dify/api/controllers/web/audio.py

103 lines
4.2 KiB
Python
Raw Normal View History

2023-07-07 17:50:42 +08:00
# -*- coding:utf-8 -*-
import logging
import services
from controllers.web import api
from controllers.web.error import (AppUnavailableError, AudioTooLargeError, CompletionRequestError,
NoAudioUploadedError, ProviderModelCurrentlyNotSupportError,
ProviderNotInitializeError, ProviderNotSupportSpeechToTextError,
ProviderQuotaExceededError, UnsupportedAudioTypeError)
2023-07-07 17:50:42 +08:00
from controllers.web.wraps import WebApiResource
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
from core.model_runtime.errors.invoke import InvokeError
from flask import request
2023-07-07 17:50:42 +08:00
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
2023-07-07 17:50:42 +08:00
class AudioApi(WebApiResource):
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(
2023-07-07 17:50:42 +08:00
tenant_id=app_model.tenant_id,
file=file,
end_user=end_user
2023-07-07 17:50:42 +08:00
)
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()
2023-07-17 00:14:19 +08:00
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
2023-07-07 17:50:42 +08:00
except QuotaExceededError:
raise ProviderQuotaExceededError()
except ModelCurrentlyNotSupportError:
raise ProviderModelCurrentlyNotSupportError()
except InvokeError as e:
2024-01-04 17:49:55 +08:00
raise CompletionRequestError(e.description)
2023-07-07 17:50:42 +08:00
except ValueError as e:
raise e
except Exception as e:
logging.exception("internal server error.")
raise InternalServerError()
class TextApi(WebApiResource):
def post(self, app_model: App, end_user):
try:
response = AudioService.transcript_tts(
tenant_id=app_model.tenant_id,
text=request.form['text'],
end_user=end_user.external_user_id,
streaming=False
)
return {'data': response.data.decode('latin1')}
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')