feat: enhance file upload with source_id and source_type metadata

Author: liuruibin

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

@@ -7,7 +7,7 @@
 
 from application.flow.i_step_node import NodeResult
 from application.flow.step_node.document_extract_node.i_document_extract_node import IDocumentExtractNode
-from knowledge.models import File
+from knowledge.models import File, FileSourceType
 from knowledge.serializers.document import split_handles, parse_table_handle_list, FileBufferHandle
 from oss.serializers.file import FileSerializer
 
@@ -62,7 +62,12 @@ def save_image(image_list):
                     'file_id': str(image.id)
                 }
                 file = bytes_to_uploaded_file(image.image, image.image_name)
-                FileSerializer(data={'file': file, 'meta': meta}).upload()
+                FileSerializer(data={
+                    'file': file,
+                    'meta': meta,
+                    'source_id': meta['application_id'],
+                    'source_type': FileSourceType.APPLICATION.value
+                }).upload()
 
         for doc in document:
             file = QuerySet(File).filter(id=doc['file_id']).first()

apps/application/flow/step_node/image_generate_step_node/impl/base_image_generate_node.py

@@ -8,6 +8,7 @@
 from application.flow.i_step_node import NodeResult
 from application.flow.step_node.image_generate_step_node.i_image_generate_node import IImageGenerateNode
 from common.utils.common import bytes_to_uploaded_file
+from knowledge.models import FileSourceType
 from oss.serializers.file import FileSerializer
 from models_provider.tools import get_model_instance_by_model_workspace_id
 
@@ -45,7 +46,12 @@ def execute(self, model_id, prompt, negative_prompt, dialogue_number, dialogue_t
                 'chat_id': chat_id,
                 'application_id': str(application.id) if application.id else None,
             }
-            file_url = FileSerializer(data={'file': file, 'meta': meta}).upload()
+            file_url = FileSerializer(data={
+                'file': file,
+                'meta': meta,
+                'source_id': meta['application_id'],
+                'source_type': FileSourceType.APPLICATION.value
+            }).upload()
             file_urls.append(file_url)
         self.context['image_list'] = [{'file_id': path.split('/')[-1], 'url': path} for path in file_urls]
         answer = ' '.join([f"![Image]({path})" for path in file_urls])

apps/application/flow/step_node/text_to_speech_step_node/impl/base_text_to_speech_node.py

@@ -6,6 +6,7 @@
 
 from application.flow.i_step_node import NodeResult
 from application.flow.step_node.text_to_speech_step_node.i_text_to_speech_node import ITextToSpeechNode
+from knowledge.models import FileSourceType
 from models_provider.tools import get_model_instance_by_model_workspace_id
 from oss.serializers.file import FileSerializer
 
@@ -55,7 +56,12 @@ def execute(self, tts_model_id, chat_id,
             'chat_id': chat_id,
             'application_id': str(application.id) if application.id else None,
         }
-        file_url = FileSerializer(data={'file': file, 'meta': meta}).upload()
+        file_url = FileSerializer(data={
+            'file': file,
+            'meta': meta,
+            'source_id': meta['application_id'],
+            'source_type': FileSourceType.APPLICATION.value
+        }).upload()
         # 拼接一个audio标签的src属性
         audio_label = f'<audio src="{file_url}" controls style = "width: 300px; height: 43px"></audio>'
         file_id = file_url.split('/')[-1]