Struct ModelInvocationInput

#[non_exhaustive]
pub struct ModelInvocationInput {
    pub trace_id: Option<String>,
    pub text: Option<String>,
    pub type: Option<PromptType>,
    pub override_lambda: Option<String>,
    pub prompt_creation_mode: Option<CreationMode>,
    pub inference_configuration: Option<InferenceConfiguration>,
    pub parser_mode: Option<CreationMode>,
    pub foundation_model: Option<String>,
}

The input for the pre-processing step.

• The type matches the agent step.

• The text contains the prompt.

• The inferenceConfiguration, parserMode, and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.

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.

trace_id: Option<String>

The unique identifier of the trace.

text: Option<String>

The text that prompted the agent at this step.

type: Option<PromptType>

The step in the agent sequence.

override_lambda: Option<String>

The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence.

prompt_creation_mode: Option<CreationMode>

Specifies whether the default prompt template was OVERRIDDEN. If it was, the basePromptTemplate that was set in the PromptOverrideConfiguration object when the agent was created or updated is used instead.

inference_configuration: Option<InferenceConfiguration>

Specifications about the inference parameters that were provided alongside the prompt. These are specified in the PromptOverrideConfiguration object that was set when the agent was created or updated. For more information, see Inference parameters for foundation models.

parser_mode: Option<CreationMode>

Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType.

foundation_model: Option<String>

The identifier of a foundation model.

Implementations

impl ModelInvocationInput

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

The unique identifier of the trace.

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

The text that prompted the agent at this step.

pub fn type(&self) -> Option<&PromptType>

The step in the agent sequence.

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

The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence.

pub fn prompt_creation_mode(&self) -> Option<&CreationMode>

Specifies whether the default prompt template was OVERRIDDEN. If it was, the basePromptTemplate that was set in the PromptOverrideConfiguration object when the agent was created or updated is used instead.

pub fn inference_configuration(&self) -> Option<&InferenceConfiguration>

Specifications about the inference parameters that were provided alongside the prompt. These are specified in the PromptOverrideConfiguration object that was set when the agent was created or updated. For more information, see Inference parameters for foundation models.

pub fn parser_mode(&self) -> Option<&CreationMode>

Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType.

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

The identifier of a foundation model.

impl ModelInvocationInput

pub fn builder() -> ModelInvocationInputBuilder

Creates a new builder-style object to manufacture ModelInvocationInput.

Trait Implementations

impl Clone for ModelInvocationInput

fn clone(&self) -> ModelInvocationInput

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelInvocationInput

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

Formats the value using the given formatter.

impl PartialEq for ModelInvocationInput

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

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

const 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 ModelInvocationInput