Merge bab530209e into 075b8bf1ae

api/AGENTS.md

@@ -51,6 +51,7 @@ This is the default standard for backend code in this repo. Follow it for new co
 
 - Use Ruff for formatting and linting (follow `.ruff.toml`).
 - Keep each line under 120 characters (including spaces).
+- Avoid using bare `# type: ignore` to ignore all type violations. Always specify an error code (e.g. `# type: ignore[operator, attr-defined]`).
 
 ### Naming Conventions
 

api/celery_entrypoint.py

@@ -1,5 +1,5 @@
-import psycogreen.gevent as pscycogreen_gevent  # type: ignore
+import psycogreen.gevent as pscycogreen_gevent  # type: ignore[reportMissingTypeStubs]
-from grpc.experimental import gevent as grpc_gevent  # type: ignore
+from grpc.experimental import gevent as grpc_gevent  # type: ignore[reportMissingTypeStubs]
 
 # grpc gevent
 grpc_gevent.init_gevent()

api/configs/__init__.py

@@ -1,3 +1,3 @@
 from .app_config import DifyConfig
 
-dify_config = DifyConfig()  # type: ignore
+dify_config = DifyConfig()  # type: ignore[call-arg, assignment]

api/context/flask_app_context.py

@@ -72,7 +72,7 @@ def capture_flask_context(user: Any = None) -> IExecutionContext:
         RuntimeError: If called outside Flask context
     """
     # Get Flask app instance
-    flask_app = current_app._get_current_object()  # type: ignore
+    flask_app = current_app._get_current_object()  # type: ignore[attr-defined]
 
     # Save current user if available
     saved_user = user

api/controllers/common/fields.py

@@ -51,7 +51,7 @@ class Site(BaseModel):
     show_workflow_steps: bool
     use_icon_as_answer_icon: bool
 
-    @computed_field(return_type=str | None)  # type: ignore
+    @computed_field(return_type=str | None)  # type: ignore[prop-decorator]
     @property
     def icon_url(self) -> str | None:
         if self.icon and self.icon_type == IconType.IMAGE:

api/controllers/console/apikey.py

@@ -148,7 +148,7 @@ class AppApiKeyListResource(BaseApiKeyListResource):
     @console_ns.doc(description="Get all API keys for an app")
     @console_ns.doc(params={"resource_id": "App ID"})
     @console_ns.response(200, "Success", api_key_list_model)
-    def get(self, resource_id):  # type: ignore
+    def get(self, resource_id):  # type: ignore[misc]
         """Get all API keys for an app"""
         return super().get(resource_id)
 
@@ -157,7 +157,7 @@ class AppApiKeyListResource(BaseApiKeyListResource):
     @console_ns.doc(params={"resource_id": "App ID"})
     @console_ns.response(201, "API key created successfully", api_key_item_model)
     @console_ns.response(400, "Maximum keys exceeded")
-    def post(self, resource_id):  # type: ignore
+    def post(self, resource_id):  # type: ignore[misc]
         """Create a new API key for an app"""
         return super().post(resource_id)
 
@@ -188,7 +188,7 @@ class DatasetApiKeyListResource(BaseApiKeyListResource):
     @console_ns.doc(description="Get all API keys for a dataset")
     @console_ns.doc(params={"resource_id": "Dataset ID"})
     @console_ns.response(200, "Success", api_key_list_model)
-    def get(self, resource_id):  # type: ignore
+    def get(self, resource_id):  # type: ignore[misc]
         """Get all API keys for a dataset"""
         return super().get(resource_id)
 
@@ -197,7 +197,7 @@ class DatasetApiKeyListResource(BaseApiKeyListResource):
     @console_ns.doc(params={"resource_id": "Dataset ID"})
     @console_ns.response(201, "API key created successfully", api_key_item_model)
     @console_ns.response(400, "Maximum keys exceeded")
-    def post(self, resource_id):  # type: ignore
+    def post(self, resource_id):  # type: ignore[misc]
         """Create a new API key for a dataset"""
         return super().post(resource_id)
 

api/controllers/console/app/advanced_prompt_template.py

@@ -34,6 +34,6 @@ class AdvancedPromptTemplateList(Resource):
     @login_required
     @account_initialization_required
     def get(self):
-        args = AdvancedPromptTemplateQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = AdvancedPromptTemplateQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         return AdvancedPromptTemplateService.get_prompt(args.model_dump())

api/controllers/console/app/agent.py

@@ -44,6 +44,6 @@ class AgentLogApi(Resource):
     @get_app_model(mode=[AppMode.AGENT_CHAT])
     def get(self, app_model):
         """Get agent logs"""
-        args = AgentLogQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = AgentLogQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         return AgentService.get_agent_logs(app_model, args.conversation_id, args.message_id)

api/controllers/console/app/annotation.py

@@ -206,7 +206,7 @@ class AnnotationApi(Resource):
     @account_initialization_required
     @edit_permission_required
     def get(self, app_id):
-        args = AnnotationListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = AnnotationListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
         page = args.page
         limit = args.limit
         keyword = args.keyword

api/controllers/console/app/app.py

@@ -299,7 +299,7 @@ class Site(ResponseModel):
     updated_by: str | None = None
     updated_at: int | None = None
 
-    @computed_field(return_type=str | None)  # type: ignore
+    @computed_field(return_type=str | None)  # type: ignore[prop-decorator]
     @property
     def icon_url(self) -> str | None:
         return _build_icon_url(self.icon_type, self.icon)
@@ -349,7 +349,7 @@ class AppPartial(ResponseModel):
     author_name: str | None = None
     has_draft_trigger: bool | None = None
 
-    @computed_field(return_type=str | None)  # type: ignore
+    @computed_field(return_type=str | None)  # type: ignore[prop-decorator]
     @property
     def icon_url(self) -> str | None:
         return _build_icon_url(self.icon_type, self.icon)
@@ -397,7 +397,7 @@ class AppDetailWithSite(AppDetail):
     deleted_tools: list[DeletedTool] = Field(default_factory=list)
     site: Site | None = None
 
-    @computed_field(return_type=str | None)  # type: ignore
+    @computed_field(return_type=str | None)  # type: ignore[prop-decorator]
     @property
     def icon_url(self) -> str | None:
         return _build_icon_url(self.icon_type, self.icon)
@@ -473,7 +473,7 @@ class AppListApi(Resource):
         """Get app list"""
         current_user, current_tenant_id = current_account_with_tenant()
 
-        args = AppListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = AppListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
         args_dict = args.model_dump()
 
         # get app list
@@ -692,7 +692,7 @@ class AppExportApi(Resource):
     @edit_permission_required
     def get(self, app_model):
         """Export app"""
-        args = AppExportQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = AppExportQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         payload = AppExportResponse(
             data=AppDslService.export_dsl(

api/controllers/console/app/audio.py

@@ -173,7 +173,7 @@ class TextModesApi(Resource):
     @account_initialization_required
     def get(self, app_model):
         try:
-            args = TextToSpeechVoiceQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+            args = TextToSpeechVoiceQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
             response = AudioService.transcript_tts_voices(
                 tenant_id=app_model.tenant_id,

api/controllers/console/app/conversation.py

@@ -342,7 +342,7 @@ class CompletionConversationApi(Resource):
     @edit_permission_required
     def get(self, app_model):
         current_user, _ = current_account_with_tenant()
-        args = CompletionConversationQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = CompletionConversationQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         query = sa.select(Conversation).where(
             Conversation.app_id == app_model.id, Conversation.mode == "completion", Conversation.is_deleted.is_(False)
@@ -378,7 +378,7 @@ class CompletionConversationApi(Resource):
         if args.annotation_status == "annotated":
             query = (
                 query.options(selectinload(Conversation.message_annotations))  # type: ignore[arg-type]
-                .join(  # type: ignore
+                .join(  # type: ignore[arg-type]
                     MessageAnnotation, MessageAnnotation.conversation_id == Conversation.id
                 )
                 .distinct()
@@ -455,7 +455,7 @@ class ChatConversationApi(Resource):
     @edit_permission_required
     def get(self, app_model):
         current_user, _ = current_account_with_tenant()
-        args = ChatConversationQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ChatConversationQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         subquery = (
             sa.select(Conversation.id.label("conversation_id"), EndUser.session_id.label("from_end_user_session_id"))
@@ -515,7 +515,7 @@ class ChatConversationApi(Resource):
             case "annotated":
                 query = (
                     query.options(selectinload(Conversation.message_annotations))  # type: ignore[arg-type]
-                    .join(  # type: ignore
+                    .join(  # type: ignore[arg-type]
                         MessageAnnotation, MessageAnnotation.conversation_id == Conversation.id
                     )
                     .distinct()

api/controllers/console/app/conversation_variables.py

@@ -55,7 +55,7 @@ class ConversationVariablesApi(Resource):
     @get_app_model(mode=AppMode.ADVANCED_CHAT)
     @marshal_with(paginated_conversation_variable_model)
     def get(self, app_model):
-        args = ConversationVariablesQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ConversationVariablesQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         stmt = (
             select(ConversationVariable)

api/controllers/console/app/ops_trace.py

@@ -50,7 +50,7 @@ class TraceAppConfigApi(Resource):
     @login_required
     @account_initialization_required
     def get(self, app_id):
-        args = TraceProviderQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = TraceProviderQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         try:
             trace_config = OpsService.get_tracing_app_config(app_id=app_id, tracing_provider=args.tracing_provider)
@@ -121,7 +121,7 @@ class TraceAppConfigApi(Resource):
     @account_initialization_required
     def delete(self, app_id):
         """Delete an existing trace app configuration"""
-        args = TraceProviderQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = TraceProviderQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         try:
             result = OpsService.delete_tracing_app_config(app_id=app_id, tracing_provider=args.tracing_provider)

api/controllers/console/app/statistic.py

@@ -54,7 +54,7 @@ class DailyMessageStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -111,7 +111,7 @@ class DailyConversationStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -167,7 +167,7 @@ class DailyTerminalsStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -224,7 +224,7 @@ class DailyTokenCostStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -284,7 +284,7 @@ class AverageSessionInteractionStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         converted_created_at = convert_datetime_to_date("c.created_at")
         sql_query = f"""SELECT
@@ -360,7 +360,7 @@ class UserSatisfactionRateStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         converted_created_at = convert_datetime_to_date("m.created_at")
         sql_query = f"""SELECT
@@ -426,7 +426,7 @@ class AverageResponseTimeStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -482,7 +482,7 @@ class TokensPerSecondStatistic(Resource):
     @account_initialization_required
     def get(self, app_model):
         account, _ = current_account_with_tenant()
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT

api/controllers/console/app/workflow.py

@@ -900,7 +900,7 @@ class DefaultBlockConfigApi(Resource):
         """
         Get default block config
         """
-        args = DefaultBlockConfigQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = DefaultBlockConfigQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         filters = None
         if args.q:
@@ -968,7 +968,7 @@ class PublishedAllWorkflowApi(Resource):
         """
         current_user, _ = current_account_with_tenant()
 
