Feat/chat support voice input (langgenius#532)

api/controllers/console/__init__.py

@@ -9,7 +9,7 @@
 from . import setup, version, apikey, admin
 
 # Import app controllers
-from .app import app, site, completion, model_config, statistic, conversation, message, generator
+from .app import app, site, completion, model_config, statistic, conversation, message, generator, audio
 
 # Import auth controllers
 from .auth import login, oauth, data_source_oauth
@@ -21,4 +21,4 @@
 from .workspace import workspace, members, providers, account
 
 # Import explore controllers
-from .explore import installed_app, recommended_app, completion, conversation, message, parameter, saved_message
+from .explore import installed_app, recommended_app, completion, conversation, message, parameter, saved_message, audio

api/controllers/console/app/app.py

@@ -22,6 +22,7 @@
     'opening_statement': fields.String,
     'suggested_questions': fields.Raw(attribute='suggested_questions_list'),
     'suggested_questions_after_answer': fields.Raw(attribute='suggested_questions_after_answer_dict'),
+    'speech_to_text': fields.Raw(attribute='speech_to_text_dict'),
     'more_like_this': fields.Raw(attribute='more_like_this_dict'),
     'model': fields.Raw(attribute='model_dict'),
     'user_input_form': fields.Raw(attribute='user_input_form_list'),
@@ -144,6 +145,7 @@ def post(self):
                 opening_statement=model_configuration['opening_statement'],
                 suggested_questions=json.dumps(model_configuration['suggested_questions']),
                 suggested_questions_after_answer=json.dumps(model_configuration['suggested_questions_after_answer']),
+                speech_to_text=json.dumps(model_configuration['speech_to_text']),
                 more_like_this=json.dumps(model_configuration['more_like_this']),
                 model=json.dumps(model_configuration['model']),
                 user_input_form=json.dumps(model_configuration['user_input_form']),
@@ -434,6 +436,7 @@ def create_app_model_config_copy(app_config, copy_app_id):
             opening_statement=app_config.opening_statement,
             suggested_questions=app_config.suggested_questions,
             suggested_questions_after_answer=app_config.suggested_questions_after_answer,
+            speech_to_text=app_config.speech_to_text,
             more_like_this=app_config.more_like_this,
             model=app_config.model,
             user_input_form=app_config.user_input_form,

api/controllers/console/app/audio.py

@@ -0,0 +1,69 @@
+# -*- coding:utf-8 -*-
+import logging
+
+from flask import request
+from flask_login import login_required
+from werkzeug.exceptions import InternalServerError, NotFound
+
+import services
+from controllers.console import api
+from controllers.console.app import _get_app
+from controllers.console.app.error import AppUnavailableError, \
+    ProviderNotInitializeError, CompletionRequestError, ProviderQuotaExceededError, \
+    ProviderModelCurrentlyNotSupportError, NoAudioUploadedError, AudioTooLargeError, \
+    UnsupportedAudioTypeError, ProviderNotSupportSpeechToTextError
+from controllers.console.setup import setup_required
+from controllers.console.wraps import account_initialization_required
+from core.llm.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
+    LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
+from flask_restful import Resource
+from services.audio_service import AudioService
+from services.errors.audio import NoAudioUploadedServiceError, AudioTooLargeServiceError, \
+    UnsupportedAudioTypeServiceError, ProviderNotSupportSpeechToTextServiceError
+
+
+class ChatMessageAudioApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, app_id):
+        app_id = str(app_id)
+        app_model = _get_app(app_id, 'chat')
+
+        file = request.files['file']
+
+        try:
+            response = AudioService.transcript(
+                tenant_id=app_model.tenant_id,
+                file=file,
+            )
+
+            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:
+            raise ProviderNotInitializeError()
+        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()
+
+
+api.add_resource(ChatMessageAudioApi, '/apps/<uuid:app_id>/audio-to-text')

