import logging from flask_restful import Resource, reqparse from werkzeug.exceptions import InternalServerError, NotFound import services from controllers.service_api import api from controllers.service_api.app.error import ( AppUnavailableError, CompletionRequestError, ConversationCompletedError, NotChatAppError, ProviderModelCurrentlyNotSupportError, ProviderNotInitializeError, ProviderQuotaExceededError, ) from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token from core.app.apps.base_app_queue_manager import AppQueueManager from core.app.entities.app_invoke_entities import InvokeFrom from core.errors.error import ( AppInvokeQuotaExceededError, ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError, ) from core.model_runtime.errors.invoke import InvokeError from libs import helper from libs.helper import uuid_value from models.model import App, AppMode, EndUser from services.app_generate_service import AppGenerateService class CompletionApi(Resource): @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True)) def post(self, app_model: App, end_user: EndUser): if app_model.mode != "completion": raise AppUnavailableError() parser = reqparse.RequestParser() parser.add_argument("inputs", type=dict, required=True, location="json") parser.add_argument("query", type=str, location="json", default="") parser.add_argument("files", type=list, required=False, location="json") parser.add_argument("response_mode", type=str, choices=["blocking", "streaming"], location="json") parser.add_argument("retriever_from", type=str, required=False, default="dev", location="json") args = parser.parse_args() streaming = args["response_mode"] == "streaming" args["auto_generate_name"] = False try: response = AppGenerateService.generate( app_model=app_model, user=end_user, args=args, invoke_from=InvokeFrom.SERVICE_API, streaming=streaming, ) return helper.compact_generate_response(response) except services.errors.conversation.ConversationNotExistsError: raise NotFound("Conversation Not Exists.") except services.errors.conversation.ConversationCompletedError: raise ConversationCompletedError() except services.errors.app_model_config.AppModelConfigBrokenError: logging.exception("App model config broken.") raise AppUnavailableError() except ProviderTokenNotInitError as ex: raise ProviderNotInitializeError(ex.description) except QuotaExceededError: raise ProviderQuotaExceededError() except ModelCurrentlyNotSupportError: raise ProviderModelCurrentlyNotSupportError() except InvokeError as e: raise CompletionRequestError(e.description) except (ValueError, AppInvokeQuotaExceededError) as e: raise e except Exception as e: logging.exception("internal server error.") raise InternalServerError() class CompletionStopApi(Resource): @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True)) def post(self, app_model: App, end_user: EndUser, task_id): if app_model.mode != "completion": raise AppUnavailableError() AppQueueManager.set_stop_flag(task_id, InvokeFrom.SERVICE_API, end_user.id) return {"result": "success"}, 200 class ChatApi(Resource): @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True)) def post(self, app_model: App, end_user: EndUser): app_mode = AppMode.value_of(app_model.mode) if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}: raise NotChatAppError() parser = reqparse.RequestParser() parser.add_argument("inputs", type=dict, required=True, location="json") parser.add_argument("query", type=str, required=True, location="json") parser.add_argument("files", type=list, required=False, location="json") parser.add_argument("response_mode", type=str, choices=["blocking", "streaming"], location="json") parser.add_argument("conversation_id", type=uuid_value, location="json") parser.add_argument("retriever_from", type=str, required=False, default="dev", location="json") parser.add_argument("auto_generate_name", type=bool, required=False, default=True, location="json") args = parser.parse_args() streaming = args["response_mode"] == "streaming" try: response = AppGenerateService.generate( app_model=app_model, user=end_user, args=args, invoke_from=InvokeFrom.SERVICE_API, streaming=streaming ) return helper.compact_generate_response(response) except services.errors.conversation.ConversationNotExistsError: raise NotFound("Conversation Not Exists.") except services.errors.conversation.ConversationCompletedError: raise ConversationCompletedError() except services.errors.app_model_config.AppModelConfigBrokenError: logging.exception("App model config broken.") raise AppUnavailableError() except ProviderTokenNotInitError as ex: raise ProviderNotInitializeError(ex.description) except QuotaExceededError: raise ProviderQuotaExceededError() except ModelCurrentlyNotSupportError: raise ProviderModelCurrentlyNotSupportError() except InvokeError as e: raise CompletionRequestError(e.description) except (ValueError, AppInvokeQuotaExceededError) as e: raise e except Exception as e: logging.exception("internal server error.") raise InternalServerError() class ChatStopApi(Resource): @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True)) def post(self, app_model: App, end_user: EndUser, task_id): app_mode = AppMode.value_of(app_model.mode) if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}: raise NotChatAppError() AppQueueManager.set_stop_flag(task_id, InvokeFrom.SERVICE_API, end_user.id) return {"result": "success"}, 200 api.add_resource(CompletionApi, "/completion-messages") api.add_resource(CompletionStopApi, "/completion-messages//stop") api.add_resource(ChatApi, "/chat-messages") api.add_resource(ChatStopApi, "/chat-messages//stop")