dify/api/controllers/console/files.py

from typing import Literal
from uuid import UUID

from flask import request
from flask_restx import Resource
from werkzeug.exceptions import Forbidden

import services
from configs import dify_config
from constants import DOCUMENT_EXTENSIONS
from controllers.common.errors import (
    BlockedFileExtensionError,
    FilenameNotExistsError,
    FileTooLargeError,
    NoFileUploadedError,
    TooManyFilesError,
    UnsupportedFileTypeError,
)
from controllers.common.fields import AllowedExtensionsResponse, TextContentResponse
from controllers.common.schema import JsonResponseWithStatus, register_response_schema_models
from controllers.console import console_ns
from controllers.console.flask_admission import console_account_admission
from controllers.console.wraps import (
    account_initialization_required,
    cloud_edition_billing_resource_check,
    setup_required,
    with_current_user,
)
from extensions.ext_application_services import application_services
from fields.file_fields import FileResponse, UploadConfig
from libs.helper import dump_response
from libs.login import login_required
from machinery.context import RequestContext
from models import Account, UploadFile
from services.feature_service import FeatureService

register_response_schema_models(
    console_ns,
    UploadConfig,
    FileResponse,
    AllowedExtensionsResponse,
    TextContentResponse,
)

PREVIEW_WORDS_LIMIT = 3000

FILE_UPLOAD_PARAMS = {
    "file": {
        "description": "File to upload",
        "in": "formData",
        "type": "file",
        "required": True,
    },
    "source": {
        "description": "Optional upload source",
        "in": "formData",
        "type": "string",
        "enum": ["datasets"],
        "required": False,
    },
}


def upload_file_from_request(*, current_user: Account, resource_tenant_id: str | None = None) -> UploadFile:
    """Validate the multipart request and persist the file under the requested resource tenant."""
    source_str = request.args.get("source") or request.form.get("source")
    source: Literal["datasets"] | None = "datasets" if source_str == "datasets" else None

    if "file" not in request.files:
        raise NoFileUploadedError()

    if len(request.files) > 1:
        raise TooManyFilesError()
    file = request.files["file"]

    if not file.filename:
        raise FilenameNotExistsError()
    if source == "datasets" and not current_user.is_dataset_editor:
        raise Forbidden()

    if source not in ("datasets", None):
        source = None

    default_file_size_limit = (
        FeatureService.get_knowledge_file_size_limit(resource_tenant_id or current_user.current_tenant_id)
        if source == "datasets"
        else None
    )

    try:
        return application_services().files.upload_file(
            filename=file.filename,
            content=file.stream.read(),
            mimetype=file.mimetype,
            user=current_user,
            tenant_id=resource_tenant_id,
            source=source,
            default_file_size_limit=default_file_size_limit,
        )
    except services.errors.file.FileTooLargeError as file_too_large_error:
        raise FileTooLargeError(file_too_large_error.description) from file_too_large_error
    except services.errors.file.UnsupportedFileTypeError as unsupported_file_type_error:
        raise UnsupportedFileTypeError() from unsupported_file_type_error
    except services.errors.file.BlockedFileExtensionError as blocked_extension_error:
        raise BlockedFileExtensionError(blocked_extension_error.description) from blocked_extension_error


@console_ns.route("/files/upload")
class FileApi(Resource):
    @console_ns.response(200, "Success", console_ns.models[UploadConfig.__name__])
    @console_account_admission()
    def get(self, request_context: RequestContext) -> JsonResponseWithStatus:
        config = UploadConfig(
            file_size_limit=dify_config.UPLOAD_FILE_SIZE_LIMIT,
            knowledge_file_size_limit=FeatureService.get_knowledge_file_size_limit(request_context.active_workspace_id),
            batch_count_limit=dify_config.UPLOAD_FILE_BATCH_LIMIT,
            file_upload_limit=dify_config.BATCH_UPLOAD_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,
            skill_file_size_limit=dify_config.UPLOAD_SKILL_FILE_SIZE_LIMIT,
            workflow_file_upload_limit=dify_config.WORKFLOW_FILE_UPLOAD_LIMIT,
            image_file_batch_limit=dify_config.IMAGE_FILE_BATCH_LIMIT,
            single_chunk_attachment_limit=dify_config.SINGLE_CHUNK_ATTACHMENT_LIMIT,
            attachment_image_file_size_limit=dify_config.ATTACHMENT_IMAGE_FILE_SIZE_LIMIT,
        )
        return dump_response(UploadConfig, config), 200

    @setup_required
    @login_required
    @account_initialization_required
    @cloud_edition_billing_resource_check("documents")
    @console_ns.doc(consumes=["multipart/form-data"], params=FILE_UPLOAD_PARAMS)
    @console_ns.response(201, "File uploaded successfully", console_ns.models[FileResponse.__name__])
    @with_current_user
    def post(self, current_user: Account) -> JsonResponseWithStatus:
        upload_file = upload_file_from_request(current_user=current_user)

        return dump_response(FileResponse, upload_file), 201


@console_ns.route("/files/<uuid:file_id>/preview")
class FilePreviewApi(Resource):
    @console_ns.response(200, "Success", console_ns.models[TextContentResponse.__name__])
    @console_account_admission()
    def get(self, request_context: RequestContext, file_id: UUID) -> dict[str, object]:
        current_tenant_id = request_context.active_workspace_id
        file_id_str = str(file_id)
        text = application_services().files.get_file_preview(file_id=file_id_str, tenant_id=current_tenant_id)
        return dump_response(TextContentResponse, {"content": text})


@console_ns.route("/files/support-type")
class FileSupportTypeApi(Resource):
    @console_ns.response(200, "Success", console_ns.models[AllowedExtensionsResponse.__name__])
    @console_account_admission()
    def get(self, _request_context: RequestContext) -> dict[str, object]:
        return dump_response(
            AllowedExtensionsResponse,
            {"allowed_extensions": list(DOCUMENT_EXTENSIONS)},
        )