Is this page helpful?

nemo_microservices.types.shared.reasoning_params#

Module Contents#

Classes#

ReasoningParams

API#

class nemo_microservices.types.shared.reasoning_params.ReasoningParams(/, **data: typing.Any)#

Bases: nemo_microservices._models.BaseModel

effort: Optional[str]#

None

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

end_token: Optional[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: Optional[bool]#

None

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