bedrockruntime

package module
v1.24.0 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Jan 17, 2025 License: Apache-2.0 Imports: 53 Imported by: 164

Documentation

Overview

Package bedrockruntime provides the API client, operations, and parameter types for Amazon Bedrock Runtime.

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

Index

Constants

View Source 
const ServiceAPIVersion = "2023-09-30"
View Source 
const ServiceID = "Bedrock Runtime"

Variables

This section is empty.

Functions

func NewDefaultEndpointResolver 

func NewDefaultEndpointResolver() *internalendpoints.Resolver

NewDefaultEndpointResolver constructs a new service endpoint resolver

func WithAPIOptions 

func WithAPIOptions(optFns ...func(*middleware.Stack) error) func(*Options)

WithAPIOptions returns a functional option for setting the Client's APIOptions option.

func WithEndpointResolver deprecated 

func WithEndpointResolver(v EndpointResolver) func(*Options)

Deprecated: EndpointResolver and WithEndpointResolver. Providing a value for this field will likely prevent you from using any endpoint-related service features released after the introduction of EndpointResolverV2 and BaseEndpoint.

To migrate an EndpointResolver implementation that uses a custom endpoint, set the client option BaseEndpoint instead.

func WithEndpointResolverV2 

func WithEndpointResolverV2(v EndpointResolverV2) func(*Options)

WithEndpointResolverV2 returns a functional option for setting the Client's EndpointResolverV2 option.

func WithSigV4SigningName added in v1.3.2 

func WithSigV4SigningName(name string) func(*Options)

WithSigV4SigningName applies an override to the authentication workflow to use the given signing name for SigV4-authenticated operations.

This is an advanced setting. The value here is FINAL, taking precedence over the resolved signing name from both auth scheme resolution and endpoint resolution.

func WithSigV4SigningRegion added in v1.3.2 

func WithSigV4SigningRegion(region string) func(*Options)

WithSigV4SigningRegion applies an override to the authentication workflow to use the given signing region for SigV4-authenticated operations.

This is an advanced setting. The value here is FINAL, taking precedence over the resolved signing region from both auth scheme resolution and endpoint resolution.

Types

type ApplyGuardrailInput added in v1.13.0 

type ApplyGuardrailInput struct {

	// The content details used in the request to apply the guardrail.
	//
	// This member is required.
	Content []types.GuardrailContentBlock

	// The guardrail identifier used in the request to apply the guardrail.
	//
	// This member is required.
	GuardrailIdentifier *string

	// The guardrail version used in the request to apply the guardrail.
	//
	// This member is required.
	GuardrailVersion *string

	// The source of data used in the request to apply the guardrail.
	//
	// This member is required.
	Source types.GuardrailContentSource
	// contains filtered or unexported fields
}

type ApplyGuardrailOutput added in v1.13.0 

type ApplyGuardrailOutput struct {

	// The action taken in the response from the guardrail.
	//
	// This member is required.
	Action types.GuardrailAction

	// The assessment details in the response from the guardrail.
	//
	// This member is required.
	Assessments []types.GuardrailAssessment

	// The output details in the response from the guardrail.
	//
	// This member is required.
	Outputs []types.GuardrailOutputContent

	// The usage details in the response from the guardrail.
	//
	// This member is required.
	Usage *types.GuardrailUsage

	// The guardrail coverage details in the apply guardrail response.
	GuardrailCoverage *types.GuardrailCoverage

	// Metadata pertaining to the operation's result.
	ResultMetadata middleware.Metadata
	// contains filtered or unexported fields
}

type AuthResolverParameters added in v1.3.2 

type AuthResolverParameters struct {
	// The name of the operation being invoked.
	Operation string

	// The region in which the operation is being invoked.
	Region string
}

AuthResolverParameters contains the set of inputs necessary for auth scheme resolution.

type AuthSchemeResolver added in v1.3.2 

type AuthSchemeResolver interface {
	ResolveAuthSchemes(context.Context, *AuthResolverParameters) ([]*smithyauth.Option, error)
}

AuthSchemeResolver returns a set of possible authentication options for an operation.

type Client 

type Client struct {
	// contains filtered or unexported fields
}

Client provides the API client to make operations call for Amazon Bedrock Runtime.

func New 

func New(options Options, optFns ...func(*Options)) *Client

New returns an initialized Client based on the functional options. Provide additional functional options to further configure the behavior of the client, such as changing the client's endpoint or adding custom middleware behavior.

func NewFromConfig 

func NewFromConfig(cfg aws.Config, optFns ...func(*Options)) *Client

NewFromConfig returns a new client from the provided config.

func (*Client) ApplyGuardrail added in v1.13.0 

func (c *Client) ApplyGuardrail(ctx context.Context, params *ApplyGuardrailInput, optFns ...func(*Options)) (*ApplyGuardrailOutput, error)

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

func (*Client) Converse added in v1.9.0 

func (c *Client) Converse(ctx context.Context, params *ConverseInput, optFns ...func(*Options)) (*ConverseOutput, error)

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

func (*Client) ConverseStream added in v1.9.0 

func (c *Client) ConverseStream(ctx context.Context, params *ConverseStreamInput, optFns ...func(*Options)) (*ConverseStreamOutput, error)

