outman/dify
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'main' into feat/new-login

Browse Source 
* main: (40 commits)
  feat: allow users to specify timeout for text generations and workflows by environment variable (#8395)
  Fix: operation postion of answer in logs (#8411)
  fix: when the variable does not exist, an error should be prompted (#8413)
  fix(workflow): the answer node after the iteration node containing the answer was output prematurely (#8419)
  fix:logs and rm unused codes in CacheEmbedding (#8409)
  fix: resolve runtime error when self.folder is None (#8401)
  Fix: Support Bedrock cross region inference #8190 (Update Model name to distinguish between different region groups) (#8402)
  fix(docker): aliyun oss path env key (#8394)
  fix: pyproject.toml typo (#8396)
  fix: o1-mini 65563 -> 65536 (#8388)
  fix: sandbox issue related httpx and requests (#8397)
  chore: improve usage of striping prefix or suffix of string with Ruff 0.6.5 (#8392)
  fix (#8322 followup): resolve the violation of pylint rules (#8391)
  chore: refurish python code by applying Pylint linter rules (#8322)
  support hunyuan-turbo (#8372)
  chore: update firecrawl scrape to V1 api (#8367)
  fix(workflow): both parallel and single branch errors occur in if-else (#8378)
  fix: edit load balancing not pass id (#8370)
  fix: add before send to remove langfuse defaultErrorResponse (#8361)
  fix: when edit load balancing config not pass the empty filed value hidden (#8366)
  ...
This commit is contained in:
Joe 2024-09-14 14:53:11 +08:00
commit cd277aa2d8
274 changed files with 2303 additions and 1475 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
api/app.py
View File

@ -164,7 +164,7 @@ def initialize_extensions(app):
@login_manager.request_loader
def load_user_from_request(request_from_flask_login):
"""Load user based on the request."""
if request.blueprint not in ["console", "inner_api"]:
if request.blueprint not in {"console", "inner_api"}:
return None
# Check if the user_id contains a dot, indicating the old format
auth_header = request.headers.get("Authorization", "")

13
api/commands.py
View File

@ -104,7 +104,7 @@ def reset_email(email, new_email, email_confirm):
)
@click.confirmation_option(
prompt=click.style(
"Are you sure you want to reset encrypt key pair?" " this operation cannot be rolled back!", fg="red"
"Are you sure you want to reset encrypt key pair? this operation cannot be rolled back!", fg="red"
)
)
def reset_encrypt_key_pair():
@ -131,7 +131,7 @@ def reset_encrypt_key_pair():
click.echo(
click.style(
"Congratulations! " "the asymmetric key pair of workspace {} has been reset.".format(tenant.id),
"Congratulations! The asymmetric key pair of workspace {} has been reset.".format(tenant.id),
fg="green",
)
)
@ -140,9 +140,9 @@ def reset_encrypt_key_pair():
@click.command("vdb-migrate", help="migrate vector db.")
@click.option("--scope", default="all", prompt=False, help="The scope of vector database to migrate, Default is All.")
def vdb_migrate(scope: str):
if scope in ["knowledge", "all"]:
if scope in {"knowledge", "all"}:
migrate_knowledge_vector_database()
if scope in ["annotation", "all"]:
if scope in {"annotation", "all"}:
migrate_annotation_vector_database()
@ -275,8 +275,7 @@ def migrate_knowledge_vector_database():
for dataset in datasets:
total_count = total_count + 1
click.echo(
f"Processing the {total_count} dataset {dataset.id}. "
+ f"{create_count} created, {skipped_count} skipped."
f"Processing the {total_count} dataset {dataset.id}. {create_count} created, {skipped_count} skipped."
)
try:
click.echo("Create dataset vdb index: {}".format(dataset.id))
@ -594,7 +593,7 @@ def create_tenant(email: str, language: Optional[str] = None, name: Optional[str
click.echo(
click.style(
"Congratulations! Account and tenant created.\n" "Account: {}\nPassword: {}".format(email, new_password),
"Congratulations! Account and tenant created.\nAccount: {}\nPassword: {}".format(email, new_password),
fg="green",
)
)

6
api/configs/feature/__init__.py
View File

@ -138,12 +138,12 @@ class EndpointConfig(BaseSettings):
)
SERVICE_API_URL: str = Field(
description="Service API Url prefix." "used to display Service API Base Url to the front-end.",
description="Service API Url prefix. used to display Service API Base Url to the front-end.",
default="",
)
APP_WEB_URL: str = Field(
description="WebApp Url prefix." "used to display WebAPP API Base Url to the front-end.",
description="WebApp Url prefix. used to display WebAPP API Base Url to the front-end.",
default="",
)
@ -281,7 +281,7 @@ class LoggingConfig(BaseSettings):
"""
LOG_LEVEL: str = Field(
description="Log output level, default to INFO." "It is recommended to set it to ERROR for production.",
description="Log output level, default to INFO. It is recommended to set it to ERROR for production.",
default="INFO",
)

2
api/configs/packaging/__init__.py
View File

@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
CURRENT_VERSION: str = Field(
description="Dify version",
default="0.8.0",
default="0.8.2",
)
COMMIT_SHA: str = Field(

2
api/controllers/console/app/audio.py
View File

@ -94,7 +94,7 @@ class ChatMessageTextApi(Resource):
message_id = args.get("message_id", None)
text = args.get("text", None)
if (
app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
and app_model.workflow
and app_model.workflow.features_dict
):

2
api/controllers/console/app/workflow.py
View File

@ -465,6 +465,6 @@ api.add_resource(
api.add_resource(PublishedWorkflowApi, "/apps/<uuid:app_id>/workflows/publish")
api.add_resource(DefaultBlockConfigsApi, "/apps/<uuid:app_id>/workflows/default-workflow-block-configs")
api.add_resource(
DefaultBlockConfigApi, "/apps/<uuid:app_id>/workflows/default-workflow-block-configs" "/<string:block_type>"
DefaultBlockConfigApi, "/apps/<uuid:app_id>/workflows/default-workflow-block-configs/<string:block_type>"
)
api.add_resource(ConvertToWorkflowApi, "/apps/<uuid:app_id>/convert-to-workflow")

2
api/controllers/console/auth/oauth.py
View File

@ -101,7 +101,7 @@ class OAuthCallback(Resource):
)
# Check account status
if account.status == AccountStatus.BANNED.value or account.status == AccountStatus.CLOSED.value:
if account.status in {AccountStatus.BANNED.value, AccountStatus.CLOSED.value}:
return {"error": "Account is banned or closed."}, 403
if account.status == AccountStatus.PENDING.value:

2
api/controllers/console/datasets/datasets.py
View File

@ -399,7 +399,7 @@ class DatasetIndexingEstimateApi(Resource):
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider " "in the Settings -> Model Provider."
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)

6
api/controllers/console/datasets/datasets_document.py
View File

@ -354,7 +354,7 @@ class DocumentIndexingEstimateApi(DocumentResource):
document_id = str(document_id)
document = self.get_document(dataset_id, document_id)
if document.indexing_status in ["completed", "error"]:
if document.indexing_status in {"completed", "error"}:
raise DocumentAlreadyFinishedError()
data_process_rule = document.dataset_process_rule
@ -421,7 +421,7 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
info_list = []
extract_settings = []
for document in documents:
if document.indexing_status in ["completed", "error"]:
if document.indexing_status in {"completed", "error"}:
raise DocumentAlreadyFinishedError()
data_source_info = document.data_source_info_dict
# format document files info
@ -665,7 +665,7 @@ class DocumentProcessingApi(DocumentResource):
db.session.commit()
elif action == "resume":
if document.indexing_status not in ["paused", "error"]:
if document.indexing_status not in {"paused", "error"}:
raise InvalidActionError("Document not in paused or error state.")
document.paused_by = None

4
api/controllers/console/error.py
View File

@ -18,9 +18,7 @@ class NotSetupError(BaseHTTPException):
class NotInitValidateError(BaseHTTPException):
error_code = "not_init_validated"
description = (
"Init validation has not been completed yet. " "Please proceed with the init validation process first."
)
description = "Init validation has not been completed yet. Please proceed with the init validation process first."
code = 401

