BedrockRuntimeClient

Suggest an Edit

Describes the API operations for running inference using Amazon Bedrock models.

Installation

NPM
npm install @aws-sdk/client-bedrock-runtime
Yarn
yarn add @aws-sdk/client-bedrock-runtime
pnpm
pnpm add @aws-sdk/client-bedrock-runtime

BedrockRuntimeClient Operations

Command
Summary
ApplyGuardrailCommand

The action to apply a guardrail.

For troubleshooting some of the common errors you might encounter when using the ApplyGuardrail API, see Troubleshooting Amazon Bedrock API Error Codes  in the Amazon Bedrock User Guide

ConverseCommand

Sends messages to the specified Amazon Bedrock model. Converse provides a consistent interface that works with all models that support messages. This allows you to write code once and use it with different models. If a model has unique inference parameters, you can also pass those unique parameters to the model.

Amazon Bedrock doesn't store any text, images, or documents that you provide as content. The data is only used to generate the response.

You can submit a prompt by including it in the messages field, specifying the modelId of a foundation model or inference profile to run inference on it, and including any other fields that are relevant to your use case.

You can also submit a prompt from Prompt management by specifying the ARN of the prompt version and including a map of variables to values in the promptVariables field. You can append more messages to the prompt by using the messages field. If you use a prompt from Prompt management, you can't include the following fields in the request: additionalModelRequestFields, inferenceConfig, system, or toolConfig. Instead, these fields must be defined through Prompt management. For more information, see Use a prompt from Prompt management .

For information about the Converse API, see Use the Converse API in the Amazon Bedrock User Guide. To use a guardrail, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide. To use a tool with a model, see Tool use (Function calling) in the Amazon Bedrock User Guide

For example code, see Converse API examples in the Amazon Bedrock User Guide.

This operation requires permission for the bedrock:InvokeModel action.

To deny all inference access to resources that you specify in the modelId field, you need to deny access to the bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream actions. Doing this also denies access to the resource through the base inference actions (InvokeModel  and InvokeModelWithResponseStream ). For more information see Deny access for inference on specific models .

For troubleshooting some of the common errors you might encounter when using the Converse API, see Troubleshooting Amazon Bedrock API Error Codes  in the Amazon Bedrock User Guide

ConverseStreamCommand

Sends messages to the specified Amazon Bedrock model and returns the response in a stream. ConverseStream provides a consistent API that works with all Amazon Bedrock models that support messages. This allows you to write code once and use it with different models. Should a model have unique inference parameters, you can also pass those unique parameters to the model.

To find out if a model supports streaming, call GetFoundationModel  and check the responseStreamingSupported field in the response.

The CLI doesn't support streaming operations in Amazon Bedrock, including ConverseStream.

Amazon Bedrock doesn't store any text, images, or documents that you provide as content. The data is only used to generate the response.

You can submit a prompt by including it in the messages field, specifying the modelId of a foundation model or inference profile to run inference on it, and including any other fields that are relevant to your use case.

You can also submit a prompt from Prompt management by specifying the ARN of the prompt version and including a map of variables to values in the promptVariables field. You can append more messages to the prompt by using the messages field. If you use a prompt from Prompt management, you can't include the following fields in the request: additionalModelRequestFields, inferenceConfig, system, or toolConfig. Instead, these fields must be defined through Prompt management. For more information, see Use a prompt from Prompt management .

For information about the Converse API, see Use the Converse API in the Amazon Bedrock User Guide. To use a guardrail, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide. To use a tool with a model, see Tool use (Function calling) in the Amazon Bedrock User Guide

For example code, see Conversation streaming example in the Amazon Bedrock User Guide.

This operation requires permission for the bedrock:InvokeModelWithResponseStream action.

To deny all inference access to resources that you specify in the modelId field, you need to deny access to the bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream actions. Doing this also denies access to the resource through the base inference actions (InvokeModel  and InvokeModelWithResponseStream ). For more information see Deny access for inference on specific models .

For troubleshooting some of the common errors you might encounter when using the ConverseStream API, see Troubleshooting Amazon Bedrock API Error Codes  in the Amazon Bedrock User Guide

GetAsyncInvokeCommand

Retrieve information about an asynchronous invocation.

InvokeModelCommand

Invokes the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. You use model inference to generate text, images, and embeddings.

