AWS cli documentation change
Summary
Updated command reference documentation with improved parameter descriptions, added details about encryption defaults, and clarified optimization job configurations. Version number updated from 2.34.55 to 2.34.57.
Security assessment
The change adds explicit documentation about encryption behavior ('encrypted with an Amazon-owned KMS key' when kmsKeyId isn't specified) which is a security feature. No evidence of addressing a specific vulnerability exists; changes are primarily clarifications and enhancements.
Diff
diff --git a/cli/latest/reference/bedrock/create-advanced-prompt-optimization-job.md b/cli/latest/reference/bedrock/create-advanced-prompt-optimization-job.md index 3ea182f92..28c724cfe 100644 --- a//cli/latest/reference/bedrock/create-advanced-prompt-optimization-job.md +++ b//cli/latest/reference/bedrock/create-advanced-prompt-optimization-job.md @@ -15 +15 @@ - * [AWS CLI 2.34.55 Command Reference](../../index.html) » + * [AWS CLI 2.34.57 Command Reference](../../index.html) » @@ -59 +59 @@ First time using the AWS CLI? See the [User Guide](https://docs.aws.amazon.com/c -Creates an asynchronous batch job for advanced prompt optimization. +Creates an advanced prompt optimization job. The job optimizes your prompt templates for specific models using your evaluation dataset and criteria. @@ -104 +104 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc -> Name of the advanced prompt optimization job. +> A name for the advanced prompt optimization job. @@ -116 +116 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc -> Description of the advanced prompt optimization job. +> A description of the advanced prompt optimization job. @@ -127 +127 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc -> Idempotency token for the request. +> 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. @@ -139 +139 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc -> Input data configuration for the advanced prompt optimization job. +> Specifies the S3 location of your JSONL input file containing prompt templates and evaluation samples. @@ -143 +143 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc ->> S3 URI of the input JSONL file. +>> The S3 URI of the JSONL input file containing prompt templates and evaluation samples. @@ -169 +169 @@ JSON Syntax: -> Output data configuration for the advanced prompt optimization job. +> Specifies the S3 location where optimization results will be stored. @@ -173 +173 @@ JSON Syntax: ->> S3 URI prefix for the output location. +>> The S3 URI prefix where the optimization results will be written. @@ -199 +199 @@ JSON Syntax: -> KMS key ARN for encrypting output data. +> 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. @@ -211 +211 @@ JSON Syntax: -> Tags to associate with the job. +> Tags to associate with the advanced prompt optimization job. @@ -268 +268 @@ JSON Syntax: -> Model configurations for advanced prompt optimization. +> A list of model configurations specifying the target models for prompt optimization. You can specify up to 5 models. @@ -279 +279 @@ JSON Syntax: ->> Configuration for a model used in advanced prompt optimization. +>> Contains the configuration for a model used in an advanced prompt optimization job, including the model ID and inference parameters. @@ -283 +283 @@ JSON Syntax: ->>> The model ID. +>>> The ID of the model to use for optimization. @@ -295 +295 @@ JSON Syntax: ->>> Inference configuration for the model. +>>> The inference configuration for the model, including parameters such as maximum tokens, temperature, and top-p. @@ -299 +299 @@ JSON Syntax: ->>>> The maximum number of tokens to generate. +>>>> 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. @@ -309 +309 @@ JSON Syntax: ->>>> The temperature for sampling. +>>>> 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. @@ -320 +320 @@ JSON Syntax: ->>>> The top-p value for nucleus sampling. +>>>> 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. @@ -331 +331 @@ JSON Syntax: ->>>> Stop sequences that end generation. +>>>> A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response. @@ -350 +350 @@ JSON Syntax: ->>> Additional model request fields. +>>> Additional model request fields. Use this to pass model-specific parameters that are not included in the standard inference configuration. @@ -503 +503 @@ jobArn -> (string) -> ARN of the created advanced prompt optimization job. +> The Amazon Resource Name (ARN) of the created advanced prompt optimization job. @@ -523 +523 @@ jobArn -> (string) - * [AWS CLI 2.34.55 Command Reference](../../index.html) » + * [AWS CLI 2.34.57 Command Reference](../../index.html) »