-        args = WorkflowListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = WorkflowListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
         page = args.page
         limit = args.limit
         user_id = args.user_id

api/controllers/console/app/workflow_app_log.py

@@ -41,7 +41,7 @@ class WorkflowAppLogQuery(BaseModel):
     def parse_datetime(cls, value: str | None) -> datetime | None:
         if value in (None, ""):
             return None
-        return isoparse(value)  # type: ignore
+        return isoparse(value)  # type: ignore[arg-type]
 
     @field_validator("detail", mode="before")
     @classmethod
@@ -83,7 +83,7 @@ class WorkflowAppLogApi(Resource):
         """
         Get workflow app logs
         """
-        args = WorkflowAppLogQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = WorkflowAppLogQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         # get paginate workflow app logs
         workflow_app_service = WorkflowAppService()
@@ -121,7 +121,7 @@ class WorkflowArchivedLogApi(Resource):
         """
         Get workflow archived logs
         """
-        args = WorkflowAppLogQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = WorkflowAppLogQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         workflow_app_service = WorkflowAppService()
         with Session(db.engine) as session:

api/controllers/console/app/workflow_draft_variable.py

@@ -233,7 +233,7 @@ class WorkflowVariableCollectionApi(Resource):
         """
         Get draft workflow
         """
-        args = WorkflowDraftVariableListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = WorkflowDraftVariableListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         # fetch draft workflow by app_model
         workflow_service = WorkflowService()

api/controllers/console/app/workflow_run.py

@@ -195,7 +195,7 @@ class AdvancedChatAppWorkflowRunListApi(Resource):
         """
         Get advanced chat app workflow run list
         """
-        args_model = WorkflowRunListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args_model = WorkflowRunListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
         args = args_model.model_dump(exclude_none=True)
 
         # Default to DEBUGGING if not specified
@@ -293,7 +293,7 @@ class AdvancedChatAppWorkflowRunCountApi(Resource):
         """
         Get advanced chat workflow runs count statistics
         """
-        args_model = WorkflowRunCountQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args_model = WorkflowRunCountQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
         args = args_model.model_dump(exclude_none=True)
 
         # Default to DEBUGGING if not specified
@@ -337,7 +337,7 @@ class WorkflowRunListApi(Resource):
         """
         Get workflow run list
         """
-        args_model = WorkflowRunListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args_model = WorkflowRunListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
         args = args_model.model_dump(exclude_none=True)
 
         # Default to DEBUGGING for workflow if not specified (backward compatibility)
@@ -385,7 +385,7 @@ class WorkflowRunCountApi(Resource):
         """
         Get workflow runs count statistics
         """
-        args_model = WorkflowRunCountQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args_model = WorkflowRunCountQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
         args = args_model.model_dump(exclude_none=True)
 
         # Default to DEBUGGING for workflow if not specified (backward compatibility)

api/controllers/console/app/workflow_statistic.py

@@ -53,7 +53,7 @@ class WorkflowDailyRunsStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         assert account.timezone is not None
 
@@ -93,7 +93,7 @@ class WorkflowDailyTerminalsStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         assert account.timezone is not None
 
@@ -133,7 +133,7 @@ class WorkflowDailyTokenCostStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         assert account.timezone is not None
 
@@ -173,7 +173,7 @@ class WorkflowAverageAppInteractionStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         assert account.timezone is not None
 

api/controllers/console/app/workflow_trigger.py

@@ -60,7 +60,7 @@ class WebhookTriggerApi(Resource):
     @marshal_with(webhook_trigger_model)
     def get(self, app_model: App):
         """Get webhook trigger for a node"""
-        args = Parser.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = Parser.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         node_id = args.node_id
 
@@ -114,9 +114,9 @@ class AppTriggersApi(Resource):
         url_prefix = dify_config.CONSOLE_API_URL + "/console/api/workspaces/current/tool-provider/builtin/"
         for trigger in triggers:
             if trigger.trigger_type == "trigger-plugin":
-                trigger.icon = url_prefix + trigger.provider_name + "/icon"  # type: ignore
+                trigger.icon = url_prefix + trigger.provider_name + "/icon"  # type: ignore[attr-defined,operator]
             else:
-                trigger.icon = ""  # type: ignore
+                trigger.icon = ""  # type: ignore[attr-defined]
 
         return {"data": triggers}
 
@@ -159,8 +159,8 @@ class AppTriggerEnableApi(Resource):
         # Add computed icon field
         url_prefix = dify_config.CONSOLE_API_URL + "/console/api/workspaces/current/tool-provider/builtin/"
         if trigger.trigger_type == "trigger-plugin":
-            trigger.icon = url_prefix + trigger.provider_name + "/icon"  # type: ignore
+            trigger.icon = url_prefix + trigger.provider_name + "/icon"  # type: ignore[attr-defined,operator]
         else:
-            trigger.icon = ""  # type: ignore
+            trigger.icon = ""  # type: ignore[attr-defined]
 
         return trigger

api/controllers/console/auth/activate.py

@@ -60,7 +60,7 @@ class ActivateCheckApi(Resource):
         ),
     )
     def get(self):
-        args = ActivateCheckQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ActivateCheckQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         workspaceId = args.workspace_id
         token = args.token

api/controllers/console/billing/billing.py

@@ -36,7 +36,7 @@ class Subscription(Resource):
     @only_edition_cloud
     def get(self):
         current_user, current_tenant_id = current_account_with_tenant()
-        args = SubscriptionQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = SubscriptionQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
         BillingService.is_tenant_owner_or_admin(current_user)
         return BillingService.get_subscription(args.plan, args.interval, current_user.email, current_tenant_id)
 

api/controllers/console/billing/compliance.py

@@ -31,7 +31,7 @@ class ComplianceApi(Resource):
     @only_edition_cloud
     def get(self):
         current_user, current_tenant_id = current_account_with_tenant()
-        args = ComplianceDownloadQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ComplianceDownloadQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         ip_address = extract_remote_ip(request)
         device_info = request.headers.get("User-Agent", "Unknown device")

api/controllers/console/datasets/rag_pipeline/datasource_content_preview.py

@@ -1,5 +1,5 @@
-from flask_restx import (  # type: ignore
+from flask_restx import (
-    Resource,  # type: ignore
+    Resource,
 )
 from pydantic import BaseModel
 from werkzeug.exceptions import Forbidden

api/controllers/console/datasets/rag_pipeline/rag_pipeline_import.py

@@ -1,5 +1,5 @@
 from flask import request
-from flask_restx import Resource, fields, marshal_with  # type: ignore
+from flask_restx import Resource, fields, marshal_with
 from pydantic import BaseModel, Field
 from sqlalchemy.orm import Session
 

api/controllers/console/datasets/rag_pipeline/rag_pipeline_workflow.py

@@ -3,7 +3,7 @@ import logging
 from typing import Any, Literal, cast
 
 from flask import abort, request
-from flask_restx import Resource, marshal_with  # type: ignore
+from flask_restx import Resource, marshal_with
 from pydantic import BaseModel, Field
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import BadRequest, Forbidden, InternalServerError, NotFound

api/controllers/console/explore/recommended_app.py

@@ -63,7 +63,7 @@ class RecommendedAppListApi(Resource):
     @marshal_with(recommended_app_list_model)
     def get(self):
         # language args
-        args = RecommendedAppsQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = RecommendedAppsQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
         language = args.language
         if language and language in languages:
             language_prefix = language

api/controllers/console/extension.py

@@ -49,7 +49,7 @@ class CodeBasedExtensionAPI(Resource):
     @login_required
     @account_initialization_required
     def get(self):
-        query = CodeBasedExtensionQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        query = CodeBasedExtensionQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         return {"module": query.module, "data": CodeBasedExtensionService.get_code_based_extension(query.module)}
 

api/controllers/console/workspace/account.py

@@ -519,7 +519,7 @@ class EducationAutoCompleteApi(Resource):
     @cloud_edition_billing_enabled
     @marshal_with(data_fields)
     def get(self):
-        payload = request.args.to_dict(flat=True)  # type: ignore
+        payload = request.args.to_dict(flat=True)  # type: ignore[arg-type]
         args = EducationAutocompleteQuery.model_validate(payload)
 
         return BillingService.EducationIdentity.autocomplete(args.keywords, args.page, args.limit)

api/controllers/console/workspace/endpoint.py

@@ -138,7 +138,7 @@ class EndpointListApi(Resource):
     def get(self):
         user, tenant_id = current_account_with_tenant()
 
-        args = EndpointListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = EndpointListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         page = args.page
         page_size = args.page_size
@@ -171,7 +171,7 @@ class EndpointListForSinglePluginApi(Resource):
     def get(self):
         user, tenant_id = current_account_with_tenant()
 
-        args = EndpointListForPluginQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = EndpointListForPluginQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         page = args.page
         page_size = args.page_size

api/controllers/console/workspace/model_providers.py

@@ -99,7 +99,7 @@ class ModelProviderListApi(Resource):
         _, current_tenant_id = current_account_with_tenant()
         tenant_id = current_tenant_id
 
-        payload = request.args.to_dict(flat=True)  # type: ignore
+        payload = request.args.to_dict(flat=True)  # type: ignore[arg-type]
         args = ParserModelList.model_validate(payload)
 
         model_provider_service = ModelProviderService()
@@ -118,7 +118,7 @@ class ModelProviderCredentialApi(Resource):
         _, current_tenant_id = current_account_with_tenant()
         tenant_id = current_tenant_id
         # if credential_id is not provided, return current used credential
-        payload = request.args.to_dict(flat=True)  # type: ignore
+        payload = request.args.to_dict(flat=True)  # type: ignore[arg-type]
         args = ParserCredentialId.model_validate(payload)
 
         model_provider_service = ModelProviderService()

api/controllers/console/workspace/models.py

@@ -133,7 +133,7 @@ class DefaultModelApi(Resource):
     def get(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = ParserGetDefault.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ParserGetDefault.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         model_provider_service = ModelProviderService()
         default_model_entity = model_provider_service.get_default_model_of_model_type(
@@ -261,7 +261,7 @@ class ModelProviderModelCredentialApi(Resource):
     def get(self, provider: str):
         _, tenant_id = current_account_with_tenant()
 
