AWS Security ChangesHomeSearch

AWS cli documentation change

Service: cli · 2026-06-19 · Documentation high

File: cli/latest/reference/bedrock-agent/update-knowledge-base.md

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)