File size: 7,205 Bytes
a8b3f00
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
import logging

from flask import request
from flask_restful import Resource, reqparse
from werkzeug.exceptions import InternalServerError

import services
from controllers.console import api
from controllers.console.app.error import (
    AppUnavailableError,
    AudioTooLargeError,
    CompletionRequestError,
    NoAudioUploadedError,
    ProviderModelCurrentlyNotSupportError,
    ProviderNotInitializeError,
    ProviderNotSupportSpeechToTextError,
    ProviderQuotaExceededError,
    UnsupportedAudioTypeError,
)
from controllers.console.app.wraps import get_app_model
from controllers.console.wraps import account_initialization_required, setup_required
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
from core.model_runtime.errors.invoke import InvokeError
from libs.login import login_required
from models.model import AppMode
from services.audio_service import AudioService
from services.errors.audio import (
    AudioTooLargeServiceError,
    NoAudioUploadedServiceError,
    ProviderNotSupportSpeechToTextServiceError,
    UnsupportedAudioTypeServiceError,
)


class ChatMessageAudioApi(Resource):
    @setup_required
    @login_required
    @account_initialization_required
    @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
    def post(self, app_model):
        file = request.files["file"]

        try:
            response = AudioService.transcript_asr(
                app_model=app_model,
                file=file,
                end_user=None,
            )

            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(f"internal server error, {str(e)}.")
            raise InternalServerError()


class ChatMessageTextApi(Resource):
    @setup_required
    @login_required
    @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") or text_to_speech.get("voice")
            else:
                try:
                    voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
                except Exception:
                    voice = None
            response = AudioService.transcript_tts(app_model=app_model, text=text, message_id=message_id, voice=voice)
            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(f"internal server error, {str(e)}.")
            raise InternalServerError()


class TextModesApi(Resource):
    @setup_required
    @login_required
    @account_initialization_required
    @get_app_model
    def get(self, app_model):
        try:
            parser = reqparse.RequestParser()
            parser.add_argument("language", type=str, required=True, location="args")
            args = parser.parse_args()

            response = AudioService.transcript_tts_voices(
                tenant_id=app_model.tenant_id,
                language=args["language"],
            )

            return response
        except services.errors.audio.ProviderNotSupportTextToSpeechLanageServiceError:
            raise AppUnavailableError("Text to audio voices language parameter loss.")
        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(f"internal server error, {str(e)}.")
            raise InternalServerError()


api.add_resource(ChatMessageAudioApi, "/apps/<uuid:app_id>/audio-to-text")
api.add_resource(ChatMessageTextApi, "/apps/<uuid:app_id>/text-to-audio")
api.add_resource(TextModesApi, "/apps/<uuid:app_id>/text-to-audio/voices")