Struct GenerationConfiguration

#[non_exhaustive]
pub struct GenerationConfiguration {
    pub prompt_template: Option<PromptTemplate>,
    pub guardrail_configuration: Option<GuardrailConfiguration>,
    pub inference_config: Option<InferenceConfig>,
    pub additional_model_request_fields: Option<HashMap<String, Document>>,
    pub performance_config: Option<PerformanceConfiguration>,
}

Contains configurations for response generation based on the knowledge base query results.

This data type is used in the following API operations:

• RetrieveAndGenerate request

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_template: Option<PromptTemplate>

Contains the template for the prompt that's sent to the model for response generation. Generation prompts must include the $search_results$ variable. For more information, see Use placeholder variables in the user guide.

guardrail_configuration: Option<GuardrailConfiguration>

The configuration details for the guardrail.

inference_config: Option<InferenceConfig>

Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.

additional_model_request_fields: Option<HashMap<String, Document>>

Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows users to provide custom model parameters specific to the language model being used.

performance_config: Option<PerformanceConfiguration>

The latency configuration for the model.

Implementations

impl GenerationConfiguration

pub fn prompt_template(&self) -> Option<&PromptTemplate>

Contains the template for the prompt that's sent to the model for response generation. Generation prompts must include the $search_results$ variable. For more information, see Use placeholder variables in the user guide.

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

The configuration details for the guardrail.

pub fn inference_config(&self) -> Option<&InferenceConfig>

Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.

pub fn additional_model_request_fields( &self, ) -> Option<&HashMap<String, Document>>

Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows users to provide custom model parameters specific to the language model being used.

pub fn performance_config(&self) -> Option<&PerformanceConfiguration>

The latency configuration for the model.

impl GenerationConfiguration

pub fn builder() -> GenerationConfigurationBuilder

Creates a new builder-style object to manufacture GenerationConfiguration.

Trait Implementations

impl Clone for GenerationConfiguration

fn clone(&self) -> GenerationConfiguration

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for GenerationConfiguration

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

Formats the value using the given formatter.

impl PartialEq for GenerationConfiguration

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