Struct InvokeInlineAgentInput

#[non_exhaustive]
pub struct InvokeInlineAgentInput {

    pub session_id: Option<String>,
    pub customer_encryption_key_arn: Option<String>,
    pub end_session: Option<bool>,
    pub enable_trace: Option<bool>,
    pub input_text: Option<String>,
    pub inline_session_state: Option<InlineSessionState>,
    pub foundation_model: Option<String>,
    pub instruction: Option<String>,
    pub idle_session_ttl_in_seconds: Option<i32>,
    pub action_groups: Option<Vec<AgentActionGroup>>,
    pub knowledge_bases: Option<Vec<KnowledgeBase>>,
    pub guardrail_configuration: Option<GuardrailConfigurationWithArn>,
    pub prompt_override_configuration: Option<PromptOverrideConfiguration>,
    pub bedrock_model_configurations: Option<InlineBedrockModelConfigurations>,
    pub streaming_configurations: Option<StreamingConfigurations>,
}

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

session_id: Option<String>

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

customer_encryption_key_arn: Option<String>

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

end_session: Option<bool>

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

enable_trace: Option<bool>

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

input_text: Option<String>

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: Option<InlineSessionState>

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: Option<String>

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: Option<String>

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

idle_session_ttl_in_seconds: Option<i32>

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: Option<Vec<AgentActionGroup>>

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

knowledge_bases: Option<Vec<KnowledgeBase>>

Contains information of the knowledge bases to associate with.

guardrail_configuration: Option<GuardrailConfigurationWithArn>

The guardrails to assign to the inline agent.

prompt_override_configuration: Option<PromptOverrideConfiguration>

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

bedrock_model_configurations: Option<InlineBedrockModelConfigurations>

Model settings for the request.

streaming_configurations: Option<StreamingConfigurations>

Specifies the configurations for streaming.

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

Implementations

impl InvokeInlineAgentInput

pub fn session_id(&self) -> Option<&str>

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

pub fn customer_encryption_key_arn(&self) -> Option<&str>

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

pub fn end_session(&self) -> Option<bool>

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

pub fn enable_trace(&self) -> Option<bool>

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

pub fn input_text(&self) -> Option<&str>

The prompt text to send to the agent.

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

pub fn inline_session_state(&self) -> Option<&InlineSessionState>

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.

pub fn foundation_model(&self) -> Option<&str>

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

pub fn instruction(&self) -> Option<&str>

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

pub fn idle_session_ttl_in_seconds(&self) -> Option<i32>

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.

pub fn action_groups(&self) -> &[AgentActionGroup]

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

If no value was sent for this field, a default will be set. If you want to determine if no value was sent, use .action_groups.is_none().

pub fn knowledge_bases(&self) -> &[KnowledgeBase]

Contains information of the knowledge bases to associate with.

If no value was sent for this field, a default will be set. If you want to determine if no value was sent, use .knowledge_bases.is_none().

pub fn guardrail_configuration(&self) -> Option<&GuardrailConfigurationWithArn>

The guardrails to assign to the inline agent.

pub fn prompt_override_configuration( &self, ) -> Option<&PromptOverrideConfiguration>

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

pub fn bedrock_model_configurations( &self, ) -> Option<&InlineBedrockModelConfigurations>

Model settings for the request.

pub fn streaming_configurations(&self) -> Option<&StreamingConfigurations>

Specifies the configurations for streaming.

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

impl InvokeInlineAgentInput

pub fn builder() -> InvokeInlineAgentInputBuilder

Creates a new builder-style object to manufacture InvokeInlineAgentInput.

Trait Implementations

impl Clone for InvokeInlineAgentInput

fn clone(&self) -> InvokeInlineAgentInput

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for InvokeInlineAgentInput

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

Formats the value using the given formatter.

impl PartialEq for InvokeInlineAgentInput

fn eq(&self, other: &InvokeInlineAgentInput) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for InvokeInlineAgentInput