chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419)

api/core/app_runner/app_runner.py

@@ -1,5 +1,6 @@
 import time
-from typing import Generator, List, Optional, Tuple, Union, cast
+from collections.abc import Generator
+from typing import Optional, Union, cast
 
 from core.application_queue_manager import ApplicationQueueManager, PublishFrom
 from core.entities.application_entities import (
@@ -84,7 +85,7 @@ class AppRunner:
         return rest_tokens
 
     def recale_llm_max_tokens(self, model_config: ModelConfigEntity,
-                              prompt_messages: List[PromptMessage]):
+                              prompt_messages: list[PromptMessage]):
         # recalc max_tokens if sum(prompt_token +  max_tokens) over model token limit
         model_type_instance = model_config.provider_model_bundle.model_type_instance
         model_type_instance = cast(LargeLanguageModel, model_type_instance)
@@ -126,7 +127,7 @@ class AppRunner:
                                  query: Optional[str] = None,
                                  context: Optional[str] = None,
                                  memory: Optional[TokenBufferMemory] = None) \
-            -> Tuple[List[PromptMessage], Optional[List[str]]]:
+            -> tuple[list[PromptMessage], Optional[list[str]]]:
         """
         Organize prompt messages
         :param context:
@@ -295,7 +296,7 @@ class AppRunner:
                               tenant_id: str,
                               app_orchestration_config_entity: AppOrchestrationConfigEntity,
                               inputs: dict,
-                              query: str) -> Tuple[bool, dict, str]:
+                              query: str) -> tuple[bool, dict, str]:
         """
         Process sensitive_word_avoidance.
         :param app_id: app id

api/core/app_runner/generate_task_pipeline.py

@@ -1,7 +1,8 @@
 import json
 import logging
 import time
-from typing import Generator, Optional, Union, cast
+from collections.abc import Generator
+from typing import Optional, Union, cast
 
 from pydantic import BaseModel
 
@@ -118,7 +119,7 @@ class GenerateTaskPipeline:
                     }
 
                     self._task_state.llm_result.message.content = annotation.content
-            elif isinstance(event, (QueueStopEvent, QueueMessageEndEvent)):
+            elif isinstance(event, QueueStopEvent | QueueMessageEndEvent):
                 if isinstance(event, QueueMessageEndEvent):
                     self._task_state.llm_result = event.llm_result
                 else:
@@ -201,7 +202,7 @@ class GenerateTaskPipeline:
                 data = self._error_to_stream_response_data(self._handle_error(event))
                 yield self._yield_response(data)
                 break
-            elif isinstance(event, (QueueStopEvent, QueueMessageEndEvent)):
+            elif isinstance(event, QueueStopEvent | QueueMessageEndEvent):
                 if isinstance(event, QueueMessageEndEvent):
                     self._task_state.llm_result = event.llm_result
                 else:
@@ -353,7 +354,7 @@ class GenerateTaskPipeline:
 
                     yield self._yield_response(response)
 
-            elif isinstance(event, (QueueMessageEvent, QueueAgentMessageEvent)):
+            elif isinstance(event, QueueMessageEvent | QueueAgentMessageEvent):
                 chunk = event.chunk
                 delta_text = chunk.delta.message.content
                 if delta_text is None:

api/core/app_runner/moderation_handler.py

@@ -1,7 +1,7 @@
 import logging
 import threading
 import time
-from typing import Any, Dict, Optional
+from typing import Any, Optional
 
 from flask import Flask, current_app
 from pydantic import BaseModel
@@ -15,7 +15,7 @@ logger = logging.getLogger(__name__)
 
 class ModerationRule(BaseModel):
     type: str
-    config: Dict[str, Any]
+    config: dict[str, Any]
 
 
 class OutputModerationHandler(BaseModel):