AWS::Bedrock::KnowledgeBase VectorKnowledgeBaseConfiguration

Contains details about the model used to create vector embeddings for the knowledge base.

Syntax

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

JSON

{
  "EmbeddingModelArn" : String,
  "EmbeddingModelConfiguration" : EmbeddingModelConfiguration,
  "SupplementalDataStorageConfiguration" : SupplementalDataStorageConfiguration
}

YAML

  EmbeddingModelArn: String
  EmbeddingModelConfiguration: 
    EmbeddingModelConfiguration
  SupplementalDataStorageConfiguration: 
    SupplementalDataStorageConfiguration

Properties

EmbeddingModelArn

The Amazon Resource Name (ARN) of the model used to create vector embeddings for the knowledge base.

Required: Yes

Type: String

Pattern: ^(arn:aws(-[^:]+)?:[a-z0-9-]+:[a-z0-9-]{1,20}:[0-9]{0,12}:[a-zA-Z0-9-:/._+]+)$

Minimum: 20

Maximum: 2048

Update requires: Replacement

EmbeddingModelConfiguration

The embeddings model configuration details for the vector model used in Knowledge Base.

Required: No

Type: EmbeddingModelConfiguration

Update requires: Replacement

SupplementalDataStorageConfiguration

If you include multimodal data from your data source, use this object to specify configurations for the storage location of the images extracted from your documents. These images can be retrieved and returned to the end user. They can also be used in generation when using RetrieveAndGenerate.

Required: No

Type: SupplementalDataStorageConfiguration

Update requires: Replacement