api/controllers/console/app/error.py

@@ -49,3 +49,27 @@ class AppMoreLikeThisDisabledError(BaseHTTPException):
     error_code = 'app_more_like_this_disabled'
     description = "The 'More like this' feature is disabled. Please refresh your page."
     code = 403
+
+
+class NoAudioUploadedError(BaseHTTPException):
+    error_code = 'no_audio_uploaded'
+    description = "Please upload your audio."
+    code = 400
+
+
+class AudioTooLargeError(BaseHTTPException):
+    error_code = 'audio_too_large'
+    description = "Audio size exceeded. {message}"
+    code = 413
+
+
+class UnsupportedAudioTypeError(BaseHTTPException):
+    error_code = 'unsupported_audio_type'
+    description = "Audio type not allowed."
+    code = 415
+
+
+class ProviderNotSupportSpeechToTextError(BaseHTTPException):
+    error_code = 'provider_not_support_speech_to_text'
+    description = "Provider not support speech to text."
+    code = 400

api/controllers/console/app/model_config.py

@@ -41,6 +41,7 @@ def post(self, app_id):
             opening_statement=model_configuration['opening_statement'],
             suggested_questions=json.dumps(model_configuration['suggested_questions']),
             suggested_questions_after_answer=json.dumps(model_configuration['suggested_questions_after_answer']),
+            speech_to_text=json.dumps(model_configuration['speech_to_text']),
             more_like_this=json.dumps(model_configuration['more_like_this']),
             model=json.dumps(model_configuration['model']),
             user_input_form=json.dumps(model_configuration['user_input_form']),

api/controllers/console/explore/audio.py

@@ -0,0 +1,66 @@
+# -*- coding:utf-8 -*-
+import logging
+
+from flask import request
+from werkzeug.exceptions import InternalServerError
+
+import services
+from controllers.console import api
+from controllers.console.app.error import AppUnavailableError, ProviderNotInitializeError, \
+    ProviderQuotaExceededError, ProviderModelCurrentlyNotSupportError, CompletionRequestError, \
+    NoAudioUploadedError, AudioTooLargeError, \
+    UnsupportedAudioTypeError, ProviderNotSupportSpeechToTextError
+from controllers.console.explore.wraps import InstalledAppResource
+from core.llm.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
+    LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
+from services.audio_service import AudioService
+from services.errors.audio import NoAudioUploadedServiceError, AudioTooLargeServiceError, \
+    UnsupportedAudioTypeServiceError, ProviderNotSupportSpeechToTextServiceError
+from models.model import AppModelConfig
+
+
+class ChatAudioApi(InstalledAppResource):
+    def post(self, installed_app):
+        app_model = installed_app.app
+        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(
+                tenant_id=app_model.tenant_id,
+                file=file,
+            )
+
+            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:
+            raise ProviderNotInitializeError()
+        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()
+
+
+api.add_resource(ChatAudioApi, '/installed-apps/<uuid:installed_app_id>/audio-to-text', endpoint='installed_app_audio')

api/controllers/console/explore/parameter.py

@@ -21,6 +21,7 @@ class AppParameterApi(InstalledAppResource):
         'opening_statement': fields.String,
         'suggested_questions': fields.Raw,
         'suggested_questions_after_answer': fields.Raw,
+        'speech_to_text': fields.Raw,
         'more_like_this': fields.Raw,
         'user_input_form': fields.Raw,
     }
@@ -35,6 +36,7 @@ def get(self, installed_app):
             'opening_statement': app_model_config.opening_statement,
             'suggested_questions': app_model_config.suggested_questions_list,
             'suggested_questions_after_answer': app_model_config.suggested_questions_after_answer_dict,
+            'speech_to_text': app_model_config.speech_to_text_dict,
             'more_like_this': app_model_config.more_like_this_dict,
             'user_input_form': app_model_config.user_input_form_list
         }

api/controllers/service_api/__init__.py

@@ -7,6 +7,6 @@
 api = ExternalApi(bp)
 