For example code, see Invoke model code examples in the Amazon Bedrock User Guide.

This operation requires permission for the bedrock:InvokeModel action.

To deny all inference access to resources that you specify in the modelId field, you need to deny access to the bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream actions. Doing this also denies access to the resource through the Converse API actions (Converse  and ConverseStream ). For more information see Deny access for inference on specific models .

For troubleshooting some of the common errors you might encounter when using the InvokeModel API, see Troubleshooting Amazon Bedrock API Error Codes  in the Amazon Bedrock User Guide

InvokeModelWithResponseStreamCommand

Invoke the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. The response is returned in a stream.

To see if a model supports streaming, call GetFoundationModel  and check the responseStreamingSupported field in the response.

The CLI doesn't support streaming operations in Amazon Bedrock, including InvokeModelWithResponseStream.

For example code, see Invoke model with streaming code example in the Amazon Bedrock User Guide.

This operation requires permissions to perform the bedrock:InvokeModelWithResponseStream action.

To deny all inference access to resources that you specify in the modelId field, you need to deny access to the bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream actions. Doing this also denies access to the resource through the Converse API actions (Converse  and ConverseStream ). For more information see Deny access for inference on specific models .

For troubleshooting some of the common errors you might encounter when using the InvokeModelWithResponseStream API, see Troubleshooting Amazon Bedrock API Error Codes  in the Amazon Bedrock User Guide

ListAsyncInvokesCommand

Lists asynchronous invocations.

StartAsyncInvokeCommand

Starts an asynchronous invocation.

This operation requires permission for the bedrock:InvokeModel action.

To deny all inference access to resources that you specify in the modelId field, you need to deny access to the bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream actions. Doing this also denies access to the resource through the Converse API actions (Converse  and ConverseStream ). For more information see Deny access for inference on specific models .

BedrockRuntimeClient Configuration

Parameter
Type
Description
defaultsMode
Optional
DefaultsMode | Provider<DefaultsMode>
The @smithy/smithy-client#DefaultsMode that will be used to determine how certain default configuration options are resolved in the SDK.
disableHostPrefix
Optional
boolean
Disable dynamically changing the endpoint of the client based on the hostPrefix trait of an operation.
eventStreamSerdeProvider
Optional
EventStreamSerdeProvider
The function that provides necessary utilities for generating and parsing event stream
extensions
Optional
RuntimeExtension[]
Optional extensions
logger
Optional
Logger
Optional logger for logging debug/info/warn/error.
maxAttempts
Optional
number | Provider<number>
Value for how many times a request will be made at most in case of retry.
profile
Optional
string
Setting a client profile is similar to setting a value for the AWS_PROFILE environment variable. Setting a profile on a client in code only affects the single client instance, unlike AWS_PROFILE.When set, and only for environments where an AWS configuration file exists, fields configurable by this file will be retrieved from the specified profile within that file. Conflicting code configuration and environment variables will still have higher priority.For client credential resolution that involves checking the AWS configuration file, the client's profile (this value) will be used unless a different profile is set in the credential provider options.
region
Optional
string | Provider<string>
The AWS region to which this client will send requests
requestHandler
Optional
__HttpHandlerUserInput
The HTTP handler to use or its constructor options. Fetch in browser and Https in Nodejs.
retryMode
Optional
string | Provider<string>
Specifies which retry algorithm to use.
useDualstackEndpoint
Optional
boolean | Provider<boolean>
Enables IPv6/IPv4 dualstack endpoint.
useFipsEndpoint
Optional
boolean | Provider<boolean>
Enables FIPS compatible endpoints.
Additional config fields are described in the full configuration type: BedrockRuntimeClientConfig

BedrockRuntimeClient Example Scenarios

Use Converse 
Use Converse 
Use Converse 
Use Converse 
Use Converse 
Use Converse 
Use Converse 
Use ConverseStream 
Use ConverseStream 
Use ConverseStream 
Use ConverseStream 
Use ConverseStream 
Use ConverseStream 
Use InvokeModel 
Use InvokeModel 
Use InvokeModel 
Use InvokeModel 
Use InvokeModel 
Use InvokeModelWithResponseStream 
Use InvokeModelWithResponseStream 
Use InvokeModel 
Invoke multiple foundation models on Amazon Bedrock