2
api/controllers/console/explore/audio.py
View File

@ -81,7 +81,7 @@ class ChatTextApi(InstalledAppResource):
message_id = args.get("message_id", None)
text = args.get("text", None)
if (
app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
and app_model.workflow
and app_model.workflow.features_dict
):

4
api/controllers/console/explore/completion.py
View File

@ -92,7 +92,7 @@ class ChatApi(InstalledAppResource):
def post(self, installed_app):
app_model = installed_app.app
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
parser = reqparse.RequestParser()
@ -140,7 +140,7 @@ class ChatStopApi(InstalledAppResource):
def post(self, installed_app, task_id):
app_model = installed_app.app
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
AppQueueManager.set_stop_flag(task_id, InvokeFrom.EXPLORE, current_user.id)

10
api/controllers/console/explore/conversation.py
View File

@ -20,7 +20,7 @@ class ConversationListApi(InstalledAppResource):
def get(self, installed_app):
app_model = installed_app.app
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
parser = reqparse.RequestParser()
@ -50,7 +50,7 @@ class ConversationApi(InstalledAppResource):
def delete(self, installed_app, c_id):
app_model = installed_app.app
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
conversation_id = str(c_id)
@ -68,7 +68,7 @@ class ConversationRenameApi(InstalledAppResource):
def post(self, installed_app, c_id):
app_model = installed_app.app
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
conversation_id = str(c_id)
@ -90,7 +90,7 @@ class ConversationPinApi(InstalledAppResource):
def patch(self, installed_app, c_id):
app_model = installed_app.app
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
conversation_id = str(c_id)
@ -107,7 +107,7 @@ class ConversationUnPinApi(InstalledAppResource):
def patch(self, installed_app, c_id):
app_model = installed_app.app
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
conversation_id = str(c_id)

2
api/controllers/console/explore/installed_app.py
View File

@ -31,7 +31,7 @@ class InstalledAppsListApi(Resource):
"app_owner_tenant_id": installed_app.app_owner_tenant_id,
"is_pinned": installed_app.is_pinned,
"last_used_at": installed_app.last_used_at,
"editable": current_user.role in ["owner", "admin"],
"editable": current_user.role in {"owner", "admin"},
"uninstallable": current_tenant_id == installed_app.app_owner_tenant_id,
}
for installed_app in installed_apps

4
api/controllers/console/explore/message.py
View File

@ -40,7 +40,7 @@ class MessageListApi(InstalledAppResource):
app_model = installed_app.app
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
parser = reqparse.RequestParser()
@ -125,7 +125,7 @@ class MessageSuggestedQuestionApi(InstalledAppResource):
def get(self, installed_app, message_id):
app_model = installed_app.app
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
message_id = str(message_id)

2
api/controllers/console/explore/parameter.py
View File

@ -43,7 +43,7 @@ class AppParameterApi(InstalledAppResource):
"""Retrieve app parameters."""
app_model = installed_app.app
if app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]:
if app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
workflow = app_model.workflow
if workflow is None:
raise AppUnavailableError()

2
api/controllers/console/workspace/model_providers.py
View File

@ -218,7 +218,7 @@ api.add_resource(ModelProviderCredentialApi, "/workspaces/current/model-provider
api.add_resource(ModelProviderValidateApi, "/workspaces/current/model-providers/<string:provider>/credentials/validate")
api.add_resource(ModelProviderApi, "/workspaces/current/model-providers/<string:provider>")
api.add_resource(
ModelProviderIconApi, "/workspaces/current/model-providers/<string:provider>/" "<string:icon_type>/<string:lang>"
ModelProviderIconApi, "/workspaces/current/model-providers/<string:provider>/<string:icon_type>/<string:lang>"
)
api.add_resource(

2
api/controllers/console/workspace/workspace.py
View File

@ -194,7 +194,7 @@ class WebappLogoWorkspaceApi(Resource):
raise TooManyFilesError()
extension = file.filename.split(".")[-1]
if extension.lower() not in ["svg", "png"]:
if extension.lower() not in {"svg", "png"}:
raise UnsupportedFileTypeError()
try:

2
api/controllers/service_api/app/app.py
View File

@ -42,7 +42,7 @@ class AppParameterApi(Resource):
@marshal_with(parameters_fields)
def get(self, app_model: App):
"""Retrieve app parameters."""
if app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]:
if app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
workflow = app_model.workflow
if workflow is None:
raise AppUnavailableError()

2
api/controllers/service_api/app/audio.py
View File

@ -79,7 +79,7 @@ class TextApi(Resource):
message_id = args.get("message_id", None)
text = args.get("text", None)
if (
app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
and app_model.workflow
and app_model.workflow.features_dict
):

4
api/controllers/service_api/app/completion.py
View File

@ -96,7 +96,7 @@ class ChatApi(Resource):
@validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True))
def post(self, app_model: App, end_user: EndUser):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
parser = reqparse.RequestParser()
@ -144,7 +144,7 @@ class ChatStopApi(Resource):
@validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True))
def post(self, app_model: App, end_user: EndUser, task_id):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
AppQueueManager.set_stop_flag(task_id, InvokeFrom.SERVICE_API, end_user.id)

6
api/controllers/service_api/app/conversation.py
View File

@ -18,7 +18,7 @@ class ConversationApi(Resource):
@marshal_with(conversation_infinite_scroll_pagination_fields)
def get(self, app_model: App, end_user: EndUser):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
parser = reqparse.RequestParser()
@ -52,7 +52,7 @@ class ConversationDetailApi(Resource):
@marshal_with(simple_conversation_fields)
def delete(self, app_model: App, end_user: EndUser, c_id):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
conversation_id = str(c_id)
@ -69,7 +69,7 @@ class ConversationRenameApi(Resource):
@marshal_with(simple_conversation_fields)
def post(self, app_model: App, end_user: EndUser, c_id):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
conversation_id = str(c_id)

4
api/controllers/service_api/app/message.py
View File

@ -76,7 +76,7 @@ class MessageListApi(Resource):
@marshal_with(message_infinite_scroll_pagination_fields)
def get(self, app_model: App, end_user: EndUser):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
parser = reqparse.RequestParser()
@ -117,7 +117,7 @@ class MessageSuggestedApi(Resource):
def get(self, app_model: App, end_user: EndUser, message_id):
message_id = str(message_id)
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
try:

27
api/controllers/service_api/app/workflow.py
View File

@ -1,6 +1,7 @@
import logging
from flask_restful import Resource, fields, marshal_with, reqparse
from flask_restful.inputs import int_range
from werkzeug.exceptions import InternalServerError
from controllers.service_api import api
@ -22,10 +23,12 @@ from core.errors.error import (
)
from core.model_runtime.errors.invoke import InvokeError
from extensions.ext_database import db
from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
from libs import helper
from models.model import App, AppMode, EndUser
from models.workflow import WorkflowRun
from services.app_generate_service import AppGenerateService
from services.workflow_app_service import WorkflowAppService
logger = logging.getLogger(__name__)
@ -113,6 +116,30 @@ class WorkflowTaskStopApi(Resource):
return {"result": "success"}
class WorkflowAppLogApi(Resource):
@validate_app_token
@marshal_with(workflow_app_log_pagination_fields)
def get(self, app_model: App):
"""
Get workflow app logs
"""
parser = reqparse.RequestParser()
parser.add_argument("keyword", type=str, location="args")
parser.add_argument("status", type=str, choices=["succeeded", "failed", "stopped"], location="args")
parser.add_argument("page", type=int_range(1, 99999), default=1, location="args")
parser.add_argument("limit", type=int_range(1, 100), default=20, location="args")
args = parser.parse_args()
# get paginate workflow app logs
workflow_app_service = WorkflowAppService()
workflow_app_log_pagination = workflow_app_service.get_paginate_workflow_app_logs(
app_model=app_model, args=args
)
return workflow_app_log_pagination
api.add_resource(WorkflowRunApi, "/workflows/run")
api.add_resource(WorkflowRunDetailApi, "/workflows/run/<string:workflow_id>")
api.add_resource(WorkflowTaskStopApi, "/workflows/tasks/<string:task_id>/stop")
api.add_resource(WorkflowAppLogApi, "/workflows/logs")

