hz/ebiz-dify-ai
1
0
Fork 0
mirror of http://112.124.100.131/huang.ze/ebiz-dify-ai.git synced 2025-12-09 19:06:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

Model Runtime (#1858)

Browse Source 
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
Co-authored-by: Garfield Dai <dai.hai@foxmail.com>
Co-authored-by: chenhe <guchenhe@gmail.com>
Co-authored-by: jyong <jyong@dify.ai>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: Yeuoly <admin@srmxy.cn>
This commit is contained in:
takatost
2024-01-02 23:42:00 +08:00
committed by GitHub
parent e91dd28a76
commit d069c668f8
807 changed files with 171310 additions and 23806 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
api/controllers/console/explore/audio.py
View File

@@ -11,8 +11,8 @@ from controllers.console.app.error import AppUnavailableError, ProviderNotInitia
NoAudioUploadedError, AudioTooLargeError, \
UnsupportedAudioTypeError, ProviderNotSupportSpeechToTextError
from controllers.console.explore.wraps import InstalledAppResource
from core.model_providers.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
from core.errors.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
from core.model_runtime.errors.invoke import InvokeError
from services.audio_service import AudioService
from services.errors.audio import NoAudioUploadedServiceError, AudioTooLargeServiceError, \
UnsupportedAudioTypeServiceError, ProviderNotSupportSpeechToTextServiceError
@@ -53,8 +53,7 @@ class ChatAudioApi(InstalledAppResource):
raise ProviderQuotaExceededError()
except ModelCurrentlyNotSupportError:
raise ProviderModelCurrentlyNotSupportError()
except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
LLMRateLimitError, LLMAuthorizationError) as e:
except InvokeError as e:
raise CompletionRequestError(str(e))
except ValueError as e:
raise e

24
api/controllers/console/explore/completion.py
View File

@@ -15,9 +15,10 @@ from controllers.console.app.error import ConversationCompletedError, AppUnavail
ProviderQuotaExceededError, ProviderModelCurrentlyNotSupportError, CompletionRequestError
from controllers.console.explore.error import NotCompletionAppError, NotChatAppError
from controllers.console.explore.wraps import InstalledAppResource
from core.conversation_message_task import PubHandler
from core.model_providers.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
from core.application_queue_manager import ApplicationQueueManager
from core.entities.application_entities import InvokeFrom
from core.errors.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
from core.model_runtime.errors.invoke import InvokeError
from extensions.ext_database import db
from libs.helper import uuid_value
from services.completion_service import CompletionService
@@ -50,7 +51,7 @@ class CompletionApi(InstalledAppResource):
app_model=app_model,
user=current_user,
args=args,
from_source='console',
invoke_from=InvokeFrom.EXPLORE,
streaming=streaming
)
@@ -68,8 +69,7 @@ class CompletionApi(InstalledAppResource):
raise ProviderQuotaExceededError()
except ModelCurrentlyNotSupportError:
raise ProviderModelCurrentlyNotSupportError()
except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
LLMRateLimitError, LLMAuthorizationError) as e:
except InvokeError as e:
raise CompletionRequestError(str(e))
except ValueError as e:
raise e
@@ -84,7 +84,7 @@ class CompletionStopApi(InstalledAppResource):
if app_model.mode != 'completion':
raise NotCompletionAppError()
PubHandler.stop(current_user, task_id)
ApplicationQueueManager.set_stop_flag(task_id, InvokeFrom.EXPLORE, current_user.id)
return {'result': 'success'}, 200
@@ -115,7 +115,7 @@ class ChatApi(InstalledAppResource):
app_model=app_model,
user=current_user,
args=args,
from_source='console',
invoke_from=InvokeFrom.EXPLORE,
streaming=streaming
)
@@ -133,8 +133,7 @@ class ChatApi(InstalledAppResource):
raise ProviderQuotaExceededError()
except ModelCurrentlyNotSupportError:
raise ProviderModelCurrentlyNotSupportError()
except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
LLMRateLimitError, LLMAuthorizationError) as e:
except InvokeError as e:
raise CompletionRequestError(str(e))
except ValueError as e:
raise e
@@ -149,7 +148,7 @@ class ChatStopApi(InstalledAppResource):
if app_model.mode != 'chat':
raise NotChatAppError()
PubHandler.stop(current_user, task_id)
ApplicationQueueManager.set_stop_flag(task_id, InvokeFrom.EXPLORE, current_user.id)
return {'result': 'success'}, 200
@@ -175,8 +174,7 @@ def compact_response(response: Union[dict, Generator]) -> Response:
yield "data: " + json.dumps(api.handle_error(ProviderQuotaExceededError()).get_json()) + "\n\n"
except ModelCurrentlyNotSupportError:
yield "data: " + json.dumps(api.handle_error(ProviderModelCurrentlyNotSupportError()).get_json()) + "\n\n"
except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
LLMRateLimitError, LLMAuthorizationError) as e:
except InvokeError as e:
yield "data: " + json.dumps(api.handle_error(CompletionRequestError(str(e))).get_json()) + "\n\n"
except ValueError as e:
yield "data: " + json.dumps(api.handle_error(e).get_json()) + "\n\n"