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

func (*Client) GetAsyncInvoke added in v1.22.0 

func (c *Client) GetAsyncInvoke(ctx context.Context, params *GetAsyncInvokeInput, optFns ...func(*Options)) (*GetAsyncInvokeOutput, error)

Retrieve information about an asynchronous invocation.

func (*Client) InvokeModel 

func (c *Client) InvokeModel(ctx context.Context, params *InvokeModelInput, optFns ...func(*Options)) (*InvokeModelOutput, error)

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

func (*Client) InvokeModelWithResponseStream 

func (c *Client) InvokeModelWithResponseStream(ctx context.Context, params *InvokeModelWithResponseStreamInput, optFns ...func(*Options)) (*InvokeModelWithResponseStreamOutput, error)

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

func (*Client) ListAsyncInvokes added in v1.22.0 

func (c *Client) ListAsyncInvokes(ctx context.Context, params *ListAsyncInvokesInput, optFns ...func(*Options)) (*ListAsyncInvokesOutput, error)

Lists asynchronous invocations.

func (*Client) Options added in v1.5.0 

func (c *Client) Options() Options

Options returns a copy of the client configuration.

Callers SHOULD NOT perform mutations on any inner structures within client config. Config overrides should instead be made on a per-operation basis through functional options.

func (*Client) StartAsyncInvoke added in v1.22.0 

func (c *Client) StartAsyncInvoke(ctx context.Context, params *StartAsyncInvokeInput, optFns ...func(*Options)) (*StartAsyncInvokeOutput, error)

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 .

type ConverseInput added in v1.9.0 

type ConverseInput struct {

	// Specifies the model or throughput with which to run inference, or the prompt
	// resource to use in inference. The value depends on the resource that you use:
	//
	//   - If you use a base model, specify the model ID or its ARN. For a list of
	//   model IDs for base models, see [Amazon Bedrock base model IDs (on-demand throughput)]in the Amazon Bedrock User Guide.
	//
	//   - If you use an inference profile, specify the inference profile ID or its
	//   ARN. For a list of inference profile IDs, see [Supported Regions and models for cross-region inference]in the Amazon Bedrock User
	//   Guide.
	//
	//   - If you use a provisioned model, specify the ARN of the Provisioned
	//   Throughput. For more information, see [Run inference using a Provisioned Throughput]in the Amazon Bedrock User Guide.
	//
	//   - If you use a custom model, first purchase Provisioned Throughput for it.
	//   Then specify the ARN of the resulting provisioned model. For more information,
	//   see [Use a custom model in Amazon Bedrock]in the Amazon Bedrock User Guide.
	//
	//   - To include a prompt that was defined in [Prompt management], specify the ARN of the prompt
	//   version to use.
	//
	// The Converse API doesn't support [imported models].
	//
	// [Run inference using a Provisioned Throughput]: https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html
	// [Use a custom model in Amazon Bedrock]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html
	// [Prompt management]: https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management.html
	// [Supported Regions and models for cross-region inference]: https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html
	// [imported models]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html
	// [Amazon Bedrock base model IDs (on-demand throughput)]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns
	//
	// This member is required.
	ModelId *string

	// Additional inference parameters that the model supports, beyond the base set of
	// inference parameters that Converse and ConverseStream support in the
	// inferenceConfig field. For more information, see [Model parameters].
	//
	// [Model parameters]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html
	AdditionalModelRequestFields document.Interface

	// Additional model parameters field paths to return in the response. Converse and
	// ConverseStream return the requested fields as a JSON Pointer object in the
	// additionalModelResponseFields field. The following is example JSON for
	// additionalModelResponseFieldPaths .
	//
	//     [ "/stop_sequence" ]
	//
	// For information about the JSON Pointer syntax, see the [Internet Engineering Task Force (IETF)] documentation.
	//
	// Converse and ConverseStream reject an empty JSON Pointer or incorrectly
	// structured JSON Pointer with a 400 error code. if the JSON Pointer is valid,
	// but the requested field is not in the model response, it is ignored by Converse .
	//
	// [Internet Engineering Task Force (IETF)]: https://datatracker.ietf.org/doc/html/rfc6901
	AdditionalModelResponseFieldPaths []string

	// Configuration information for a guardrail that you want to use in the request.
	// If you include guardContent blocks in the content field in the messages field,
	// the guardrail operates only on those messages. If you include no guardContent
	// blocks, the guardrail operates on all messages in the request body and in any
	// included prompt resource.
	GuardrailConfig *types.GuardrailConfiguration

	// Inference parameters to pass to the model. Converse and ConverseStream support
	// a base set of inference parameters. If you need to pass additional parameters
	// that the model supports, use the additionalModelRequestFields request field.
	InferenceConfig *types.InferenceConfiguration

	// The messages that you want to send to the model.
	Messages []types.Message

	// Model performance settings for the request.
	PerformanceConfig *types.PerformanceConfiguration

	// Contains a map of variables in a prompt from Prompt management to objects
	// containing the values to fill in for them when running model invocation. This
	// field is ignored if you don't specify a prompt resource in the modelId field.
	PromptVariables map[string]types.PromptVariableValues

	// Key-value pairs that you can use to filter invocation logs.
	RequestMetadata map[string]string

	// A prompt that provides instructions or context to the model about the task it
	// should perform, or the persona it should adopt during the conversation.
	System []types.SystemContentBlock