2
api/controllers/web/app.py
View File

@ -41,7 +41,7 @@ class AppParameterApi(WebApiResource):
@marshal_with(parameters_fields)
def get(self, app_model: App, end_user):
"""Retrieve app parameters."""
if app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]:
if app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
workflow = app_model.workflow
if workflow is None:
raise AppUnavailableError()

2
api/controllers/web/audio.py
View File

@ -78,7 +78,7 @@ class TextApi(WebApiResource):
message_id = args.get("message_id", None)
text = args.get("text", None)
if (
app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
and app_model.workflow
and app_model.workflow.features_dict
):

4
api/controllers/web/completion.py
View File

@ -87,7 +87,7 @@ class CompletionStopApi(WebApiResource):
class ChatApi(WebApiResource):
def post(self, app_model, end_user):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
parser = reqparse.RequestParser()
@ -136,7 +136,7 @@ class ChatApi(WebApiResource):
class ChatStopApi(WebApiResource):
def post(self, app_model, end_user, task_id):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
AppQueueManager.set_stop_flag(task_id, InvokeFrom.WEB_APP, end_user.id)

10
api/controllers/web/conversation.py
View File

@ -18,7 +18,7 @@ class ConversationListApi(WebApiResource):
@marshal_with(conversation_infinite_scroll_pagination_fields)
def get(self, app_model, end_user):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
parser = reqparse.RequestParser()
@ -56,7 +56,7 @@ class ConversationListApi(WebApiResource):
class ConversationApi(WebApiResource):
def delete(self, app_model, end_user, c_id):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
conversation_id = str(c_id)
@ -73,7 +73,7 @@ class ConversationRenameApi(WebApiResource):
@marshal_with(simple_conversation_fields)
def post(self, app_model, end_user, c_id):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
conversation_id = str(c_id)
@ -92,7 +92,7 @@ class ConversationRenameApi(WebApiResource):
class ConversationPinApi(WebApiResource):
def patch(self, app_model, end_user, c_id):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
conversation_id = str(c_id)
@ -108,7 +108,7 @@ class ConversationPinApi(WebApiResource):
class ConversationUnPinApi(WebApiResource):
def patch(self, app_model, end_user, c_id):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
conversation_id = str(c_id)

4
api/controllers/web/message.py
View File

@ -78,7 +78,7 @@ class MessageListApi(WebApiResource):
@marshal_with(message_infinite_scroll_pagination_fields)
def get(self, app_model, end_user):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotChatAppError()
parser = reqparse.RequestParser()
@ -160,7 +160,7 @@ class MessageMoreLikeThisApi(WebApiResource):
class MessageSuggestedQuestionApi(WebApiResource):
def get(self, app_model, end_user, message_id):
app_mode = AppMode.value_of(app_model.mode)
if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
raise NotCompletionAppError()
message_id = str(message_id)

4
api/core/agent/output_parser/cot_output_parser.py
View File

@ -90,7 +90,7 @@ class CotAgentOutputParser:
if not in_code_block and not in_json:
if delta.lower() == action_str[action_idx] and action_idx == 0:
if last_character not in ["\n", " ", ""]:
if last_character not in {"\n", " ", ""}:
index += steps
yield delta
continue
@ -117,7 +117,7 @@ class CotAgentOutputParser:
action_idx = 0
if delta.lower() == thought_str[thought_idx] and thought_idx == 0:
if last_character not in ["\n", " ", ""]:
if last_character not in {"\n", " ", ""}:
index += steps
yield delta
continue

2
api/core/app/app_config/base_app_config_manager.py
View File

@ -29,7 +29,7 @@ class BaseAppConfigManager:
additional_features.show_retrieve_source = RetrievalResourceConfigManager.convert(config=config_dict)
additional_features.file_upload = FileUploadConfigManager.convert(
config=config_dict, is_vision=app_mode in [AppMode.CHAT, AppMode.COMPLETION, AppMode.AGENT_CHAT]
config=config_dict, is_vision=app_mode in {AppMode.CHAT, AppMode.COMPLETION, AppMode.AGENT_CHAT}
)
additional_features.opening_statement, additional_features.suggested_questions = (

6
api/core/app/app_config/easy_ui_based_app/agent/manager.py
View File

@ -18,7 +18,7 @@ class AgentConfigManager:
if agent_strategy == "function_call":
strategy = AgentEntity.Strategy.FUNCTION_CALLING
elif agent_strategy == "cot" or agent_strategy == "react":
elif agent_strategy in {"cot", "react"}:
strategy = AgentEntity.Strategy.CHAIN_OF_THOUGHT
else:
# old configs, try to detect default strategy
@ -43,10 +43,10 @@ class AgentConfigManager:
agent_tools.append(AgentToolEntity(**agent_tool_properties))
if "strategy" in config["agent_mode"] and config["agent_mode"]["strategy"] not in [
if "strategy" in config["agent_mode"] and config["agent_mode"]["strategy"] not in {
"react_router",
"router",
]:
}:
agent_prompt = agent_dict.get("prompt", None) or {}
# check model mode
model_mode = config.get("model", {}).get("mode", "completion")

2
api/core/app/app_config/easy_ui_based_app/dataset/manager.py
View File

@ -167,7 +167,7 @@ class DatasetConfigManager:
config["agent_mode"]["strategy"] = PlanningStrategy.ROUTER.value
has_datasets = False
if config["agent_mode"]["strategy"] in [PlanningStrategy.ROUTER.value, PlanningStrategy.REACT_ROUTER.value]:
if config["agent_mode"]["strategy"] in {PlanningStrategy.ROUTER.value, PlanningStrategy.REACT_ROUTER.value}:
for tool in config["agent_mode"]["tools"]:
key = list(tool.keys())[0]
if key == "dataset":

2
api/core/app/app_config/easy_ui_based_app/prompt_template/manager.py
View File

@ -86,7 +86,7 @@ class PromptTemplateConfigManager:
if config["prompt_type"] == PromptTemplateEntity.PromptType.ADVANCED.value:
if not config["chat_prompt_config"] and not config["completion_prompt_config"]:
raise ValueError(
"chat_prompt_config or completion_prompt_config is required " "when prompt_type is advanced"
"chat_prompt_config or completion_prompt_config is required when prompt_type is advanced"
)
model_mode_vals = [mode.value for mode in ModelMode]

8
api/core/app/app_config/easy_ui_based_app/variables/manager.py
View File

@ -42,12 +42,12 @@ class BasicVariablesConfigManager:
variable=variable["variable"], type=variable["type"], config=variable["config"]
)
)
elif variable_type in [
elif variable_type in {
VariableEntityType.TEXT_INPUT,
VariableEntityType.PARAGRAPH,
VariableEntityType.NUMBER,
VariableEntityType.SELECT,
]:
}:
variable = variables[variable_type]
variable_entities.append(
VariableEntity(
@ -97,7 +97,7 @@ class BasicVariablesConfigManager:
variables = []
for item in config["user_input_form"]:
key = list(item.keys())[0]
if key not in ["text-input", "select", "paragraph", "number", "external_data_tool"]:
if key not in {"text-input", "select", "paragraph", "number", "external_data_tool"}:
raise ValueError("Keys in user_input_form list can only be 'text-input', 'paragraph' or 'select'")
form_item = item[key]
@ -115,7 +115,7 @@ class BasicVariablesConfigManager:
pattern = re.compile(r"^(?!\d)[\u4e00-\u9fa5A-Za-z0-9_\U0001F300-\U0001F64F\U0001F680-\U0001F6FF]{1,100}$")
if pattern.match(form_item["variable"]) is None:
raise ValueError("variable in user_input_form must be a string, " "and cannot start with a number")
raise ValueError("variable in user_input_form must be a string, and cannot start with a number")
variables.append(form_item["variable"])

2
api/core/app/app_config/entities.py
View File

@ -92,7 +92,7 @@ class VariableEntityType(str, Enum):
SELECT = "select"
PARAGRAPH = "paragraph"
NUMBER = "number"
EXTERNAL_DATA_TOOL = "external-data-tool"
EXTERNAL_DATA_TOOL = "external_data_tool"
class VariableEntity(BaseModel):

