Struct Client

pub struct Client { /* private fields */ }

Client for Agents for Amazon Bedrock Runtime

Client for invoking operations on Agents for Amazon Bedrock Runtime. Each operation on Agents for Amazon Bedrock Runtime is a method on this this struct. .send() MUST be invoked on the generated operations to dispatch the request to the service.

Constructing a Client

A Config is required to construct a client. For most use cases, the aws-config crate should be used to automatically resolve this config using aws_config::load_from_env(), since this will resolve an SdkConfig which can be shared across multiple different AWS SDK clients. This config resolution process can be customized by calling aws_config::from_env() instead, which returns a ConfigLoader that uses the builder pattern to customize the default config.

In the simplest case, creating a client looks as follows:

let config = aws_config::load_from_env().await;
let client = aws_sdk_bedrockagentruntime::Client::new(&config);

Occasionally, SDKs may have additional service-specific values that can be set on the Config that is absent from SdkConfig, or slightly different settings for a specific client may be desired. The Builder struct implements From<&SdkConfig>, so setting these specific settings can be done as follows:

let sdk_config = ::aws_config::load_from_env().await;
let config = aws_sdk_bedrockagentruntime::config::Builder::from(&sdk_config)
    .some_service_specific_setting("value")
    .build();

See the aws-config docs and Config for more information on customizing configuration.

Note: Client construction is expensive due to connection thread pool initialization, and should be done once at application start-up.

Implementations

impl Client

pub fn delete_agent_memory(&self) -> DeleteAgentMemoryFluentBuilder

Constructs a fluent builder for the DeleteAgentMemory operation.

• The fluent builder is configurable:
  • agent_id(impl Into<String>) / set_agent_id(Option<String>):
    required: true
    

    The unique identifier of the agent to which the alias belongs.

    
    
  • agent_alias_id(impl Into<String>) / set_agent_alias_id(Option<String>):
    required: true
    

    The unique identifier of an alias of an agent.

    
    
  • memory_id(impl Into<String>) / set_memory_id(Option<String>):
    required: false
    

    The unique identifier of the memory.

    
    
  • session_id(impl Into<String>) / set_session_id(Option<String>):
    required: false
    

    The unique session identifier of the memory.

    
    
• On success, responds with DeleteAgentMemoryOutput
• On failure, responds with SdkError<DeleteAgentMemoryError>

impl Client

pub fn generate_query(&self) -> GenerateQueryFluentBuilder

Constructs a fluent builder for the GenerateQuery operation.

• The fluent builder is configurable:
  • query_generation_input(QueryGenerationInput) / set_query_generation_input(Option<QueryGenerationInput>):
    required: true
    

    Specifies information about a natural language query to transform into SQL.

    
    
  • transformation_configuration(TransformationConfiguration) / set_transformation_configuration(Option<TransformationConfiguration>):
    required: true
    

    Specifies configurations for transforming the natural language query into SQL.

    
    
• On success, responds with GenerateQueryOutput with field(s):
  • queries(Option<Vec::<GeneratedQuery>>):

    A list of objects, each of which defines a generated query that can correspond to the natural language queries.

• On failure, responds with SdkError<GenerateQueryError>

impl Client

pub fn get_agent_memory(&self) -> GetAgentMemoryFluentBuilder

Constructs a fluent builder for the GetAgentMemory operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    If the total number of results is greater than the maxItems value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

    
    
  • max_items(i32) / set_max_items(Option<i32>):
    required: false
    

    The maximum number of items to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

    
    
  • agent_id(impl Into<String>) / set_agent_id(Option<String>):
    required: true
    

    The unique identifier of the agent to which the alias belongs.

    
    
  • agent_alias_id(impl Into<String>) / set_agent_alias_id(Option<String>):
    required: true
    

    The unique identifier of an alias of an agent.

    
    
  • memory_type(MemoryType) / set_memory_type(Option<MemoryType>):
    required: true
    

    The type of memory.

    
    
  • memory_id(impl Into<String>) / set_memory_id(Option<String>):
    required: true
    

    The unique identifier of the memory.

    
    
• On success, responds with GetAgentMemoryOutput with field(s):
  • next_token(Option<String>):

    If the total number of results is greater than the maxItems value provided in the request, use this token when making another request in the nextToken field to return the next batch of results.