-        args = ParserGetCredentials.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ParserGetCredentials.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         model_provider_service = ModelProviderService()
         current_credential = model_provider_service.get_model_credential(
@@ -513,7 +513,7 @@ class ModelProviderModelParameterRuleApi(Resource):
     @login_required
     @account_initialization_required
     def get(self, provider: str):
-        args = ParserParameter.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ParserParameter.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
         _, tenant_id = current_account_with_tenant()
 
         model_provider_service = ModelProviderService()

api/controllers/console/workspace/plugin.py

@@ -211,7 +211,7 @@ class PluginListApi(Resource):
     @account_initialization_required
     def get(self):
         _, tenant_id = current_account_with_tenant()
-        args = ParserList.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ParserList.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
         try:
             plugins_with_total = PluginService.list_with_total(tenant_id, args.page, args.page_size)
         except PluginDaemonClientSideError as e:
@@ -261,7 +261,7 @@ class PluginIconApi(Resource):
     @console_ns.expect(console_ns.models[ParserIcon.__name__])
     @setup_required
     def get(self):
-        args = ParserIcon.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ParserIcon.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         try:
             icon_bytes, mimetype = PluginService.get_asset(args.tenant_id, args.filename)
@@ -279,7 +279,7 @@ class PluginAssetApi(Resource):
     @login_required
     @account_initialization_required
     def get(self):
-        args = ParserAsset.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ParserAsset.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         _, tenant_id = current_account_with_tenant()
         try:
@@ -421,7 +421,7 @@ class PluginFetchMarketplacePkgApi(Resource):
     @plugin_permission_required(install_required=True)
     def get(self):
         _, tenant_id = current_account_with_tenant()
-        args = ParserPluginIdentifierQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ParserPluginIdentifierQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         try:
             return jsonable_encoder(
@@ -446,7 +446,7 @@ class PluginFetchManifestApi(Resource):
     def get(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = ParserPluginIdentifierQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ParserPluginIdentifierQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         try:
             return jsonable_encoder(
@@ -466,7 +466,7 @@ class PluginFetchInstallTasksApi(Resource):
     def get(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = ParserTasks.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ParserTasks.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         try:
             return jsonable_encoder({"tasks": PluginService.fetch_install_tasks(tenant_id, args.page, args.page_size)})
@@ -660,7 +660,7 @@ class PluginFetchDynamicSelectOptionsApi(Resource):
         current_user, tenant_id = current_account_with_tenant()
         user_id = current_user.id
 
-        args = ParserDynamicOptions.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ParserDynamicOptions.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         try:
             options = PluginParameterService.get_dynamic_select_options(
@@ -822,7 +822,7 @@ class PluginReadmeApi(Resource):
     @account_initialization_required
     def get(self):
         _, tenant_id = current_account_with_tenant()
-        args = ParserReadme.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ParserReadme.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
         return jsonable_encoder(
             {"readme": PluginService.fetch_plugin_readme(tenant_id, args.plugin_unique_identifier, args.language)}
         )

api/controllers/console/workspace/tool_providers.py

@@ -267,7 +267,7 @@ class ToolProviderListApi(Resource):
         raw_args = request.args.to_dict()
         query = ToolProviderListQuery.model_validate(raw_args)
 
-        return ToolCommonService.list_tool_providers(user_id, tenant_id, query.type)  # type: ignore
+        return ToolCommonService.list_tool_providers(user_id, tenant_id, query.type)  # type: ignore[arg-type, operator]
 
 
 @console_ns.route("/workspaces/current/tool-provider/builtin/<path:provider>/tools")

api/controllers/console/workspace/workspace.py

@@ -155,7 +155,7 @@ class WorkspaceListApi(Resource):
     @setup_required
     @admin_required
     def get(self):
-        payload = request.args.to_dict(flat=True)  # type: ignore
+        payload = request.args.to_dict(flat=True)  # type: ignore[arg-type]
         args = WorkspaceListQuery.model_validate(payload)
 
         stmt = select(Tenant).order_by(Tenant.created_at.desc())

api/controllers/console/wraps.py

@@ -313,7 +313,7 @@ def edit_permission_required(f: Callable[P, R]):
         from libs.login import current_user
         from models import Account
 
-        user = current_user._get_current_object()  # type: ignore
+        user = current_user._get_current_object()  # type: ignore[attr-defined]
         if not isinstance(user, Account):
             raise Forbidden()
         if not current_user.has_edit_permission:

api/controllers/files/image_preview.py

@@ -58,7 +58,7 @@ class ImagePreviewApi(Resource):
     def get(self, file_id):
         file_id = str(file_id)
 
-        args = FileSignatureQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = FileSignatureQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
         timestamp = args.timestamp
         nonce = args.nonce
         sign = args.sign
@@ -100,7 +100,7 @@ class FilePreviewApi(Resource):
     def get(self, file_id):
         file_id = str(file_id)
 
-        args = FilePreviewQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = FilePreviewQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         try:
             generator, upload_file = FileService(db.engine).get_file_generator_by_file_id(

api/controllers/files/upload.py

@@ -69,7 +69,7 @@ class PluginUploadFileApi(Resource):
             FileTooLargeError: File exceeds size limit
             UnsupportedFileTypeError: File type not supported
         """
-        args = PluginUploadQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = PluginUploadQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore[arg-type]
 
         file = request.files.get("file")
         if file is None:

api/controllers/inner_api/mail.py

@@ -32,7 +32,7 @@ class BaseMail(Resource):
             to=args.to,
             subject=args.subject,
             body=args.body,
-            substitutions=args.substitutions,  # type: ignore
+            substitutions=args.substitutions,  # type: ignore[arg-type]
         )
         return {"message": "success"}, 200
 

api/controllers/inner_api/plugin/wraps.py

@@ -89,8 +89,8 @@ def get_user_tenant(view_func: Callable[P, R]):
         user = get_user(tenant_id, user_id)
         kwargs["user_model"] = user
 
-        current_app.login_manager._update_request_context_with_user(user)  # type: ignore
+        current_app.login_manager._update_request_context_with_user(user)  # type: ignore[attr-defined]
-        user_logged_in.send(current_app._get_current_object(), user=current_user)  # type: ignore
+        user_logged_in.send(current_app._get_current_object(), user=current_user)  # type: ignore[attr-defined]
 
         return view_func(*args, **kwargs)
 

api/controllers/service_api/app/file.py

@@ -34,7 +34,7 @@ class FileApi(Resource):
             415: "Unsupported file type",
         }
     )
-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.FORM))  # type: ignore
+    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.FORM))  # type: ignore[misc]
     @service_api_ns.response(HTTPStatus.CREATED, "File uploaded", service_api_ns.models[FileResponse.__name__])
     def post(self, app_model: App, end_user: EndUser):
         """Upload a file for use in conversations.

api/controllers/service_api/wraps.py

@@ -101,8 +101,8 @@ def validate_app_token(
                 kwargs["end_user"] = end_user
 
                 # Set EndUser as current logged-in user for flask_login.current_user
-                current_app.login_manager._update_request_context_with_user(end_user)  # type: ignore
+                current_app.login_manager._update_request_context_with_user(end_user)  # type: ignore[attr-defined]
-                user_logged_in.send(current_app._get_current_object(), user=end_user)  # type: ignore
+                user_logged_in.send(current_app._get_current_object(), user=end_user)  # type: ignore[attr-defined]
             else:
                 # For service API without end-user context, ensure an Account is logged in
                 # so services relying on current_account_with_tenant() work correctly.
@@ -121,8 +121,8 @@ def validate_app_token(
                 if tenant_owner_info:
                     tenant_model, account = tenant_owner_info
                     account.current_tenant = tenant_model
-                    current_app.login_manager._update_request_context_with_user(account)  # type: ignore
+                    current_app.login_manager._update_request_context_with_user(account)  # type: ignore[attr-defined]
-                    user_logged_in.send(current_app._get_current_object(), user=current_user)  # type: ignore
+                    user_logged_in.send(current_app._get_current_object(), user=current_user)  # type: ignore[attr-defined]
                 else:
                     raise Unauthorized("Tenant owner account not found or tenant is not active.")
 
@@ -303,8 +303,8 @@ def validate_dataset_token(
                 # Login admin
                 if account:
                     account.current_tenant = tenant
-                    current_app.login_manager._update_request_context_with_user(account)  # type: ignore
+                    current_app.login_manager._update_request_context_with_user(account)  # type: ignore[attr-defined]
-                    user_logged_in.send(current_app._get_current_object(), user=current_user)  # type: ignore
+                    user_logged_in.send(current_app._get_current_object(), user=current_user)  # type: ignore[attr-defined]
                 else:
                     raise Unauthorized("Tenant owner account does not exist.")
             else:

api/core/app/apps/advanced_chat/app_generator.py

@@ -171,7 +171,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
 
         if invoke_from == InvokeFrom.DEBUGGER:
             # always enable retriever resource in debugger mode
-            app_config.additional_features.show_retrieve_source = True  # type: ignore
+            app_config.additional_features.show_retrieve_source = True  # type: ignore[attr-defined]
 