	// Configuration information for the tools that the model can use when generating
	// a response.
	//
	// For information about models that support tool use, see [Supported models and model features].
	//
	// [Supported models and model features]: https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html#conversation-inference-supported-models-features
	ToolConfig *types.ToolConfiguration
	// contains filtered or unexported fields
}

type ConverseOutput added in v1.9.0 

type ConverseOutput struct {

	// Metrics for the call to Converse .
	//
	// This member is required.
	Metrics *types.ConverseMetrics

	// The result from the call to Converse .
	//
	// This member is required.
	Output types.ConverseOutput

	// The reason why the model stopped generating output.
	//
	// This member is required.
	StopReason types.StopReason

	// The total number of tokens used in the call to Converse . The total includes the
	// tokens input to the model and the tokens generated by the model.
	//
	// This member is required.
	Usage *types.TokenUsage

	// Additional fields in the response that are unique to the model.
	AdditionalModelResponseFields document.Interface

	// Model performance settings for the request.
	PerformanceConfig *types.PerformanceConfiguration

	// A trace object that contains information about the Guardrail behavior.
	Trace *types.ConverseTrace

	// Metadata pertaining to the operation's result.
	ResultMetadata middleware.Metadata
	// contains filtered or unexported fields
}

type ConverseStreamEventStream added in v1.9.0 

type ConverseStreamEventStream struct {
	// ConverseStreamOutputReader is the EventStream reader for the
	// ConverseStreamOutput events. This value is automatically set by the SDK when the
	// API call is made Use this member when unit testing your code with the SDK to
	// mock out the EventStream Reader.
	//
	// Must not be nil.
	Reader ConverseStreamOutputReader
	// contains filtered or unexported fields
}

ConverseStreamEventStream provides the event stream handling for the ConverseStream operation.

For testing and mocking the event stream this type should be initialized via the NewConverseStreamEventStream constructor function. Using the functional options to pass in nested mock behavior.

func NewConverseStreamEventStream added in v1.9.0 

func NewConverseStreamEventStream(optFns ...func(*ConverseStreamEventStream)) *ConverseStreamEventStream

NewConverseStreamEventStream initializes an ConverseStreamEventStream. This function should only be used for testing and mocking the ConverseStreamEventStream stream within your application.

The Reader member must be set before reading events from the stream.

func (*ConverseStreamEventStream) Close added in v1.9.0 

func (es *ConverseStreamEventStream) Close() error

Close closes the stream. This will also cause the stream to be closed. Close must be called when done using the stream API. Not calling Close may result in resource leaks.

Will close the underlying EventStream writer and reader, and no more events can be sent or received.

func (*ConverseStreamEventStream) Err added in v1.9.0 

func (es *ConverseStreamEventStream) Err() error

Err returns any error that occurred while reading or writing EventStream Events from the service API's response. Returns nil if there were no errors.

func (*ConverseStreamEventStream) Events added in v1.9.0 

func (es *ConverseStreamEventStream) Events() <-chan types.ConverseStreamOutput

Events returns a channel to read events from.

type ConverseStreamInput added in v1.9.0 

type ConverseStreamInput struct {

	// Specifies the model or throughput with which to run inference, or the prompt
	// resource to use in inference. The value depends on the resource that you use:
	//
	//   - If you use a base model, specify the model ID or its ARN. For a list of
	//   model IDs for base models, see [Amazon Bedrock base model IDs (on-demand throughput)]in the Amazon Bedrock User Guide.
	//
	//   - If you use an inference profile, specify the inference profile ID or its
	//   ARN. For a list of inference profile IDs, see [Supported Regions and models for cross-region inference]in the Amazon Bedrock User
	//   Guide.
	//
	//   - If you use a provisioned model, specify the ARN of the Provisioned
	//   Throughput. For more information, see [Run inference using a Provisioned Throughput]in the Amazon Bedrock User Guide.
	//
	//   - If you use a custom model, first purchase Provisioned Throughput for it.
	//   Then specify the ARN of the resulting provisioned model. For more information,
	//   see [Use a custom model in Amazon Bedrock]in the Amazon Bedrock User Guide.
	//
	//   - To include a prompt that was defined in [Prompt management], specify the ARN of the prompt
	//   version to use.
	//
	// The Converse API doesn't support [imported models].
	//
	// [Run inference using a Provisioned Throughput]: https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html
	// [Use a custom model in Amazon Bedrock]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html
	// [Prompt management]: https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management.html
	// [Supported Regions and models for cross-region inference]: https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html
	// [imported models]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html
	// [Amazon Bedrock base model IDs (on-demand throughput)]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns
	//
	// This member is required.
	ModelId *string

	// Additional inference parameters that the model supports, beyond the base set of
	// inference parameters that Converse and ConverseStream support in the
	// inferenceConfig field. For more information, see [Model parameters].
	//
	// [Model parameters]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html
	AdditionalModelRequestFields document.Interface

