Feat/add-remote-file-upload-api (#9906)

api/controllers/console/datasets/data_source.py

@@ -7,8 +7,7 @@ from flask_restful import Resource, marshal_with, reqparse
 from werkzeug.exceptions import NotFound
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.indexing_runner import IndexingRunner
 from core.rag.extractor.entity.extract_setting import ExtractSetting
 from core.rag.extractor.notion_extractor import NotionExtractor

api/controllers/console/datasets/datasets.py

@@ -10,8 +10,7 @@ from controllers.console import api
 from controllers.console.apikey import api_key_fields, api_key_list
 from controllers.console.app.error import ProviderNotInitializeError
 from controllers.console.datasets.error import DatasetInUseError, DatasetNameDuplicateError, IndexingEstimateError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.indexing_runner import IndexingRunner
 from core.model_runtime.entities.model_entities import ModelType

api/controllers/console/datasets/datasets_document.py

@@ -24,8 +24,11 @@ from controllers.console.datasets.error import (
     InvalidActionError,
     InvalidMetadataError,
 )
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from core.errors.error import (
     LLMBadRequestError,
     ModelCurrentlyNotSupportError,

api/controllers/console/datasets/datasets_segments.py

@@ -11,11 +11,11 @@ import services
 from controllers.console import api
 from controllers.console.app.error import ProviderNotInitializeError
 from controllers.console.datasets.error import InvalidActionError, NoFileUploadedError, TooManyFilesError
-from controllers.console.setup import setup_required
 from controllers.console.wraps import (
     account_initialization_required,
     cloud_edition_billing_knowledge_limit_check,
     cloud_edition_billing_resource_check,
+    setup_required,
 )
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.model_manager import ModelManager

api/controllers/console/datasets/external.py

@@ -6,8 +6,7 @@ from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 import services
 from controllers.console import api
 from controllers.console.datasets.error import DatasetNameDuplicateError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.dataset_fields import dataset_detail_fields
 from libs.login import login_required
 from services.dataset_service import DatasetService

api/controllers/console/datasets/file.py

@@ -1,105 +0,0 @@
-import urllib.parse
-
-from flask import request
-from flask_login import current_user
-from flask_restful import Resource, marshal_with, reqparse
-
-import services
-from configs import dify_config
-from constants import DOCUMENT_EXTENSIONS
-from controllers.console import api
-from controllers.console.datasets.error import (
-    FileTooLargeError,
-    NoFileUploadedError,
-    TooManyFilesError,
-    UnsupportedFileTypeError,
-)
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
-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 FileService
-
-PREVIEW_WORDS_LIMIT = 3000
-
-
-class FileApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @marshal_with(upload_config_fields)
-    def get(self):
-        return {
-            "file_size_limit": dify_config.UPLOAD_FILE_SIZE_LIMIT,
-            "batch_count_limit": dify_config.UPLOAD_FILE_BATCH_LIMIT,
-            "image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT,
-            "video_file_size_limit": dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT,
-            "audio_file_size_limit": dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT,
-        }, 200
-
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @marshal_with(file_fields)
-    @cloud_edition_billing_resource_check("documents")
-    def post(self):
-        # get file from request
-        file = request.files["file"]
-
-        parser = reqparse.RequestParser()
-        parser.add_argument("source", type=str, required=False, location="args")
-        source = parser.parse_args().get("source")
-
-        # check file
-        if "file" not in request.files:
-            raise NoFileUploadedError()
-
-        if len(request.files) > 1:
-            raise TooManyFilesError()
-        try:
-            upload_file = FileService.upload_file(file=file, user=current_user, source=source)
-        except services.errors.file.FileTooLargeError as file_too_large_error:
-            raise FileTooLargeError(file_too_large_error.description)
-        except services.errors.file.UnsupportedFileTypeError:
-            raise UnsupportedFileTypeError()
-
-        return upload_file, 201
-
-
-class FilePreviewApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def get(self, file_id):
-        file_id = str(file_id)
-        text = FileService.get_file_preview(file_id)
-        return {"content": text}
-
-
-class FileSupportTypeApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def get(self):
-        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>")

api/controllers/console/datasets/hit_testing.py

@@ -2,8 +2,7 @@ from flask_restful import Resource
 
 from controllers.console import api
 from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 
 

api/controllers/console/datasets/website.py

@@ -2,8 +2,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.datasets.error import WebsiteCrawlError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 from services.website_service import WebsiteService