         # init application generate entity
         application_generate_entity = AdvancedChatAppGenerateEntity(
@@ -504,7 +504,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         worker_thread = threading.Thread(
             target=self._generate_worker,
             kwargs={
-                "flask_app": current_app._get_current_object(),  # type: ignore
+                "flask_app": current_app._get_current_object(),  # type: ignore[attr-defined]
                 "application_generate_entity": application_generate_entity,
                 "queue_manager": queue_manager,
                 "conversation_id": conversation.id,

api/core/app/apps/agent_chat/app_generator.py

@@ -191,7 +191,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
         worker_thread = threading.Thread(
             target=self._generate_worker,
             kwargs={
-                "flask_app": current_app._get_current_object(),  # type: ignore
+                "flask_app": current_app._get_current_object(),  # type: ignore[attr-defined]
                 "context": context,
                 "application_generate_entity": application_generate_entity,
                 "queue_manager": queue_manager,

api/core/app/apps/chat/app_generator.py

@@ -181,7 +181,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
         @copy_current_request_context
         def worker_with_context():
             return self._generate_worker(
-                flask_app=current_app._get_current_object(),  # type: ignore
+                flask_app=current_app._get_current_object(),  # type: ignore[attr-defined]
                 application_generate_entity=application_generate_entity,
                 queue_manager=queue_manager,
                 conversation_id=conversation.id,

api/core/app/apps/completion/app_generator.py

@@ -164,7 +164,7 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
         @copy_current_request_context
         def worker_with_context():
             return self._generate_worker(
-                flask_app=current_app._get_current_object(),  # type: ignore
+                flask_app=current_app._get_current_object(),  # type: ignore[attr-defined]
                 application_generate_entity=application_generate_entity,
                 queue_manager=queue_manager,
                 message_id=message.id,
@@ -327,7 +327,7 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
         @copy_current_request_context
         def worker_with_context():
             return self._generate_worker(
-                flask_app=current_app._get_current_object(),  # type: ignore
+                flask_app=current_app._get_current_object(),  # type: ignore[attr-defined]
                 application_generate_entity=application_generate_entity,
                 queue_manager=queue_manager,
                 message_id=message.id,

api/core/app/apps/pipeline/pipeline_generator.py

@@ -217,7 +217,7 @@ class PipelineGenerator(BaseAppGenerator):
             )
             if invoke_from == InvokeFrom.DEBUGGER or is_retry:
                 return self._generate(
-                    flask_app=current_app._get_current_object(),  # type: ignore
+                    flask_app=current_app._get_current_object(),  # type: ignore[attr-defined]
                     context=contextvars.copy_context(),
                     pipeline=pipeline,
                     workflow_id=workflow.id,
@@ -315,7 +315,7 @@ class PipelineGenerator(BaseAppGenerator):
             worker_thread = threading.Thread(
                 target=self._generate_worker,
                 kwargs={
-                    "flask_app": current_app._get_current_object(),  # type: ignore
+                    "flask_app": current_app._get_current_object(),  # type: ignore[attr-defined]
                     "context": context,
                     "queue_manager": queue_manager,
                     "application_generate_entity": application_generate_entity,
@@ -428,7 +428,7 @@ class PipelineGenerator(BaseAppGenerator):
         )
 
         return self._generate(
-            flask_app=current_app._get_current_object(),  # type: ignore
+            flask_app=current_app._get_current_object(),  # type: ignore[attr-defined]
             pipeline=pipeline,
             workflow_id=workflow.id,
             user=user,
@@ -524,7 +524,7 @@ class PipelineGenerator(BaseAppGenerator):
         )
 
         return self._generate(
-            flask_app=current_app._get_current_object(),  # type: ignore
+            flask_app=current_app._get_current_object(),  # type: ignore[attr-defined]
             pipeline=pipeline,
             workflow_id=workflow.id,
             user=user,

api/core/app/apps/workflow/app_generator.py

@@ -320,7 +320,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
         worker_thread = threading.Thread(
             target=self._generate_worker,
             kwargs={
-                "flask_app": current_app._get_current_object(),  # type: ignore
+                "flask_app": current_app._get_current_object(),  # type: ignore[attr-defined]
                 "application_generate_entity": application_generate_entity,
                 "queue_manager": queue_manager,
                 "context": context,

api/core/app/entities/app_invoke_entities.py

@@ -138,7 +138,7 @@ class EasyUIBasedAppGenerateEntity(AppGenerateEntity):
     """
 
     # app config
-    app_config: EasyUIBasedAppConfig = None  # type: ignore
+    app_config: EasyUIBasedAppConfig = None  # type: ignore[assignment]
     model_conf: ModelConfigWithCredentialsEntity
 
     query: str = ""
@@ -202,7 +202,7 @@ class AdvancedChatAppGenerateEntity(ConversationAppGenerateEntity):
     """
 
     # app config
-    app_config: WorkflowUIBasedAppConfig = None  # type: ignore
+    app_config: WorkflowUIBasedAppConfig = None  # type: ignore[assignment]
 
     workflow_run_id: str | None = None
     query: str
@@ -234,7 +234,7 @@ class WorkflowAppGenerateEntity(AppGenerateEntity):
     """
 
     # app config
-    app_config: WorkflowUIBasedAppConfig = None  # type: ignore
+    app_config: WorkflowUIBasedAppConfig = None  # type: ignore[assignment]
     workflow_execution_id: str
 
     class SingleIterationRunEntity(BaseModel):

api/core/app/layers/timeslice_layer.py

@@ -2,7 +2,7 @@ import logging
 import uuid
 from typing import ClassVar
 
-from apscheduler.schedulers.background import BackgroundScheduler  # type: ignore
+from apscheduler.schedulers.background import BackgroundScheduler  # type: ignore[reportMissingTypeStubs]
 
 from dify_graph.graph_engine.entities.commands import CommandType, GraphEngineCommand
 from dify_graph.graph_engine.layers.base import GraphEngineLayer

api/core/app/task_pipeline/message_cycle_manager.py

@@ -100,7 +100,7 @@ class MessageCycleManager:
                 1,
                 self._generate_conversation_name_worker,
                 kwargs={
-                    "flask_app": current_app._get_current_object(),  # type: ignore
+                    "flask_app": current_app._get_current_object(),  # type: ignore[attr-defined]
                     "conversation_id": conversation_id,
                     "query": query,
                 },

api/core/datasource/local_file/local_file_provider.py

@@ -31,7 +31,7 @@ class LocalFileDatasourcePluginProviderController(DatasourcePluginProviderContro
         """
         pass
 
-    def get_datasource(self, datasource_name: str) -> LocalFileDatasourcePlugin:  # type: ignore
+    def get_datasource(self, datasource_name: str) -> LocalFileDatasourcePlugin:  # type: ignore[return-value]
         """
         return datasource with given name
         """

api/core/datasource/online_document/online_document_provider.py

@@ -23,7 +23,7 @@ class OnlineDocumentDatasourcePluginProviderController(DatasourcePluginProviderC
         """
         return DatasourceProviderType.ONLINE_DOCUMENT
 
-    def get_datasource(self, datasource_name: str) -> OnlineDocumentDatasourcePlugin:  # type: ignore
+    def get_datasource(self, datasource_name: str) -> OnlineDocumentDatasourcePlugin:  # type: ignore[return-value]
         """
         return datasource with given name
         """

api/core/datasource/online_drive/online_drive_provider.py

@@ -23,7 +23,7 @@ class OnlineDriveDatasourcePluginProviderController(DatasourcePluginProviderCont
         """
         return DatasourceProviderType.ONLINE_DRIVE
 
-    def get_datasource(self, datasource_name: str) -> OnlineDriveDatasourcePlugin:  # type: ignore
+    def get_datasource(self, datasource_name: str) -> OnlineDriveDatasourcePlugin:  # type: ignore[return-value]
         """
         return datasource with given name
         """

api/core/datasource/website_crawl/website_crawl_provider.py

@@ -27,7 +27,7 @@ class WebsiteCrawlDatasourcePluginProviderController(DatasourcePluginProviderCon
         """
         return DatasourceProviderType.WEBSITE_CRAWL
 
-    def get_datasource(self, datasource_name: str) -> WebsiteCrawlDatasourcePlugin:  # type: ignore
+    def get_datasource(self, datasource_name: str) -> WebsiteCrawlDatasourcePlugin:  # type: ignore[return-value]
         """
         return datasource with given name
         """

api/core/external_data_tool/external_data_fetch.py

@@ -37,7 +37,7 @@ class ExternalDataFetch:
             for tool in external_data_tools:
                 future: Future[tuple[str | None, str | None]] = executor.submit(
                     self._query_external_data_tool,
-                    current_app._get_current_object(),  # type: ignore
+                    current_app._get_current_object(),  # type: ignore[attr-defined]
                     tenant_id,
                     app_id,
                     tool,

api/core/external_data_tool/factory.py

@@ -24,7 +24,7 @@ class ExternalDataToolFactory:
         """
         extension_class = code_based_extension.extension_class(ExtensionModule.EXTERNAL_DATA_TOOL, name)
         # FIXME mypy issue here, figure out how to fix it
-        extension_class.validate_config(tenant_id, config)  # type: ignore
+        extension_class.validate_config(tenant_id, config)  # type: ignore[attr-defined, operator]
 
     def query(self, inputs: Mapping[str, Any], query: str | None = None) -> str:
         """

api/core/indexing_runner.py

@@ -592,7 +592,7 @@ class IndexingRunner:
             # create keyword index
             create_keyword_thread = threading.Thread(
                 target=self._process_keyword_index,
-                args=(current_app._get_current_object(), dataset.id, dataset_document.id, documents),  # type: ignore
+                args=(current_app._get_current_object(), dataset.id, dataset_document.id, documents),  # type: ignore[attr-defined]
             )
             create_keyword_thread.start()
 
@@ -615,7 +615,7 @@ class IndexingRunner:
                     futures.append(
                         executor.submit(
                             self._process_chunk,
-                            current_app._get_current_object(),  # type: ignore
+                            current_app._get_current_object(),  # type: ignore[attr-defined]
                             index_processor,
                             chunk_documents,
                             dataset,
@@ -742,7 +742,7 @@ class IndexingRunner:
 
         if extra_update_params:
             update_params.update(extra_update_params)
-        db.session.query(DatasetDocument).filter_by(id=document_id).update(update_params)  # type: ignore
+        db.session.query(DatasetDocument).filter_by(id=document_id).update(update_params)  # type: ignore[arg-type, operator]
         db.session.commit()
 
     @staticmethod

api/core/moderation/factory.py

@@ -22,7 +22,7 @@ class ModerationFactory:
         """
         extension_class = code_based_extension.extension_class(ExtensionModule.MODERATION, name)
         # FIXME: mypy error, try to fix it instead of using type: ignore
-        extension_class.validate_config(tenant_id, config)  # type: ignore
+        extension_class.validate_config(tenant_id, config)  # type: ignore[attr-defined, operator]
 
     def moderation_for_inputs(self, inputs: dict, query: str = "") -> ModerationInputsResult:
         """

api/core/moderation/output_moderation.py

@@ -75,7 +75,7 @@ class OutputModeration(BaseModel):
         thread = threading.Thread(
             target=self.worker,
             kwargs={
-                "flask_app": current_app._get_current_object(),  # type: ignore
+                "flask_app": current_app._get_current_object(),  # type: ignore[attr-defined]
                 "buffer_size": buffer_size if buffer_size > 0 else dify_config.MODERATION_BUFFER_SIZE,
             },
         )

api/core/ops/ops_trace_manager.py

@@ -936,7 +936,7 @@ class TraceQueueManager:
         self.app_id = app_id
         self.user_id = user_id
         self.trace_instance = OpsTraceManager.get_ops_trace_instance(app_id)
-        self.flask_app = current_app._get_current_object()  # type: ignore
+        self.flask_app = current_app._get_current_object()  # type: ignore[attr-defined]
         if trace_manager_timer is None:
             self.start_timer()
 
