langchain.js
    Preparing search index...

    Class for interacting with the Cassandra database. It extends the VectorStore class and provides methods for adding vectors and documents, searching for similar vectors, and creating instances from texts or documents.

    Hierarchy (View Summary)

    Index

    Constructors

    • Parameters

      Returns CassandraStore

    Properties

    FilterType: WhereClause

    Methods

    • Returns string

    • Method to add documents to the Cassandra database.

      Parameters

      • documents: Document[]

        The documents to add.

      Returns Promise<void>

      Promise that resolves when the documents have been added.

    • Method to save vectors to the Cassandra database.

      Parameters

      • vectors: number[][]

        Vectors to save.

      • documents: Document[]

        The documents associated with the vectors.

      Returns Promise<void>

      Promise that resolves when the vectors have been added.

    • Returns CassandraTable

    • Method to search for vectors that are similar to a given query vector, but with the results selected using the maximal marginal relevance.

      Parameters

      • query: string

        The query string.

      • options: MaxMarginalRelevanceSearchOptions<this["FilterType"]>
        • k

          The number of similar Documents to return.

        • fetchK=4*k

          The number of records to fetch before passing to the MMR algorithm.

        • lambda=0.5

          The degree of diversity among the results between 0 (maximum diversity) and 1 (minimum diversity).

        • filter

          Optional filter to be applied as a WHERE clause.

      Returns Promise<Document[]>

      List of documents selected by maximal marginal relevance.

    • Helper method to search for vectors that are similar to a given query vector.

      Parameters

      • query: number[]

        The query vector.

      • k: number

        The number of similar Documents to return.

      • Optionalfilter: WhereClause

        Optional filter to be applied as a WHERE clause.

      • OptionalincludeEmbedding: boolean

        Whether to include the embedding vectors in the results.

      Returns Promise<[Document, number][]>

      Promise that resolves with an array of tuples, each containing a Document and a score.

    • Method to search for vectors that are similar to a given query vector.

      Parameters

      • query: number[]

        The query vector.

      • k: number

        The number of similar Documents to return.

      • Optionalfilter: WhereClause

        Optional filter to be applied as a WHERE clause.

      Returns Promise<[Document, number][]>

      Promise that resolves with an array of tuples, each containing a Document and a score.

    • Static method to create an instance of CassandraStore from documents.

      Parameters

      • docs: Document[]

        The documents to use.

      • embeddings: EmbeddingsInterface

        The embeddings to use.

      • args: CassandraLibArgs

        The arguments for the CassandraStore.

      Returns Promise<CassandraStore>

      Promise that resolves with a new instance of CassandraStore.

    • Static method to create an instance of CassandraStore from an existing index.

      Parameters

      • embeddings: EmbeddingsInterface

        The embeddings to use.

      • args: CassandraLibArgs

        The arguments for the CassandraStore.

      Returns Promise<CassandraStore>

      Promise that resolves with a new instance of CassandraStore.

    • Static method to create an instance of CassandraStore from texts.

      Parameters

      • texts: string[]

        The texts to use.

      • metadatas: object | object[]

        The metadata associated with the texts.

      • embeddings: EmbeddingsInterface

        The embeddings to use.

      • args: CassandraLibArgs

        The arguments for the CassandraStore.

      Returns Promise<CassandraStore>

      Promise that resolves with a new instance of CassandraStore.