Class AmazonKendraRetriever

Class for interacting with Amazon Kendra, an intelligent search service provided by AWS. Extends the BaseRetriever class.

Example

const retriever = new AmazonKendraRetriever({
  topK: 10,
  indexId: "YOUR_INDEX_ID",
  region: "us-east-2",
  clientOptions: {
    credentials: {
      accessKeyId: "YOUR_ACCESS_KEY_ID",
      secretAccessKey: "YOUR_SECRET_ACCESS_KEY",
    },
  },
});

const docs = await retriever.getRelevantDocuments("How are clouds formed?");

Hierarchy (view full)

Constructors

constructor

Properties

indexId kendraClient topK attributeFilter?

Methods

cleanResult combineText convertQueryItem convertRetrieverItem getDocAttributeValue getDocAttributes getQueryDocs getQueryItemExcerpt getRetrieverDocs queryKendra

Constructors

constructor

Properties

indexId

indexId: string

kendraClient

kendraClient: KendraClient

topK

topK: number

Optional attributeFilter

attributeFilter?: AttributeFilter

Methods

cleanResult

combineText

  • combineText(title?, excerpt?): string

  • Combines title and excerpt into a single string.

    Parameters

    • Optional title: string

      The title of the document.

    • Optional excerpt: string

      An excerpt from the document.

    Returns string

    A single string combining the title and excerpt.

convertQueryItem

convertRetrieverItem

getDocAttributeValue

  • getDocAttributeValue(value): string | number | string[] | Date

  • Extracts the attribute value from a DocumentAttributeValue object.

    Parameters

    • value: DocumentAttributeValue

      The DocumentAttributeValue object to extract the value from.

    Returns string | number | string[] | Date

    The extracted attribute value.

getDocAttributes

  • getDocAttributes(documentAttributes?): {
        [key: string]: unknown;
    }

  • Extracts the attribute key-value pairs from an array of DocumentAttribute objects.

    Parameters

    • Optional documentAttributes: DocumentAttribute[]

      The array of DocumentAttribute objects to extract the key-value pairs from.

    Returns {
        [key: string]: unknown;
    }

    An object containing the extracted attribute key-value pairs.

    • [key: string]: unknown

getQueryDocs

  • getQueryDocs(response, pageSize): any[]

  • Extracts the top-k documents from a QueryCommandOutput object.

    Parameters

    • response: QueryCommandOutput

      The QueryCommandOutput object to extract the documents from.

    • pageSize: number

      The number of documents to extract.

    Returns any[]

    An array of Document objects.

getQueryItemExcerpt

getRetrieverDocs

  • getRetrieverDocs(response, pageSize): Document[]

  • Extracts the top-k documents from a RetrieveCommandOutput object.

    Parameters

    • response: RetrieveCommandOutput

      The RetrieveCommandOutput object to extract the documents from.

    • pageSize: number

      The number of documents to extract.

    Returns Document[]

    An array of Document objects.

queryKendra

  • queryKendra(query, topK, attributeFilter?): Promise<any[]>

  • Sends a retrieve or query request to Kendra and returns the top-k documents.

    Parameters

    • query: string

      The query to send to Kendra.

    • topK: number

      The number of top documents to return.

    • Optional attributeFilter: AttributeFilter

      Optional filter to apply when retrieving documents.

    Returns Promise<any[]>

    A Promise that resolves to an array of Document objects.

Settings

Member Visibility

Theme

On This Page

Generated using TypeDoc