@@ -995,4 +995,4 @@ class TraceQueueManager:
                     "file_id": file_id,
                     "app_id": task.app_id,
                 }
-                process_trace_tasks.delay(file_info)  # type: ignore
+                process_trace_tasks.delay(file_info)  # type: ignore[operator]

api/core/plugin/impl/base.py

@@ -198,7 +198,7 @@ class BasePluginClient:
         Make a stream request to the plugin daemon inner API and yield the response as a model.
         """
         for line in self._stream_request(method, path, params, headers, data, files):
-            yield type_(**json.loads(line))  # type: ignore
+            yield type_(**json.loads(line))  # type: ignore[misc, operator]
 
     def _request_with_model(
         self,
@@ -246,7 +246,7 @@ class BasePluginClient:
             if transformer:
                 json_response = transformer(json_response)
             # https://stackoverflow.com/questions/59634937/variable-foo-class-is-not-valid-as-type-but-why
-            rep = PluginDaemonBasicResponse[type_].model_validate(json_response)  # type: ignore
+            rep = PluginDaemonBasicResponse[type_].model_validate(json_response)  # type: ignore[valid-type, operator]
         except Exception:
             msg = (
                 f"Failed to parse response from plugin daemon to PluginDaemonBasicResponse [{str(type_.__name__)}],"
@@ -283,7 +283,7 @@ class BasePluginClient:
         """
         for line in self._stream_request(method, path, params, headers, data, files):
             try:
-                rep = PluginDaemonBasicResponse[type_].model_validate_json(line)  # type: ignore
+                rep = PluginDaemonBasicResponse[type_].model_validate_json(line)  # type: ignore[valid-type, operator]
             except (ValueError, TypeError):
                 # TODO modify this when line_data has code and message
                 try:

api/core/plugin/utils/chunk_merger.py

@@ -88,7 +88,7 @@ def merge_blob_chunks(
                     meta=resp.meta,
                 )
                 assert isinstance(merged_message, (ToolInvokeMessage, AgentInvokeMessage))
-                yield merged_message  # type: ignore
+                yield merged_message  # type: ignore[misc]
                 # Clean up the buffer
                 del files[chunk_id]
         else:

api/core/provider_manager.py

@@ -629,7 +629,7 @@ class ProviderManager:
                                 provider_name=ModelProviderID(provider_name).provider_name,
                                 provider_type=ProviderType.SYSTEM,
                                 quota_type=quota.quota_type,
-                                quota_limit=0,  # type: ignore
+                                quota_limit=0,  # type: ignore[assignment]
                                 quota_used=0,
                                 is_valid=True,
                             )

api/core/rag/datasource/keyword/jieba/jieba_keyword_table_handler.py

@@ -44,7 +44,7 @@ class JiebaKeywordTableHandler:
                                         │  & cache to default    │    │  _SimpleTFIDF   │
                                         └────────────────────────┘    └─────────────────┘
         """
-        import jieba.analyse  # type: ignore
+        import jieba.analyse
 
         tfidf = getattr(jieba.analyse, "default_tfidf", None)
         if tfidf is not None:
@@ -53,7 +53,7 @@ class JiebaKeywordTableHandler:
         tfidf_class = getattr(jieba.analyse, "TFIDF", None)
         if tfidf_class is None:
             try:
-                from jieba.analyse.tfidf import TFIDF  # type: ignore
+                from jieba.analyse.tfidf import TFIDF
 
                 tfidf_class = TFIDF
             except Exception:
@@ -69,7 +69,7 @@ class JiebaKeywordTableHandler:
     @staticmethod
     def _build_fallback_tfidf():
         """Fallback lightweight TFIDF for environments missing jieba's TFIDF."""
-        import jieba  # type: ignore
+        import jieba
 
         from core.rag.datasource.keyword.jieba.stopwords import STOPWORDS
 

api/core/rag/datasource/retrieval_service.py

@@ -115,14 +115,14 @@ class RetrievalService:
         exceptions: list[str] = []
 
         # Optimize multithreading with thread pools
-        with ThreadPoolExecutor(max_workers=dify_config.RETRIEVAL_SERVICE_EXECUTORS) as executor:  # type: ignore
+        with ThreadPoolExecutor(max_workers=dify_config.RETRIEVAL_SERVICE_EXECUTORS) as executor:  # type: ignore[operator]
             futures = []
             retrieval_service = RetrievalService()
             if query:
                 futures.append(
                     executor.submit(
                         retrieval_service._retrieve,
-                        flask_app=current_app._get_current_object(),  # type: ignore
+                        flask_app=current_app._get_current_object(),  # type: ignore[attr-defined]
                         retrieval_method=retrieval_method,
                         dataset=dataset,
                         query=query,
@@ -142,7 +142,7 @@ class RetrievalService:
                     futures.append(
                         executor.submit(
                             retrieval_service._retrieve,
-                            flask_app=current_app._get_current_object(),  # type: ignore
+                            flask_app=current_app._get_current_object(),  # type: ignore[attr-defined]
                             retrieval_method=retrieval_method,
                             dataset=dataset,
                             query=None,
@@ -541,7 +541,7 @@ class RetrievalService:
                         DocumentSegment.status == "completed",
                         DocumentSegment.index_node_id.in_(index_node_ids),
                     )
-                    index_node_segments = session.execute(document_segment_stmt).scalars().all()  # type: ignore
+                    index_node_segments = session.execute(document_segment_stmt).scalars().all()  # type: ignore[assignment, operator]
                     for index_node_segment in index_node_segments:
                         doc_segment_map[index_node_segment.id] = [index_node_segment.index_node_id]
 
@@ -551,7 +551,7 @@ class RetrievalService:
                         DocumentSegment.status == "completed",
                         DocumentSegment.id.in_(segment_ids),
                     )
-                    segments = session.execute(document_segment_stmt).scalars().all()  # type: ignore
+                    segments = session.execute(document_segment_stmt).scalars().all()  # type: ignore[assignment, operator]
 
                 if index_node_segments:
                     segments.extend(index_node_segments)
@@ -564,7 +564,7 @@ class RetrievalService:
                         DocumentSegment.status == "completed",
                         DocumentSegment.id.in_(summary_segment_ids_list),
                     )
-                    summary_segments = session.execute(summary_segment_stmt).scalars().all()  # type: ignore
+                    summary_segments = session.execute(summary_segment_stmt).scalars().all()  # type: ignore[operator]
                     segments.extend(summary_segments)
                     # Add summary segment IDs to segment_ids for summary query
                     for seg in summary_segments:
@@ -747,13 +747,13 @@ class RetrievalService:
         with flask_app.app_context():
             all_documents_item: list[Document] = []
             # Optimize multithreading with thread pools
-            with ThreadPoolExecutor(max_workers=dify_config.RETRIEVAL_SERVICE_EXECUTORS) as executor:  # type: ignore
+            with ThreadPoolExecutor(max_workers=dify_config.RETRIEVAL_SERVICE_EXECUTORS) as executor:  # type: ignore[operator]
                 futures = []
                 if retrieval_method == RetrievalMethod.KEYWORD_SEARCH and query:
                     futures.append(
                         executor.submit(
                             self.keyword_search,
-                            flask_app=current_app._get_current_object(),  # type: ignore
+                            flask_app=current_app._get_current_object(),  # type: ignore[attr-defined]
                             dataset_id=dataset.id,
                             query=query,
                             top_k=top_k,
@@ -767,7 +767,7 @@ class RetrievalService:
                         futures.append(
                             executor.submit(
                                 self.embedding_search,
-                                flask_app=current_app._get_current_object(),  # type: ignore
+                                flask_app=current_app._get_current_object(),  # type: ignore[attr-defined]
                                 dataset_id=dataset.id,
                                 query=query,
                                 top_k=top_k,
@@ -784,7 +784,7 @@ class RetrievalService:
                         futures.append(
                             executor.submit(
                                 self.embedding_search,
-                                flask_app=current_app._get_current_object(),  # type: ignore
+                                flask_app=current_app._get_current_object(),  # type: ignore[attr-defined]
                                 dataset_id=dataset.id,
                                 query=attachment_id,
                                 top_k=top_k,
@@ -801,7 +801,7 @@ class RetrievalService:
                     futures.append(
                         executor.submit(
                             self.full_text_index_search,
-                            flask_app=current_app._get_current_object(),  # type: ignore
+                            flask_app=current_app._get_current_object(),  # type: ignore[attr-defined]
                             dataset_id=dataset.id,
                             query=query,
                             top_k=top_k,

api/core/rag/datasource/vdb/analyticdb/analyticdb_vector_openapi.py

@@ -55,8 +55,8 @@ class AnalyticdbVectorOpenAPIConfig(BaseModel):
 class AnalyticdbVectorOpenAPI:
     def __init__(self, collection_name: str, config: AnalyticdbVectorOpenAPIConfig):
         try:
-            from alibabacloud_gpdb20160503.client import Client  # type: ignore
+            from alibabacloud_gpdb20160503.client import Client
-            from alibabacloud_tea_openapi import models as open_api_models  # type: ignore
+            from alibabacloud_tea_openapi import models as open_api_models
         except:
             raise ImportError(_import_err_msg)
         self._collection_name = collection_name.lower()
@@ -77,7 +77,7 @@ class AnalyticdbVectorOpenAPI:
             redis_client.set(database_exist_cache_key, 1, ex=3600)
 
     def _initialize_vector_database(self):
-        from alibabacloud_gpdb20160503 import models as gpdb_20160503_models  # type: ignore
+        from alibabacloud_gpdb20160503 import models as gpdb_20160503_models
 
         request = gpdb_20160503_models.InitVectorDatabaseRequest(
             dbinstance_id=self.config.instance_id,
@@ -89,7 +89,7 @@ class AnalyticdbVectorOpenAPI:
 
     def _create_namespace_if_not_exists(self):
         from alibabacloud_gpdb20160503 import models as gpdb_20160503_models
-        from Tea.exceptions import TeaException  # type: ignore
+        from Tea.exceptions import TeaException
 
