Skip to content

Creates an advanced prompt optimization job

Description

Creates an advanced prompt optimization job. The job optimizes your prompt templates for specific models using your evaluation dataset and criteria.

Usage

bedrock_create_advanced_prompt_optimization_job(jobName, jobDescription,
  clientToken, inputConfig, outputConfig, encryptionKeyArn, tags,
  modelConfigurations)

Arguments

  • jobName

    [required] A name for the advanced prompt optimization job.

  • jobDescription

    A description of the advanced prompt optimization job.

  • clientToken

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request but does not return an error.

  • inputConfig

    [required] Specifies the S3 location of your JSONL input file containing prompt templates and evaluation samples.

  • outputConfig

    [required] Specifies the S3 location where optimization results will be stored.

  • encryptionKeyArn

    The Amazon Resource Name (ARN) of the KMS key used for encrypting the output data. If not specified, the output is encrypted with an Amazon-owned KMS key.

  • tags

    Tags to associate with the advanced prompt optimization job.

  • modelConfigurations

    [required] A list of model configurations specifying the target models for prompt optimization. You can specify up to 5 models.

Value

A list with the following syntax:

list(
  jobArn = "string"
)

Request syntax

svc$create_advanced_prompt_optimization_job(
  jobName = "string",
  jobDescription = "string",
  clientToken = "string",
  inputConfig = list(
    s3Uri = "string"
  ),
  outputConfig = list(
    s3Uri = "string"
  ),
  encryptionKeyArn = "string",
  tags = list(
    list(
      key = "string",
      value = "string"
    )
  ),
  modelConfigurations = list(
    list(
      modelId = "string",
      inferenceConfig = list(
        maxTokens = 123,
        temperature = 123.0,
        topP = 123.0,
        stopSequences = list(
          "string"
        )
      ),
      additionalModelRequestFields = list(
        list()
      )
    )
  )
)