4
api/core/app/app_config/features/file_upload/manager.py
View File

@ -54,14 +54,14 @@ class FileUploadConfigManager:
if is_vision:
detail = config["file_upload"]["image"]["detail"]
if detail not in ["high", "low"]:
if detail not in {"high", "low"}:
raise ValueError("detail must be in ['high', 'low']")
transfer_methods = config["file_upload"]["image"]["transfer_methods"]
if not isinstance(transfer_methods, list):
raise ValueError("transfer_methods must be of list type")
for method in transfer_methods:
if method not in ["remote_url", "local_file"]:
if method not in {"remote_url", "local_file"}:
raise ValueError("transfer_methods must be in ['remote_url', 'local_file']")
return config, ["file_upload"]

4
api/core/app/apps/advanced_chat/app_runner.py
View File

@ -73,7 +73,7 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
raise ValueError("Workflow not initialized")
user_id = None
if self.application_generate_entity.invoke_from in [InvokeFrom.WEB_APP, InvokeFrom.SERVICE_API]:
if self.application_generate_entity.invoke_from in {InvokeFrom.WEB_APP, InvokeFrom.SERVICE_API}:
end_user = db.session.query(EndUser).filter(EndUser.id == self.application_generate_entity.user_id).first()
if end_user:
user_id = end_user.session_id
@ -175,7 +175,7 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
user_id=self.application_generate_entity.user_id,
user_from=(
UserFrom.ACCOUNT
if self.application_generate_entity.invoke_from in [InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER]
if self.application_generate_entity.invoke_from in {InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER}
else UserFrom.END_USER
),
invoke_from=self.application_generate_entity.invoke_from,

2
api/core/app/apps/base_app_generate_response_converter.py
View File

@ -16,7 +16,7 @@ class AppGenerateResponseConverter(ABC):
def convert(
cls, response: Union[AppBlockingResponse, Generator[AppStreamResponse, Any, None]], invoke_from: InvokeFrom
) -> dict[str, Any] | Generator[str, Any, None]:
if invoke_from in [InvokeFrom.DEBUGGER, InvokeFrom.SERVICE_API]:
if invoke_from in {InvokeFrom.DEBUGGER, InvokeFrom.SERVICE_API}:
if isinstance(response, AppBlockingResponse):
return cls.convert_blocking_full_response(response)
else:

6
api/core/app/apps/base_app_generator.py
View File

@ -22,11 +22,11 @@ class BaseAppGenerator:
return var.default or ""
if (
var.type
in (
in {
VariableEntityType.TEXT_INPUT,
VariableEntityType.SELECT,
VariableEntityType.PARAGRAPH,
)
}
and user_input_value
and not isinstance(user_input_value, str)
):
@ -44,7 +44,7 @@ class BaseAppGenerator:
options = var.options or []
if user_input_value not in options:
raise ValueError(f"{var.variable} in input form must be one of the following: {options}")
elif var.type in (VariableEntityType.TEXT_INPUT, VariableEntityType.PARAGRAPH):
elif var.type in {VariableEntityType.TEXT_INPUT, VariableEntityType.PARAGRAPH}:
if var.max_length and user_input_value and len(user_input_value) > var.max_length:
raise ValueError(f"{var.variable} in input form must be less than {var.max_length} characters")

4
api/core/app/apps/base_app_queue_manager.py
View File

@ -32,7 +32,7 @@ class AppQueueManager:
self._user_id = user_id
self._invoke_from = invoke_from
user_prefix = "account" if self._invoke_from in [InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER] else "end-user"
user_prefix = "account" if self._invoke_from in {InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER} else "end-user"
redis_client.setex(
AppQueueManager._generate_task_belong_cache_key(self._task_id), 1800, f"{user_prefix}-{self._user_id}"
)
@ -118,7 +118,7 @@ class AppQueueManager:
if result is None:
return
user_prefix = "account" if invoke_from in [InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER] else "end-user"
user_prefix = "account" if invoke_from in {InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER} else "end-user"
if result.decode("utf-8") != f"{user_prefix}-{user_id}":
return

2
api/core/app/apps/base_app_runner.py
View File

@ -379,7 +379,7 @@ class AppRunner:
queue_manager=queue_manager,
app_generate_entity=application_generate_entity,
prompt_messages=prompt_messages,
text="I apologize for any confusion, " "but I'm an AI assistant to be helpful, harmless, and honest.",
text="I apologize for any confusion, but I'm an AI assistant to be helpful, harmless, and honest.",
stream=application_generate_entity.stream,
)

6
api/core/app/apps/message_based_app_generator.py
View File

@ -148,7 +148,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):
# get from source
end_user_id = None
account_id = None
if application_generate_entity.invoke_from in [InvokeFrom.WEB_APP, InvokeFrom.SERVICE_API]:
if application_generate_entity.invoke_from in {InvokeFrom.WEB_APP, InvokeFrom.SERVICE_API}:
from_source = "api"
end_user_id = application_generate_entity.user_id
else:
@ -165,11 +165,11 @@ class MessageBasedAppGenerator(BaseAppGenerator):
model_provider = application_generate_entity.model_conf.provider
model_id = application_generate_entity.model_conf.model
override_model_configs = None
if app_config.app_model_config_from == EasyUIBasedAppModelConfigFrom.ARGS and app_config.app_mode in [
if app_config.app_model_config_from == EasyUIBasedAppModelConfigFrom.ARGS and app_config.app_mode in {
AppMode.AGENT_CHAT,
AppMode.CHAT,
AppMode.COMPLETION,
]:
}:
override_model_configs = app_config.app_model_config_dict
# get conversation introduction

4
api/core/app/apps/workflow/app_runner.py
View File

@ -53,7 +53,7 @@ class WorkflowAppRunner(WorkflowBasedAppRunner):
app_config = cast(WorkflowAppConfig, app_config)
user_id = None
if self.application_generate_entity.invoke_from in [InvokeFrom.WEB_APP, InvokeFrom.SERVICE_API]:
if self.application_generate_entity.invoke_from in {InvokeFrom.WEB_APP, InvokeFrom.SERVICE_API}:
end_user = db.session.query(EndUser).filter(EndUser.id == self.application_generate_entity.user_id).first()
if end_user:
user_id = end_user.session_id
@ -113,7 +113,7 @@ class WorkflowAppRunner(WorkflowBasedAppRunner):
user_id=self.application_generate_entity.user_id,
user_from=(
UserFrom.ACCOUNT
if self.application_generate_entity.invoke_from in [InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER]
if self.application_generate_entity.invoke_from in {InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER}
else UserFrom.END_USER
),
invoke_from=self.application_generate_entity.invoke_from,

6
api/core/app/apps/workflow_logging_callback.py
View File

@ -84,7 +84,7 @@ class WorkflowLoggingCallback(WorkflowCallback):
if route_node_state.node_run_result:
node_run_result = route_node_state.node_run_result
self.print_text(
f"Inputs: " f"{jsonable_encoder(node_run_result.inputs) if node_run_result.inputs else ''}",
f"Inputs: {jsonable_encoder(node_run_result.inputs) if node_run_result.inputs else ''}",
color="green",
)
self.print_text(
@ -116,7 +116,7 @@ class WorkflowLoggingCallback(WorkflowCallback):
node_run_result = route_node_state.node_run_result
self.print_text(f"Error: {node_run_result.error}", color="red")
self.print_text(
f"Inputs: " f"" f"{jsonable_encoder(node_run_result.inputs) if node_run_result.inputs else ''}",
f"Inputs: {jsonable_encoder(node_run_result.inputs) if node_run_result.inputs else ''}",
color="red",
)
self.print_text(
@ -125,7 +125,7 @@ class WorkflowLoggingCallback(WorkflowCallback):
color="red",
)
self.print_text(
f"Outputs: " f"{jsonable_encoder(node_run_result.outputs) if node_run_result.outputs else ''}",
f"Outputs: {jsonable_encoder(node_run_result.outputs) if node_run_result.outputs else ''}",
color="red",
)

