refactor: streamline image handling by updating application and knowledge ID management

Author: liuruibin

apps/application/flow/step_node/document_extract_node/impl/base_document_extract_node.py

@@ -51,28 +51,31 @@ def execute(self, document, chat_id=None, **kwargs):
             return NodeResult({'content': '', 'document_list': []}, {})
 
         # 安全获取 application
-        application = None
+        application_id = None
         if (self.workflow_manage and
                 self.workflow_manage.work_flow_post_handler and
                 self.workflow_manage.work_flow_post_handler.chat_info):
-            application = self.workflow_manage.work_flow_post_handler.chat_info.application
+            application_id = self.workflow_manage.work_flow_post_handler.chat_info.application.id
+        knowledge_id = self.workflow_params.get('knowledge_id')
 
         # doc文件中的图片保存
         def save_image(image_list):
             for image in image_list:
                 meta = {
-                    'debug': False if (application and application.id) else True,
+                    'debug': False if (application_id or knowledge_id) else True,
                     'chat_id': chat_id,
-                    'application_id': str(application.id) if (application and application.id) else None,
+                    'application_id': str(application_id) if application_id else None,
+                    'knowledge_id': str(knowledge_id) if knowledge_id else None,
                     'file_id': str(image.id)
                 }
                 file_bytes = image.meta.pop('content')
                 f = bytes_to_uploaded_file(file_bytes, image.file_name)
                 FileSerializer(data={
                     'file': f,
                     'meta': meta,
-                    'source_id': meta['application_id'],
-                    'source_type': FileSourceType.APPLICATION.value
+                    'source_id': meta['application_id'] if meta['application_id'] else meta['knowledge_id'],
+                    'source_type': FileSourceType.APPLICATION.value if meta[
+                        'application_id'] else FileSourceType.KNOWLEDGE.value
                 }).upload()
 
         document_list = []

apps/application/flow/step_node/document_split_node/impl/base_document_split_node.py

@@ -4,11 +4,9 @@
 from typing import List
 
 from django.core.files.uploadedfile import InMemoryUploadedFile
-from django.db.models import QuerySet
 
 from application.flow.i_step_node import NodeResult
 from application.flow.step_node.document_split_node.i_document_split_node import IDocumentSplitNode
-from knowledge.models import File, FileSourceType
 from knowledge.serializers.document import default_split_handle, FileBufferHandle
 
 
@@ -73,18 +71,7 @@ def execute(self, document_list, knowledge_id, split_strategy, paragraph_title_r
         return NodeResult({'paragraph_list': paragraph_list}, {})
 
     def _save_image(self, image_list):
-        if image_list is not None and len(image_list) > 0:
-            exist_image_list = [str(i.get('id')) for i in
-                                QuerySet(File).filter(id__in=[i.id for i in image_list]).values('id')]
-            save_image_list = [image for image in image_list if not exist_image_list.__contains__(str(image.id))]
-            save_image_list = list({img.id: img for img in save_image_list}.values())
-            # save image
-            for file in save_image_list:
-                file_bytes = file.meta.pop('content')
-                file.meta['knowledge_id'] = self.context.get('knowledge_id')
-                file.source_type = FileSourceType.KNOWLEDGE
-                file.source_id = self.context.get('knowledge_id')
-                file.save(file_bytes)
+        pass
 
     def _process_split_result(
             self, item, knowledge_id, source_file_id, file_name,