jyapayne/dify
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat:add tts-streaming config and future (#5492)

Browse source
This commit is contained in:
chenxu9741 2024-07-09 11:33:58 +08:00 • committed by GitHub
commit 6ef401a9f0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
44 changed files with 1280 additions and 358 deletions
Download patch file Download diff file Expand all files Collapse all files

31
api/controllers/console/app/audio.py
View file

@ -81,15 +81,36 @@ class ChatMessageTextApi(Resource):
@account_initialization_required
@get_app_model
def post(self, app_model):
from werkzeug.exceptions import InternalServerError
try:
parser = reqparse.RequestParser()
parser.add_argument('message_id', type=str, location='json')
parser.add_argument('text', type=str, location='json')
parser.add_argument('voice', type=str, location='json')
parser.add_argument('streaming', type=bool, location='json')
args = parser.parse_args()
message_id = args.get('message_id', None)
text = args.get('text', None)
if (app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
and app_model.workflow
and app_model.workflow.features_dict):
text_to_speech = app_model.workflow.features_dict.get('text_to_speech')
voice = args.get('voice') if args.get('voice') else text_to_speech.get('voice')
else:
try:
voice = args.get('voice') if args.get('voice') else app_model.app_model_config.text_to_speech_dict.get(
'voice')
except Exception:
voice = None
response = AudioService.transcript_tts(
app_model=app_model,
text=request.form['text'],
voice=request.form['voice'],
streaming=False
text=text,
message_id=message_id,
voice=voice
)
return {'data': response.data.decode('latin1')}
return response
except services.errors.app_model_config.AppModelConfigBrokenError:
logging.exception("App model config broken.")
raise AppUnavailableError()

30
api/controllers/console/explore/audio.py
View file

@ -19,6 +19,7 @@ from controllers.console.app.error import (
from controllers.console.explore.wraps import InstalledAppResource
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
from core.model_runtime.errors.invoke import InvokeError
from models.model import AppMode
from services.audio_service import AudioService
from services.errors.audio import (
AudioTooLargeServiceError,
@ -70,16 +71,33 @@ class ChatAudioApi(InstalledAppResource):
class ChatTextApi(InstalledAppResource):
def post(self, installed_app):
app_model = installed_app.app
from flask_restful import reqparse
app_model = installed_app.app
try:
parser = reqparse.RequestParser()
parser.add_argument('message_id', type=str, required=False, location='json')
parser.add_argument('voice', type=str, location='json')
parser.add_argument('streaming', type=bool, location='json')
args = parser.parse_args()
message_id = args.get('message_id')
if (app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
and app_model.workflow
and app_model.workflow.features_dict):
text_to_speech = app_model.workflow.features_dict.get('text_to_speech')
voice = args.get('voice') if args.get('voice') else text_to_speech.get('voice')
else:
try:
voice = args.get('voice') if args.get('voice') else app_model.app_model_config.text_to_speech_dict.get('voice')
except Exception:
voice = None
response = AudioService.transcript_tts(
app_model=app_model,
text=request.form['text'],
voice=request.form['voice'] if request.form.get('voice') else app_model.app_model_config.text_to_speech_dict.get('voice'),
streaming=False
message_id=message_id,
voice=voice
)
return {'data': response.data.decode('latin1')}
return response
except services.errors.app_model_config.AppModelConfigBrokenError:
logging.exception("App model config broken.")
raise AppUnavailableError()
@ -108,3 +126,5 @@ class ChatTextApi(InstalledAppResource):
api.add_resource(ChatAudioApi, '/installed-apps/<uuid:installed_app_id>/audio-to-text', endpoint='installed_app_audio')
api.add_resource(ChatTextApi, '/installed-apps/<uuid:installed_app_id>/text-to-audio', endpoint='installed_app_text')
# api.add_resource(ChatTextApiWithMessageId, '/installed-apps/<uuid:installed_app_id>/text-to-audio/message-id',
# endpoint='installed_app_text_with_message_id')

33
api/controllers/service_api/app/audio.py
View file

@ -20,7 +20,7 @@ from controllers.service_api.app.error import (
from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
from core.model_runtime.errors.invoke import InvokeError
from models.model import App, EndUser
from models.model import App, AppMode, EndUser
from services.audio_service import AudioService
from services.errors.audio import (
AudioTooLargeServiceError,
@ -72,19 +72,30 @@ class AudioApi(Resource):
class TextApi(Resource):
@validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON))
def post(self, app_model: App, end_user: EndUser):
parser = reqparse.RequestParser()
parser.add_argument('text', type=str, required=True, nullable=False, location='json')
parser.add_argument('voice', type=str, location='json')
parser.add_argument('streaming', type=bool, required=False, nullable=False, location='json')
args = parser.parse_args()
try:
parser = reqparse.RequestParser()
parser.add_argument('message_id', type=str, required=False, location='json')
parser.add_argument('voice', type=str, location='json')
parser.add_argument('streaming', type=bool, location='json')
args = parser.parse_args()
message_id = args.get('message_id')
if (app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
and app_model.workflow
and app_model.workflow.features_dict):
text_to_speech = app_model.workflow.features_dict.get('text_to_speech')
voice = args.get('voice') if args.get('voice') else text_to_speech.get('voice')
else:
try:
voice = args.get('voice') if args.get('voice') else app_model.app_model_config.text_to_speech_dict.get(
'voice')
except Exception:
voice = None
response = AudioService.transcript_tts(
app_model=app_model,
text=args['text'],
end_user=end_user,
voice=args.get('voice'),
streaming=args['streaming']
message_id=message_id,
end_user=end_user.external_user_id,
voice=voice
)
return response

29
api/controllers/web/audio.py
View file

@ -19,7 +19,7 @@ from controllers.web.error import (
from controllers.web.wraps import WebApiResource
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
from core.model_runtime.errors.invoke import InvokeError
from models.model import App
from models.model import App, AppMode
from services.audio_service import AudioService
from services.errors.audio import (
AudioTooLargeServiceError,
@ -69,16 +69,35 @@ class AudioApi(WebApiResource):
class TextApi(WebApiResource):
def post(self, app_model: App, end_user):
from flask_restful import reqparse
try:
parser = reqparse.RequestParser()
parser.add_argument('message_id', type=str, required=False, location='json')
parser.add_argument('voice', type=str, location='json')
parser.add_argument('streaming', type=bool, location='json')
args = parser.parse_args()
message_id = args.get('message_id')
if (app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
and app_model.workflow
and app_model.workflow.features_dict):
text_to_speech = app_model.workflow.features_dict.get('text_to_speech')
voice = args.get('voice') if args.get('voice') else text_to_speech.get('voice')
else:
try:
voice = args.get('voice') if args.get(
'voice') else app_model.app_model_config.text_to_speech_dict.get('voice')
except Exception:
voice = None
response = AudioService.transcript_tts(
app_model=app_model,
text=request.form['text'],
message_id=message_id,
end_user=end_user.external_user_id,
voice=request.form['voice'] if request.form.get('voice') else None,
streaming=False
voice=voice
)
return {'data': response.data.decode('latin1')}
return response
except services.errors.app_model_config.AppModelConfigBrokenError:
logging.exception("App model config broken.")
raise AppUnavailableError()