AWS bedrock documentation change
Summary
Updated terminology from 'knowledge base evaluations' to 'RAG evaluations', added cross-region inference profile support documentation, and modified section headers
Security assessment
Changes focus on rebranding to RAG terminology and adding cross-region inference capabilities without mentioning security vulnerabilities or security-specific features
Diff
diff --git a/bedrock/latest/userguide/knowledge-base-evaluation-prereq.md b/bedrock/latest/userguide/knowledge-base-evaluation-prereq.md index 776b2c6ee..1ab0bb720 100644 --- a/bedrock/latest/userguide/knowledge-base-evaluation-prereq.md +++ b/bedrock/latest/userguide/knowledge-base-evaluation-prereq.md @@ -7 +7 @@ Required permissions to create a Amazon Bedrock Knowledge Bases evaluation job -# Prerequisites for creating knowledge base evaluations in Amazon Bedrock +# Prerequisites for creating RAG evaluations in Amazon Bedrock @@ -9 +9 @@ Required permissions to create a Amazon Bedrock Knowledge Bases evaluation job -To create an evaluation job that uses knowledge bases, you need access to specific service level resources, and Amazon Bedrock foundation models. Use the linked topics to learn more about getting setting up. +To create an evaluation job for Amazon Bedrock Knowledge Bases or other RAG sources, you need access to specific service level resources, and Amazon Bedrock foundation models. Use the linked topics to learn more about getting setting up. @@ -25 +25,3 @@ Prior to starting the model evaluation job, check to make sure that you have ing - 2. Create a prompt dataset. Your prompt dataset represents the user queries you want to use to see how well the knowledge base retrieves information and generates responses. For more information, see [Use a prompt dataset for a knowledge base evaluation in Amazon Bedrock](./knowledge-base-evaluation-prompt.html). +[Cross region inference](./cross-region-inference.html) profiles are supported for the listed models. To learn more, see [Supported cross-region inference profiles](./inference-profiles-support.html#inference-profiles-support-system). + + 2. Create a prompt dataset. Your prompt dataset represents the user queries you want to use to see how well the knowledge base retrieves information and generates responses. For more information, see [Create a prompt dataset for a RAG evaluation in Amazon Bedrock](./knowledge-base-evaluation-prompt.html). @@ -110 +112 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -Knowledge base evaluation jobs +RAG evaluation jobs @@ -112 +114 @@ Knowledge base evaluation jobs -Prompt dataset for knowledge base evaluation +Prompt dataset for RAG evaluation