2
api/core/app/features/annotation_reply/annotation_reply.py
View File

@ -63,7 +63,7 @@ class AnnotationReplyFeature:
score = documents[0].metadata["score"]
annotation = AppAnnotationService.get_annotation_by_id(annotation_id)
if annotation:
if invoke_from in [InvokeFrom.SERVICE_API, InvokeFrom.WEB_APP]:
if invoke_from in {InvokeFrom.SERVICE_API, InvokeFrom.WEB_APP}:
from_source = "api"
else:
from_source = "console"

2
api/core/app/task_pipeline/easy_ui_based_generate_task_pipeline.py
View File

@ -372,7 +372,7 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
self._message,
application_generate_entity=self._application_generate_entity,
conversation=self._conversation,
is_first_message=self._application_generate_entity.app_config.app_mode in [AppMode.AGENT_CHAT, AppMode.CHAT]
is_first_message=self._application_generate_entity.app_config.app_mode in {AppMode.AGENT_CHAT, AppMode.CHAT}
and self._application_generate_entity.conversation_id is None,
extras=self._application_generate_entity.extras,
)

4
api/core/app/task_pipeline/workflow_cycle_manage.py
View File

@ -383,7 +383,7 @@ class WorkflowCycleManage:
:param workflow_node_execution: workflow node execution
:return:
"""
if workflow_node_execution.node_type in [NodeType.ITERATION.value, NodeType.LOOP.value]:
if workflow_node_execution.node_type in {NodeType.ITERATION.value, NodeType.LOOP.value}:
return None
response = NodeStartStreamResponse(
@ -430,7 +430,7 @@ class WorkflowCycleManage:
:param workflow_node_execution: workflow node execution
:return:
"""
if workflow_node_execution.node_type in [NodeType.ITERATION.value, NodeType.LOOP.value]:
if workflow_node_execution.node_type in {NodeType.ITERATION.value, NodeType.LOOP.value}:
return None
return NodeFinishStreamResponse(

2
api/core/callback_handler/index_tool_callback_handler.py
View File

@ -29,7 +29,7 @@ class DatasetIndexToolCallbackHandler:
source="app",
source_app_id=self._app_id,
created_by_role=(
"account" if self._invoke_from in [InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER] else "end_user"
"account" if self._invoke_from in {InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER} else "end_user"
),
created_by=self._user_id,
)

11
api/core/embedding/cached_embedding.py
View File

@ -65,7 +65,7 @@ class CacheEmbedding(Embeddings):
except IntegrityError:
db.session.rollback()
except Exception as e:
logging.exception("Failed transform embedding: ", e)
logging.exception("Failed transform embedding: %s", e)
cache_embeddings = []
try:
for i, embedding in zip(embedding_queue_indices, embedding_queue_embeddings):
@ -85,7 +85,7 @@ class CacheEmbedding(Embeddings):
db.session.rollback()
except Exception as ex:
db.session.rollback()
logger.error("Failed to embed documents: ", ex)
logger.error("Failed to embed documents: %s", ex)
raise ex
return text_embeddings
@ -116,10 +116,7 @@ class CacheEmbedding(Embeddings):
# Transform to string
encoded_str = encoded_vector.decode("utf-8")
redis_client.setex(embedding_cache_key, 600, encoded_str)
except IntegrityError:
db.session.rollback()
except:
logging.exception("Failed to add embedding to redis")
except Exception as ex:
logging.exception("Failed to add embedding to redis %s", ex)
return embedding_results

2
api/core/indexing_runner.py
View File

@ -292,7 +292,7 @@ class IndexingRunner:
self, index_processor: BaseIndexProcessor, dataset_document: DatasetDocument, process_rule: dict
) -> list[Document]:
# load file
if dataset_document.data_source_type not in ["upload_file", "notion_import", "website_crawl"]:
if dataset_document.data_source_type not in {"upload_file", "notion_import", "website_crawl"}:
return []
data_source_info = dataset_document.data_source_info_dict

2
api/core/memory/token_buffer_memory.py
View File

@ -52,7 +52,7 @@ class TokenBufferMemory:
files = db.session.query(MessageFile).filter(MessageFile.message_id == message.id).all()
if files:
file_extra_config = None
if self.conversation.mode not in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]:
if self.conversation.mode not in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
file_extra_config = FileUploadConfigManager.convert(self.conversation.model_config)
else:
if message.workflow_run_id:

12
api/core/model_runtime/entities/model_entities.py
View File

@ -27,17 +27,17 @@ class ModelType(Enum):
:return: model type
"""
if origin_model_type == "text-generation" or origin_model_type == cls.LLM.value:
if origin_model_type in {"text-generation", cls.LLM.value}:
return cls.LLM
elif origin_model_type == "embeddings" or origin_model_type == cls.TEXT_EMBEDDING.value:
elif origin_model_type in {"embeddings", cls.TEXT_EMBEDDING.value}:
return cls.TEXT_EMBEDDING
elif origin_model_type == "reranking" or origin_model_type == cls.RERANK.value:
elif origin_model_type in {"reranking", cls.RERANK.value}:
return cls.RERANK
elif origin_model_type == "speech2text" or origin_model_type == cls.SPEECH2TEXT.value:
elif origin_model_type in {"speech2text", cls.SPEECH2TEXT.value}:
return cls.SPEECH2TEXT
elif origin_model_type == "tts" or origin_model_type == cls.TTS.value:
elif origin_model_type in {"tts", cls.TTS.value}:
return cls.TTS
elif origin_model_type == "text2img" or origin_model_type == cls.TEXT2IMG.value:
elif origin_model_type in {"text2img", cls.TEXT2IMG.value}:
return cls.TEXT2IMG
elif origin_model_type == cls.MODERATION.value:
return cls.MODERATION

2
api/core/model_runtime/model_providers/__base/ai_model.py
View File

@ -200,7 +200,7 @@ class AIModel(ABC):
except Exception as e:
model_schema_yaml_file_name = os.path.basename(model_schema_yaml_path).rstrip(".yaml")
raise Exception(
f"Invalid model schema for {provider_name}.{model_type}.{model_schema_yaml_file_name}:" f" {str(e)}"
f"Invalid model schema for {provider_name}.{model_type}.{model_schema_yaml_file_name}: {str(e)}"
)
# cache model schema

2
api/core/model_runtime/model_providers/anthropic/llm/llm.py
View File

@ -494,7 +494,7 @@ class AnthropicLargeLanguageModel(LargeLanguageModel):
mime_type = data_split[0].replace("data:", "")
base64_data = data_split[1]
if mime_type not in ["image/jpeg", "image/png", "image/gif", "image/webp"]:
if mime_type not in {"image/jpeg", "image/png", "image/gif", "image/webp"}:
raise ValueError(
f"Unsupported image type {mime_type}, "
f"only support image/jpeg, image/png, image/gif, and image/webp"

6
api/core/model_runtime/model_providers/azure_openai/azure_openai.yaml
View File

@ -53,6 +53,12 @@ model_credential_schema:
type: select
required: true
options:
- label:
en_US: 2024-08-01-preview
value: 2024-08-01-preview
- label:
en_US: 2024-07-01-preview
value: 2024-07-01-preview
- label:
en_US: 2024-05-01-preview
value: 2024-05-01-preview

4
api/core/model_runtime/model_providers/azure_openai/tts/tts.py
View File

@ -85,14 +85,14 @@ class AzureOpenAIText2SpeechModel(_CommonAzureOpenAI, TTSModel):
for i in range(len(sentences))
]
for future in futures:
yield from future.result().__enter__().iter_bytes(1024)
yield from future.result().__enter__().iter_bytes(1024) # noqa:PLC2801
else:
response = client.audio.speech.with_streaming_response.create(
model=model, voice=voice, response_format="mp3", input=content_text.strip()
)
yield from response.__enter__().iter_bytes(1024)
yield from response.__enter__().iter_bytes(1024) # noqa:PLC2801
except Exception as ex:
raise InvokeBadRequestError(str(ex))

