AWS redshift documentation change
Summary
Added examples for Bedrock model configuration with IAM roles and response types
Security assessment
Emphasizes proper IAM role configuration for secure model access but does not fix a specific security issue.
Diff
diff --git a/redshift/latest/dg/machine-learning-br.md b/redshift/latest/dg/machine-learning-br.md index 1789cb6a2..e64f4d1ee 100644 --- a//redshift/latest/dg/machine-learning-br.md +++ b//redshift/latest/dg/machine-learning-br.md @@ -94 +94 @@ The `CREATE EXTERNAL MODEL` command has a unified and consistent interface with -If an FM doesn't support messages, then you must set the `request_type` setting to `RAW`. When you set `request_type` to `RAW`, you must construct the request sent to Amazon Bedrock when using the inference function based on the selected FM. +If an FM doesn't support messages, then you must set the `request_type` setting to `RAW`, as the following example demonstrates. When you set `request_type` to `RAW`, you must construct the request sent to Amazon Bedrock when using the inference function based on the selected FM. Make sure that you enable access to the Titan Text G1 – Express model in Amazon Bedrock before running the following example. @@ -96 +96,23 @@ If an FM doesn't support messages, then you must set the `request_type` setting -The `PROMPT` parameter for the `CREATE EXTERNAL MODEL` command is a static prompt. If you need a dynamic prompt for your application, you must specify it when using the inference function. For more details, see Prompt engineering for Amazon Redshift ML integration with Amazon Bedrock following. + + CREATE EXTERNAL MODEL titan_raw + FUNCTION func_titan_raw + IAM_ROLE '<IAM role arn>' + MODEL_TYPE BEDROCK + SETTINGS ( + MODEL_ID 'amazon.titan-text-express-v1', + REQUEST_TYPE RAW, + RESPONSE_TYPE SUPER); + +If you need more information about an input request such as total tokens, you can request the `RESPONSE_TYPE` to be `super` when you create the model. + + + CREATE EXTERNAL MODEL patient_recommendations_v2 + FUNCTION patient_recommendations_func_v2 + IAM_ROLE '<IAM role arn>' + MODEL_TYPE BEDROCK + SETTINGS ( + MODEL_ID 'anthropic.claude-v2', + PROMPT 'Generate personalized diet plan for following patient:', + RESPONSE_TYPE SUPER); + +The `PROMPT` parameter for the `CREATE EXTERNAL MODEL` command is a static prompt. If you need a dynamic prompt for your application, you must specify it when using the inference function. For more details, see Prompt engineering for Amazon Redshift ML integration with Amazon Bedrock.