  • memory_contents(Option<Vec::<Memory>>):

    Contains details of the sessions stored in the memory

• On failure, responds with SdkError<GetAgentMemoryError>

impl Client

pub fn invoke_agent(&self) -> InvokeAgentFluentBuilder

Constructs a fluent builder for the InvokeAgent operation.

• The fluent builder is configurable:
  • session_state(SessionState) / set_session_state(Option<SessionState>):
    required: false
    

    Contains parameters that specify various attributes of the session. For more information, see Control session context.

    If you include returnControlInvocationResults in the sessionState field, the inputText field will be ignored.

    
    
  • agent_id(impl Into<String>) / set_agent_id(Option<String>):
    required: true
    

    The unique identifier of the agent to use.

    
    
  • agent_alias_id(impl Into<String>) / set_agent_alias_id(Option<String>):
    required: true
    

    The alias of the agent to use.

    
    
  • session_id(impl Into<String>) / set_session_id(Option<String>):
    required: true
    

    The unique identifier of the session. Use the same value across requests to continue the same conversation.

    
    
  • end_session(bool) / set_end_session(Option<bool>):
    required: false
    

    Specifies whether to end the session with the agent or not.

    
    
  • enable_trace(bool) / set_enable_trace(Option<bool>):
    required: false
    

    Specifies whether to turn on the trace or not to track the agent’s reasoning process. For more information, see Trace enablement.

    
    
  • input_text(impl Into<String>) / set_input_text(Option<String>):
    required: false
    

    The prompt text to send the agent.

    If you include returnControlInvocationResults in the sessionState field, the inputText field will be ignored.

    
    
  • memory_id(impl Into<String>) / set_memory_id(Option<String>):
    required: false
    

    The unique identifier of the agent memory.

    
    
  • bedrock_model_configurations(BedrockModelConfigurations) / set_bedrock_model_configurations(Option<BedrockModelConfigurations>):
    required: false
    

    Model performance settings for the request.

    
    
  • streaming_configurations(StreamingConfigurations) / set_streaming_configurations(Option<StreamingConfigurations>):
    required: false
    

    Specifies the configurations for streaming.

    To use agent streaming, you need permissions to perform the bedrock:InvokeModelWithResponseStream action.

    
    
  • source_arn(impl Into<String>) / set_source_arn(Option<String>):
    required: false
    

    The ARN of the resource making the request.

    
    
• On success, responds with InvokeAgentOutput with field(s):
  • completion(EventReceiver<ResponseStream, ResponseStreamError>):

    The agent’s response to the user prompt.

  • content_type(String):

    The MIME type of the input data in the request. The default value is application/json.

  • session_id(String):

    The unique identifier of the session with the agent.

  • memory_id(Option<String>):

    The unique identifier of the agent memory.

• On failure, responds with SdkError<InvokeAgentError>

impl Client

pub fn invoke_flow(&self) -> InvokeFlowFluentBuilder

Constructs a fluent builder for the InvokeFlow operation.

• The fluent builder is configurable:
  • flow_identifier(impl Into<String>) / set_flow_identifier(Option<String>):
    required: true
    

    The unique identifier of the flow.

    
    
  • flow_alias_identifier(impl Into<String>) / set_flow_alias_identifier(Option<String>):
    required: true
    

    The unique identifier of the flow alias.

    
    
  • inputs(FlowInput) / set_inputs(Option<Vec::<FlowInput>>):
    required: true
    

    A list of objects, each containing information about an input into the flow.

    
    
  • enable_trace(bool) / set_enable_trace(Option<bool>):
    required: false
    

    Specifies whether to return the trace for the flow or not. Traces track inputs and outputs for nodes in the flow. For more information, see Track each step in your prompt flow by viewing its trace in Amazon Bedrock.

    
    
  • model_performance_configuration(ModelPerformanceConfiguration) / set_model_performance_configuration(Option<ModelPerformanceConfiguration>):
    required: false
    

    Model performance settings for the request.

    
    
  • execution_id(impl Into<String>) / set_execution_id(Option<String>):
    required: false
    

    The unique identifier for the current flow execution. If you don’t provide a value, Amazon Bedrock creates the identifier for you.

