@cdklabs/generative-ai-cdk-constructs
@cdklabs/generative-ai-cdk-constructs / bedrock / KnowledgeBaseProps
Properties for a knowledge base
readonly
optional
description:string
The description of the knowledge base.
- No description provided.
readonly
embeddingsModel:BedrockFoundationModel
The embeddings model for the knowledge base
readonly
optional
existingRole:IRole
Existing IAM role with a policy statement granting permission to invoke the specific embeddings model. 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.
readonly
optional
indexName:string
The name of the vector index.
If vectorStore is not of type VectorCollection
,
do not include this property as it will throw error.
- 'bedrock-knowledge-base-default-index'
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.
- No description provided.
readonly
optional
knowledgeBaseState:string
Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
readonly
optional
name:string
The name of the knowledge base.
readonly
optional
tags:Record
<string
,string
>
OPTIONAL: Tag (KEY-VALUE) bedrock agent resource
- false
readonly
optional
vectorField:string
The name of the field in the vector index.
If vectorStore is not of type VectorCollection
,
do not include this property as it will throw error.
- 'bedrock-knowledge-base-default-vector'
readonly
optional
vectorIndex:VectorIndex
The vector index for the OpenSearch Serverless backed knowledge base.
If vectorStore is not of type VectorCollection
, do not include
this property as it will throw error.
VectorCollection
type.
readonly
optional
vectorStore:ExistingAmazonAuroraVectorStore
|AmazonAuroraVectorStore
|VectorCollection
|PineconeVectorStore
The vector store for the knowledge base. Must be either of
type VectorCollection
, RedisEnterpriseVectorStore
,
PineconeVectorStore
or AmazonAuroraVectorStore
.
- A new OpenSearch Serverless vector collection is created.