feat: max_retries set to 1

api/core/llm/streamable_azure_chat_open_ai.py

@@ -12,7 +12,7 @@ from core.llm.wrappers.openai_wrapper import handle_openai_exceptions
 class StreamableAzureChatOpenAI(AzureChatOpenAI):
     request_timeout: Optional[Union[float, Tuple[float, float]]] = (5.0, 300.0)
     """Timeout for requests to OpenAI completion API. Default is 600 seconds."""
-    max_retries: int = 2
+    max_retries: int = 1
     """Maximum number of retries to make when generating."""
 
     @root_validator()

api/core/llm/streamable_azure_open_ai.py

@@ -13,7 +13,7 @@ class StreamableAzureOpenAI(AzureOpenAI):
     openai_api_version: str = ""
     request_timeout: Optional[Union[float, Tuple[float, float]]] = (5.0, 300.0)
     """Timeout for requests to OpenAI completion API. Default is 600 seconds."""
-    max_retries: int = 2
+    max_retries: int = 1
     """Maximum number of retries to make when generating."""
 
     @root_validator()

api/core/llm/streamable_chat_open_ai.py

@@ -13,7 +13,7 @@ from core.llm.wrappers.openai_wrapper import handle_openai_exceptions
 class StreamableChatOpenAI(ChatOpenAI):
     request_timeout: Optional[Union[float, Tuple[float, float]]] = (5.0, 300.0)
     """Timeout for requests to OpenAI completion API. Default is 600 seconds."""
-    max_retries: int = 2
+    max_retries: int = 1
     """Maximum number of retries to make when generating."""
 
     @root_validator()

api/core/llm/streamable_open_ai.py

@@ -12,7 +12,7 @@ from core.llm.wrappers.openai_wrapper import handle_openai_exceptions
 class StreamableOpenAI(OpenAI):
     request_timeout: Optional[Union[float, Tuple[float, float]]] = (5.0, 300.0)
     """Timeout for requests to OpenAI completion API. Default is 600 seconds."""
-    max_retries: int = 2
+    max_retries: int = 1
     """Maximum number of retries to make when generating."""
 
     @root_validator()