	// Additional model parameters field paths to return in the response. Converse and
	// ConverseStream return the requested fields as a JSON Pointer object in the
	// additionalModelResponseFields field. The following is example JSON for
	// additionalModelResponseFieldPaths .
	//
	//     [ "/stop_sequence" ]
	//
	// For information about the JSON Pointer syntax, see the [Internet Engineering Task Force (IETF)] documentation.
	//
	// Converse and ConverseStream reject an empty JSON Pointer or incorrectly
	// structured JSON Pointer with a 400 error code. if the JSON Pointer is valid,
	// but the requested field is not in the model response, it is ignored by Converse .
	//
	// [Internet Engineering Task Force (IETF)]: https://datatracker.ietf.org/doc/html/rfc6901
	AdditionalModelResponseFieldPaths []string

	// Configuration information for a guardrail that you want to use in the request.
	// If you include guardContent blocks in the content field in the messages field,
	// the guardrail operates only on those messages. If you include no guardContent
	// blocks, the guardrail operates on all messages in the request body and in any
	// included prompt resource.
	GuardrailConfig *types.GuardrailStreamConfiguration

	// Inference parameters to pass to the model. Converse and ConverseStream support
	// a base set of inference parameters. If you need to pass additional parameters
	// that the model supports, use the additionalModelRequestFields request field.
	InferenceConfig *types.InferenceConfiguration

	// The messages that you want to send to the model.
	Messages []types.Message

	// Model performance settings for the request.
	PerformanceConfig *types.PerformanceConfiguration

	// Contains a map of variables in a prompt from Prompt management to objects
	// containing the values to fill in for them when running model invocation. This
	// field is ignored if you don't specify a prompt resource in the modelId field.
	PromptVariables map[string]types.PromptVariableValues

	// Key-value pairs that you can use to filter invocation logs.
	RequestMetadata map[string]string

	// A prompt that provides instructions or context to the model about the task it
	// should perform, or the persona it should adopt during the conversation.
	System []types.SystemContentBlock

	// Configuration information for the tools that the model can use when generating
	// a response.
	//
	// For information about models that support streaming tool use, see [Supported models and model features].
	//
	// [Supported models and model features]: https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html#conversation-inference-supported-models-features
	ToolConfig *types.ToolConfiguration
	// contains filtered or unexported fields
}

type ConverseStreamOutput added in v1.9.0 

type ConverseStreamOutput struct {

	// Metadata pertaining to the operation's result.
	ResultMetadata middleware.Metadata
	// contains filtered or unexported fields
}

func (*ConverseStreamOutput) GetStream added in v1.9.0 

func (o *ConverseStreamOutput) GetStream() *ConverseStreamEventStream

GetStream returns the type to interact with the event stream.

type ConverseStreamOutputReader added in v1.9.0 

type ConverseStreamOutputReader interface {
	Events() <-chan types.ConverseStreamOutput
	Close() error
	Err() error
}

ConverseStreamOutputReader provides the interface for reading events from a stream.

The writer's Close method must allow multiple concurrent calls.

type EndpointParameters 

type EndpointParameters struct {
	// The AWS region used to dispatch the request.
	//
	// Parameter is
	// required.
	//
	// AWS::Region
	Region *string

	// When true, use the dual-stack endpoint. If the configured endpoint does not
	// support dual-stack, dispatching the request MAY return an error.
	//
	// Defaults to
	// false if no value is provided.
	//
	// AWS::UseDualStack
	UseDualStack *bool

	// When true, send this request to the FIPS-compliant regional endpoint. If the
	// configured endpoint does not have a FIPS compliant endpoint, dispatching the
	// request will return an error.
	//
	// Defaults to false if no value is
	// provided.
	//
	// AWS::UseFIPS
	UseFIPS *bool

	// Override the endpoint used to send this request
	//
	// Parameter is
	// required.
	//
	// SDK::Endpoint
	Endpoint *string
}

EndpointParameters provides the parameters that influence how endpoints are resolved.

func (EndpointParameters) ValidateRequired 

func (p EndpointParameters) ValidateRequired() error

ValidateRequired validates required parameters are set.

func (EndpointParameters) WithDefaults 

func (p EndpointParameters) WithDefaults() EndpointParameters

WithDefaults returns a shallow copy of EndpointParameterswith default values applied to members where applicable.

type EndpointResolver 

type EndpointResolver interface {
	ResolveEndpoint(region string, options EndpointResolverOptions) (aws.Endpoint, error)
}

EndpointResolver interface for resolving service endpoints.

func EndpointResolverFromURL 

func EndpointResolverFromURL(url string, optFns ...func(*aws.Endpoint)) EndpointResolver

EndpointResolverFromURL returns an EndpointResolver configured using the provided endpoint url. By default, the resolved endpoint resolver uses the client region as signing region, and the endpoint source is set to EndpointSourceCustom.You can provide functional options to configure endpoint values for the resolved endpoint.

type EndpointResolverFunc 

type EndpointResolverFunc func(region string, options EndpointResolverOptions) (aws.Endpoint, error)

EndpointResolverFunc is a helper utility that wraps a function so it satisfies the EndpointResolver interface. This is useful when you want to add additional endpoint resolving logic, or stub out specific endpoints with custom values.

func (EndpointResolverFunc) ResolveEndpoint 

func (fn EndpointResolverFunc) ResolveEndpoint(region string, options EndpointResolverOptions) (endpoint aws.Endpoint, err error)

type EndpointResolverOptions 

type EndpointResolverOptions = internalendpoints.Options

EndpointResolverOptions is the service endpoint resolver options

type EndpointResolverV2 

type EndpointResolverV2 interface {
	// ResolveEndpoint attempts to resolve the endpoint with the provided options,
	// returning the endpoint if found. Otherwise an error is returned.
	ResolveEndpoint(ctx context.Context, params EndpointParameters) (
		smithyendpoints.Endpoint, error,
	)
}

