generative-ai-cdk-constructs

@cdklabs/generative-ai-cdk-constructs


@cdklabs/generative-ai-cdk-constructs / bedrock / GraphKnowledgeBaseProps

Interface: GraphKnowledgeBaseProps

Properties for creating a Kendra Index Knowledge Base.

Extends

Properties

description?

readonly optional description: string

The description of the knowledge base.

Default

- No description provided.

Inherited from

CommonKnowledgeBaseProps.description


embeddingModel

readonly embeddingModel: BedrockFoundationModel

The embeddings model for the knowledge base.


existingRole?

readonly optional existingRole: IRole

Existing IAM role with policy statements granting appropriate permissions to invoke the specific embeddings models. Any entity (e.g., an AWS service or application) that assumes this role will be able to invoke or use the specified embeddings model within the Bedrock service.

Inherited from

CommonKnowledgeBaseProps.existingRole


fieldMapping?

readonly optional fieldMapping: VectorFieldMapping

The vector field mapping configuration.

Default

- { metadataField: "AMAZON_BEDROCK_METADATA", textField: "AMAZON_BEDROCK_TEXT" }

graph?

readonly optional graph: INeptuneGraph

The Neptune Analytics vector store

Default

- A new Neptune Analytics vector store is created

instruction?

readonly optional instruction: string

A narrative description of the knowledge base.

A Bedrock Agent can use this instruction to determine if it should query this Knowledge Base.

Default

- No description provided.

Inherited from

CommonKnowledgeBaseProps.instruction


name?

readonly optional name: string

The name of the knowledge base.

Inherited from

CommonKnowledgeBaseProps.name