AWS bedrock documentation change
Summary
Added model invocation type selection (InvokeModel/Converse API) as step 5 and updated subsequent step numbering. Added documentation for modelInvocationType parameter.
Security assessment
The change introduces a new configuration option for API format selection but does not address security vulnerabilities or weaknesses. The encryption documentation for output data remains unchanged.
Diff
diff --git a/bedrock/latest/userguide/batch-inference-create.md b/bedrock/latest/userguide/batch-inference-create.md index 490070be8..768478d9b 100644 --- a//bedrock/latest/userguide/batch-inference-create.md +++ b//bedrock/latest/userguide/batch-inference-create.md @@ -28 +28,3 @@ Console - 5. In the **Input data** section, choose **Browse S3** and select an S3 location for your batch inference job. Batch inference processes all JSONL and accompanying content files at that S3 location, whether the location is an S3 folder or a single JSONL file. + 5. In the **Model invocation type** section, choose the API format for your input data. Choose **InvokeModel** if your input data uses model-specific request formats, or choose **Converse** if your input data uses the Converse API format. The default is **InvokeModel**. + + 6. In the **Input data** section, choose **Browse S3** and select an S3 location for your batch inference job. Batch inference processes all JSONL and accompanying content files at that S3 location, whether the location is an S3 folder or a single JSONL file. @@ -34 +36 @@ If the input data is in an S3 bucket that belongs to a different account from th - 6. In the **Output data** section, choose **Browse S3** and select an S3 location to store the outtput files from your batch inference job. By default, the output data will be encrypted by an AWS managed key. To choose a custom KMS key, select **Customize encryption settings (advanced)** and choose a key. For more information about encryption of Amazon Bedrock resources and setting up a custom KMS key see [Data encryption](./data-encryption.html). + 7. In the **Output data** section, choose **Browse S3** and select an S3 location to store the outtput files from your batch inference job. By default, the output data will be encrypted by an AWS managed key. To choose a custom KMS key, select **Customize encryption settings (advanced)** and choose a key. For more information about encryption of Amazon Bedrock resources and setting up a custom KMS key see [Data encryption](./data-encryption.html). @@ -40 +42 @@ If you plan to write the output data to an S3 bucket that belongs to a different - 7. In the **Service access** section, select one of the following options: + 8. In the **Service access** section, select one of the following options: @@ -46 +48 @@ If you plan to write the output data to an S3 bucket that belongs to a different - 8. (Optional) To associate tags with the batch inference job, expand the **Tags** section and add a key and optional value for each tag. For more information, see [Tagging Amazon Bedrock resources](./tagging.html). + 9. (Optional) To associate tags with the batch inference job, expand the **Tags** section and add a key and optional value for each tag. For more information, see [Tagging Amazon Bedrock resources](./tagging.html). @@ -48 +50 @@ If you plan to write the output data to an S3 bucket that belongs to a different - 9. Choose **Create batch inference job**. + 10. Choose **Create batch inference job**. @@ -71,0 +74 @@ Field | Use case +modelInvocationType | To specify the API format of the input data. Set to `Converse` to use the Converse API format, or `InvokeModel` (default) to use model-specific request formats. For more information about the Converse request format, see [Converse](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html).