interface KnowledgeBaseFlowNodeConfigurationProperty

Language	Type name
.NET	`Amazon.CDK.aws_bedrock.CfnFlow.KnowledgeBaseFlowNodeConfigurationProperty`
Go	`github.com/aws/aws-cdk-go/awscdk/v2/awsbedrock#CfnFlow_KnowledgeBaseFlowNodeConfigurationProperty`
Java	`software.amazon.awscdk.services.bedrock.CfnFlow.KnowledgeBaseFlowNodeConfigurationProperty`
Python	`aws_cdk.aws_bedrock.CfnFlow.KnowledgeBaseFlowNodeConfigurationProperty`
TypeScript	`aws-cdk-lib` » `aws_bedrock` » `CfnFlow` » `KnowledgeBaseFlowNodeConfigurationProperty`

Contains configurations for a knowledge base node in a flow.

This node takes a query as the input and returns, as the output, the retrieved responses directly (as an array) or a response generated based on the retrieved responses. For more information, see Node types in a flow in the Amazon Bedrock User Guide.

Example

// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { aws_bedrock as bedrock } from 'aws-cdk-lib';

declare const additionalModelRequestFields: any;
const knowledgeBaseFlowNodeConfigurationProperty: bedrock.CfnFlow.KnowledgeBaseFlowNodeConfigurationProperty = {
  knowledgeBaseId: 'knowledgeBaseId',

  // the properties below are optional
  guardrailConfiguration: {
    guardrailIdentifier: 'guardrailIdentifier',
    guardrailVersion: 'guardrailVersion',
  },
  inferenceConfiguration: {
    text: {
      maxTokens: 123,
      stopSequences: ['stopSequences'],
      temperature: 123,
      topP: 123,
    },
  },
  modelId: 'modelId',
  numberOfResults: 123,
  orchestrationConfiguration: {
    additionalModelRequestFields: additionalModelRequestFields,
    inferenceConfig: {
      text: {
        maxTokens: 123,
        stopSequences: ['stopSequences'],
        temperature: 123,
        topP: 123,
      },
    },
    performanceConfig: {
      latency: 'latency',
    },
    promptTemplate: {
      textPromptTemplate: 'textPromptTemplate',
    },
  },
  promptTemplate: {
    textPromptTemplate: 'textPromptTemplate',
  },
  rerankingConfiguration: {
    type: 'type',

    // the properties below are optional
    bedrockRerankingConfiguration: {
      modelConfiguration: {
        modelArn: 'modelArn',

        // the properties below are optional
        additionalModelRequestFields: additionalModelRequestFields,
      },

      // the properties below are optional
      metadataConfiguration: {
        selectionMode: 'selectionMode',

        // the properties below are optional
        selectiveModeConfiguration: {
          fieldsToExclude: [{
            fieldName: 'fieldName',
          }],
          fieldsToInclude: [{
            fieldName: 'fieldName',
          }],
        },
      },
      numberOfRerankedResults: 123,
    },
  },
};

Properties

Name	Type	Description
knowledgeBaseId	`string`	The unique identifier of the knowledge base to query.
guardrailConfiguration?	`IResolvable` `\|` `GuardrailConfigurationProperty`	Contains configurations for a guardrail to apply during query and response generation for the knowledge base in this configuration.
inferenceConfiguration?	`IResolvable` `\|` `PromptInferenceConfigurationProperty`	Contains inference configurations for the prompt.
modelId?	`string`	The unique identifier of the model or inference profile to use to generate a response from the query results. Omit this field if you want to return the retrieved results as an array.
numberOfResults?	`number`	The number of results to retrieve from the knowledge base.
orchestrationConfiguration?	`IResolvable` `\|` `KnowledgeBaseOrchestrationConfigurationProperty`	The configuration for orchestrating the retrieval and generation process in the knowledge base node.
promptTemplate?	`IResolvable` `\|` `KnowledgeBasePromptTemplateProperty`	A custom prompt template to use with the knowledge base for generating responses.
rerankingConfiguration?	`IResolvable` `\|` `VectorSearchRerankingConfigurationProperty`	The configuration for reranking the retrieved results from the knowledge base to improve relevance.

knowledgeBaseId

Type: string

The unique identifier of the knowledge base to query.

guardrailConfiguration?

Type: IResolvable | GuardrailConfigurationProperty (optional)

Contains configurations for a guardrail to apply during query and response generation for the knowledge base in this configuration.

inferenceConfiguration?

Type: IResolvable | PromptInferenceConfigurationProperty (optional)

Contains inference configurations for the prompt.

modelId?

Type: string (optional)

The unique identifier of the model or inference profile to use to generate a response from the query results. Omit this field if you want to return the retrieved results as an array.

numberOfResults?

Type: number (optional)

The number of results to retrieve from the knowledge base.

orchestrationConfiguration?

Type: IResolvable | KnowledgeBaseOrchestrationConfigurationProperty (optional)

The configuration for orchestrating the retrieval and generation process in the knowledge base node.

promptTemplate?

Type: IResolvable | KnowledgeBasePromptTemplateProperty (optional)

A custom prompt template to use with the knowledge base for generating responses.

rerankingConfiguration?

Type: IResolvable | VectorSearchRerankingConfigurationProperty (optional)

The configuration for reranking the retrieved results from the knowledge base to improve relevance.