         try:
             request = gpdb_20160503_models.DescribeNamespaceRequest(

api/core/rag/datasource/vdb/baidu/baidu_vector.py

@@ -6,12 +6,19 @@ from typing import Any
 
 import numpy as np
 from pydantic import BaseModel, model_validator
-from pymochow import MochowClient  # type: ignore
+from pymochow import MochowClient
-from pymochow.auth.bce_credentials import BceCredentials  # type: ignore
+from pymochow.auth.bce_credentials import BceCredentials
-from pymochow.configuration import Configuration  # type: ignore
+from pymochow.configuration import Configuration
-from pymochow.exception import ServerError  # type: ignore
+from pymochow.exception import ServerError
 from pymochow.model.database import Database
-from pymochow.model.enum import FieldType, IndexState, IndexType, MetricType, ServerErrCode, TableState  # type: ignore
+from pymochow.model.enum import (
+    FieldType,
+    IndexState,
+    IndexType,
+    MetricType,
+    ServerErrCode,
+    TableState,
+)
 from pymochow.model.schema import (
     AutoBuildRowCountIncrement,
     Field,
@@ -24,8 +31,14 @@ from pymochow.model.schema import (
     InvertedIndexParseMode,
     Schema,
     VectorIndex,
-)  # type: ignore
+)
-from pymochow.model.table import AnnSearch, BM25SearchRequest, HNSWSearchParams, Partition, Row  # type: ignore
+from pymochow.model.table import (
+    AnnSearch,
+    BM25SearchRequest,
+    HNSWSearchParams,
+    Partition,
+    Row,
+)
 
 from configs import dify_config
 from core.rag.datasource.vdb.field import Field as VDBField

api/core/rag/datasource/vdb/chroma/chroma_vector.py

@@ -72,13 +72,13 @@ class ChromaVector(BaseVector):
 
         collection = self._client.get_or_create_collection(self._collection_name)
         # FIXME: chromadb using numpy array, fix the type error later
-        collection.upsert(ids=uuids, documents=texts, embeddings=embeddings, metadatas=metadatas)  # type: ignore
+        collection.upsert(ids=uuids, documents=texts, embeddings=embeddings, metadatas=metadatas)  # type: ignore[arg-type, operator]
         return uuids
 
     def delete_by_metadata_field(self, key: str, value: str):
         collection = self._client.get_or_create_collection(self._collection_name)
         # FIXME: fix the type error later
-        collection.delete(where={key: {"$eq": value}})  # type: ignore
+        collection.delete(where={key: {"$eq": value}})  # type: ignore[arg-type, dict-item]
 
     def delete(self):
         self._client.delete_collection(self._collection_name)
@@ -101,10 +101,10 @@ class ChromaVector(BaseVector):
             results: QueryResult = collection.query(
                 query_embeddings=query_vector,
                 n_results=kwargs.get("top_k", 4),
-                where={"document_id": {"$in": document_ids_filter}},  # type: ignore
+                where={"document_id": {"$in": document_ids_filter}},  # type: ignore[arg-type, dict-item]
             )
         else:
-            results: QueryResult = collection.query(query_embeddings=query_vector, n_results=kwargs.get("top_k", 4))  # type: ignore
+            results: QueryResult = collection.query(query_embeddings=query_vector, n_results=kwargs.get("top_k", 4))  # type: ignore[arg-type, no-redef]
         score_threshold = float(kwargs.get("score_threshold") or 0.0)
 
         # Check if results contain data

api/core/rag/datasource/vdb/clickzetta/clickzetta_vector.py

@@ -10,11 +10,11 @@ import time
 import uuid
 from typing import TYPE_CHECKING, Any
 
-import clickzetta  # type: ignore
+import clickzetta
 from pydantic import BaseModel, model_validator
 
 if TYPE_CHECKING:
-    from clickzetta.connector.v0.connection import Connection  # type: ignore
+    from clickzetta.connector.v0.connection import Connection
 
 from configs import dify_config
 from core.rag.datasource.vdb.field import Field

api/core/rag/datasource/vdb/couchbase/couchbase_vector.py

@@ -5,14 +5,14 @@ import uuid
 from datetime import timedelta
 from typing import Any
 
-from couchbase import search  # type: ignore
+from couchbase import search
-from couchbase.auth import PasswordAuthenticator  # type: ignore
+from couchbase.auth import PasswordAuthenticator
-from couchbase.cluster import Cluster  # type: ignore
+from couchbase.cluster import Cluster
-from couchbase.management.search import SearchIndex  # type: ignore
+from couchbase.management.search import SearchIndex
 
 # needed for options -- cluster, timeout, SQL++ (N1QL) query, etc.
-from couchbase.options import ClusterOptions, SearchOptions  # type: ignore
+from couchbase.options import ClusterOptions, SearchOptions
-from couchbase.vector_search import VectorQuery, VectorSearch  # type: ignore
+from couchbase.vector_search import VectorQuery, VectorSearch
 from flask import current_app
 from pydantic import BaseModel, model_validator
 

api/core/rag/datasource/vdb/hologres/hologres_vector.py

@@ -3,7 +3,7 @@ import logging
 import time
 from typing import Any
 
-import holo_search_sdk as holo  # type: ignore
+import holo_search_sdk as holo
 from holo_search_sdk.types import BaseQuantizationType, DistanceType, TokenizerType
 from psycopg import sql as psql
 from pydantic import BaseModel, model_validator

api/core/rag/datasource/vdb/lindorm/lindorm_vector.py

@@ -268,7 +268,7 @@ class LindormVectorStore(BaseVector):
         try:
             params = {"timeout": self._client_config.request_timeout}
             if self._using_ugc:
-                params["routing"] = self._routing  # type: ignore
+                params["routing"] = self._routing  # type: ignore[arg-type, assignment]
             response = self._client.search(index=self._collection_name, body=search_query, params=params)
         except Exception:
             logger.exception("Error executing vector search, query: %s", search_query)

api/core/rag/datasource/vdb/matrixone/matrixone_vector.py

@@ -5,7 +5,7 @@ from collections.abc import Callable
 from functools import wraps
 from typing import Any, Concatenate, ParamSpec, TypeVar
 
-from mo_vector.client import MoVectorClient  # type: ignore
+from mo_vector.client import MoVectorClient
 from pydantic import BaseModel, model_validator
 
 from configs import dify_config

api/core/rag/datasource/vdb/milvus/milvus_vector.py

@@ -4,8 +4,8 @@ from typing import Any
 
 from packaging import version
 from pydantic import BaseModel, model_validator
-from pymilvus import MilvusClient, MilvusException  # type: ignore
+from pymilvus import MilvusClient, MilvusException
-from pymilvus.milvus_client import IndexParams  # type: ignore
+from pymilvus.milvus_client import IndexParams
 
 from configs import dify_config
 from core.rag.datasource.vdb.field import Field
@@ -304,8 +304,14 @@ class MilvusVector(BaseVector):
                 return
             # Grab the existing collection if it exists
             if not self._client.has_collection(self._collection_name):
-                from pymilvus import CollectionSchema, DataType, FieldSchema, Function, FunctionType  # type: ignore
+                from pymilvus import (
-                from pymilvus.orm.types import infer_dtype_bydata  # type: ignore
+                    CollectionSchema,
+                    DataType,
+                    FieldSchema,
+                    Function,
+                    FunctionType,
+                )
+                from pymilvus.orm.types import infer_dtype_bydata
 
                 # Determine embedding dim
                 dim = len(embeddings[0])

api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py

@@ -4,7 +4,13 @@ import re
 from typing import Any, Literal
 
 from pydantic import BaseModel, model_validator
-from pyobvector import VECTOR, ObVecClient, cosine_distance, inner_product, l2_distance  # type: ignore
+from pyobvector import (
+    VECTOR,
+    ObVecClient,
+    cosine_distance,
+    inner_product,
+    l2_distance,
+)
 from sqlalchemy import JSON, Column, String
 from sqlalchemy.dialects.mysql import LONGTEXT
 from sqlalchemy.exc import SQLAlchemyError

api/core/rag/datasource/vdb/oracle/oraclevector.py

@@ -5,7 +5,7 @@ import re
 import uuid
 from typing import Any
 
-import jieba.posseg as pseg  # type: ignore
+import jieba.posseg as pseg
 import numpy
 import oracledb
 from oracledb.connection import Connection
@@ -271,8 +271,8 @@ class OracleVector(BaseVector):
 
     def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
         # lazy import
-        import nltk  # type: ignore
+        import nltk
-        from nltk.corpus import stopwords  # type: ignore
+        from nltk.corpus import stopwords
 
         # Validate and sanitize top_k to prevent SQL injection
         top_k = kwargs.get("top_k", 5)

api/core/rag/datasource/vdb/pgvecto_rs/pgvecto_rs.py

@@ -4,7 +4,7 @@ from typing import Any
 from uuid import UUID, uuid4
 
 from numpy import ndarray
-from pgvecto_rs.sqlalchemy import VECTOR  # type: ignore
+from pgvecto_rs.sqlalchemy import VECTOR
 from pydantic import BaseModel, model_validator
 from sqlalchemy import Float, create_engine, insert, select, text
 from sqlalchemy import text as sql_text

api/core/rag/datasource/vdb/relyt/relyt_vector.py

@@ -108,7 +108,7 @@ class RelytVector(BaseVector):
             redis_client.set(collection_exist_cache_key, 1, ex=3600)
 
     def add_texts(self, documents: list[Document], embeddings: list[list[float]], **kwargs):
-        from pgvecto_rs.sqlalchemy import VECTOR  # type: ignore
+        from pgvecto_rs.sqlalchemy import VECTOR
 
         ids = [str(uuid.uuid1()) for _ in documents]
         metadatas = [d.metadata for d in documents if d.metadata is not None]

api/core/rag/datasource/vdb/tablestore/tablestore_vector.py

@@ -4,7 +4,7 @@ import math
 from collections.abc import Iterable
 from typing import Any
 