EndpointResolverV2 provides the interface for resolving service endpoints.

func NewDefaultEndpointResolverV2 

func NewDefaultEndpointResolverV2() EndpointResolverV2

type GetAsyncInvokeInput added in v1.22.0 

type GetAsyncInvokeInput struct {

	// The invocation's ARN.
	//
	// This member is required.
	InvocationArn *string
	// contains filtered or unexported fields
}

type GetAsyncInvokeOutput added in v1.22.0 

type GetAsyncInvokeOutput struct {

	// The invocation's ARN.
	//
	// This member is required.
	InvocationArn *string

	// The invocation's model ARN.
	//
	// This member is required.
	ModelArn *string

	// Output data settings.
	//
	// This member is required.
	OutputDataConfig types.AsyncInvokeOutputDataConfig

	// The invocation's status.
	//
	// This member is required.
	Status types.AsyncInvokeStatus

	// When the invocation request was submitted.
	//
	// This member is required.
	SubmitTime *time.Time

	// The invocation's idempotency token.
	ClientRequestToken *string

	// When the invocation ended.
	EndTime *time.Time

	// An error message.
	FailureMessage *string

	// The invocation's last modified time.
	LastModifiedTime *time.Time

	// Metadata pertaining to the operation's result.
	ResultMetadata middleware.Metadata
	// contains filtered or unexported fields
}

type HTTPClient 

type HTTPClient interface {
	Do(*http.Request) (*http.Response, error)
}

type HTTPSignerV4 

type HTTPSignerV4 interface {
	SignHTTP(ctx context.Context, credentials aws.Credentials, r *http.Request, payloadHash string, service string, region string, signingTime time.Time, optFns ...func(*v4.SignerOptions)) error
}

type IdempotencyTokenProvider added in v1.22.0 

type IdempotencyTokenProvider interface {
	GetIdempotencyToken() (string, error)
}

IdempotencyTokenProvider interface for providing idempotency token

type InvokeModelInput 

type InvokeModelInput struct {

	// The unique identifier of the model to invoke to run inference.
	//
	// The modelId to provide depends on the type of model or throughput that you use:
	//
	//   - If you use a base model, specify the model ID or its ARN. For a list of
	//   model IDs for base models, see [Amazon Bedrock base model IDs (on-demand throughput)]in the Amazon Bedrock User Guide.
	//
	//   - If you use an inference profile, specify the inference profile ID or its
	//   ARN. For a list of inference profile IDs, see [Supported Regions and models for cross-region inference]in the Amazon Bedrock User
	//   Guide.
	//
	//   - If you use a provisioned model, specify the ARN of the Provisioned
	//   Throughput. For more information, see [Run inference using a Provisioned Throughput]in the Amazon Bedrock User Guide.
	//
	//   - If you use a custom model, first purchase Provisioned Throughput for it.
	//   Then specify the ARN of the resulting provisioned model. For more information,
	//   see [Use a custom model in Amazon Bedrock]in the Amazon Bedrock User Guide.
	//
	//   - If you use an [imported model], specify the ARN of the imported model. You can get the
	//   model ARN from a successful call to [CreateModelImportJob]or from the Imported models page in the
	//   Amazon Bedrock console.
	//
	// [Run inference using a Provisioned Throughput]: https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html
	// [Use a custom model in Amazon Bedrock]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html
	// [imported model]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html
	// [CreateModelImportJob]: https://docs.aws.amazon.com/bedrock/latest/APIReference/API_CreateModelImportJob.html
	// [Supported Regions and models for cross-region inference]: https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html
	// [Amazon Bedrock base model IDs (on-demand throughput)]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns
	//
	// This member is required.
	ModelId *string

	// The desired MIME type of the inference body in the response. The default value
	// is application/json .
	Accept *string

	// The prompt and inference parameters in the format specified in the contentType
	// in the header. You must provide the body in JSON format. To see the format and
	// content of the request and response bodies for different models, refer to [Inference parameters]. For
	// more information, see [Run inference]in the Bedrock User Guide.
	//
	// [Inference parameters]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html
	// [Run inference]: https://docs.aws.amazon.com/bedrock/latest/userguide/api-methods-run.html
	Body []byte

	// The MIME type of the input data in the request. You must specify
	// application/json .
	ContentType *string

	// The unique identifier of the guardrail that you want to use. If you don't
	// provide a value, no guardrail is applied to the invocation.
	//
	// An error will be thrown in the following situations.
	//
	//   - You don't provide a guardrail identifier but you specify the
	//   amazon-bedrock-guardrailConfig field in the request body.
	//
	//   - You enable the guardrail but the contentType isn't application/json .
	//
	//   - You provide a guardrail identifier, but guardrailVersion isn't specified.
	GuardrailIdentifier *string

	// The version number for the guardrail. The value can also be DRAFT .
	GuardrailVersion *string

	// Model performance settings for the request.
	PerformanceConfigLatency types.PerformanceConfigLatency

