@ -40,6 +40,7 @@ def save_context(self, details, workflow_manage):
         self.context['document'] = details.get('document_list')
         self.context['image'] = details.get('image_list')
         self.context['audio'] = details.get('audio_list')
+        self.context['other'] = details.get('other_list')
         self.status = details.get('status')
         self.err_message = details.get('err_message')
         for key, value in workflow_variable.items():
@@ -59,7 +60,8 @@ def execute(self, question, **kwargs) -> NodeResult:
             'question': question,
             'image': self.workflow_manage.image_list,
             'document': self.workflow_manage.document_list,
-            'audio': self.workflow_manage.audio_list
+            'audio': self.workflow_manage.audio_list,
+            'other': self.workflow_manage.other_list,
         }
         return NodeResult(node_variable, workflow_variable)
 
@@ -83,5 +85,6 @@ def get_details(self, index: int, **kwargs):
             'image_list': self.context.get('image'),
             'document_list': self.context.get('document'),
             'audio_list': self.context.get('audio'),
+            'other_list': self.context.get('other'),
             'global_fields': global_fields
         }

apps/application/flow/workflow_manage.py

@@ -238,6 +238,7 @@ def __init__(self, flow: Flow, params, work_flow_post_handler: WorkFlowPostHandl
                  base_to_response: BaseToResponse = SystemToResponse(), form_data=None, image_list=None,
                  document_list=None,
                  audio_list=None,
+                 other_list=None,
                  start_node_id=None,
                  start_node_data=None, chat_record=None, child_node=None):
         if form_data is None:
@@ -248,12 +249,15 @@ def __init__(self, flow: Flow, params, work_flow_post_handler: WorkFlowPostHandl
             document_list = []
         if audio_list is None:
             audio_list = []
+        if other_list is None:
+            other_list = []
         self.start_node_id = start_node_id
         self.start_node = None
         self.form_data = form_data
         self.image_list = image_list
         self.document_list = document_list
         self.audio_list = audio_list
+        self.other_list = other_list
         self.params = params
         self.flow = flow
         self.context = {}

apps/application/models/application.py

@@ -11,7 +11,7 @@
 from django.contrib.postgres.fields import ArrayField
 from django.db import models
 from langchain.schema import HumanMessage, AIMessage
-
+from django.utils.translation import gettext as _
 from common.encoder.encoder import SystemEncoder
 from common.mixins.app_model_mixin import AppModelMixin
 from dataset.models.data_set import DataSet
@@ -167,7 +167,11 @@ def get_human_message(self):
         return HumanMessage(content=self.problem_text)
 
     def get_ai_message(self):
-        return AIMessage(content=self.answer_text)
+        answer_text = self.answer_text
+        if answer_text is None or len(str(answer_text).strip()) == 0:
+            answer_text = _(
+                'Sorry, no relevant content was found. Please re-describe your problem or provide more information. ')
+        return AIMessage(content=answer_text)
 
     def get_node_details_runtime_node_id(self, runtime_node_id):
         return self.details.get(runtime_node_id, None)

apps/application/serializers/chat_message_serializers.py

@@ -213,12 +213,21 @@ def get_message(instance):
         return instance.get('messages')[-1].get('content')
 
     @staticmethod
-    def generate_chat(chat_id, application_id, message, client_id):
+    def generate_chat(chat_id, application_id, message, client_id, asker=None):
         if chat_id is None:
             chat_id = str(uuid.uuid1())
         chat = QuerySet(Chat).filter(id=chat_id).first()
         if chat is None:
-            Chat(id=chat_id, application_id=application_id, abstract=message[0:1024], client_id=client_id).save()
+            asker_dict = {'user_name': '游客'}
+            if asker is not None:
+                if isinstance(asker, str):
+                    asker_dict = {
+                        'user_name': asker
+                    }
+                elif isinstance(asker, dict):
+                    asker_dict = asker
+            Chat(id=chat_id, application_id=application_id, abstract=message[0:1024], client_id=client_id,
+                 asker=asker_dict).save()
         return chat_id
 
     def chat(self, instance: Dict, with_valid=True):
@@ -232,7 +241,8 @@ def chat(self, instance: Dict, with_valid=True):
         application_id = self.data.get('application_id')
         client_id = self.data.get('client_id')
         client_type = self.data.get('client_type')
-        chat_id = self.generate_chat(chat_id, application_id, message, client_id)
+        chat_id = self.generate_chat(chat_id, application_id, message, client_id,
+                                     asker=instance.get('form_data', {}).get("asker"))
         return ChatMessageSerializer(
             data={
                 'chat_id': chat_id, 'message': message,
@@ -245,6 +255,7 @@ def chat(self, instance: Dict, with_valid=True):
                 'image_list': instance.get('image_list', []),
                 'document_list': instance.get('document_list', []),
                 'audio_list': instance.get('audio_list', []),
+                'other_list': instance.get('other_list', []),
             }
         ).chat(base_to_response=OpenaiToResponse())
 
