sagemakerjobruntime/aws.sdk.kotlin.services.sagemakerjobruntime

Package-level declarations

Types

SagemakerJobRuntimeClient

interface SagemakerJobRuntimeClient : SdkClient

Agentic RFT Runtime Service - manages trajectory and transition data for reinforcement fine-tuning jobs.

Properties

SdkVersion

const val SdkVersion: String

ServiceApiVersion

const val ServiceApiVersion: String

ServiceId

const val ServiceId: String

Inherited functions

completeRollout

inline suspend fun SagemakerJobRuntimeClient.completeRollout(crossinline block: CompleteRolloutRequest.Builder.() -> Unit): CompleteRolloutResponse

Marks a rollout as complete, indicating that no further turns will be appended to the trajectory. After calling this operation, the trajectory is sealed and eligible for reward submission via the UpdateReward operation.

sample

inline suspend fun SagemakerJobRuntimeClient.sample(crossinline block: SampleRequest.Builder.() -> Unit): SampleResponse

Sends an inference request to the model during a job execution. The request and response bodies are forwarded to and from the model without modification. Each turn (prompt and response) is captured for later use.

updateReward

inline suspend fun SagemakerJobRuntimeClient.updateReward(crossinline block: UpdateRewardRequest.Builder.() -> Unit): UpdateRewardResponse

Updates the reward values for a trajectory and transitions it to reward-received status, signaling that it is eligible for processing. Call this operation after CompleteRollout to provide the computed reward scores.

withConfig

fun SagemakerJobRuntimeClient.withConfig(block: SagemakerJobRuntimeClient.Config.Builder.() -> Unit): SagemakerJobRuntimeClient

Create a copy of the client with one or more configuration values overridden. This method allows the caller to perform scoped config overrides for one or more client operations.