	// Specifies whether to enable or disable the Bedrock trace. If enabled, you can
	// see the full Bedrock trace.
	Trace types.Trace
	// contains filtered or unexported fields
}

type InvokeModelOutput 

type InvokeModelOutput struct {

	// Inference response from the model in the format specified in the contentType
	// header. To see the format and content of the request and response bodies for
	// different models, refer to [Inference parameters].
	//
	// [Inference parameters]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html
	//
	// This member is required.
	Body []byte

	// The MIME type of the inference result.
	//
	// This member is required.
	ContentType *string

	// Model performance settings for the request.
	PerformanceConfigLatency types.PerformanceConfigLatency

	// Metadata pertaining to the operation's result.
	ResultMetadata middleware.Metadata
	// contains filtered or unexported fields
}

type InvokeModelWithResponseStreamEventStream 

type InvokeModelWithResponseStreamEventStream struct {
	// ResponseStreamReader is the EventStream reader for the ResponseStream events.
	// This value is automatically set by the SDK when the API call is made Use this
	// member when unit testing your code with the SDK to mock out the EventStream
	// Reader.
	//
	// Must not be nil.
	Reader ResponseStreamReader
	// contains filtered or unexported fields
}

InvokeModelWithResponseStreamEventStream provides the event stream handling for the InvokeModelWithResponseStream operation.

For testing and mocking the event stream this type should be initialized via the NewInvokeModelWithResponseStreamEventStream constructor function. Using the functional options to pass in nested mock behavior.

func NewInvokeModelWithResponseStreamEventStream 

func NewInvokeModelWithResponseStreamEventStream(optFns ...func(*InvokeModelWithResponseStreamEventStream)) *InvokeModelWithResponseStreamEventStream

NewInvokeModelWithResponseStreamEventStream initializes an InvokeModelWithResponseStreamEventStream. This function should only be used for testing and mocking the InvokeModelWithResponseStreamEventStream stream within your application.

The Reader member must be set before reading events from the stream.

func (*InvokeModelWithResponseStreamEventStream) Close 

func (es *InvokeModelWithResponseStreamEventStream) Close() error

Close closes the stream. This will also cause the stream to be closed. Close must be called when done using the stream API. Not calling Close may result in resource leaks.

Will close the underlying EventStream writer and reader, and no more events can be sent or received.

func (*InvokeModelWithResponseStreamEventStream) Err 

func (es *InvokeModelWithResponseStreamEventStream) Err() error

Err returns any error that occurred while reading or writing EventStream Events from the service API's response. Returns nil if there were no errors.

func (*InvokeModelWithResponseStreamEventStream) Events 

func (es *InvokeModelWithResponseStreamEventStream) Events() <-chan types.ResponseStream

Events returns a channel to read events from.

type InvokeModelWithResponseStreamInput 

type InvokeModelWithResponseStreamInput struct {

	// The unique identifier of the model to invoke to run inference.
	//
	// The modelId to provide depends on the type of model or throughput that you use:
	//
	//   - If you use a base model, specify the model ID or its ARN. For a list of
	//   model IDs for base models, see [Amazon Bedrock base model IDs (on-demand throughput)]in the Amazon Bedrock User Guide.
	//
	//   - If you use an inference profile, specify the inference profile ID or its
	//   ARN. For a list of inference profile IDs, see [Supported Regions and models for cross-region inference]in the Amazon Bedrock User
	//   Guide.
	//
	//   - If you use a provisioned model, specify the ARN of the Provisioned
	//   Throughput. For more information, see [Run inference using a Provisioned Throughput]in the Amazon Bedrock User Guide.
	//
	//   - If you use a custom model, first purchase Provisioned Throughput for it.
	//   Then specify the ARN of the resulting provisioned model. For more information,
	//   see [Use a custom model in Amazon Bedrock]in the Amazon Bedrock User Guide.
	//
	//   - If you use an [imported model], specify the ARN of the imported model. You can get the
	//   model ARN from a successful call to [CreateModelImportJob]or from the Imported models page in the
	//   Amazon Bedrock console.
	//
	// [Run inference using a Provisioned Throughput]: https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html
	// [Use a custom model in Amazon Bedrock]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html
	// [imported model]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html
	// [CreateModelImportJob]: https://docs.aws.amazon.com/bedrock/latest/APIReference/API_CreateModelImportJob.html
	// [Supported Regions and models for cross-region inference]: https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html
	// [Amazon Bedrock base model IDs (on-demand throughput)]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns
	//
	// This member is required.
	ModelId *string

	// The desired MIME type of the inference body in the response. The default value
	// is application/json .
	Accept *string

	// The prompt and inference parameters in the format specified in the contentType
	// in the header. You must provide the body in JSON format. To see the format and
	// content of the request and response bodies for different models, refer to [Inference parameters]. For
	// more information, see [Run inference]in the Bedrock User Guide.
	//
	// [Inference parameters]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html
	// [Run inference]: https://docs.aws.amazon.com/bedrock/latest/userguide/api-methods-run.html
	Body []byte

	// The MIME type of the input data in the request. You must specify
	// application/json .
	ContentType *string

	// The unique identifier of the guardrail that you want to use. If you don't
	// provide a value, no guardrail is applied to the invocation.
	//
	// An error is thrown in the following situations.
	//
	//   - You don't provide a guardrail identifier but you specify the
	//   amazon-bedrock-guardrailConfig field in the request body.
	//
	//   - You enable the guardrail but the contentType isn't application/json .
	//
	//   - You provide a guardrail identifier, but guardrailVersion isn't specified.
	GuardrailIdentifier *string

