Struct PromptConfiguration

#[non_exhaustive]
pub struct PromptConfiguration {
    pub prompt_type: Option<PromptType>,
    pub prompt_creation_mode: Option<CreationMode>,
    pub prompt_state: Option<PromptState>,
    pub base_prompt_template: Option<String>,
    pub inference_configuration: Option<InferenceConfiguration>,
    pub parser_mode: Option<CreationMode>,
    pub foundation_model: Option<String>,
}

Contains configurations to override a prompt template in one part of an agent sequence. For more information, see Advanced prompts.

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.

prompt_type: Option<PromptType>

The step in the agent sequence that this prompt configuration applies to.

prompt_creation_mode: Option<CreationMode>

Specifies whether to override the default prompt template for this promptType. Set this value to OVERRIDDEN to use the prompt that you provide in the basePromptTemplate. If you leave it as DEFAULT, the agent uses a default prompt template.

prompt_state: Option<PromptState>

Specifies whether to allow the agent to carry out the step specified in the promptType. If you set this value to DISABLED, the agent skips that step. The default state for each promptType is as follows.

• PRE_PROCESSING – ENABLED

• ORCHESTRATION – ENABLED

• KNOWLEDGE_BASE_RESPONSE_GENERATION – ENABLED

• POST_PROCESSING – DISABLED

base_prompt_template: Option<String>

Defines the prompt template with which to replace the default prompt template. You can use placeholder variables in the base prompt template to customize the prompt. For more information, see Prompt template placeholder variables. For more information, see Configure the prompt templates.

inference_configuration: Option<InferenceConfiguration>

Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the promptType. 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. If you set the field as OVERRIDEN, the overrideLambda field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function.

foundation_model: Option<String>

The agent's foundation model.

Implementations

impl PromptConfiguration

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

The step in the agent sequence that this prompt configuration applies to.

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

Specifies whether to override the default prompt template for this promptType. Set this value to OVERRIDDEN to use the prompt that you provide in the basePromptTemplate. If you leave it as DEFAULT, the agent uses a default prompt template.

pub fn prompt_state(&self) -> Option<&PromptState>

Specifies whether to allow the agent to carry out the step specified in the promptType. If you set this value to DISABLED, the agent skips that step. The default state for each promptType is as follows.

• PRE_PROCESSING – ENABLED

• ORCHESTRATION – ENABLED

• KNOWLEDGE_BASE_RESPONSE_GENERATION – ENABLED

• POST_PROCESSING – DISABLED

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

Defines the prompt template with which to replace the default prompt template. You can use placeholder variables in the base prompt template to customize the prompt. For more information, see Prompt template placeholder variables. For more information, see Configure the prompt templates.

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

Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the promptType. 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. If you set the field as OVERRIDEN, the overrideLambda field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function.

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

The agent's foundation model.

impl PromptConfiguration

pub fn builder() -> PromptConfigurationBuilder

Creates a new builder-style object to manufacture PromptConfiguration.

Trait Implementations

impl Clone for PromptConfiguration

fn clone(&self) -> PromptConfiguration

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for PromptConfiguration

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

Formats the value using the given formatter.

impl PartialEq for PromptConfiguration

fn eq(&self, other: &PromptConfiguration) -> 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 PromptConfiguration