-import tablestore  # type: ignore
+import tablestore
 from pydantic import BaseModel, model_validator
 from tablestore import BatchGetRowRequest, TableInBatchGetRowItem
 

api/core/rag/datasource/vdb/tencent/tencent_vector.py

@@ -4,11 +4,16 @@ import math
 from typing import Any
 
 from pydantic import BaseModel
-from tcvdb_text.encoder import BM25Encoder  # type: ignore
+from tcvdb_text.encoder import BM25Encoder
-from tcvectordb import RPCVectorDBClient, VectorDBException  # type: ignore
+from tcvectordb import RPCVectorDBClient, VectorDBException
-from tcvectordb.model import document, enum  # type: ignore
+from tcvectordb.model import document, enum
-from tcvectordb.model import index as vdb_index  # type: ignore
+from tcvectordb.model import index as vdb_index
-from tcvectordb.model.document import AnnSearch, Filter, KeywordSearch, WeightedRerank  # type: ignore
+from tcvectordb.model.document import (
+    AnnSearch,
+    Filter,
+    KeywordSearch,
+    WeightedRerank,
+)
 
 from configs import dify_config
 from core.rag.datasource.vdb.vector_base import BaseVector

api/core/rag/datasource/vdb/tidb_vector/tidb_vector.py

@@ -50,7 +50,7 @@ class TiDBVector(BaseVector):
         return VectorType.TIDB_VECTOR
 
     def _table(self, dim: int) -> Table:
-        from tidb_vector.sqlalchemy import VectorType  # type: ignore
+        from tidb_vector.sqlalchemy import VectorType
 
         return Table(
             self._collection_name,

api/core/rag/datasource/vdb/vikingdb/vikingdb_vector.py

@@ -2,7 +2,7 @@ import json
 from typing import Any
 
 from pydantic import BaseModel
-from volcengine.viking_db import (  # type: ignore
+from volcengine.viking_db import (
     Data,
     DistanceType,
     Field,
@@ -126,7 +126,7 @@ class VikingDBVector(BaseVector):
             # FIXME: fix the type of metadata later
             doc = Data(
                 {
-                    vdb_Field.PRIMARY_KEY: metadatas[i]["doc_id"],  # type: ignore
+                    vdb_Field.PRIMARY_KEY: metadatas[i]["doc_id"],  # type: ignore[operator]
                     vdb_Field.VECTOR: embeddings[i] if embeddings else None,
                     vdb_Field.CONTENT_KEY: page_content,
                     vdb_Field.METADATA_KEY: json.dumps(metadata),

api/core/rag/embedding/cached_embedding.py

@@ -71,7 +71,7 @@ class CacheEmbedding(Embeddings):
                     for vector in embedding_result.embeddings:
                         try:
                             # FIXME: type ignore for numpy here
-                            normalized_embedding = (vector / np.linalg.norm(vector)).tolist()  # type: ignore
+                            normalized_embedding = (vector / np.linalg.norm(vector)).tolist()  # type: ignore[call-overload, operator]
                             # stackoverflow best way: https://stackoverflow.com/questions/20319813/how-to-check-list-containing-nan
                             if np.isnan(normalized_embedding).any():
                                 # for issue #11827  float values are not json compliant
@@ -154,7 +154,7 @@ class CacheEmbedding(Embeddings):
                     for vector in embedding_result.embeddings:
                         try:
                             # FIXME: type ignore for numpy here
-                            normalized_embedding = (vector / np.linalg.norm(vector)).tolist()  # type: ignore
+                            normalized_embedding = (vector / np.linalg.norm(vector)).tolist()  # type: ignore[call-overload, operator]
                             # stackoverflow best way: https://stackoverflow.com/questions/20319813/how-to-check-list-containing-nan
                             if np.isnan(normalized_embedding).any():
                                 # for issue #11827  float values are not json compliant
@@ -207,7 +207,7 @@ class CacheEmbedding(Embeddings):
 
             embedding_results = embedding_result.embeddings[0]
             # FIXME: type ignore for numpy here
-            embedding_results = (embedding_results / np.linalg.norm(embedding_results)).tolist()  # type: ignore
+            embedding_results = (embedding_results / np.linalg.norm(embedding_results)).tolist()  # type: ignore[call-overload, operator]
             if np.isnan(embedding_results).any():
                 raise ValueError("Normalized embedding is nan please try again")
         except Exception as ex:
@@ -231,7 +231,7 @@ class CacheEmbedding(Embeddings):
                 )
             raise ex
 
-        return embedding_results  # type: ignore
+        return embedding_results  # type: ignore[return-value]
 
     def embed_multimodal_query(self, multimodel_document: dict) -> list[float]:
         """Embed multimodal documents."""
@@ -250,7 +250,7 @@ class CacheEmbedding(Embeddings):
 
             embedding_results = embedding_result.embeddings[0]
             # FIXME: type ignore for numpy here
-            embedding_results = (embedding_results / np.linalg.norm(embedding_results)).tolist()  # type: ignore
+            embedding_results = (embedding_results / np.linalg.norm(embedding_results)).tolist()  # type: ignore[call-overload, operator]
             if np.isnan(embedding_results).any():
                 raise ValueError("Normalized embedding is nan please try again")
         except Exception as ex:
@@ -274,4 +274,4 @@ class CacheEmbedding(Embeddings):
                 )
             raise ex
 
-        return embedding_results  # type: ignore
+        return embedding_results  # type: ignore[return-value]

api/core/rag/extractor/extract_processor.py

@@ -75,7 +75,7 @@ class ExtractProcessor:
                             suffix = ""
             # https://stackoverflow.com/questions/26541416/generate-temporary-file-names-without-creating-actual-file-in-python#comment90414256_26541521
             # Generate a temporary filename under the created temp_dir and ensure the directory exists
-            file_path = f"{temp_dir}/{next(tempfile._get_candidate_names())}{suffix}"  # type: ignore
+            file_path = f"{temp_dir}/{next(tempfile._get_candidate_names())}{suffix}"  # type: ignore[attr-defined, operator]
             Path(file_path).write_bytes(response.content)
             extract_setting = ExtractSetting(datasource_type=DatasourceType.FILE, document_model="text_model")
             if return_text:
@@ -100,7 +100,7 @@ class ExtractProcessor:
                     upload_file: UploadFile = extract_setting.upload_file
                     suffix = Path(upload_file.key).suffix
                     # FIXME mypy: Cannot determine type of 'tempfile._get_candidate_names' better not use it here
-                    file_path = f"{temp_dir}/{next(tempfile._get_candidate_names())}{suffix}"  # type: ignore
+                    file_path = f"{temp_dir}/{next(tempfile._get_candidate_names())}{suffix}"  # type: ignore[attr-defined, operator]
                     storage.download(upload_file.key, file_path)
                 input_file = Path(file_path)
                 file_extension = input_file.suffix.lower()

api/core/rag/extractor/notion_extractor.py

@@ -348,7 +348,7 @@ class NotionExtractor(BaseExtractor):
 
         db.session.query(DocumentModel).filter_by(id=document_model.id).update(
             {DocumentModel.data_source_info: json.dumps(data_source_info)}
-        )  # type: ignore
+        )  # type: ignore[operator]
         db.session.commit()
 
     def get_notion_last_edited_time(self) -> str:

api/core/rag/extractor/unstructured/unstructured_epub_extractor.py

@@ -1,6 +1,6 @@
 import logging
 
-import pypandoc  # type: ignore
+import pypandoc
 
 from configs import dify_config
 from core.rag.extractor.extractor_base import BaseExtractor

api/core/rag/index_processor/index_processor.py

@@ -175,7 +175,7 @@ class IndexProcessor:
 
             flask_app = None
             try:
-                flask_app = current_app._get_current_object()  # type: ignore
+                flask_app = current_app._get_current_object()  # type: ignore[attr-defined]
             except RuntimeError:
                 logger.warning("No Flask application context available, summary generation may fail")
 

api/core/rag/index_processor/index_processor_base.py

@@ -147,7 +147,7 @@ class BaseIndexProcessor(ABC):
                 embedding_model_instance=embedding_model_instance,
             )
 
-        return character_splitter  # type: ignore
+        return character_splitter  # type: ignore[return-value]
 
     def _get_content_files(self, document: Document, current_user: Account | None = None) -> list[AttachmentDocument]:
         """

api/core/rag/index_processor/processor/paragraph_index_processor.py

@@ -294,7 +294,7 @@ class ParagraphIndexProcessor(BaseIndexProcessor):
         # Capture Flask app context for worker threads
         flask_app = None
         try:
-            flask_app = current_app._get_current_object()  # type: ignore
+            flask_app = current_app._get_current_object()  # type: ignore[attr-defined]
         except RuntimeError:
             logger.warning("No Flask application context available, summary generation may fail")
 

api/core/rag/index_processor/processor/parent_child_index_processor.py

@@ -379,7 +379,7 @@ class ParentChildIndexProcessor(BaseIndexProcessor):
         # Capture Flask app context for worker threads
         flask_app = None
         try:
-            flask_app = current_app._get_current_object()  # type: ignore
+            flask_app = current_app._get_current_object()  # type: ignore[attr-defined]
         except RuntimeError:
             logger.warning("No Flask application context available, summary generation may fail")
 

api/core/rag/index_processor/processor/qa_index_processor.py

@@ -87,8 +87,8 @@ class QAIndexProcessor(BaseIndexProcessor):
             all_documents.extend(split_documents)
         if preview:
             self._format_qa_document(
-                current_app._get_current_object(),  # type: ignore
+                current_app._get_current_object(),  # type: ignore[attr-defined]
-                kwargs.get("tenant_id"),  # type: ignore
+                kwargs.get("tenant_id"),  # type: ignore[arg-type]
                 all_documents[0],
                 all_qa_documents,
                 kwargs.get("doc_language", "English"),
@@ -101,8 +101,8 @@ class QAIndexProcessor(BaseIndexProcessor):
                     document_format_thread = threading.Thread(
                         target=self._format_qa_document,
                         kwargs={
-                            "flask_app": current_app._get_current_object(),  # type: ignore
+                            "flask_app": current_app._get_current_object(),  # type: ignore[attr-defined]
-                            "tenant_id": kwargs.get("tenant_id"),  # type: ignore
+                            "tenant_id": kwargs.get("tenant_id"),  # type: ignore[arg-type]
                             "document_node": doc,
                             "all_qa_documents": all_qa_documents,
                             "document_language": kwargs.get("doc_language", "English"),
@@ -121,7 +121,7 @@ class QAIndexProcessor(BaseIndexProcessor):
 
         try:
             # Skip the first row
-            df = pd.read_csv(file)  # type: ignore
+            df = pd.read_csv(file)  # type: ignore[misc]
             text_docs = []
             for _, row in df.iterrows():
                 data = Document(page_content=row.iloc[0], metadata={"answer": row.iloc[1]})