    
    
• On success, responds with InvokeFlowOutput with field(s):
  • response_stream(EventReceiver<FlowResponseStream, FlowResponseStreamError>):

    The output of the flow, returned as a stream. If there’s an error, the error is returned.

  • execution_id(Option<String>):

    The unique identifier for the current flow execution.

• On failure, responds with SdkError<InvokeFlowError>

impl Client

pub fn invoke_inline_agent(&self) -> InvokeInlineAgentFluentBuilder

Constructs a fluent builder for the InvokeInlineAgent operation.

• The fluent builder is configurable:
  • session_id(impl Into<String>) / set_session_id(Option<String>):
    required: true
    

    The unique identifier of the session. Use the same value across requests to continue the same conversation.

    
    
  • customer_encryption_key_arn(impl Into<String>) / set_customer_encryption_key_arn(Option<String>):
    required: false
    

    The Amazon Resource Name (ARN) of the Amazon Web Services KMS key to use to encrypt your inline agent.

    
    
  • end_session(bool) / set_end_session(Option<bool>):
    required: false
    

    Specifies whether to end the session with the inline agent or not.

    
    
  • enable_trace(bool) / set_enable_trace(Option<bool>):
    required: false
    

    Specifies whether to turn on the trace or not to track the agent’s reasoning process. For more information, see Using trace.

    
    
  • input_text(impl Into<String>) / set_input_text(Option<String>):
    required: false
    

    The prompt text to send to the agent.

    If you include returnControlInvocationResults in the sessionState field, the inputText field will be ignored.

    
    
  • inline_session_state(InlineSessionState) / set_inline_session_state(Option<InlineSessionState>):
    required: false
    

    Parameters that specify the various attributes of a sessions. You can include attributes for the session or prompt or, if you configured an action group to return control, results from invocation of the action group. For more information, see Control session context.

    If you include returnControlInvocationResults in the sessionState field, the inputText field will be ignored.

    
    
  • foundation_model(impl Into<String>) / set_foundation_model(Option<String>):
    required: true
    

    The model identifier (ID) of the model to use for orchestration by the inline agent. For example, meta.llama3-1-70b-instruct-v1:0.

    
    
  • instruction(impl Into<String>) / set_instruction(Option<String>):
    required: true
    

    The instructions that tell the inline agent what it should do and how it should interact with users.

    
    
  • idle_session_ttl_in_seconds(i32) / set_idle_session_ttl_in_seconds(Option<i32>):
    required: false
    

    The number of seconds for which the inline agent should maintain session information. After this time expires, the subsequent InvokeInlineAgent request begins a new session.

    A user interaction remains active for the amount of time specified. If no conversation occurs during this time, the session expires and the data provided before the timeout is deleted.

    
    
  • action_groups(AgentActionGroup) / set_action_groups(Option<Vec::<AgentActionGroup>>):
    required: false
    

    A list of action groups with each action group defining the action the inline agent needs to carry out.

    
    
  • knowledge_bases(KnowledgeBase) / set_knowledge_bases(Option<Vec::<KnowledgeBase>>):
    required: false
    

    Contains information of the knowledge bases to associate with.

    
    
  • guardrail_configuration(GuardrailConfigurationWithArn) / set_guardrail_configuration(Option<GuardrailConfigurationWithArn>):
    required: false
    

    The guardrails to assign to the inline agent.

    
    
  • prompt_override_configuration(PromptOverrideConfiguration) / set_prompt_override_configuration(Option<PromptOverrideConfiguration>):
    required: false
    

    Configurations for advanced prompts used to override the default prompts to enhance the accuracy of the inline agent.

    
    
  • bedrock_model_configurations(InlineBedrockModelConfigurations) / set_bedrock_model_configurations(Option<InlineBedrockModelConfigurations>):
    required: false
    

    Model settings for the request.

    
    
  • streaming_configurations(StreamingConfigurations) / set_streaming_configurations(Option<StreamingConfigurations>):
    required: false
    

    Specifies the configurations for streaming.

    To use agent streaming, you need permissions to perform the bedrock:InvokeModelWithResponseStream action.

    
    
• On success, responds with InvokeInlineAgentOutput with field(s):
  • completion(EventReceiver<InlineAgentResponseStream, InlineAgentResponseStreamError>):

  • content_type(String):

    The MIME type of the input data in the request. The default value is application/json.