 
-from .app import completion, app, conversation, message
+from .app import completion, app, conversation, message, audio
 
 from .dataset import document

api/controllers/service_api/app/app.py

@@ -22,6 +22,7 @@ class AppParameterApi(AppApiResource):
         'opening_statement': fields.String,
         'suggested_questions': fields.Raw,
         'suggested_questions_after_answer': fields.Raw,
+        'speech_to_text': fields.Raw,
         'more_like_this': fields.Raw,
         'user_input_form': fields.Raw,
     }
@@ -35,6 +36,7 @@ def get(self, app_model, end_user):
             'opening_statement': app_model_config.opening_statement,
             'suggested_questions': app_model_config.suggested_questions_list,
             'suggested_questions_after_answer': app_model_config.suggested_questions_after_answer_dict,
+            'speech_to_text': app_model_config.speech_to_text_dict,
             'more_like_this': app_model_config.more_like_this_dict,
             'user_input_form': app_model_config.user_input_form_list
         }

api/controllers/service_api/app/audio.py

@@ -0,0 +1,61 @@
+import logging
+
+from flask import request
+from werkzeug.exceptions import InternalServerError
+
+import services
+from controllers.service_api import api
+from controllers.service_api.app.error import AppUnavailableError, ProviderNotInitializeError, CompletionRequestError, ProviderQuotaExceededError, \
+    ProviderModelCurrentlyNotSupportError, NoAudioUploadedError, AudioTooLargeError, UnsupportedAudioTypeError, \
+    ProviderNotSupportSpeechToTextError
+from controllers.service_api.wraps import AppApiResource
+from core.llm.error import LLMBadRequestError, LLMAuthorizationError, LLMAPIUnavailableError, LLMAPIConnectionError, \
+    LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
+from models.model import App, AppModelConfig
+from services.audio_service import AudioService
+from services.errors.audio import NoAudioUploadedServiceError, AudioTooLargeServiceError, \
+    UnsupportedAudioTypeServiceError, ProviderNotSupportSpeechToTextServiceError
+
+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(
+                tenant_id=app_model.tenant_id,
+                file=file,
+            )
+
+            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:
+            raise ProviderNotInitializeError()
+        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()
+
+api.add_resource(AudioApi, '/audio-to-text')

api/controllers/service_api/app/error.py

@@ -51,3 +51,27 @@ class CompletionRequestError(BaseHTTPException):
     description = "Completion request failed."
     code = 400
 
+
+class NoAudioUploadedError(BaseHTTPException):
+    error_code = 'no_audio_uploaded'
+    description = "Please upload your audio."
+    code = 400
+
+
+class AudioTooLargeError(BaseHTTPException):
+    error_code = 'audio_too_large'
+    description = "Audio size exceeded. {message}"
+    code = 413
+
+
+class UnsupportedAudioTypeError(BaseHTTPException):
+    error_code = 'unsupported_audio_type'
+    description = "Audio type not allowed."
+    code = 415
+
+
+class ProviderNotSupportSpeechToTextError(BaseHTTPException):
+    error_code = 'provider_not_support_speech_to_text'
+    description = "Provider not support speech to text."
+    code = 400
+

api/controllers/web/__init__.py

@@ -7,4 +7,4 @@
 api = ExternalApi(bp)
 
 
-from . import completion, app, conversation, message, site, saved_message
+from . import completion, app, conversation, message, site, saved_message, audio

api/controllers/web/app.py

@@ -21,6 +21,7 @@ class AppParameterApi(WebApiResource):
         'opening_statement': fields.String,
         'suggested_questions': fields.Raw,
         'suggested_questions_after_answer': fields.Raw,
+        'speech_to_text': fields.Raw,
         'more_like_this': fields.Raw,
         'user_input_form': fields.Raw,
     }
@@ -34,6 +35,7 @@ def get(self, app_model, end_user):
             'opening_statement': app_model_config.opening_statement,
             'suggested_questions': app_model_config.suggested_questions_list,
             'suggested_questions_after_answer': app_model_config.suggested_questions_after_answer_dict,
+            'speech_to_text': app_model_config.speech_to_text_dict,
             'more_like_this': app_model_config.more_like_this_dict,
             'user_input_form': app_model_config.user_input_form_list
         }