2
api/core/model_runtime/model_providers/baichuan/llm/baichuan3-turbo-128k.yaml
View File

@ -33,7 +33,7 @@ parameter_rules:
- name: res_format
label:
zh_Hans: 回复格式
en_US: response format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

2
api/core/model_runtime/model_providers/baichuan/llm/baichuan3-turbo.yaml
View File

@ -33,7 +33,7 @@ parameter_rules:
- name: res_format
label:
zh_Hans: 回复格式
en_US: response format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

2
api/core/model_runtime/model_providers/baichuan/llm/baichuan4.yaml
View File

@ -33,7 +33,7 @@ parameter_rules:
- name: res_format
label:
zh_Hans: 回复格式
en_US: response format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

59
api/core/model_runtime/model_providers/bedrock/llm/eu.anthropic.claude-3-haiku-v1.yaml Normal file
View File

@ -0,0 +1,59 @@
model: eu.anthropic.claude-3-haiku-20240307-v1:0
label:
en_US: Claude 3 Haiku(EU.Cross Region Inference)
model_type: llm
features:
- agent-thought
- vision
- tool-call
- stream-tool-call
model_properties:
mode: chat
context_size: 200000
# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
parameter_rules:
- name: max_tokens
use_template: max_tokens
required: true
type: int
default: 4096
min: 1
max: 4096
help:
zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
# docs: https://docs.anthropic.com/claude/docs/system-prompts
- name: temperature
use_template: temperature
required: false
type: float
default: 1
min: 0.0
max: 1.0
help:
zh_Hans: 生成内容的随机性。
en_US: The amount of randomness injected into the response.
- name: top_p
required: false
type: float
default: 0.999
min: 0.000
max: 1.000
help:
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
- name: top_k
required: false
type: int
default: 0
min: 0
# tip docs from aws has error, max value is 500
max: 500
help:
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
pricing:
input: '0.00025'
output: '0.00125'
unit: '0.001'
currency: USD

58
api/core/model_runtime/model_providers/bedrock/llm/eu.anthropic.claude-3-sonnet-v1.5.yaml Normal file
View File

@ -0,0 +1,58 @@
model: eu.anthropic.claude-3-5-sonnet-20240620-v1:0
label:
en_US: Claude 3.5 Sonnet(EU.Cross Region Inference)
model_type: llm
features:
- agent-thought
- vision
- tool-call
- stream-tool-call
model_properties:
mode: chat
context_size: 200000
# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
parameter_rules:
- name: max_tokens
use_template: max_tokens
required: true
type: int
default: 4096
min: 1
max: 4096
help:
zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
- name: temperature
use_template: temperature
required: false
type: float
default: 1
min: 0.0
max: 1.0
help:
zh_Hans: 生成内容的随机性。
en_US: The amount of randomness injected into the response.
- name: top_p
required: false
type: float
default: 0.999
min: 0.000
max: 1.000
help:
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
- name: top_k
required: false
type: int
default: 0
min: 0
# tip docs from aws has error, max value is 500
max: 500
help:
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
pricing:
input: '0.003'
output: '0.015'
unit: '0.001'
currency: USD

58
api/core/model_runtime/model_providers/bedrock/llm/eu.anthropic.claude-3-sonnet-v1.yaml Normal file
View File

@ -0,0 +1,58 @@
model: eu.anthropic.claude-3-sonnet-20240229-v1:0
label:
en_US: Claude 3 Sonnet(EU.Cross Region Inference)
model_type: llm
features:
- agent-thought
- vision
- tool-call
- stream-tool-call
model_properties:
mode: chat
context_size: 200000
# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
parameter_rules:
- name: max_tokens
use_template: max_tokens
required: true
type: int
default: 4096
min: 1
max: 4096
help:
zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
- name: temperature
use_template: temperature
required: false
type: float
default: 1
min: 0.0
max: 1.0
help:
zh_Hans: 生成内容的随机性。
en_US: The amount of randomness injected into the response.
- name: top_p
required: false
type: float
default: 0.999
min: 0.000
max: 1.000
help:
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
- name: top_k
required: false
type: int
default: 0
min: 0
# tip docs from aws has error, max value is 500
max: 500
help:
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
pricing:
input: '0.003'
output: '0.015'
unit: '0.001'
currency: USD

12
api/core/model_runtime/model_providers/bedrock/llm/llm.py
View File

@ -61,6 +61,8 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
CONVERSE_API_ENABLED_MODEL_INFO = [
{"prefix": "anthropic.claude-v2", "support_system_prompts": True, "support_tool_use": False},
{"prefix": "anthropic.claude-v1", "support_system_prompts": True, "support_tool_use": False},
{"prefix": "us.anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
{"prefix": "eu.anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
{"prefix": "anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
{"prefix": "meta.llama", "support_system_prompts": True, "support_tool_use": False},
{"prefix": "mistral.mistral-7b-instruct", "support_system_prompts": False, "support_tool_use": False},
@ -452,7 +454,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
base64_data = data_split[1]
image_content = base64.b64decode(base64_data)
if mime_type not in ["image/jpeg", "image/png", "image/gif", "image/webp"]:
if mime_type not in {"image/jpeg", "image/png", "image/gif", "image/webp"}:
raise ValueError(
f"Unsupported image type {mime_type}, "
f"only support image/jpeg, image/png, image/gif, and image/webp"
@ -884,16 +886,16 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
if error_code == "AccessDeniedException":
return InvokeAuthorizationError(error_msg)
elif error_code in ["ResourceNotFoundException", "ValidationException"]:
elif error_code in {"ResourceNotFoundException", "ValidationException"}:
return InvokeBadRequestError(error_msg)
elif error_code in ["ThrottlingException", "ServiceQuotaExceededException"]:
elif error_code in {"ThrottlingException", "ServiceQuotaExceededException"}:
return InvokeRateLimitError(error_msg)
elif error_code in [
elif error_code in {
"ModelTimeoutException",
"ModelErrorException",
"InternalServerException",
"ModelNotReadyException",
]:
}:
return InvokeServerUnavailableError(error_msg)
elif error_code == "ModelStreamErrorException":
return InvokeConnectionError(error_msg)

59
api/core/model_runtime/model_providers/bedrock/llm/us.anthropic.claude-3-haiku-v1.yaml Normal file
View File

@ -0,0 +1,59 @@
model: us.anthropic.claude-3-haiku-20240307-v1:0
label:
en_US: Claude 3 Haiku(US.Cross Region Inference)
model_type: llm
features:
- agent-thought
- vision
- tool-call
- stream-tool-call
model_properties:
mode: chat
context_size: 200000
# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
parameter_rules:
- name: max_tokens
use_template: max_tokens
required: true
type: int
default: 4096
min: 1
max: 4096
help:
zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
# docs: https://docs.anthropic.com/claude/docs/system-prompts
- name: temperature
use_template: temperature
required: false
type: float
default: 1
min: 0.0
max: 1.0
help:
zh_Hans: 生成内容的随机性。
en_US: The amount of randomness injected into the response.
- name: top_p
required: false
type: float
default: 0.999
min: 0.000
max: 1.000
help:
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
- name: top_k
required: false
type: int
default: 0
min: 0
# tip docs from aws has error, max value is 500
max: 500
help:
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
pricing:
input: '0.00025'
output: '0.00125'
unit: '0.001'
currency: USD

59
api/core/model_runtime/model_providers/bedrock/llm/us.anthropic.claude-3-opus-v1.yaml Normal file
View File

@ -0,0 +1,59 @@
model: us.anthropic.claude-3-opus-20240229-v1:0
label:
en_US: Claude 3 Opus(US.Cross Region Inference)
model_type: llm
features:
- agent-thought
- vision
- tool-call
- stream-tool-call
model_properties:
mode: chat
context_size: 200000
# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
parameter_rules:
- name: max_tokens
use_template: max_tokens
required: true
type: int
default: 4096
min: 1
max: 4096
help:
zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
# docs: https://docs.anthropic.com/claude/docs/system-prompts
- name: temperature
use_template: temperature
required: false
type: float
default: 1
min: 0.0
max: 1.0
help:
zh_Hans: 生成内容的随机性。
en_US: The amount of randomness injected into the response.
- name: top_p
required: false
type: float
default: 0.999
min: 0.000
max: 1.000
help:
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
- name: top_k
required: false
type: int
default: 0
min: 0
# tip docs from aws has error, max value is 500
max: 500
help:
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
pricing:
input: '0.015'
output: '0.075'
unit: '0.001'
currency: USD