@@ -274,6 +285,7 @@ class ChatMessageSerializer(serializers.Serializer):
     image_list = serializers.ListField(required=False, error_messages=ErrMessage.list(_("picture")))
     document_list = serializers.ListField(required=False, error_messages=ErrMessage.list(_("document")))
     audio_list = serializers.ListField(required=False, error_messages=ErrMessage.list(_("Audio")))
+    other_list = serializers.ListField(required=False, error_messages=ErrMessage.list(_("Other")))
     child_node = serializers.DictField(required=False, allow_null=True,
                                        error_messages=ErrMessage.dict(_("Child Nodes")))
 
@@ -372,6 +384,7 @@ def chat_work_flow(self, chat_info: ChatInfo, base_to_response):
         image_list = self.data.get('image_list')
         document_list = self.data.get('document_list')
         audio_list = self.data.get('audio_list')
+        other_list = self.data.get('other_list')
         user_id = chat_info.application.user_id
         chat_record_id = self.data.get('chat_record_id')
         chat_record = None
@@ -388,7 +401,7 @@ def chat_work_flow(self, chat_info: ChatInfo, base_to_response):
                                            'client_id': client_id,
                                            'client_type': client_type,
                                            'user_id': user_id}, WorkFlowPostHandler(chat_info, client_id, client_type),
-                                          base_to_response, form_data, image_list, document_list, audio_list,
+                                          base_to_response, form_data, image_list, document_list, audio_list, other_list,
                                           self.data.get('runtime_node_id'),
                                           self.data.get('node_data'), chat_record, self.data.get('child_node'))
         r = work_flow_manage.run()

apps/application/views/chat_views.py

@@ -144,6 +144,8 @@ def post(self, request: Request, chat_id: str):
                                                    'document_list') if 'document_list' in request.data else [],
                                                'audio_list': request.data.get(
                                                    'audio_list') if 'audio_list' in request.data else [],
+                                               'other_list': request.data.get(
+                                                   'other_list') if 'other_list' in request.data else [],
                                                'client_type': request.auth.client_type,
                                                'node_id': request.data.get('node_id', None),
                                                'runtime_node_id': request.data.get('runtime_node_id', None),

apps/common/handle/impl/doc_split_handle.py

@@ -112,11 +112,7 @@ def get_image_id(image_id):
 
 title_font_list = [
     [36, 100],
-    [26, 36],
-    [24, 26],
-    [22, 24],
-    [18, 22],
-    [16, 18]
+    [30, 36]
 ]
 
 
@@ -130,7 +126,7 @@ def get_title_level(paragraph: Paragraph):
         if len(paragraph.runs) == 1:
             font_size = paragraph.runs[0].font.size
             pt = font_size.pt
-            if pt >= 16:
+            if pt >= 30:
                 for _value, index in zip(title_font_list, range(len(title_font_list))):
                     if pt >= _value[0] and pt < _value[1]:
                         return index + 1

apps/locales/zh_CN/LC_MESSAGES/django.po

@@ -4536,7 +4536,7 @@ msgstr "修改知识库信息"
 #: community/apps/dataset/views/document.py:463
 #: community/apps/dataset/views/document.py:464
 msgid "Get the knowledge base paginated list"
-msgstr "获取知识库分页列表"
+msgstr "获取知识库文档分页列表"
 
 #: community/apps/dataset/views/document.py:31
 #: community/apps/dataset/views/document.py:32

apps/locales/zh_Hant/LC_MESSAGES/django.po

@@ -4545,7 +4545,7 @@ msgstr "修改知識庫信息"
 #: community/apps/dataset/views/document.py:463
 #: community/apps/dataset/views/document.py:464
 msgid "Get the knowledge base paginated list"
-msgstr "獲取知識庫分頁列表"
+msgstr "獲取知識庫文档分頁列表"
 
 #: community/apps/dataset/views/document.py:31
 #: community/apps/dataset/views/document.py:32