# -*- coding:utf-8 -*- import json import logging from typing import Generator, Union from flask import Response, stream_with_context from flask_restful import reqparse from werkzeug.exceptions import InternalServerError, NotFound import services from controllers.web import api from controllers.web.error import AppUnavailableError, ConversationCompletedError, \ ProviderNotInitializeError, NotChatAppError, NotCompletionAppError, CompletionRequestError, \ ProviderQuotaExceededError, ProviderModelCurrentlyNotSupportError from controllers.web.wraps import WebApiResource from core.conversation_message_task import PubHandler from core.model_providers.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \ LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError from libs.helper import uuid_value from services.completion_service import CompletionService # define completion api for user class CompletionApi(WebApiResource): def post(self, app_model, end_user): if app_model.mode != 'completion': raise NotCompletionAppError() 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='web_app', location='json') args = parser.parse_args() streaming = args['response_mode'] == 'streaming' args['auto_generate_name'] = False try: response = CompletionService.completion( app_model=app_model, user=end_user, args=args, from_source='api', streaming=streaming ) return compact_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 (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError, LLMRateLimitError, LLMAuthorizationError) as e: raise CompletionRequestError(str(e)) except ValueError as e: raise e except Exception as e: logging.exception("internal server error.") raise InternalServerError() class CompletionStopApi(WebApiResource): def post(self, app_model, end_user, task_id): if app_model.mode != 'completion': raise NotCompletionAppError() PubHandler.stop(end_user, task_id) return {'result': 'success'}, 200 class ChatApi(WebApiResource): def post(self, app_model, end_user): if app_model.mode != '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='web_app', location='json') args = parser.parse_args() streaming = args['response_mode'] == 'streaming' args['auto_generate_name'] = False try: response = CompletionService.completion( app_model=app_model, user=end_user, args=args, from_source='api', streaming=streaming ) return compact_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 (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError, LLMRateLimitError, LLMAuthorizationError) as e: raise CompletionRequestError(str(e)) except ValueError as e: raise e except Exception as e: logging.exception("internal server error.") raise InternalServerError() class ChatStopApi(WebApiResource): def post(self, app_model, end_user, task_id): if app_model.mode != 'chat': raise NotChatAppError() PubHandler.stop(end_user, task_id) return {'result': 'success'}, 200 def compact_response(response: Union[dict, Generator]) -> Response: if isinstance(response, dict): return Response(response=json.dumps(response), status=200, mimetype='application/json') else: def generate() -> Generator: try: for chunk in response: yield chunk except services.errors.conversation.ConversationNotExistsError: yield "data: " + json.dumps(api.handle_error(NotFound("Conversation Not Exists.")).get_json()) + "\n\n" except services.errors.conversation.ConversationCompletedError: yield "data: " + json.dumps(api.handle_error(ConversationCompletedError()).get_json()) + "\n\n" except services.errors.app_model_config.AppModelConfigBrokenError: logging.exception("App model config broken.") yield "data: " + json.dumps(api.handle_error(AppUnavailableError()).get_json()) + "\n\n" except ProviderTokenNotInitError as ex: yield "data: " + json.dumps(api.handle_error(ProviderNotInitializeError(ex.description)).get_json()) + "\n\n" except QuotaExceededError: yield "data: " + json.dumps(api.handle_error(ProviderQuotaExceededError()).get_json()) + "\n\n" except ModelCurrentlyNotSupportError: yield "data: " + json.dumps(api.handle_error(ProviderModelCurrentlyNotSupportError()).get_json()) + "\n\n" except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError, LLMRateLimitError, LLMAuthorizationError) as e: yield "data: " + json.dumps(api.handle_error(CompletionRequestError(str(e))).get_json()) + "\n\n" except ValueError as e: yield "data: " + json.dumps(api.handle_error(e).get_json()) + "\n\n" except Exception: logging.exception("internal server error.") yield "data: " + json.dumps(api.handle_error(InternalServerError()).get_json()) + "\n\n" return Response(stream_with_context(generate()), status=200, mimetype='text/event-stream') 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')