catch openai rate limit error (#7658)

api/controllers/console/app/completion.py

@@ -17,6 +17,7 @@ from controllers.console.app.error import (
 from controllers.console.app.wraps import get_app_model
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
+from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
@@ -31,6 +32,7 @@ from libs.helper import uuid_value
 from libs.login import login_required
 from models.model import AppMode
 from services.app_generate_service import AppGenerateService
+from services.errors.llm import InvokeRateLimitError
 
 
 # define completion message api for user
@@ -135,6 +137,8 @@ class ChatMessageApi(Resource):
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
             raise ProviderModelCurrentlyNotSupportError()
+        except InvokeRateLimitError as ex:
+            raise InvokeRateLimitHttpError(ex.description)
         except InvokeError as e:
             raise CompletionRequestError(e.description)
         except (ValueError, AppInvokeQuotaExceededError) as e:

api/controllers/console/app/error.py

@@ -119,3 +119,11 @@ class TracingConfigCheckError(BaseHTTPException):
     error_code = "trace_config_check_error"
     description = "Invalid Credentials."
     code = 400
+
+
+class InvokeRateLimitError(BaseHTTPException):
+    """Raised when the Invoke returns rate limit error."""
+
+    error_code = "rate_limit_error"
+    description = "Rate Limit Error"
+    code = 429

api/controllers/web/completion.py

@@ -15,6 +15,7 @@ from controllers.web.error import (
     ProviderNotInitializeError,
     ProviderQuotaExceededError,
 )
+from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
 from controllers.web.wraps import WebApiResource
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
@@ -24,6 +25,7 @@ from libs import helper
 from libs.helper import uuid_value
 from models.model import AppMode
 from services.app_generate_service import AppGenerateService
+from services.errors.llm import InvokeRateLimitError
 
 
 # define completion api for user
@@ -120,6 +122,8 @@ class ChatApi(WebApiResource):
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
             raise ProviderModelCurrentlyNotSupportError()
+        except InvokeRateLimitError as ex:
+            raise InvokeRateLimitHttpError(ex.description)
         except InvokeError as e:
             raise CompletionRequestError(e.description)
         except ValueError as e:

api/controllers/web/error.py

@@ -125,3 +125,11 @@ class WebSSOAuthRequiredError(BaseHTTPException):
     error_code = "web_sso_auth_required"
     description = "Web SSO authentication required."
     code = 401
+
+
+class InvokeRateLimitError(BaseHTTPException):
+    """Raised when the Invoke returns rate limit error."""
+
+    error_code = "rate_limit_error"
+    description = "Rate Limit Error"
+    code = 429

api/core/errors/error.py

@@ -43,3 +43,8 @@ class ModelCurrentlyNotSupportError(Exception):
     Custom exception raised when the model not support
     """
     description = "Model Currently Not Support"
+
+
+class InvokeRateLimitError(Exception):
+    """Raised when the Invoke returns rate limit error."""
+    description = "Rate Limit Error"

api/services/app_generate_service.py

@@ -1,6 +1,8 @@
 from collections.abc import Generator
 from typing import Any, Union
 
+from openai._exceptions import RateLimitError
+
 from configs import dify_config
 from core.app.apps.advanced_chat.app_generator import AdvancedChatAppGenerator
 from core.app.apps.agent_chat.app_generator import AgentChatAppGenerator
@@ -10,6 +12,7 @@ from core.app.apps.workflow.app_generator import WorkflowAppGenerator
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.app.features.rate_limiting import RateLimit
 from models.model import Account, App, AppMode, EndUser
+from services.errors.llm import InvokeRateLimitError
 from services.workflow_service import WorkflowService
 
 
@@ -86,6 +89,8 @@ class AppGenerateService:
                 )
             else:
                 raise ValueError(f"Invalid app mode {app_model.mode}")
+        except RateLimitError as e:
+            raise InvokeRateLimitError(str(e))
         finally:
             if not streaming:
                 rate_limit.exit(request_id)

api/services/errors/llm.py

@@ -0,0 +1,19 @@
+from typing import Optional
+
+
+class InvokeError(Exception):
+    """Base class for all LLM exceptions."""
+
+    description: Optional[str] = None
+
+    def __init__(self, description: Optional[str] = None) -> None:
+        self.description = description
+
+    def __str__(self):
+        return self.description or self.__class__.__name__
+
+
+class InvokeRateLimitError(InvokeError):
+    """Raised when the Invoke returns rate limit error."""
+
+    description = "Rate Limit Error"