AWS cli medium security documentation change
Summary
Updated documentation for Amazon Bedrock knowledge base creation, adding support for managed knowledge bases with multimedia processing (audio/video), encryption configuration, and new embedding model options.
Security assessment
The change introduces server-side encryption configuration with KMS key ARN for managed knowledge bases ('serverSideEncryptionConfiguration' field), which directly addresses data-at-rest security. This provides explicit documentation for encrypting sensitive knowledge base content using customer-managed keys.
Diff
diff --git a/cli/latest/reference/bedrock-agent/create-knowledge-base.md b/cli/latest/reference/bedrock-agent/create-knowledge-base.md index 3fc8f80c6..c191a4e01 100644 --- a//cli/latest/reference/bedrock-agent/create-knowledge-base.md +++ b//cli/latest/reference/bedrock-agent/create-knowledge-base.md @@ -15 +15 @@ - * [AWS CLI 2.35.5 Command Reference](../../index.html) » + * [AWS CLI 2.35.8 Command Reference](../../index.html) » @@ -63 +63 @@ Creates a knowledge base. A knowledge base contains your data sources so that La -If you prefer to let Amazon Bedrock create and manage a vector store for you in Amazon OpenSearch Service, use the console. For more information, see [Create a knowledge base](https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base-create) . +To create a managed knowledge base, provide a `managedKnowledgeBaseConfiguration` during creation. For more information, see [Build a managed knowledge base](https://docs.aws.amazon.com/bedrock/latest/userguide/kb-build-managed.html) . @@ -67,2 +67,3 @@ If you prefer to let Amazon Bedrock create and manage a vector store for you in - * Provide the embedding model to use in the `embeddingModelArn` field in the `knowledgeBaseConfiguration` object. - * Provide the configuration for your vector store in the `storageConfiguration` object. + * For managed knowledge bases, set `embeddingModelType` to `MANAGED` to use the service-managed embedding model, or `CUSTOM` with an `embeddingModelArn` to use your own. To use your own KMS key for encryption, provide the ARN in `serverSideEncryptionConfiguration` . No vector store configuration is required for managed knowledge bases. + * For self-managed knowledge bases, provide the embedding model to use in the `embeddingModelArn` field in the `knowledgeBaseConfiguration` object. + * For self-managed knowledge bases, provide the configuration for your vector store in the `storageConfiguration` object. @@ -165 +166 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc ->> The type of data that the data source is converted into for the knowledge base. +>> The type of data that the data source is converted into for the knowledge base. Choose `MANAGED` to create a managed knowledge base. @@ -171,0 +173 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc +>> * `MANAGED` @@ -287 +289 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc ->>>> A list of objects specifying storage locations for images extracted from multimodal documents in your data source. +>>>> A list of objects specifying storage locations for multimedia content (images, audio, and video) extracted from multimodal documents in your data source. @@ -298 +300 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc ->>>>> Contains information about a storage location for images extracted from multimodal documents in your data source. +>>>>> Contains information about a storage location for multimedia content (images, audio, and video) extracted from multimodal documents in your data source. @@ -312 +314 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc ->>>>>> Contains information about the Amazon S3 location for the extracted images. +>>>>>> Contains information about the Amazon S3 location for the extracted multimedia content. @@ -324,0 +327,133 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc +> +> managedKnowledgeBaseConfiguration -> (structure) +> +>> Configurations for a managed knowledge base. +>> +>> embeddingModelType -> (string) +>> +>>> Choose `CUSTOM` to provide your own Bedrock embedding model ARN. Choose `MANAGED` to use a service-managed embedding model. For more information, see [Embedding model options](https://docs.aws.amazon.com/bedrock/latest/userguide/kb-managed-create.html#kb-managed-embedding-models) . +>>> +>>> Possible values: +>>> +>>> * `CUSTOM` +>>> * `MANAGED` +>>> + +>> +>> embeddingModelArn -> (string) +>> +>>> The ARN for the embeddings model. +>>> +>>> Constraints: +>>> +>>> * min: `20` +>>> * max: `2048` +>>> * pattern: `(arn:aws(-[^:]{1,12})?:(bedrock|sagemaker):[a-z0-9-]{1,20}:([0-9]{12})?:([a-z-]+/)?)