	// The version number for the guardrail. The value can also be DRAFT .
	GuardrailVersion *string

	// Model performance settings for the request.
	PerformanceConfigLatency types.PerformanceConfigLatency

	// Specifies whether to enable or disable the Bedrock trace. If enabled, you can
	// see the full Bedrock trace.
	Trace types.Trace
	// contains filtered or unexported fields
}

type InvokeModelWithResponseStreamOutput 

type InvokeModelWithResponseStreamOutput struct {

	// The MIME type of the inference result.
	//
	// This member is required.
	ContentType *string

	// Model performance settings for the request.
	PerformanceConfigLatency types.PerformanceConfigLatency

	// Metadata pertaining to the operation's result.
	ResultMetadata middleware.Metadata
	// contains filtered or unexported fields
}

func (*InvokeModelWithResponseStreamOutput) GetStream 

func (o *InvokeModelWithResponseStreamOutput) GetStream() *InvokeModelWithResponseStreamEventStream

GetStream returns the type to interact with the event stream.

type ListAsyncInvokesAPIClient added in v1.22.0 

type ListAsyncInvokesAPIClient interface {
	ListAsyncInvokes(context.Context, *ListAsyncInvokesInput, ...func(*Options)) (*ListAsyncInvokesOutput, error)
}

ListAsyncInvokesAPIClient is a client that implements the ListAsyncInvokes operation.

type ListAsyncInvokesInput added in v1.22.0 

type ListAsyncInvokesInput struct {

	// The maximum number of invocations to return in one page of results.
	MaxResults *int32

	// Specify the pagination token from a previous request to retrieve the next page
	// of results.
	NextToken *string

	// How to sort the response.
	SortBy types.SortAsyncInvocationBy

	// The sorting order for the response.
	SortOrder types.SortOrder

	// Filter invocations by status.
	StatusEquals types.AsyncInvokeStatus

	// Include invocations submitted after this time.
	SubmitTimeAfter *time.Time

	// Include invocations submitted before this time.
	SubmitTimeBefore *time.Time
	// contains filtered or unexported fields
}

type ListAsyncInvokesOutput added in v1.22.0 

type ListAsyncInvokesOutput struct {

	// A list of invocation summaries.
	AsyncInvokeSummaries []types.AsyncInvokeSummary

	// Specify the pagination token from a previous request to retrieve the next page
	// of results.
	NextToken *string

	// Metadata pertaining to the operation's result.
	ResultMetadata middleware.Metadata
	// contains filtered or unexported fields
}

type ListAsyncInvokesPaginator added in v1.22.0 

type ListAsyncInvokesPaginator struct {
	// contains filtered or unexported fields
}

ListAsyncInvokesPaginator is a paginator for ListAsyncInvokes

func NewListAsyncInvokesPaginator added in v1.22.0 

func NewListAsyncInvokesPaginator(client ListAsyncInvokesAPIClient, params *ListAsyncInvokesInput, optFns ...func(*ListAsyncInvokesPaginatorOptions)) *ListAsyncInvokesPaginator

NewListAsyncInvokesPaginator returns a new ListAsyncInvokesPaginator

func (*ListAsyncInvokesPaginator) HasMorePages added in v1.22.0 

func (p *ListAsyncInvokesPaginator) HasMorePages() bool

HasMorePages returns a boolean indicating whether more pages are available

func (*ListAsyncInvokesPaginator) NextPage added in v1.22.0 

func (p *ListAsyncInvokesPaginator) NextPage(ctx context.Context, optFns ...func(*Options)) (*ListAsyncInvokesOutput, error)

NextPage retrieves the next ListAsyncInvokes page.

type ListAsyncInvokesPaginatorOptions added in v1.22.0 

type ListAsyncInvokesPaginatorOptions struct {
	// The maximum number of invocations to return in one page of results.
	Limit int32

	// Set to true if pagination should stop if the service returns a pagination token
	// that matches the most recent token provided to the service.
	StopOnDuplicateToken bool
}

ListAsyncInvokesPaginatorOptions is the paginator options for ListAsyncInvokes

type Options 

type Options struct {
	// Set of options to modify how an operation is invoked. These apply to all
	// operations invoked for this client. Use functional options on operation call to
	// modify this list for per operation behavior.
	APIOptions []func(*middleware.Stack) error

	// The optional application specific identifier appended to the User-Agent header.
	AppID string

	// This endpoint will be given as input to an EndpointResolverV2. It is used for
	// providing a custom base endpoint that is subject to modifications by the
	// processing EndpointResolverV2.
	BaseEndpoint *string

	// Configures the events that will be sent to the configured logger.
	ClientLogMode aws.ClientLogMode

	// The credentials object to use when signing requests.
	Credentials aws.CredentialsProvider

	// The configuration DefaultsMode that the SDK should use when constructing the
	// clients initial default settings.
	DefaultsMode aws.DefaultsMode

	// The endpoint options to be used when attempting to resolve an endpoint.
	EndpointOptions EndpointResolverOptions

