nemo_microservices.types.shared_params.reasoning_params#

Module Contents#

Classes#

API#

class nemo_microservices.types.shared_params.reasoning_params.ReasoningParams#

Bases: typing_extensions.TypedDict

effort: str#

None

Option for OpenAI models to specify low, medium, or high reasoning effort which balances between speed and reasoning accuracy.

end_token: str#

None

Configure the end token to trim reasoning context based on the model’s reasoning API. Used for omitting Nemotron reasoning steps from output denoted with tags

include_if_not_finished: bool#

None

Configure whether to include reasoning context if the model has not finished reasoning.