?([a-zA-Z0-9.-]{1,63}){0,2}(([:][a-z0-9-]{1,63}){0,2})?(/[a-z0-9]{1,12})?` +>>> + +>> +>> embeddingModelConfiguration -> (structure) +>> +>>> The configuration details for the embeddings model. +>>> +>>> bedrockEmbeddingModelConfiguration -> (structure) +>>> +>>>> The vector configuration details on the Bedrock embeddings model. +>>>> +>>>> dimensions -> (integer) +>>>> +>>>>> The dimensions details for the vector configuration used on the Bedrock embeddings model. +>>>>> +>>>>> Constraints: +>>>>> +>>>>> * min: `0` +>>>>> * max: `4096` +>>>>> + +>>>> +>>>> embeddingDataType -> (string) +>>>> +>>>>> The data type for the vectors when using a model to convert text into vector embeddings. The model must support the specified data type for vector embeddings. Floating-point (float32) is the default data type, and is supported by most models for vector embeddings. See [Supported embeddings models](https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base-supported.html) for information on the available models and their vector data types. +>>>>> +>>>>> Possible values: +>>>>> +>>>>> * `FLOAT32` +>>>>> * `BINARY` +>>>>> + +>>>> +>>>> audio -> (list) +>>>> +>>>>> Configuration settings for processing audio content in multimodal knowledge bases. +>>>>> +>>>>> Constraints: +>>>>> +>>>>> * min: `1` +>>>>> * max: `1` +>>>>> + +>>>>> +>>>>> (structure) +>>>>> +>>>>>> Audio configuration for multi modal ingestion. +>>>>>> +>>>>>> segmentationConfiguration -> (structure) [required] +>>>>>> +>>>>>>> Configuration for segmenting audio content during processing. +>>>>>>> +>>>>>>> fixedLengthDuration -> (integer) [required] +>>>>>>> +>>>>>>>> The duration in seconds for each audio segment. Audio files will be divided into chunks of this length for processing. +>>>>>>>> +>>>>>>>> Constraints: +>>>>>>>> +>>>>>>>> * min: `1` +>>>>>>>> * max: `30` +>>>>>>>> + +>>>> +>>>> video -> (list) +>>>> +>>>>> Configuration settings for processing video content in multimodal knowledge bases. +>>>>> +>>>>> Constraints: +>>>>> +>>>>> * min: `1` +>>>>> * max: `1` +>>>>> + +>>>>> +>>>>> (structure) +>>>>> +>>>>>> Video configuration for multi modal ingestion. +>>>>>> +>>>>>> segmentationConfiguration -> (structure) [required] +>>>>>> +>>>>>>> Configuration for segmenting video content during processing. +>>>>>>> +>>>>>>> fixedLengthDuration -> (integer) [required] +>>>>>>> +>>>>>>>> The duration in seconds for each video segment. Video files will be divided into chunks of this length for processing. +>>>>>>>> +>>>>>>>> Constraints: +>>>>>>>> +>>>>>>>> * min: `1` +>>>>>>>> * max: `30` +>>>>>>>> + +>> +>> serverSideEncryptionConfiguration -> (structure) +>> +>>> Contains the configuration for server-side encryption for your managed knowledge base. +>>> +>>> kmsKeyArn -> (string) +>>> +>>>> The Amazon Resource Name (ARN) of the KMS key used to encrypt the resource. +>>>> +>>>> Constraints: +>>>> +>>>> * min: `1` +>>>> * max: `2048` +>>>> * pattern: `arn:aws(|-cn|-us-gov):kms:[a-zA-Z0-9-]*:[0-9]{12}:key/[a-zA-Z0-9-]{36}` +>>>> + @@ -671 +806 @@ JSON Syntax: - "type": "VECTOR"|"KENDRA"|"SQL", + "type": "VECTOR"|"KENDRA"|"SQL"|"MANAGED", @@ -707,0 +843,29 @@ JSON Syntax: + "managedKnowledgeBaseConfiguration": { + "embeddingModelType": "CUSTOM"|"MANAGED", + "embeddingModelArn": "string", + "embeddingModelConfiguration": { + "bedrockEmbeddingModelConfiguration": { + "dimensions": integer, + "embeddingDataType": "FLOAT32"|"BINARY", + "audio": [ + { + "segmentationConfiguration": { + "fixedLengthDuration": integer + } + } + ... + ], + "video": [ + { + "segmentationConfiguration": { + "fixedLengthDuration": integer + } + } + ... + ] + } + }, + "serverSideEncryptionConfiguration": { + "kmsKeyArn": "string" + } + }, @@ -1701 +1865 @@ knowledgeBase -> (structure) ->>> The type of data that the data source is converted into for the knowledge base. +>>> The type of data that the data source is converted into for the knowledge base. Choose `MANAGED` to create a managed knowledge base.