api/core/rag/retrieval/dataset_retrieval.py

@@ -417,8 +417,8 @@ class DatasetRetrieval:
             query,
             tenant_id,
             user_id,
-            retrieve_config.metadata_filtering_mode,  # type: ignore
+            retrieve_config.metadata_filtering_mode,  # type: ignore[arg-type]
-            retrieve_config.metadata_model_config,  # type: ignore
+            retrieve_config.metadata_model_config,  # type: ignore[arg-type]
             retrieve_config.metadata_filtering_conditions,
             inputs,
         )
@@ -535,11 +535,11 @@ class DatasetRetrieval:
                         DatasetDocument.enabled == True,
                         DatasetDocument.archived == False,
                     )
-                    documents = db.session.execute(dataset_document_stmt).scalars().all()  # type: ignore
+                    documents = db.session.execute(dataset_document_stmt).scalars().all()  # type: ignore[operator]
                     dataset_stmt = select(Dataset).where(
                         Dataset.id.in_(dataset_ids),
                     )
-                    datasets = db.session.execute(dataset_stmt).scalars().all()  # type: ignore
+                    datasets = db.session.execute(dataset_stmt).scalars().all()  # type: ignore[operator]
                     dataset_map = {i.id: i for i in datasets}
                     document_map = {i.id: i for i in documents}
                     for record in records:
@@ -709,7 +709,7 @@ class DatasetRetrieval:
                     thread = threading.Thread(
                         target=self._on_retrieval_end,
                         kwargs={
-                            "flask_app": current_app._get_current_object(),  # type: ignore
+                            "flask_app": current_app._get_current_object(),  # type: ignore[attr-defined]
                             "documents": results,
                             "message_id": message_id,
                             "timer": timer,
@@ -783,7 +783,7 @@ class DatasetRetrieval:
                 query_thread = threading.Thread(
                     target=self._multiple_retrieve_thread,
                     kwargs={
-                        "flask_app": current_app._get_current_object(),  # type: ignore
+                        "flask_app": current_app._get_current_object(),  # type: ignore[attr-defined]
                         "available_datasets": available_datasets,
                         "metadata_condition": metadata_condition,
                         "metadata_filter_document_ids": metadata_filter_document_ids,
@@ -809,7 +809,7 @@ class DatasetRetrieval:
                     attachment_thread = threading.Thread(
                         target=self._multiple_retrieve_thread,
                         kwargs={
-                            "flask_app": current_app._get_current_object(),  # type: ignore
+                            "flask_app": current_app._get_current_object(),  # type: ignore[attr-defined]
                             "available_datasets": available_datasets,
                             "metadata_condition": metadata_condition,
                             "metadata_filter_document_ids": metadata_filter_document_ids,
@@ -850,7 +850,7 @@ class DatasetRetrieval:
             retrieval_end_thread = threading.Thread(
                 target=self._on_retrieval_end,
                 kwargs={
-                    "flask_app": current_app._get_current_object(),  # type: ignore
+                    "flask_app": current_app._get_current_object(),  # type: ignore[attr-defined]
                     "documents": all_documents,
                     "message_id": message_id,
                     "timer": timer,
@@ -1313,7 +1313,7 @@ class DatasetRetrieval:
             DatasetDocument.enabled == True,
             DatasetDocument.archived == False,
         )
-        filters = []  # type: ignore
+        filters = []  # type: ignore[var-annotated]
         metadata_condition = None
         if metadata_filtering_mode == "disabled":
             return None, None
@@ -1326,28 +1326,28 @@ class DatasetRetrieval:
                 for sequence, filter in enumerate(automatic_metadata_filters):
                     self.process_metadata_filter_func(
                         sequence,
-                        filter.get("condition"),  # type: ignore
+                        filter.get("condition"),  # type: ignore[arg-type]
-                        filter.get("metadata_name"),  # type: ignore
+                        filter.get("metadata_name"),  # type: ignore[arg-type]
                         filter.get("value"),
-                        filters,  # type: ignore
+                        filters,  # type: ignore[arg-type]
                     )
                     conditions.append(
                         Condition(
-                            name=filter.get("metadata_name"),  # type: ignore
+                            name=filter.get("metadata_name"),  # type: ignore[arg-type]
-                            comparison_operator=filter.get("condition"),  # type: ignore
+                            comparison_operator=filter.get("condition"),  # type: ignore[arg-type]
                             value=filter.get("value"),
                         )
                     )
                 metadata_condition = MetadataCondition(
                     logical_operator=metadata_filtering_conditions.logical_operator
                     if metadata_filtering_conditions
-                    else "or",  # type: ignore
+                    else "or",  # type: ignore[assignment]
                     conditions=conditions,
                 )
         elif metadata_filtering_mode == "manual":
             if metadata_filtering_conditions:
                 conditions = []
-                for sequence, condition in enumerate(metadata_filtering_conditions.conditions):  # type: ignore
+                for sequence, condition in enumerate(metadata_filtering_conditions.conditions):  # type: ignore[arg-type]
                     metadata_name = condition.name
                     expected_value = condition.value
                     if expected_value is not None and condition.comparison_operator not in ("empty", "not empty"):
@@ -1374,15 +1374,15 @@ class DatasetRetrieval:
         else:
             raise ValueError("Invalid metadata filtering mode")
         if filters:
-            if metadata_filtering_conditions and metadata_filtering_conditions.logical_operator == "and":  # type: ignore
+            if metadata_filtering_conditions and metadata_filtering_conditions.logical_operator == "and":  # type: ignore[assignment]
                 document_query = document_query.where(and_(*filters))
             else:
                 document_query = document_query.where(or_(*filters))
         documents = document_query.all()
         # group by dataset_id
-        metadata_filter_document_ids = defaultdict(list) if documents else None  # type: ignore
+        metadata_filter_document_ids = defaultdict(list) if documents else None  # type: ignore[var-annotated]
         for document in documents:
-            metadata_filter_document_ids[document.dataset_id].append(document.id)  # type: ignore
+            metadata_filter_document_ids[document.dataset_id].append(document.id)  # type: ignore[index]
         return metadata_filter_document_ids, metadata_condition
 
     def _replace_metadata_filter_value(self, text: str, inputs: dict) -> str:

api/core/repositories/celery_workflow_execution_repository.py

@@ -108,7 +108,7 @@ class CeleryWorkflowExecutionRepository(WorkflowExecutionRepository):
             execution_data = execution.model_dump()
 
             # Queue the save operation as a Celery task (fire and forget)
-            save_workflow_execution_task.delay(  # type: ignore
+            save_workflow_execution_task.delay(  # type: ignore[operator]
                 execution_data=execution_data,
                 tenant_id=self._tenant_id,
                 app_id=self._app_id or "",

api/core/tools/builtin_tool/provider.py

@@ -162,7 +162,7 @@ class BuiltinToolProviderController(ToolProviderController):
         """
         return self._get_builtin_tools()
 
-    def get_tool(self, tool_name: str) -> BuiltinTool | None:  # type: ignore
+    def get_tool(self, tool_name: str) -> BuiltinTool | None:  # type: ignore[override, return-value]
         """
         returns the tool that the provider can provide
         """

api/core/tools/builtin_tool/providers/audio/tools/asr.py

@@ -23,12 +23,12 @@ class ASRTool(BuiltinTool):
         message_id: str | None = None,
     ) -> Generator[ToolInvokeMessage, None, None]:
         file = tool_parameters.get("audio_file")
-        if file.type != FileType.AUDIO:  # type: ignore
+        if file.type != FileType.AUDIO:  # type: ignore[attr-defined, union-attr]
             yield self.create_text_message("not a valid audio file")
             return
-        audio_binary = io.BytesIO(download(file))  # type: ignore
+        audio_binary = io.BytesIO(download(file))  # type: ignore[arg-type]
         audio_binary.name = "temp.mp3"
-        provider, model = tool_parameters.get("model").split("#")  # type: ignore
+        provider, model = tool_parameters.get("model").split("#")  # type: ignore[operator, union-attr]
         model_manager = ModelManager()
         model_instance = model_manager.get_model_instance(
             tenant_id=self.runtime.tenant_id,

api/core/tools/builtin_tool/providers/audio/tools/tts.py

@@ -20,7 +20,7 @@ class TTSTool(BuiltinTool):
         app_id: str | None = None,
         message_id: str | None = None,
     ) -> Generator[ToolInvokeMessage, None, None]:
-        provider, model = tool_parameters.get("model").split("#")  # type: ignore
+        provider, model = tool_parameters.get("model").split("#")  # type: ignore[operator, union-attr]
         voice = tool_parameters.get(f"voice#{provider}#{model}")
         model_manager = ModelManager()
         if not self.runtime:
@@ -40,7 +40,7 @@ class TTSTool(BuiltinTool):
             else:
                 raise ValueError("Sorry, no voice available.")
         tts = model_instance.invoke_tts(
-            content_text=tool_parameters.get("text"),  # type: ignore
+            content_text=tool_parameters.get("text"),  # type: ignore[arg-type]
             user=user_id,
             tenant_id=self.runtime.tenant_id,
             voice=voice,

api/core/tools/builtin_tool/providers/time/tools/localtime_to_timestamp.py

@@ -27,7 +27,7 @@ class LocaltimeToTimestampTool(BuiltinTool):
             timezone = None
         time_format = "%Y-%m-%d %H:%M:%S"
 
-        timestamp = self.localtime_to_timestamp(localtime, time_format, timezone)  # type: ignore
+        timestamp = self.localtime_to_timestamp(localtime, time_format, timezone)  # type: ignore[arg-type, misc]
         if not timestamp:
             yield self.create_text_message(f"Invalid localtime: {localtime}")
             return
@@ -40,11 +40,11 @@ class LocaltimeToTimestampTool(BuiltinTool):
         try:
             local_time = datetime.strptime(localtime, time_format)
             if local_tz is None:
-                localtime = local_time.astimezone()  # type: ignore
+                localtime = local_time.astimezone()  # type: ignore[assignment, operator]
             elif isinstance(local_tz, str):
                 local_tz = pytz.timezone(local_tz)
-                localtime = local_tz.localize(local_time)  # type: ignore
+                localtime = local_tz.localize(local_time)  # type: ignore[operator]
-            timestamp = int(localtime.timestamp())  # type: ignore
+            timestamp = int(localtime.timestamp())  # type: ignore[attr-defined, operator]
             return timestamp
         except Exception as e:
             raise ToolInvokeError(str(e))

api/core/tools/builtin_tool/providers/time/tools/timezone_conversion.py

@@ -24,7 +24,7 @@ class TimezoneConversionTool(BuiltinTool):
         current_time = tool_parameters.get("current_time")
         current_timezone = tool_parameters.get("current_timezone", "Asia/Shanghai")
         target_timezone = tool_parameters.get("target_timezone", "Asia/Tokyo")
-        target_time = self.timezone_convert(current_time, current_timezone, target_timezone)  # type: ignore
+        target_time = self.timezone_convert(current_time, current_timezone, target_timezone)  # type: ignore[arg-type, misc]
         if not target_time:
             yield self.create_text_message(
                 f"Invalid datetime and timezone: {current_time},{current_timezone},{target_timezone}"