AWS cli documentation change
Summary
Added support for managed knowledge bases with new configuration options including embedding model settings, multimedia content processing (audio/video), and server-side encryption
Security assessment
The changes introduce server-side encryption configuration using KMS keys (security feature documentation) but show no evidence of addressing existing vulnerabilities. The encryption addition enhances security posture but isn't tied to a specific disclosed issue.
Diff
diff --git a/cli/latest/reference/bedrock-agent/update-knowledge-base.md b/cli/latest/reference/bedrock-agent/update-knowledge-base.md index 704a991f7..ecee569b9 100644 --- a//cli/latest/reference/bedrock-agent/update-knowledge-base.md +++ b//cli/latest/reference/bedrock-agent/update-knowledge-base.md @@ -15 +15 @@ - * [AWS CLI 2.35.5 Command Reference](../../index.html) » + * [AWS CLI 2.35.8 Command Reference](../../index.html) » @@ -157 +157 @@ 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. @@ -163,0 +164 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc +>> * `MANAGED` @@ -279 +280 @@ 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. @@ -290 +291 @@ 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. @@ -304 +305 @@ 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. @@ -316,0 +318,133 @@ 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}` +>>>> + @@ -663 +797 @@ JSON Syntax: - "type": "VECTOR"|"KENDRA"|"SQL", + "type": "VECTOR"|"KENDRA"|"SQL"|"MANAGED", @@ -699,0 +834,29 @@ 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" + } + }, @@ -1656 +1819 @@ 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. @@ -1662,0 +1826 @@ knowledgeBase -> (structure) +>>> * `MANAGED` @@ -1778 +1942 @@ knowledgeBase -> (structure) ->>>>> 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. @@ -1789 +1953 @@ knowledgeBase -> (structure) ->>>>>> 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. @@ -1803 +1967 @@ knowledgeBase -> (structure)