dify/api/controllers/service_api/app/audio.py
Charlie.Wei 6355e61eb8
tts models support (#2033)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Yeuoly <45712896+Yeuoly@users.noreply.github.com>
2024-01-24 01:05:37 +08:00

108 lines
4.5 KiB
Python

import logging
import services
from controllers.service_api import api
from controllers.service_api.app.error import (AppUnavailableError, AudioTooLargeError, CompletionRequestError,
NoAudioUploadedError, ProviderModelCurrentlyNotSupportError,
ProviderNotInitializeError, ProviderNotSupportSpeechToTextError,
ProviderQuotaExceededError, UnsupportedAudioTypeError)
from controllers.service_api.wraps import AppApiResource
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
from core.model_runtime.errors.invoke import InvokeError
from flask import request
from flask_restful import reqparse
from models.model import App, AppModelConfig
from services.audio_service import AudioService
from services.errors.audio import (AudioTooLargeServiceError, NoAudioUploadedServiceError,
ProviderNotSupportSpeechToTextServiceError, UnsupportedAudioTypeServiceError)
from werkzeug.exceptions import InternalServerError
class AudioApi(AppApiResource):
def post(self, app_model: App, end_user):
app_model_config: AppModelConfig = app_model.app_model_config
if not app_model_config.speech_to_text_dict['enabled']:
raise AppUnavailableError()
file = request.files['file']
try:
response = AudioService.transcript_asr(
tenant_id=app_model.tenant_id,
file=file,
end_user=end_user
)
return response
except services.errors.app_model_config.AppModelConfigBrokenError:
logging.exception("App model config broken.")
raise AppUnavailableError()
except NoAudioUploadedServiceError:
raise NoAudioUploadedError()
except AudioTooLargeServiceError as e:
raise AudioTooLargeError(str(e))
except UnsupportedAudioTypeServiceError:
raise UnsupportedAudioTypeError()
except ProviderNotSupportSpeechToTextServiceError:
raise ProviderNotSupportSpeechToTextError()
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 as e:
raise e
except Exception as e:
logging.exception("internal server error.")
raise InternalServerError()
class TextApi(AppApiResource):
def post(self, app_model: App, end_user):
parser = reqparse.RequestParser()
parser.add_argument('text', type=str, required=True, nullable=False, location='json')
parser.add_argument('user', type=str, required=True, nullable=False, location='json')
args = parser.parse_args()
try:
response = AudioService.transcript_tts(
tenant_id=app_model.tenant_id,
text=args['text'],
end_user=args['user'],
streaming=False
)
return response
except services.errors.app_model_config.AppModelConfigBrokenError:
logging.exception("App model config broken.")
raise AppUnavailableError()
except NoAudioUploadedServiceError:
raise NoAudioUploadedError()
except AudioTooLargeServiceError as e:
raise AudioTooLargeError(str(e))
except UnsupportedAudioTypeServiceError:
raise UnsupportedAudioTypeError()
except ProviderNotSupportSpeechToTextServiceError:
raise ProviderNotSupportSpeechToTextError()
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 as e:
raise e
except Exception as e:
logging.exception("internal server error.")
raise InternalServerError()
api.add_resource(AudioApi, '/audio-to-text')
api.add_resource(TextApi, '/text-to-audio')