Reduce default retries

libs/langchain/langchain/chat_models/litellm.py

@@ -218,7 +218,7 @@ class ChatLiteLLM(BaseChatModel):
        not return the full n completions if duplicates are generated."""
     max_tokens: int = 256
 
-    max_retries: int = 6
+    max_retries: int = 4 
 
     @property
     def _default_params(self) -> Dict[str, Any]:

libs/langchain/langchain/chat_models/openai.py

@@ -156,7 +156,7 @@ class ChatOpenAI(BaseChatModel):
     openai_proxy: Optional[str] = None
     request_timeout: Optional[Union[float, Tuple[float, float]]] = None
     """Timeout for requests to OpenAI completion API. Default is 600 seconds."""
-    max_retries: int = 6
+    max_retries: int = 4 
     """Maximum number of retries to make when generating."""
     streaming: bool = False
     """Whether to stream the results or not."""

libs/langchain/langchain/embeddings/openai.py

@@ -177,7 +177,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
     disallowed_special: Union[Literal["all"], Set[str], Sequence[str]] = "all"
     chunk_size: int = 1000
     """Maximum number of texts to embed in each batch"""
-    max_retries: int = 6
+    max_retries: int = 4
     """Maximum number of retries to make when generating."""
     request_timeout: Optional[Union[float, Tuple[float, float]]] = None
     """Timeout in seconds for the OpenAPI request."""

libs/langchain/langchain/llms/openai.py

@@ -174,7 +174,7 @@ class BaseOpenAI(BaseLLM):
     """Timeout for requests to OpenAI completion API. Default is 600 seconds."""
     logit_bias: Optional[Dict[str, float]] = Field(default_factory=dict)
     """Adjust the probability of specific tokens being generated."""
-    max_retries: int = 6
+    max_retries: int = 4
     """Maximum number of retries to make when generating."""
     streaming: bool = False
     """Whether to stream the results or not."""
@@ -715,7 +715,7 @@ class OpenAIChat(BaseLLM):
     openai_api_base: Optional[str] = None
     # to support explicit proxy for OpenAI
     openai_proxy: Optional[str] = None
-    max_retries: int = 6
+    max_retries: int = 4
     """Maximum number of retries to make when generating."""
     prefix_messages: List = Field(default_factory=list)
     """Series of messages for Chat input."""