	// The service endpoint resolver.
	//
	// Deprecated: Deprecated: EndpointResolver and WithEndpointResolver. Providing a
	// value for this field will likely prevent you from using any endpoint-related
	// service features released after the introduction of EndpointResolverV2 and
	// BaseEndpoint.
	//
	// To migrate an EndpointResolver implementation that uses a custom endpoint, set
	// the client option BaseEndpoint instead.
	EndpointResolver EndpointResolver

	// Resolves the endpoint used for a particular service operation. This should be
	// used over the deprecated EndpointResolver.
	EndpointResolverV2 EndpointResolverV2

	// Signature Version 4 (SigV4) Signer
	HTTPSignerV4 HTTPSignerV4

	// Provides idempotency tokens values that will be automatically populated into
	// idempotent API operations.
	IdempotencyTokenProvider IdempotencyTokenProvider

	// The logger writer interface to write logging messages to.
	Logger logging.Logger

	// The client meter provider.
	MeterProvider metrics.MeterProvider

	// The region to send requests to. (Required)
	Region string

	// RetryMaxAttempts specifies the maximum number attempts an API client will call
	// an operation that fails with a retryable error. A value of 0 is ignored, and
	// will not be used to configure the API client created default retryer, or modify
	// per operation call's retry max attempts.
	//
	// If specified in an operation call's functional options with a value that is
	// different than the constructed client's Options, the Client's Retryer will be
	// wrapped to use the operation's specific RetryMaxAttempts value.
	RetryMaxAttempts int

	// RetryMode specifies the retry mode the API client will be created with, if
	// Retryer option is not also specified.
	//
	// When creating a new API Clients this member will only be used if the Retryer
	// Options member is nil. This value will be ignored if Retryer is not nil.
	//
	// Currently does not support per operation call overrides, may in the future.
	RetryMode aws.RetryMode

	// Retryer guides how HTTP requests should be retried in case of recoverable
	// failures. When nil the API client will use a default retryer. The kind of
	// default retry created by the API client can be changed with the RetryMode
	// option.
	Retryer aws.Retryer

	// The RuntimeEnvironment configuration, only populated if the DefaultsMode is set
	// to DefaultsModeAuto and is initialized using config.LoadDefaultConfig . You
	// should not populate this structure programmatically, or rely on the values here
	// within your applications.
	RuntimeEnvironment aws.RuntimeEnvironment

	// The client tracer provider.
	TracerProvider tracing.TracerProvider

	// The HTTP client to invoke API calls with. Defaults to client's default HTTP
	// implementation if nil.
	HTTPClient HTTPClient

	// The auth scheme resolver which determines how to authenticate for each
	// operation.
	AuthSchemeResolver AuthSchemeResolver

	// The list of auth schemes supported by the client.
	AuthSchemes []smithyhttp.AuthScheme
	// contains filtered or unexported fields
}

func (Options) Copy 

func (o Options) Copy() Options

Copy creates a clone where the APIOptions list is deep copied.

func (Options) GetIdentityResolver added in v1.3.2 

func (o Options) GetIdentityResolver(schemeID string) smithyauth.IdentityResolver

type ResolveEndpoint 

type ResolveEndpoint struct {
	Resolver EndpointResolver
	Options  EndpointResolverOptions
}

func (*ResolveEndpoint) HandleSerialize 

func (m *ResolveEndpoint) HandleSerialize(ctx context.Context, in middleware.SerializeInput, next middleware.SerializeHandler) (
	out middleware.SerializeOutput, metadata middleware.Metadata, err error,
)

func (*ResolveEndpoint) ID 

func (*ResolveEndpoint) ID() string

type ResponseStreamReader 

type ResponseStreamReader interface {
	Events() <-chan types.ResponseStream
	Close() error
	Err() error
}

ResponseStreamReader provides the interface for reading events from a stream.

The writer's Close method must allow multiple concurrent calls.

type StartAsyncInvokeInput added in v1.22.0 

type StartAsyncInvokeInput struct {

	// The model to invoke.
	//
	// This member is required.
	ModelId *string

	// Input to send to the model.
	//
	// This member is required.
	ModelInput document.Interface

	// Where to store the output.
	//
	// This member is required.
	OutputDataConfig types.AsyncInvokeOutputDataConfig

	// Specify idempotency token to ensure that requests are not duplicated.
	ClientRequestToken *string

	// Tags to apply to the invocation.
	Tags []types.Tag
	// contains filtered or unexported fields
}

type StartAsyncInvokeOutput added in v1.22.0 

type StartAsyncInvokeOutput struct {

	// The ARN of the invocation.
	//
	// This member is required.
	InvocationArn *string

	// Metadata pertaining to the operation's result.
	ResultMetadata middleware.Metadata
	// contains filtered or unexported fields
}

type UnknownEventMessageError 

type UnknownEventMessageError struct {
	Type    string
	Message *eventstream.Message
}

UnknownEventMessageError provides an error when a message is received from the stream, but the reader is unable to determine what kind of message it is.

func (*UnknownEventMessageError) Error 

func (e *UnknownEventMessageError) Error() string

Error retruns the error message string.

Source Files

View all Source files

Directories

Path Synopsis
Package document implements encoding and decoding of open-content that has a JSON-like data model.
 Package document implements encoding and decoding of open-content that has a JSON-like data model.
internal
document
endpoints

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.