Bedrock / Client / create_advanced_prompt_optimization_job

create_advanced_prompt_optimization_job

Bedrock.Client.create_advanced_prompt_optimization_job(**kwargs)

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

See also: AWS API Documentation

Request Syntax

response = client.create_advanced_prompt_optimization_job(
    jobName='string',
    jobDescription='string',
    clientToken='string',
    inputConfig={
        's3Uri': 'string'
    },
    outputConfig={
        's3Uri': 'string'
    },
    encryptionKeyArn='string',
    tags=[
        {
            'key': 'string',
            'value': 'string'
        },
    ],
    modelConfigurations=[
        {
            'modelId': 'string',
            'inferenceConfig': {
                'maxTokens': 123,
                'temperature': ...,
                'topP': ...,
                'stopSequences': [
                    'string',
                ]
            },
            'additionalModelRequestFields': {
                'string': {...}|[...]|123|123.4|'string'|True|None
            }
        },
    ]
)
Parameters:

  • jobName (string) –

    [REQUIRED]

    A name for the advanced prompt optimization job.

  • jobDescription (string) – A description of the advanced prompt optimization job.

  • clientToken (string) –

    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.

    This field is autopopulated if not provided.

  • inputConfig (dict) –

    [REQUIRED]

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

    • s3Uri (string) – [REQUIRED]

      The S3 URI of the JSONL input file containing prompt templates and evaluation samples.

  • outputConfig (dict) –

    [REQUIRED]

    Specifies the S3 location where optimization results will be stored.

    • s3Uri (string) – [REQUIRED]

      The S3 URI prefix where the optimization results will be written.

  • encryptionKeyArn (string) – 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 (list) –

    Tags to associate with the advanced prompt optimization job.

    • (dict) –

      Definition of the key/value pair for a tag.

      • key (string) – [REQUIRED]

        Key for the tag.

      • value (string) – [REQUIRED]

        Value for the tag.

  • modelConfigurations (list) –

    [REQUIRED]

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

    • (dict) –

      Contains the configuration for a model used in an advanced prompt optimization job, including the model ID and inference parameters.

      • modelId (string) – [REQUIRED]

        The ID of the model to use for optimization.

      • inferenceConfig (dict) –

        The inference configuration for the model, including parameters such as maximum tokens, temperature, and top-p.

        • maxTokens (integer) –

          The maximum number of tokens to allow in the generated response. The default value is the maximum allowed value for the model that you are using.

        • temperature (float) –

          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.

        • topP (float) –

          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.

        • stopSequences (list) –

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

          • (string) –

      • additionalModelRequestFields (dict) –

        Additional model request fields. Use this to pass model-specific parameters that are not included in the standard inference configuration.

Return type:

dict

Returns:

Response Syntax

{
    'jobArn': 'string'
}

Response Structure

  • (dict) –

    Create Advanced Prompt Optimization Job Response

    • jobArn (string) –

      The Amazon Resource Name (ARN) of the created advanced prompt optimization job.

Exceptions