fix(community): allow support for disabling max_tokens args (#21534)

This PR fixes an issue with not able to use unlimited/infinity tokens from the respective provider for the LiteLLM provider. This is an issue when working in an agent environment that the token usage can drastically increase beyond the initial value set causing unexpected behavior.
langchain-ai · Jun 27, 2024 · c6f700b · c6f700b
1 parent 2a0d678
commit c6f700b
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/libs/community/langchain_community/chat_models/litellm.py b/libs/community/langchain_community/chat_models/litellm.py
@@ -191,7 191,7 @@ class ChatLiteLLM(BaseChatModel):
  n: int = 1
  """Number of chat completions to generate for each prompt. Note that the API may
  not return the full n completions if duplicates are generated."""
- max_tokens: int = 256
  max_tokens: Optional[int] = None
 
  max_retries: int = 6