2023-05-15 08:51:32 +08:00
|
|
|
# -*- 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
|
2023-08-12 00:57:00 +08:00
|
|
|
from core.model_providers.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
|
2023-05-15 08:51:32 +08:00
|
|
|
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')
|
2023-09-10 00:12:34 +08:00
|
|
|
parser.add_argument('query', type=str, location='json', default='')
|
2023-11-13 22:05:46 +08:00
|
|
|
parser.add_argument('files', type=list, required=False, location='json')
|
2023-05-15 08:51:32 +08:00
|
|
|
parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
|
2023-09-10 15:17:43 +08:00
|
|
|
parser.add_argument('retriever_from', type=str, required=False, default='web_app', location='json')
|
|
|
|
|
2023-05-15 08:51:32 +08:00
|
|
|
args = parser.parse_args()
|
|
|
|
|
|
|
|
streaming = args['response_mode'] == 'streaming'
|
2023-11-13 22:05:46 +08:00
|
|
|
args['auto_generate_name'] = False
|
2023-05-15 08:51:32 +08:00
|
|
|
|
|
|
|
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()
|
2023-07-17 00:14:19 +08:00
|
|
|
except ProviderTokenNotInitError as ex:
|
|
|
|
raise ProviderNotInitializeError(ex.description)
|
2023-05-15 08:51:32 +08:00
|
|
|
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')
|
2023-11-13 22:05:46 +08:00
|
|
|
parser.add_argument('files', type=list, required=False, location='json')
|
2023-05-15 08:51:32 +08:00
|
|
|
parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
|
|
|
|
parser.add_argument('conversation_id', type=uuid_value, location='json')
|
2023-09-10 15:17:43 +08:00
|
|
|
parser.add_argument('retriever_from', type=str, required=False, default='web_app', location='json')
|
|
|
|
|
2023-05-15 08:51:32 +08:00
|
|
|
args = parser.parse_args()
|
|
|
|
|
|
|
|
streaming = args['response_mode'] == 'streaming'
|
2023-11-13 22:05:46 +08:00
|
|
|
args['auto_generate_name'] = False
|
2023-05-15 08:51:32 +08:00
|
|
|
|
|
|
|
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()
|
2023-07-17 00:14:19 +08:00
|
|
|
except ProviderTokenNotInitError as ex:
|
|
|
|
raise ProviderNotInitializeError(ex.description)
|
2023-05-15 08:51:32 +08:00
|
|
|
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
|
|
|
|
|
|
|
|
|
2023-11-06 19:36:16 +08:00
|
|
|
def compact_response(response: Union[dict, Generator]) -> Response:
|
2023-05-15 08:51:32 +08:00
|
|
|
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"
|
2023-07-17 00:14:19 +08:00
|
|
|
except ProviderTokenNotInitError as ex:
|
|
|
|
yield "data: " + json.dumps(api.handle_error(ProviderNotInitializeError(ex.description)).get_json()) + "\n\n"
|
2023-05-15 08:51:32 +08:00
|
|
|
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/<string:task_id>/stop')
|
|
|
|
api.add_resource(ChatApi, '/chat-messages')
|
|
|
|
api.add_resource(ChatStopApi, '/chat-messages/<string:task_id>/stop')
|