AWS sagemaker-unified-studio documentation change
Summary
Expanded documentation for creating Knowledge Bases with details about embeddings models, vector stores, chunking strategies, and parsing configurations. Added notes about vector store limitations and preview features.
Security assessment
The changes document security-related configurations such as vector store types (including access control notes for Neptune Analytics) and data processing methods, but there is no evidence of addressing a specific security vulnerability. The note about contacting administrators for permissions relates to standard access management rather than patching a security issue.
Diff
diff --git a/sagemaker-unified-studio/latest/userguide/creating-a-knowledge-base-component.md b/sagemaker-unified-studio/latest/userguide/creating-a-knowledge-base-component.md index 8d7fe61e3..316494935 100644 --- a//sagemaker-unified-studio/latest/userguide/creating-a-knowledge-base-component.md +++ b//sagemaker-unified-studio/latest/userguide/creating-a-knowledge-base-component.md @@ -7 +7 @@ -You can create a Knowledge base as a component in an Amazon Bedrock in SageMaker Unified Studio project. If you are creating an app, you can also create a Knowledge Base when you configure the app. When you create a Knowledge Base, you choose data source which can be a [document](./data-source-document.html) or a [web crawler](./data-source-document-web-crawler.html) example, see [Create a flow app with Amazon Bedrock](./build-flow.html). You can also how the Knowledge Base should [parse](./kb-chunking-parsing.html) the data in the data source. +You can create a Knowledge base as a component in an Amazon Bedrock in SageMaker Unified Studio project. If you are creating an app, you can also create a Knowledge Base when you configure the app. When you create a Knowledge Base, you choose your data source, an embeddings model for transforming your data into vectors, and a vector store to store and manage the vectors. You can also specify how the Knowledge Base should preprocess data from the data source, either through chunking or parsing. The following procedure demonstrates how to create a Knowledge Base in Amazon Bedrock in SageMaker Unified Studio. @@ -11 +11 @@ You can create a Knowledge base as a component in an Amazon Bedrock in SageMaker - 1. Navigate to the Amazon SageMaker Unified Studio landing page by using the URL from your admininstrator. + 1. Navigate to the Amazon SageMaker Unified Studio landing page by using the URL from your administrator. @@ -55 +55 @@ For more information, see [Document data source](./data-source-document.html). - 12. Choose **Back** to leave the web crawler configuration pane. + * Choose **Back** to leave the web crawler configuration pane. @@ -57 +57 @@ For more information, see [Document data source](./data-source-document.html). - 13. For **parsing** Choose either **default** parsing or choose **parsing with foundation model**. + 12. In **Configurations** , under **Data storage and processing** , do the following: @@ -59 +59,25 @@ For more information, see [Document data source](./data-source-document.html). - 14. If you choose **parsing with foundation model** , do the following: + 1. For **Embeddings model** , select a foundation model from the drop down to use for transforming your data into vector embeddings. + + 2. For **Embedding type** and **Vector dimensions** , select an option from the dropdown to optimize accuracy, cost, and latency. Your options for embedding types and vector dimensions may be limited depending on the embeddings model that you chose. + +###### Note + +Amazon OpenSearch Serverless is the only vector store that supports binary vector embeddings. Floating-point vector embeddings are supported by all available vector stores. + + 3. For **Vector store** choose from one of the following options: + + * **Vector engine for Amazon OpenSearch Serverless** ‐ Provides contextually relevant responses across billions of vectors in milliseconds. Supports searches combined with text-based keywords for hybrid requests. + + * **Amazon S3 vectors** ‐ Optimizes cost-effectiveness, durability, and latency for storage of large, long-term vector data sets. Amazon S3 vector buckets do not support web crawler data sources. + + * **Amazon Neptune Analytics (GraphRAG)** ‐ Provides high-performance graph analytics and graph-based Retrieval Augmented Generation (GraphRAG) solutions. You must have access to Claude 3 Haiku in order to use this vector store. Contact your administrator if you do not have the necessary permissions. + +###### Note + +Support for Amazon S3 vectors is in preview release for Amazon Bedrock in SageMaker Unified Studio and is subject to change. + +Once you select an option for your vector store, Amazon Bedrock in SageMaker Unified Studio will create the vector store on your behalf. + + 4. For **Chunking strategy** , choose either **Default** , **Fixed sized** , **Hierarchical** , **Semantic** , or **None**. These options represent different methods for breaking down data into smaller segments before embedding. + + 5. For **Parsing strategy** , choose either **Bedrock default parser** or **Foundation model as a parser**. If you choose **Foundation model as a parser** , do the following: @@ -65,3 +89 @@ For more information, see [Document data source](./data-source-document.html). - 15. (Optional) For **Embeddings model** , choose a model for converting your data into vector embeddings, or use the default model. - - 16. Choose **Create** to create the Knowledge Base. + 13. Choose **Create** to create the Knowledge Base. @@ -69 +91 @@ For more information, see [Document data source](./data-source-document.html). - 17. Use the Knowledge Base in an app, by doing one of the following: + 14. Use the Knowledge Base in an app, by doing one of the following: