estel/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 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

24
api/controllers/service_api/app/completion.py
View File

@@ -13,9 +13,10 @@ from controllers.service_api.app.error import AppUnavailableError, ProviderNotIn
ConversationCompletedError, CompletionRequestError, ProviderQuotaExceededError, \
ProviderModelCurrentlyNotSupportError
from controllers.service_api.wraps import AppApiResource
from core.conversation_message_task import PubHandler
from core.model_providers.error import LLMBadRequestError, LLMAuthorizationError, LLMAPIUnavailableError, 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 libs.helper import uuid_value
from services.completion_service import CompletionService
@@ -47,7 +48,7 @@ class CompletionApi(AppApiResource):
app_model=app_model,
user=end_user,
args=args,
from_source='api',
invoke_from=InvokeFrom.SERVICE_API,
streaming=streaming,
)
@@ -65,8 +66,7 @@ class CompletionApi(AppApiResource):
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
@@ -80,7 +80,7 @@ class CompletionStopApi(AppApiResource):
if app_model.mode != 'completion':
raise AppUnavailableError()
PubHandler.stop(end_user, task_id)
ApplicationQueueManager.set_stop_flag(task_id, InvokeFrom.SERVICE_API, end_user.id)
return {'result': 'success'}, 200
@@ -112,7 +112,7 @@ class ChatApi(AppApiResource):
app_model=app_model,
user=end_user,
args=args,
from_source='api',
invoke_from=InvokeFrom.SERVICE_API,
streaming=streaming
)
@@ -130,8 +130,7 @@ class ChatApi(AppApiResource):
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
@@ -145,7 +144,7 @@ class ChatStopApi(AppApiResource):
if app_model.mode != 'chat':
raise NotChatAppError()
PubHandler.stop(end_user, task_id)
ApplicationQueueManager.set_stop_flag(task_id, InvokeFrom.SERVICE_API, end_user.id)
return {'result': 'success'}, 200
@@ -171,8 +170,7 @@ 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"