Uses of Class
com.amazonaws.services.bedrockagent.model.InferenceConfiguration

Packages that use InferenceConfiguration

Package	Description
com.amazonaws.services.bedrockagent.model

Uses of InferenceConfiguration in com.amazonaws.services.bedrockagent.model

Methods in com.amazonaws.services.bedrockagent.model that return InferenceConfiguration

Modifier and Type	Method and Description
InferenceConfiguration	InferenceConfiguration.clone()
InferenceConfiguration	PromptConfiguration.getInferenceConfiguration() Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the promptType.
InferenceConfiguration	InferenceConfiguration.withMaximumLength(Integer maximumLength) The maximum number of tokens to allow in the generated response.
InferenceConfiguration	InferenceConfiguration.withStopSequences(Collection<String> stopSequences) A list of stop sequences.
InferenceConfiguration	InferenceConfiguration.withStopSequences(String... stopSequences) A list of stop sequences.
InferenceConfiguration	InferenceConfiguration.withTemperature(Float temperature) The likelihood of the model selecting higher-probability options while generating a response.
InferenceConfiguration	InferenceConfiguration.withTopK(Integer topK) While generating a response, the model determines the probability of the following token at each point of generation.
InferenceConfiguration	InferenceConfiguration.withTopP(Float topP) While generating a response, the model determines the probability of the following token at each point of generation.

Methods in com.amazonaws.services.bedrockagent.model with parameters of type InferenceConfiguration

Modifier and Type	Method and Description
void	PromptConfiguration.setInferenceConfiguration(InferenceConfiguration inferenceConfiguration) Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the promptType.
PromptConfiguration	PromptConfiguration.withInferenceConfiguration(InferenceConfiguration inferenceConfiguration) Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the promptType.