AWS::Bedrock::KnowledgeBase BedrockEmbeddingModelConfiguration - AWS CloudFormation

This is the new CloudFormation Template Reference Guide. Please update your bookmarks and links. For help getting started with CloudFormation, see the AWS CloudFormation User Guide.

AWS::Bedrock::KnowledgeBase BedrockEmbeddingModelConfiguration

The vector configuration details for the Bedrock embeddings model.

Syntax

To declare this entity in your CloudFormation template, use the following syntax:

JSON

{ "Audio" : [ AudioConfiguration, ... ], "Dimensions" : Integer, "EmbeddingDataType" : String, "Video" : [ VideoConfiguration, ... ] }

Properties

Audio

Configuration settings for processing audio content in multimodal knowledge bases.

Required: No

Type: Array of AudioConfiguration

Minimum: 1

Maximum: 1

Update requires: Replacement

Dimensions

The dimensions details for the vector configuration used on the Bedrock embeddings model.

Required: No

Type: Integer

Minimum: 0

Maximum: 4096

Update requires: Replacement

EmbeddingDataType

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 for information on the available models and their vector data types.

Required: No

Type: String

Allowed values: FLOAT32 | BINARY

Update requires: Replacement

Video

Configuration settings for processing video content in multimodal knowledge bases.

Required: No

Type: Array of VideoConfiguration

Minimum: 1

Maximum: 1

Update requires: Replacement