58
api/core/model_runtime/model_providers/bedrock/llm/us.anthropic.claude-3-sonnet-v1.5.yaml Normal file
View File

@ -0,0 +1,58 @@
model: us.anthropic.claude-3-5-sonnet-20240620-v1:0
label:
en_US: Claude 3.5 Sonnet(US.Cross Region Inference)
model_type: llm
features:
- agent-thought
- vision
- tool-call
- stream-tool-call
model_properties:
mode: chat
context_size: 200000
# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
parameter_rules:
- name: max_tokens
use_template: max_tokens
required: true
type: int
default: 4096
min: 1
max: 4096
help:
zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
- name: temperature
use_template: temperature
required: false
type: float
default: 1
min: 0.0
max: 1.0
help:
zh_Hans: 生成内容的随机性。
en_US: The amount of randomness injected into the response.
- name: top_p
required: false
type: float
default: 0.999
min: 0.000
max: 1.000
help:
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
- name: top_k
required: false
type: int
default: 0
min: 0
# tip docs from aws has error, max value is 500
max: 500
help:
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
pricing:
input: '0.003'
output: '0.015'
unit: '0.001'
currency: USD

58
api/core/model_runtime/model_providers/bedrock/llm/us.anthropic.claude-3-sonnet-v1.yaml Normal file
View File

@ -0,0 +1,58 @@
model: us.anthropic.claude-3-sonnet-20240229-v1:0
label:
en_US: Claude 3 Sonnet(US.Cross Region Inference)
model_type: llm
features:
- agent-thought
- vision
- tool-call
- stream-tool-call
model_properties:
mode: chat
context_size: 200000
# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
parameter_rules:
- name: max_tokens
use_template: max_tokens
required: true
type: int
default: 4096
min: 1
max: 4096
help:
zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
- name: temperature
use_template: temperature
required: false
type: float
default: 1
min: 0.0
max: 1.0
help:
zh_Hans: 生成内容的随机性。
en_US: The amount of randomness injected into the response.
- name: top_p
required: false
type: float
default: 0.999
min: 0.000
max: 1.000
help:
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
- name: top_k
required: false
type: int
default: 0
min: 0
# tip docs from aws has error, max value is 500
max: 500
help:
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
pricing:
input: '0.003'
output: '0.015'
unit: '0.001'
currency: USD

8
api/core/model_runtime/model_providers/bedrock/text_embedding/text_embedding.py
View File

@ -186,16 +186,16 @@ class BedrockTextEmbeddingModel(TextEmbeddingModel):
if error_code == "AccessDeniedException":
return InvokeAuthorizationError(error_msg)
elif error_code in ["ResourceNotFoundException", "ValidationException"]:
elif error_code in {"ResourceNotFoundException", "ValidationException"}:
return InvokeBadRequestError(error_msg)
elif error_code in ["ThrottlingException", "ServiceQuotaExceededException"]:
elif error_code in {"ThrottlingException", "ServiceQuotaExceededException"}:
return InvokeRateLimitError(error_msg)
elif error_code in [
elif error_code in {
"ModelTimeoutException",
"ModelErrorException",
"InternalServerException",
"ModelNotReadyException",
]:
}:
return InvokeServerUnavailableError(error_msg)
elif error_code == "ModelStreamErrorException":
return InvokeConnectionError(error_msg)

2
api/core/model_runtime/model_providers/cohere/llm/llm.py
View File

@ -621,7 +621,7 @@ class CohereLargeLanguageModel(LargeLanguageModel):
desc = p_val["description"]
if "enum" in p_val:
desc += f"; Only accepts one of the following predefined options: " f"[{', '.join(p_val['enum'])}]"
desc += f"; Only accepts one of the following predefined options: [{', '.join(p_val['enum'])}]"
parameter_definitions[p_key] = ToolParameterDefinitionsValue(
description=desc, type=p_val["type"], required=required

2
api/core/model_runtime/model_providers/deepseek/llm/deepseek-chat.yaml
View File

@ -62,7 +62,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

4
api/core/model_runtime/model_providers/google/llm/llm.py
View File

@ -6,10 +6,10 @@ from collections.abc import Generator
from typing import Optional, Union, cast
import google.ai.generativelanguage as glm
import google.api_core.exceptions as exceptions
import google.generativeai as genai
import google.generativeai.client as client
import requests
from google.api_core import exceptions
from google.generativeai import client
from google.generativeai.types import ContentType, GenerateContentResponse, HarmBlockThreshold, HarmCategory
from google.generativeai.types.content_types import to_part
from PIL import Image

8
api/core/model_runtime/model_providers/huggingface_hub/llm/llm.py
View File

@ -77,7 +77,7 @@ class HuggingfaceHubLargeLanguageModel(_CommonHuggingfaceHub, LargeLanguageModel
if "huggingfacehub_api_type" not in credentials:
raise CredentialsValidateFailedError("Huggingface Hub Endpoint Type must be provided.")
if credentials["huggingfacehub_api_type"] not in ("inference_endpoints", "hosted_inference_api"):
if credentials["huggingfacehub_api_type"] not in {"inference_endpoints", "hosted_inference_api"}:
raise CredentialsValidateFailedError("Huggingface Hub Endpoint Type is invalid.")
if "huggingfacehub_api_token" not in credentials:
@ -94,9 +94,9 @@ class HuggingfaceHubLargeLanguageModel(_CommonHuggingfaceHub, LargeLanguageModel
credentials["huggingfacehub_api_token"], model
)
if credentials["task_type"] not in ("text2text-generation", "text-generation"):
if credentials["task_type"] not in {"text2text-generation", "text-generation"}:
raise CredentialsValidateFailedError(
"Huggingface Hub Task Type must be one of text2text-generation, " "text-generation."
"Huggingface Hub Task Type must be one of text2text-generation, text-generation."
)
client = InferenceClient(token=credentials["huggingfacehub_api_token"])
@ -282,7 +282,7 @@ class HuggingfaceHubLargeLanguageModel(_CommonHuggingfaceHub, LargeLanguageModel
valid_tasks = ("text2text-generation", "text-generation")
if model_info.pipeline_tag not in valid_tasks:
raise ValueError(f"Model {model_name} is not a valid task, " f"must be one of {valid_tasks}.")
raise ValueError(f"Model {model_name} is not a valid task, must be one of {valid_tasks}.")
except Exception as e:
raise CredentialsValidateFailedError(f"{str(e)}")

2
api/core/model_runtime/model_providers/huggingface_hub/text_embedding/text_embedding.py
View File

@ -121,7 +121,7 @@ class HuggingfaceHubTextEmbeddingModel(_CommonHuggingfaceHub, TextEmbeddingModel
valid_tasks = "feature-extraction"
if model_info.pipeline_tag not in valid_tasks:
raise ValueError(f"Model {model_name} is not a valid task, " f"must be one of {valid_tasks}.")
raise ValueError(f"Model {model_name} is not a valid task, must be one of {valid_tasks}.")
except Exception as e:
raise CredentialsValidateFailedError(f"{str(e)}")

3
api/core/model_runtime/model_providers/huggingface_tei/rerank/rerank.py
View File

@ -49,8 +49,7 @@ class HuggingfaceTeiRerankModel(RerankModel):
return RerankResult(model=model, docs=[])
server_url = credentials["server_url"]
if server_url.endswith("/"):
server_url = server_url[:-1]
server_url = server_url.removesuffix("/")
try:
results = TeiHelper.invoke_rerank(server_url, query, docs)

2
api/core/model_runtime/model_providers/huggingface_tei/tei_helper.py
View File

@ -75,7 +75,7 @@ class TeiHelper:
if len(model_type.keys()) < 1:
raise RuntimeError("model_type is empty")
model_type = list(model_type.keys())[0]
if model_type not in ["embedding", "reranker"]:
if model_type not in {"embedding", "reranker"}:
raise RuntimeError(f"invalid model_type: {model_type}")
max_input_length = response_json.get("max_input_length", 512)

