Experimental
@aws-cdk/aws-bedrock-alpha is an experimental (alpha) package: its API may change in any release, without a major version bump.
PromptInferenceConfigurationProps Struct
Properties for creating a prompt inference configuration.
Example
ts
const cmk = new kms.Key(this, 'cmk', {});
const claudeModel = bedrock.BedrockFoundationModel.ANTHROPIC_CLAUDE_SONNET_V1_0;
const variant1 = bedrock.PromptVariant.text({
variantName: 'variant1',
model: claudeModel,
promptVariables: ['topic'],
promptText: 'This is my first text prompt. Please summarize our conversation on: {{topic}}.',
inferenceConfiguration: bedrock.PromptInferenceConfiguration.text({
temperature: 1.0,
topP: 0.999,
maxTokens: 2000,
}),
});
const prompt1 = new bedrock.Prompt(this, 'prompt1', {
promptName: 'prompt1',
description: 'my first prompt',
defaultVariant: variant1,
variants: [variant1],
kmsKey: cmk,
});
Properties
maxTokensoptionalnumbermax_tokensoptionalint | floatmaxTokensoptionalNumberMaxTokensoptionaldoubleMaxTokensoptional*float64#The maximum number of tokens to return in the response.
Default: No limit specified
stopSequencesoptionalstring[]stop_sequencesoptionaltyping.List[str]stopSequencesoptionalList<String>StopSequencesoptionalstring[]StopSequencesoptional*[]*string#A list of strings that define sequences after which the model will stop generating.
Default: No stop sequences
temperatureoptionalnumbertemperatureoptionalint | floattemperatureoptionalNumberTemperatureoptionaldoubleTemperatureoptional*float64#Controls the randomness of the response.
Default: Model default temperature
Higher values make output more random, lower values more deterministic. Valid range is 0.0 to 1.0.
The percentage of most-likely candidates that the model considers for the next token.
Default: Model default topP
Valid range is 0.0 to 1.0.