prompt-executor-bedrock-client/ai.koog.prompt.executor.clients.bedrock/BedrockLLMClient

BedrockLLMClient

class BedrockLLMClient @JvmOverloads constructor(bedrockClient: BedrockRuntimeClient, apiMethod: BedrockAPIMethod = BedrockAPIMethod.InvokeModel, moderationGuardrailsSettings: BedrockGuardrailsSettings? = null, fallbackModelFamily: BedrockModelFamilies? = null, clock: Clock = Clock.System) : LLMClient(source)

Creates a new Bedrock LLM client configured with the specified AWS credentials and settings.

Return

A configured LLMClient instance for Bedrock

Parameters

bedrockClient

The runtime client for interacting with Bedrock, highly configurable

apiMethod

The API method to use for interacting with Bedrock models that support messages, defaults to BedrockAPIMethod.InvokeModel.

moderationGuardrailsSettings

Optional settings of the AWS bedrock Guardrails (see AWS documentation ) that would be used for the LLMClient.moderate request

fallbackModelFamily

Optional fallback model family to use for unsupported models. If not provided, unsupported models will throw an exception.

clock

A clock used for time-based operations

Constructors

BedrockLLMClient

@JvmOverloads

constructor(bedrockClient: BedrockRuntimeClient, apiMethod: BedrockAPIMethod = BedrockAPIMethod.InvokeModel, moderationGuardrailsSettings: BedrockGuardrailsSettings? = null, fallbackModelFamily: BedrockModelFamilies? = null, clock: Clock = Clock.System)

constructor(identityProvider: IdentityProvider, settings: BedrockClientSettings = BedrockClientSettings(), clock: Clock = Clock.System)

Creates a new Bedrock LLM client configured with the specified identity provider and settings.

Properties

clientName

open val clientName: String

Functions

open override fun close()

embed

open suspend override fun embed(text: String, model: LLModel): List<Double>

Embeds the given text using the AWS Bedrock InvokeModel API.

open suspend override fun embed(inputs: List<String>, model: LLModel): List<List<Double>>

Batch embedding is not currently supported by the Bedrock client.

embedBlocking

@JvmName(name = "embed")

@JvmOverloads

fun embedBlocking(text: String, model: LLModel, executorService: ExecutorService?): List<Double>

@JvmName(name = "embed")

@JvmOverloads

fun embedBlocking(inputs: List<String>, model: LLModel, executorService: ExecutorService?): List<List<Double>>

execute

@JvmOverloads

fun execute(prompt: Prompt, model: LLModel, tools: List<ToolDescriptor>, executorService: ExecutorService?): List<Message.Response>

open suspend override fun execute(prompt: Prompt, model: LLModel, tools: List<ToolDescriptor>): List<Message.Response>

executeMultipleChoices

@JvmOverloads

fun executeMultipleChoices(prompt: Prompt, model: LLModel, tools: List<ToolDescriptor>, executorService: ExecutorService?): List<LLMChoice>

open suspend fun executeMultipleChoices(prompt: Prompt, model: LLModel, tools: List<ToolDescriptor>): List<LLMChoice>

executeStreaming

open fun executeStreaming(prompt: Prompt, model: LLModel): Flow<StreamFrame>

open override fun executeStreaming(prompt: Prompt, model: LLModel, tools: List<ToolDescriptor>): Flow<StreamFrame>

executeStreamingWithPublisher

@JvmOverloads

fun executeStreamingWithPublisher(prompt: Prompt, model: LLModel, tools: List<ToolDescriptor>): Flow.Publisher<StreamFrame>

getBasicJsonSchemaGenerator

open fun getBasicJsonSchemaGenerator(): BasicJsonSchemaGenerator

getStandardJsonSchemaGenerator

open fun getStandardJsonSchemaGenerator(): StandardJsonSchemaGenerator

llmProvider

open override fun llmProvider(): LLMProvider

models

@JvmOverloads

fun models(executorService: ExecutorService?): List<LLModel>

open suspend fun models(): List<LLModel>

moderate

@JvmOverloads

fun moderate(prompt: Prompt, model: LLModel, executorService: ExecutorService?): ModerationResult

open suspend override fun moderate(prompt: Prompt, model: LLModel): ModerationResult

Moderates the provided prompt using AWS Bedrock Guardrails.