Package software.amazon.awscdk.services.bedrock

Interface CfnAgent.InferenceConfigurationProperty

All Superinterfaces:

software.amazon.jsii.JsiiSerializable

All Known Implementing Classes:

CfnAgent.InferenceConfigurationProperty.Jsii$Proxy

Enclosing class:

CfnAgent

@Stability(Stable)
public static interface CfnAgent.InferenceConfigurationProperty
extends software.amazon.jsii.JsiiSerializable

Base inference parameters to pass to a model in a call to Converse or ConverseStream . For more information, see Inference parameters for foundation models .

If you need to pass additional parameters that the model supports, use the additionalModelRequestFields request field in the call to Converse or ConverseStream . For more information, see Model parameters .

Example:

 // The code below shows an example of how to instantiate this type.
 // The values are placeholders you should change.
 import software.amazon.awscdk.services.bedrock.*;
 InferenceConfigurationProperty inferenceConfigurationProperty = InferenceConfigurationProperty.builder()
         .maximumLength(123)
         .stopSequences(List.of("stopSequences"))
         .temperature(123)
         .topK(123)
         .topP(123)
         .build();
 

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-agent-inferenceconfiguration.html

Nested Class Summary

Nested Classes

Modifier and Type	Interface	Description
static final class	CfnAgent.InferenceConfigurationProperty.Builder	A builder for CfnAgent.InferenceConfigurationProperty
static final class	CfnAgent.InferenceConfigurationProperty.Jsii$Proxy	An implementation for CfnAgent.InferenceConfigurationProperty

Method Summary

Modifier and Type	Method	Description
static CfnAgent.InferenceConfigurationProperty.Builder	builder()
default Number	getMaximumLength()	The maximum number of tokens allowed in the generated response.
default List<String>	getStopSequences()	A list of stop sequences.
default Number	getTemperature()	The likelihood of the model selecting higher-probability options while generating a response.
default Number	getTopK()	While generating a response, the model determines the probability of the following token at each point of generation.
default Number	getTopP()	The percentage of most-likely candidates that the model considers for the next token.

Methods inherited from interface software.amazon.jsii.JsiiSerializable

$jsii$toJson

Method Details

getMaximumLength

@Stability(Stable)
@Nullable
default Number getMaximumLength()

The maximum number of tokens allowed in the generated response.

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-agent-inferenceconfiguration.html#cfn-bedrock-agent-inferenceconfiguration-maximumlength

getStopSequences

@Stability(Stable)
@Nullable
default List<String> getStopSequences()

A list of stop sequences.

A stop sequence is a sequence of characters that causes the model to stop generating the response.

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-agent-inferenceconfiguration.html#cfn-bedrock-agent-inferenceconfiguration-stopsequences

getTemperature

@Stability(Stable)
@Nullable
default Number getTemperature()

The likelihood of the model selecting higher-probability options while generating a response.

A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.

The default value is the default value for the model that you are using. For more information, see Inference parameters for foundation models .

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-agent-inferenceconfiguration.html#cfn-bedrock-agent-inferenceconfiguration-temperature

getTopK

@Stability(Stable)
@Nullable
default Number getTopK()

While generating a response, the model determines the probability of the following token at each point of generation.

The value that you set for topK is the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topK to 50, the model selects the next token from among the top 50 most likely choices.

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-agent-inferenceconfiguration.html#cfn-bedrock-agent-inferenceconfiguration-topk

getTopP

@Stability(Stable)
@Nullable
default Number getTopP()

The percentage of most-likely candidates that the model considers for the next token.

For example, if you choose a value of 0.8 for topP , the model selects from the top 80% of the probability distribution of tokens that could be next in the sequence.

The default value is the default value for the model that you are using. For more information, see Inference parameters for foundation models .

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-agent-inferenceconfiguration.html#cfn-bedrock-agent-inferenceconfiguration-topp

builder

@Stability(Stable)
static CfnAgent.InferenceConfigurationProperty.Builder builder()

Returns:

a CfnAgent.InferenceConfigurationProperty.Builder of CfnAgent.InferenceConfigurationProperty