  • session_id(String):

    The unique identifier of the session with the agent.

• On failure, responds with SdkError<InvokeInlineAgentError>

impl Client

pub fn optimize_prompt(&self) -> OptimizePromptFluentBuilder

Constructs a fluent builder for the OptimizePrompt operation.

• The fluent builder is configurable:
  • input(InputPrompt) / set_input(Option<InputPrompt>):
    required: true
    

    Contains the prompt to optimize.

    
    
  • target_model_id(impl Into<String>) / set_target_model_id(Option<String>):
    required: true
    

    The unique identifier of the model that you want to optimize the prompt for.

    
    
• On success, responds with OptimizePromptOutput with field(s):
  • optimized_prompt(EventReceiver<OptimizedPromptStream, OptimizedPromptStreamError>):

    The prompt after being optimized for the task.

• On failure, responds with SdkError<OptimizePromptError>

impl Client

pub fn rerank(&self) -> RerankFluentBuilder

Constructs a fluent builder for the Rerank operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • queries(RerankQuery) / set_queries(Option<Vec::<RerankQuery>>):
    required: true
    

    An array of objects, each of which contains information about a query to submit to the reranker model.

    
    
  • sources(RerankSource) / set_sources(Option<Vec::<RerankSource>>):
    required: true
    

    An array of objects, each of which contains information about the sources to rerank.

    
    
  • reranking_configuration(RerankingConfiguration) / set_reranking_configuration(Option<RerankingConfiguration>):
    required: true
    

    Contains configurations for reranking.

    
    
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    If the total number of results was greater than could fit in a response, a token is returned in the nextToken field. You can enter that token in this field to return the next batch of results.

    
    
• On success, responds with RerankOutput with field(s):
  • results(Vec::<RerankResult>):

    An array of objects, each of which contains information about the results of reranking.

  • next_token(Option<String>):

    If the total number of results is greater than can fit in the response, use this token in the nextToken field when making another request to return the next batch of results.

• On failure, responds with SdkError<RerankError>

impl Client

pub fn retrieve(&self) -> RetrieveFluentBuilder

Constructs a fluent builder for the Retrieve operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • knowledge_base_id(impl Into<String>) / set_knowledge_base_id(Option<String>):
    required: true
    

    The unique identifier of the knowledge base to query.

    
    
  • retrieval_query(KnowledgeBaseQuery) / set_retrieval_query(Option<KnowledgeBaseQuery>):
    required: true
    

    Contains the query to send the knowledge base.

    
    
  • retrieval_configuration(KnowledgeBaseRetrievalConfiguration) / set_retrieval_configuration(Option<KnowledgeBaseRetrievalConfiguration>):
    required: false
    

    Contains configurations for the knowledge base query and retrieval process. For more information, see Query configurations.

    
    
  • guardrail_configuration(GuardrailConfiguration) / set_guardrail_configuration(Option<GuardrailConfiguration>):
    required: false
    

    Guardrail settings.

    
    
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    If there are more results than can fit in the response, the response returns a nextToken. Use this token in the nextToken field of another request to retrieve the next batch of results.

    
    
• On success, responds with RetrieveOutput with field(s):
  • retrieval_results(Vec::<KnowledgeBaseRetrievalResult>):

    A list of results from querying the knowledge base.

  • guardrail_action(Option<GuadrailAction>):

    Specifies if there is a guardrail intervention in the response.

  • next_token(Option<String>):

    If there are more results than can fit in the response, the response returns a nextToken. Use this token in the nextToken field of another request to retrieve the next batch of results.

• On failure, responds with SdkError<RetrieveError>

impl Client

pub fn retrieve_and_generate(&self) -> RetrieveAndGenerateFluentBuilder

Constructs a fluent builder for the RetrieveAndGenerate operation.

• The fluent builder is configurable:
  • session_id(impl Into<String>) / set_session_id(Option<String>):
    required: false
    

    The unique identifier of the session. When you first make a RetrieveAndGenerate request, Amazon Bedrock automatically generates this value. You must reuse this value for all subsequent requests in the same conversational session. This value allows Amazon Bedrock to maintain context and knowledge from previous interactions. You can’t explicitly set the sessionId yourself.

