dify/api/controllers/web/completion.py

184 lines
8.2 KiB
Python
Raw Normal View History

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
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')
parser.add_argument('query', type=str, location='json', default='')
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('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'
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')
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')
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'
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
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')