6
api/core/model_runtime/model_providers/huggingface_tei/text_embedding/text_embedding.py
View File

@ -42,8 +42,7 @@ class HuggingfaceTeiTextEmbeddingModel(TextEmbeddingModel):
"""
server_url = credentials["server_url"]
if server_url.endswith("/"):
server_url = server_url[:-1]
server_url = server_url.removesuffix("/")
# get model properties
context_size = self._get_context_size(model, credentials)
@ -119,8 +118,7 @@ class HuggingfaceTeiTextEmbeddingModel(TextEmbeddingModel):
num_tokens = 0
server_url = credentials["server_url"]
if server_url.endswith("/"):
server_url = server_url[:-1]
server_url = server_url.removesuffix("/")
batch_tokens = TeiHelper.invoke_tokenize(server_url, texts)
num_tokens = sum(len(tokens) for tokens in batch_tokens)

1
api/core/model_runtime/model_providers/hunyuan/llm/_position.yaml
View File

@ -2,3 +2,4 @@
- hunyuan-standard
- hunyuan-standard-256k
- hunyuan-pro
- hunyuan-turbo

38
api/core/model_runtime/model_providers/hunyuan/llm/hunyuan-turbo.yaml Normal file
View File

@ -0,0 +1,38 @@
model: hunyuan-turbo
label:
zh_Hans: hunyuan-turbo
en_US: hunyuan-turbo
model_type: llm
features:
- agent-thought
- tool-call
- multi-tool-call
- stream-tool-call
model_properties:
mode: chat
context_size: 32000
parameter_rules:
- name: temperature
use_template: temperature
- name: top_p
use_template: top_p
- name: max_tokens
use_template: max_tokens
default: 1024
min: 1
max: 32000
- name: enable_enhance
label:
zh_Hans: 功能增强
en_US: Enable Enhancement
type: boolean
help:
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
en_US: Allow the model to perform external search to enhance the generation results.
required: false
default: true
pricing:
input: '0.015'
output: '0.05'
unit: '0.001'
currency: RMB

3
api/core/model_runtime/model_providers/jina/rerank/rerank.py
View File

@ -48,8 +48,7 @@ class JinaRerankModel(RerankModel):
return RerankResult(model=model, docs=[])
base_url = credentials.get("base_url", "https://api.jina.ai/v1")
if base_url.endswith("/"):
base_url = base_url[:-1]
base_url = base_url.removesuffix("/")
try:
response = httpx.post(

3
api/core/model_runtime/model_providers/jina/text_embedding/text_embedding.py
View File

@ -44,8 +44,7 @@ class JinaTextEmbeddingModel(TextEmbeddingModel):
raise CredentialsValidateFailedError("api_key is required")
base_url = credentials.get("base_url", self.api_base)
if base_url.endswith("/"):
base_url = base_url[:-1]
base_url = base_url.removesuffix("/")
url = base_url + "/embeddings"
headers = {"Authorization": "Bearer " + api_key, "Content-Type": "application/json"}

4
api/core/model_runtime/model_providers/minimax/llm/chat_completion.py
View File

@ -100,9 +100,9 @@ class MinimaxChatCompletion:
return self._handle_chat_generate_response(response)
def _handle_error(self, code: int, msg: str):
if code == 1000 or code == 1001 or code == 1013 or code == 1027:
if code in {1000, 1001, 1013, 1027}:
raise InternalServerError(msg)
elif code == 1002 or code == 1039:
elif code in {1002, 1039}:
raise RateLimitReachedError(msg)
elif code == 1004:
raise InvalidAuthenticationError(msg)

4
api/core/model_runtime/model_providers/minimax/llm/chat_completion_pro.py
View File

@ -105,9 +105,9 @@ class MinimaxChatCompletionPro:
return self._handle_chat_generate_response(response)
def _handle_error(self, code: int, msg: str):
if code == 1000 or code == 1001 or code == 1013 or code == 1027:
if code in {1000, 1001, 1013, 1027}:
raise InternalServerError(msg)
elif code == 1002 or code == 1039:
elif code in {1002, 1039}:
raise RateLimitReachedError(msg)
elif code == 1004:
raise InvalidAuthenticationError(msg)

2
api/core/model_runtime/model_providers/minimax/text_embedding/text_embedding.py
View File

@ -114,7 +114,7 @@ class MinimaxTextEmbeddingModel(TextEmbeddingModel):
raise CredentialsValidateFailedError("Invalid api key")
def _handle_error(self, code: int, msg: str):
if code == 1000 or code == 1001:
if code in {1000, 1001}:
raise InternalServerError(msg)
elif code == 1002:
raise RateLimitReachedError(msg)

2
api/core/model_runtime/model_providers/moonshot/llm/moonshot-v1-128k.yaml
View File

@ -24,7 +24,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

2
api/core/model_runtime/model_providers/moonshot/llm/moonshot-v1-32k.yaml
View File

@ -24,7 +24,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

2
api/core/model_runtime/model_providers/moonshot/llm/moonshot-v1-8k.yaml
View File

@ -24,7 +24,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

4
api/core/model_runtime/model_providers/ollama/llm/llm.py
View File

@ -572,7 +572,7 @@ class OllamaLargeLanguageModel(LargeLanguageModel):
label=I18nObject(en_US="Size of context window"),
type=ParameterType.INT,
help=I18nObject(
en_US="Sets the size of the context window used to generate the next token. " "(Default: 2048)"
en_US="Sets the size of the context window used to generate the next token. (Default: 2048)"
),
default=2048,
min=1,
@ -650,7 +650,7 @@ class OllamaLargeLanguageModel(LargeLanguageModel):
label=I18nObject(en_US="Format"),
type=ParameterType.STRING,
help=I18nObject(
en_US="the format to return a response in." " Currently the only accepted value is json."
en_US="the format to return a response in. Currently the only accepted value is json."
),
options=["json"],
),

4
api/core/model_runtime/model_providers/openai/llm/_position.yaml
View File

@ -5,6 +5,10 @@
- chatgpt-4o-latest
- gpt-4o-mini
- gpt-4o-mini-2024-07-18
- o1-preview
- o1-preview-2024-09-12
- o1-mini
- o1-mini-2024-09-12
- gpt-4-turbo
- gpt-4-turbo-2024-04-09
- gpt-4-turbo-preview

2
api/core/model_runtime/model_providers/openai/llm/chatgpt-4o-latest.yaml
View File

@ -28,7 +28,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

2
api/core/model_runtime/model_providers/openai/llm/gpt-3.5-turbo-0125.yaml
View File

@ -27,7 +27,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

2
api/core/model_runtime/model_providers/openai/llm/gpt-3.5-turbo-1106.yaml
View File

@ -27,7 +27,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

2
api/core/model_runtime/model_providers/openai/llm/gpt-3.5-turbo.yaml
View File

@ -27,7 +27,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

2
api/core/model_runtime/model_providers/openai/llm/gpt-4-0125-preview.yaml
View File

@ -40,7 +40,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

2
api/core/model_runtime/model_providers/openai/llm/gpt-4-1106-preview.yaml
View File

@ -40,7 +40,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

2
api/core/model_runtime/model_providers/openai/llm/gpt-4-32k.yaml
View File

@ -40,7 +40,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

2
api/core/model_runtime/model_providers/openai/llm/gpt-4-turbo-2024-04-09.yaml
View File

@ -41,7 +41,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

2
api/core/model_runtime/model_providers/openai/llm/gpt-4-turbo-preview.yaml
View File

@ -40,7 +40,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

2
api/core/model_runtime/model_providers/openai/llm/gpt-4-turbo.yaml
View File

@ -41,7 +41,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

2
api/core/model_runtime/model_providers/openai/llm/gpt-4-vision-preview.yaml
View File

@ -38,7 +38,7 @@ parameter_rules:
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
en_US: Response Format
type: string
help:
zh_Hans: 指定模型必须输出的格式

Some files were not shown because too many files have changed in this diff Show More