AWS bedrock documentation change
Summary
Added documentation for S3 Vectors integration including KMS encryption options and metadata security constraints
Security assessment
Introduces security-related documentation about KMS encryption configuration for vector stores and explicit metadata size limitations (40KB total with 2KB filterable). These are preventive security controls but don't address an existing vulnerability.
Diff
diff --git a/bedrock/latest/userguide/knowledge-base-create.md b/bedrock/latest/userguide/knowledge-base-create.md index 31d65f76a..5c4f3e87e 100644 --- a//bedrock/latest/userguide/knowledge-base-create.md +++ b//bedrock/latest/userguide/knowledge-base-create.md @@ -58 +58,5 @@ Expand the section that corresponds to your use case: - * **Quick create a new vector store** – choose one of the available vector stores for Amazon Bedrock to create. + * **Quick create a new vector store** – choose one of the available vector stores for Amazon Bedrock to create. You can also optionally configure AWS KMS key encryption for your vector store. + +###### Note + +When using this option, Amazon Bedrock automatically handles the metadata placement for each vector store. @@ -65,0 +70,14 @@ Expand the section that corresponds to your use case: + * **Amazon S3 Vectors** – Amazon Bedrock Knowledge Bases creates an S3 vector bucket and a vector index that will store the embeddings generated from your data sources. + +###### Important + +The Amazon S3 Vectors integration with Amazon Bedrock Knowledge Bases is in preview release and is subject to change. + +You can create a knowledge base for Amazon S3 Vectors in all AWS Regions where both Amazon Bedrock and Amazon S3 Vectors are available. For region availability information, see [Amazon S3 Vectors](https://docs.aws.amazon.com/AmazonS3/latest/userguide/s3-vectors.html) in the _Amazon S3 User Guide_. + +###### Note + +When Amazon Bedrock Knowledge Bases creates a vector index for you, it can attach up to a maximum of 40 KB of metadata for each vector. Within this 40 KB, up to a maximum of 2 KB can be used as filterable metadata. + +Amazon Bedrock will store the text in the non-filterable space as the `AMAZON_BEDROCK_TEXT` key. The metadata added by Amazon Bedrock is stored in the filterable metadata space. For more information about S3 vector bucket metadata limitations, see [Prerequisites for using Amazon S3 Vectors with Amazon Bedrock Knowledge Bases](https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base-setup.html#knowledge-base-setup-s3). +