Package com.google.genai.types

Class ReinforcementTuningSpec

java.lang.Object

com.google.genai.JsonSerializable

com.google.genai.types.ReinforcementTuningSpec

public abstract class ReinforcementTuningSpec
extends JsonSerializable

Reinforcement tuning spec for tuning.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	ReinforcementTuningSpec.Builder	Builder for ReinforcementTuningSpec.

Field Summary

Fields inherited from class com.google.genai.JsonSerializable

MAX_READ_LENGTH_PROPERTY

Constructor Summary

Constructors

Constructor	Description
ReinforcementTuningSpec()

Method Summary

Modifier and Type	Method	Description
static ReinforcementTuningSpec.Builder	builder()	Instantiates a builder for ReinforcementTuningSpec.
abstract Optional<CompositeReinforcementTuningRewardConfig>	compositeRewardConfig()
static ReinforcementTuningSpec	fromJson(String jsonString)	Deserializes a JSON string to a ReinforcementTuningSpec object.
abstract Optional<ReinforcementTuningHyperParameters>	hyperParameters()	Additional hyper-parameters to use during tuning.
abstract Optional<SingleReinforcementTuningRewardConfig>	singleRewardConfig()	Single reward function configuration for reinforcement tuning.
abstract ReinforcementTuningSpec.Builder	toBuilder()	Creates a builder with the same values as this instance.
abstract Optional<String>	trainingDatasetUri()	Cloud Storage path to file containing training dataset for tuning.
abstract Optional<String>	validationDatasetUri()	Cloud Storage path to file containing validation dataset for tuning.

Methods inherited from class com.google.genai.JsonSerializable

fromJsonNode, fromJsonString, objectMapper, setMaxReadLength, stringToJsonNode, toJson, toJsonNode, toJsonString

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

ReinforcementTuningSpec

public ReinforcementTuningSpec()

Method Details

compositeRewardConfig

public abstract Optional<CompositeReinforcementTuningRewardConfig> compositeRewardConfig()

trainingDatasetUri

public abstract Optional<String> trainingDatasetUri()

Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file.

validationDatasetUri

public abstract Optional<String> validationDatasetUri()

Cloud Storage path to file containing validation dataset for tuning. The dataset must be formatted as a JSONL file. If no validation dataset is provided, by default the API splits 25% of the training dataset or 50 examples, whichever is larger, as the validation dataset.

hyperParameters

public abstract Optional<ReinforcementTuningHyperParameters> hyperParameters()

Additional hyper-parameters to use during tuning.

singleRewardConfig

public abstract Optional<SingleReinforcementTuningRewardConfig> singleRewardConfig()

Single reward function configuration for reinforcement tuning.

builder

public static ReinforcementTuningSpec.Builder builder()

Instantiates a builder for ReinforcementTuningSpec.

toBuilder

public abstract ReinforcementTuningSpec.Builder toBuilder()

Creates a builder with the same values as this instance.

fromJson

public static ReinforcementTuningSpec fromJson(String jsonString)

Deserializes a JSON string to a ReinforcementTuningSpec object.