feat/enhance the multi-modal support (#8818)

api/controllers/console/datasets/data_source.py

@@ -15,8 +15,7 @@ from core.rag.extractor.notion_extractor import NotionExtractor
 from extensions.ext_database import db
 from fields.data_source_fields import integrate_list_fields, integrate_notion_info_list_fields
 from libs.login import login_required
-from models.dataset import Document
-from models.source import DataSourceOauthBinding
+from models import DataSourceOauthBinding, Document
 from services.dataset_service import DatasetService, DocumentService
 from tasks.document_indexing_sync_task import document_indexing_sync_task
 

api/controllers/console/datasets/datasets.py

@@ -24,8 +24,8 @@ from fields.app_fields import related_app_list
 from fields.dataset_fields import dataset_detail_fields, dataset_query_detail_fields
 from fields.document_fields import document_status_fields
 from libs.login import login_required
-from models.dataset import Dataset, DatasetPermissionEnum, Document, DocumentSegment
-from models.model import ApiToken, UploadFile
+from models import ApiToken, Dataset, Document, DocumentSegment, UploadFile
+from models.dataset import DatasetPermissionEnum
 from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
 
 

api/controllers/console/datasets/datasets_document.py

@@ -46,8 +46,7 @@ from fields.document_fields import (
     document_with_segments_fields,
 )
 from libs.login import login_required
-from models.dataset import Dataset, DatasetProcessRule, Document, DocumentSegment
-from models.model import UploadFile
+from models import Dataset, DatasetProcessRule, Document, DocumentSegment, UploadFile
 from services.dataset_service import DatasetService, DocumentService
 from tasks.add_document_to_index_task import add_document_to_index_task
 from tasks.remove_document_from_index_task import remove_document_from_index_task

api/controllers/console/datasets/datasets_segments.py

@@ -24,7 +24,7 @@ from extensions.ext_database import db
 from extensions.ext_redis import redis_client
 from fields.segment_fields import segment_fields
 from libs.login import login_required
-from models.dataset import DocumentSegment
+from models import DocumentSegment
 from services.dataset_service import DatasetService, DocumentService, SegmentService
 from tasks.batch_create_segment_to_index_task import batch_create_segment_to_index_task
 from tasks.disable_segment_from_index_task import disable_segment_from_index_task

api/controllers/console/datasets/file.py

@@ -1,9 +1,12 @@
+import urllib.parse
+
 from flask import request
 from flask_login import current_user
 from flask_restful import Resource, marshal_with
 
 import services
 from configs import dify_config
+from constants import DOCUMENT_EXTENSIONS
 from controllers.console import api
 from controllers.console.datasets.error import (
     FileTooLargeError,
@@ -13,9 +16,10 @@ from controllers.console.datasets.error import (
 )
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
-from fields.file_fields import file_fields, upload_config_fields
+from core.helper import ssrf_proxy
+from fields.file_fields import file_fields, remote_file_info_fields, upload_config_fields
 from libs.login import login_required
-from services.file_service import ALLOWED_EXTENSIONS, UNSTRUCTURED_ALLOWED_EXTENSIONS, FileService
+from services.file_service import FileService
 
 PREVIEW_WORDS_LIMIT = 3000
 
@@ -51,7 +55,7 @@ class FileApi(Resource):
         if len(request.files) > 1:
             raise TooManyFilesError()
         try:
-            upload_file = FileService.upload_file(file, current_user)
+            upload_file = FileService.upload_file(file=file, user=current_user)
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)
         except services.errors.file.UnsupportedFileTypeError:
@@ -75,11 +79,24 @@ class FileSupportTypeApi(Resource):
     @login_required
     @account_initialization_required
     def get(self):
-        etl_type = dify_config.ETL_TYPE
-        allowed_extensions = UNSTRUCTURED_ALLOWED_EXTENSIONS if etl_type == "Unstructured" else ALLOWED_EXTENSIONS
-        return {"allowed_extensions": allowed_extensions}
+        return {"allowed_extensions": DOCUMENT_EXTENSIONS}
+
+
+class RemoteFileInfoApi(Resource):
+    @marshal_with(remote_file_info_fields)
+    def get(self, url):
+        decoded_url = urllib.parse.unquote(url)
+        try:
+            response = ssrf_proxy.head(decoded_url)
+            return {
+                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
+                "file_length": int(response.headers.get("Content-Length", 0)),
+            }
+        except Exception as e:
+            return {"error": str(e)}, 400
 
 
 api.add_resource(FileApi, "/files/upload")
 api.add_resource(FilePreviewApi, "/files/<uuid:file_id>/preview")
 api.add_resource(FileSupportTypeApi, "/files/support-type")
+api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")