validateReward

suspend fun validateReward(parent: String, sampleResponse: Content, example: ReinforcementTuningExample, singleRewardConfig: SingleReinforcementTuningRewardConfig? = null, compositeRewardConfig: CompositeReinforcementTuningRewardConfig? = null, config: ValidateRewardConfig? = null): ValidateRewardResponse

Validates a reinforcement tuning reward configuration.

Allows users to validate a reinforcement tuning reward configuration against a sample response and example before creating a reinforcement tuning job, so that they can iterate on the reward configuration without having to create a tuning job each time.

Return

A ValidateRewardResponse with the computed reward(s).

Parameters

parent

The resource name of the Location to validate the reward in, e.g. projects/{project}/locations/{location}.

sampleResponse

The sample response for validating the reward configuration.

example

The example to validate the reward configuration.

singleRewardConfig

Single reward function configuration for reinforcement tuning. Mutually exclusive with compositeRewardConfig.

compositeRewardConfig

Composite reward function configuration for reinforcement tuning. Mutually exclusive with singleRewardConfig.

config

A ValidateRewardConfig for configuring the request.