    
    
  • input(RetrieveAndGenerateInput) / set_input(Option<RetrieveAndGenerateInput>):
    required: true
    

    Contains the query to be made to the knowledge base.

    
    
  • retrieve_and_generate_configuration(RetrieveAndGenerateConfiguration) / set_retrieve_and_generate_configuration(Option<RetrieveAndGenerateConfiguration>):
    required: false
    

    Contains configurations for the knowledge base query and retrieval process. For more information, see Query configurations.

    
    
  • session_configuration(RetrieveAndGenerateSessionConfiguration) / set_session_configuration(Option<RetrieveAndGenerateSessionConfiguration>):
    required: false
    

    Contains details about the session with the knowledge base.

    
    
• On success, responds with RetrieveAndGenerateOutput with field(s):
  • session_id(String):

    The unique identifier of the session. When you first make a RetrieveAndGenerate request, Amazon Bedrock automatically generates this value. You must reuse this value for all subsequent requests in the same conversational session. This value allows Amazon Bedrock to maintain context and knowledge from previous interactions. You can’t explicitly set the sessionId yourself.

  • output(Option<RetrieveAndGenerateOutput>):

    Contains the response generated from querying the knowledge base.

  • citations(Option<Vec::<Citation>>):

    A list of segments of the generated response that are based on sources in the knowledge base, alongside information about the sources.

  • guardrail_action(Option<GuadrailAction>):

    Specifies if there is a guardrail intervention in the response.

• On failure, responds with SdkError<RetrieveAndGenerateError>

impl Client

pub fn retrieve_and_generate_stream( &self, ) -> RetrieveAndGenerateStreamFluentBuilder

Constructs a fluent builder for the RetrieveAndGenerateStream operation.

• The fluent builder is configurable:
  • session_id(impl Into<String>) / set_session_id(Option<String>):
    required: false
    

    The unique identifier of the session. When you first make a RetrieveAndGenerate request, Amazon Bedrock automatically generates this value. You must reuse this value for all subsequent requests in the same conversational session. This value allows Amazon Bedrock to maintain context and knowledge from previous interactions. You can’t explicitly set the sessionId yourself.

    
    
  • input(RetrieveAndGenerateInput) / set_input(Option<RetrieveAndGenerateInput>):
    required: true
    

    Contains the query to be made to the knowledge base.

    
    
  • retrieve_and_generate_configuration(RetrieveAndGenerateConfiguration) / set_retrieve_and_generate_configuration(Option<RetrieveAndGenerateConfiguration>):
    required: false
    

    Contains configurations for the knowledge base query and retrieval process. For more information, see Query configurations.

    
    
  • session_configuration(RetrieveAndGenerateSessionConfiguration) / set_session_configuration(Option<RetrieveAndGenerateSessionConfiguration>):
    required: false
    

    Contains details about the session with the knowledge base.

    
    
• On success, responds with RetrieveAndGenerateStreamOutput with field(s):
  • stream(EventReceiver<RetrieveAndGenerateStreamResponseOutput, RetrieveAndGenerateStreamResponseOutputError>):

    A stream of events from the model.

  • session_id(String):

    The session ID.

• On failure, responds with SdkError<RetrieveAndGenerateStreamError>

impl Client

pub fn from_conf(conf: Config) -> Self

Creates a new client from the service Config.

Panics

This method will panic in the following cases:

• Retries or timeouts are enabled without a sleep_impl configured.
• Identity caching is enabled without a sleep_impl and time_source configured.
• No behavior_version is provided.

The panic message for each of these will have instructions on how to resolve them.

pub fn config(&self) -> &Config

Returns the client’s configuration.

impl Client

pub fn new(sdk_config: &SdkConfig) -> Self

Creates a new client from an SDK Config.

Panics

• This method will panic if the sdk_config is missing an async sleep implementation. If you experience this panic, set the sleep_impl on the Config passed into this function to fix it.
• This method will panic if the sdk_config is missing an HTTP connector. If you experience this panic, set the http_connector on the Config passed into this function to fix it.
• This method will panic if no BehaviorVersion is provided. If you experience this panic, set behavior_version on the Config or enable the behavior-version-latest Cargo feature.

Trait Implementations

impl Clone for Client

fn clone(&self) -> Client

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Client

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.