29
api/controllers/console/explore/message.py
View File

@@ -5,7 +5,7 @@ from typing import Generator, Union
from flask import stream_with_context, Response
from flask_login import current_user
from flask_restful import reqparse, fields, marshal_with
from flask_restful import reqparse, marshal_with
from flask_restful.inputs import int_range
from werkzeug.exceptions import NotFound, InternalServerError
@@ -13,12 +13,14 @@ import services
from controllers.console import api
from controllers.console.app.error import AppMoreLikeThisDisabledError, ProviderNotInitializeError, \
ProviderQuotaExceededError, ProviderModelCurrentlyNotSupportError, CompletionRequestError
from controllers.console.explore.error import NotCompletionAppError, AppSuggestedQuestionsAfterAnswerDisabledError
from controllers.console.explore.error import NotCompletionAppError, AppSuggestedQuestionsAfterAnswerDisabledError, \
NotChatAppError
from controllers.console.explore.wraps import InstalledAppResource
from core.model_providers.error import LLMRateLimitError, LLMBadRequestError, LLMAuthorizationError, LLMAPIConnectionError, \
ProviderTokenNotInitError, LLMAPIUnavailableError, QuotaExceededError, ModelCurrentlyNotSupportError
from core.entities.application_entities import InvokeFrom
from core.errors.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
from core.model_runtime.errors.invoke import InvokeError
from fields.message_fields import message_infinite_scroll_pagination_fields
from libs.helper import uuid_value, TimestampField
from libs.helper import uuid_value
from services.completion_service import CompletionService
from services.errors.app import MoreLikeThisDisabledError
from services.errors.conversation import ConversationNotExistsError
@@ -83,7 +85,13 @@ class MessageMoreLikeThisApi(InstalledAppResource):
streaming = args['response_mode'] == 'streaming'
try:
response = CompletionService.generate_more_like_this(app_model, current_user, message_id, streaming)
response = CompletionService.generate_more_like_this(
app_model=app_model,
user=current_user,
message_id=message_id,
invoke_from=InvokeFrom.EXPLORE,
streaming=streaming
)
return compact_response(response)
except MessageNotExistsError:
raise NotFound("Message Not Exists.")
@@ -95,8 +103,7 @@ class MessageMoreLikeThisApi(InstalledAppResource):
raise ProviderQuotaExceededError()
except ModelCurrentlyNotSupportError:
raise ProviderModelCurrentlyNotSupportError()
except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
LLMRateLimitError, LLMAuthorizationError) as e:
except InvokeError as e:
raise CompletionRequestError(str(e))
except ValueError as e:
raise e
@@ -123,8 +130,7 @@ def compact_response(response: Union[dict, Generator]) -> Response:
yield "data: " + json.dumps(api.handle_error(ProviderQuotaExceededError()).get_json()) + "\n\n"
except ModelCurrentlyNotSupportError:
yield "data: " + json.dumps(api.handle_error(ProviderModelCurrentlyNotSupportError()).get_json()) + "\n\n"
except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
LLMRateLimitError, LLMAuthorizationError) as e:
except InvokeError as e:
yield "data: " + json.dumps(api.handle_error(CompletionRequestError(str(e))).get_json()) + "\n\n"
except ValueError as e:
yield "data: " + json.dumps(api.handle_error(e).get_json()) + "\n\n"
@@ -162,8 +168,7 @@ class MessageSuggestedQuestionApi(InstalledAppResource):
raise ProviderQuotaExceededError()
except ModelCurrentlyNotSupportError:
raise ProviderModelCurrentlyNotSupportError()
except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
LLMRateLimitError, LLMAuthorizationError) as e:
except InvokeError as e:
raise CompletionRequestError(str(e))
except Exception:
logging.exception("internal server error.")