refactor: file to oss

Author: wxg0103

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

@@ -9,7 +9,7 @@
 from application.flow.step_node.document_extract_node.i_document_extract_node import IDocumentExtractNode
 from knowledge.models import File
 from knowledge.serializers.document import split_handles, parse_table_handle_list, FileBufferHandle
-from knowledge.serializers.file import FileSerializer
+from oss.serializers.file import FileSerializer
 
 
 def bytes_to_uploaded_file(file_bytes, file_name="file.txt"):

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

@@ -8,7 +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.serializers.file import FileSerializer
+from oss.serializers.file import FileSerializer
 from models_provider.tools import get_model_instance_by_model_user_id
 
 

apps/application/flow/step_node/image_understand_step_node/impl/base_image_understand_node.py

@@ -130,7 +130,7 @@ def generate_history_human_message_for_details(self, chat_record):
                 file_id_list = [image.get('file_id') for image in image_list]
                 return HumanMessage(content=[
                     {'type': 'text', 'text': data['question']},
-                    *[{'type': 'image_url', 'image_url': {'url': f'/api/file/{file_id}'}} for file_id in file_id_list]
+                    *[{'type': 'image_url', 'image_url': {'url': f'/oss/file/{file_id}'}} for file_id in file_id_list]
 
                 ])
         return HumanMessage(content=chat_record.problem_text)

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

@@ -6,7 +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.serializers.file import FileSerializer
+from oss.serializers.file import FileSerializer
 from models_provider.tools import get_model_instance_by_model_user_id
 
 

apps/common/handle/impl/table/xlsx_parse_table_handle.py

@@ -110,7 +110,7 @@ def get_content(self, file, save_image):
 
                 md_tables += md_table + '\n\n'
 
-                md_tables = md_tables.replace('/api/image/', '/api/file/')
+                md_tables = md_tables.replace('/api/image/', '/oss/file/')
             return md_tables
         except Exception as e:
             max_kb.error(f'excel split handle error: {e}')

apps/common/handle/impl/text/doc_split_handle.py

@@ -226,7 +226,7 @@ def get_content(self, file, save_image):
             doc = Document(io.BytesIO(buffer))
             content = self.to_md(doc, image_list, get_image_id_func())
             if len(image_list) > 0:
-                content = content.replace('/api/image/', '/api/file/')
+                content = content.replace('/api/image/', '/oss/file/')
                 save_image(image_list)
             return content
         except BaseException as e:

apps/knowledge/serializers/common.py

@@ -167,8 +167,8 @@ def write_image(zip_path: str, image_list: List[str]):
         search = re.search("\(.*\)", image)
         if search:
             text = search.group()
-            if text.startswith('(/api/file/'):
-                r = text.replace('(/api/file/', '').replace(')', '')
+            if text.startswith('(/oss/file/'):
+                r = text.replace('(/oss/file/', '').replace(')', '')
                 r = r.strip().split(" ")[0]
                 if not is_valid_uuid(r):
                     break

apps/knowledge/serializers/document.py

@@ -46,7 +46,6 @@
     TaskType, File, FileSourceType
 from knowledge.serializers.common import ProblemParagraphManage, BatchSerializer, \
     get_embedding_model_id_by_knowledge_id, MetaSerializer, write_image, zip_dir
-from knowledge.serializers.file import FileSerializer
 from knowledge.serializers.paragraph import ParagraphSerializers, ParagraphInstanceSerializer, \
     delete_problems_and_mappings
 from knowledge.task.embedding import embedding_by_document, delete_embedding_by_document_list, \
@@ -56,6 +55,7 @@
 from knowledge.task.sync import sync_web_document
 from maxkb.const import PROJECT_DIR
 from models_provider.models import Model
+from oss.serializers.file import FileSerializer
 
 default_split_handle = TextSplitHandle()
 split_handles = [

apps/knowledge/urls.py

@@ -56,7 +56,5 @@
     path('workspace/<str:workspace_id>/knowledge/<str:knowledge_id>/problem/<int:current_page>/<int:page_size>', views.ProblemView.Page.as_view()),
     path('workspace/<str:workspace_id>/knowledge/<str:knowledge_id>/document/<int:current_page>/<int:page_size>', views.DocumentView.Page.as_view()),
     path('workspace/<str:workspace_id>/knowledge/<int:current_page>/<int:page_size>', views.KnowledgeView.Page.as_view()),
-    path('file', views.FileView.as_view()),
-    path('file/<str:file_id>', views.FileView.Operate.as_view()),
 
 ]

apps/knowledge/views/__init__.py

@@ -2,4 +2,3 @@
 from .knowledge import *
 from .paragraph import *
 from .problem import *
-from .file import *