langchain.js
    Preparing search index...

    Class that implements a vector store using CloseVector, It extends the SaveableVectorStore class and provides methods for adding documents and vectors, performing similarity searches, and saving and loading the vector store.

    Hierarchy

    • CloseVector<CloseVectorHNSWWeb>
      • CloseVectorWeb
    Index

    Constructors

    • Parameters

      • embeddings: EmbeddingsInterface
      • args: CloseVectorWebArgs
      • Optionalcredentials: CloseVectorCredentials

      Returns CloseVectorWeb

    Properties

    _instance?: CloseVectorHNSWWeb
    credentials?: CloseVectorCredentials
    FilterType: (doc: Document) => boolean

    Accessors

    • get instance(): CloseVectorHNSWImplementation

      Returns CloseVectorHNSWImplementation

    • set instance(instance: CloseVectorHNSWImplementation): void

      Parameters

      • instance: CloseVectorHNSWImplementation

      Returns void

    Methods

    • Returns string

    • Method to add documents to the vector store. It first converts the documents to vectors using the embeddings, then adds the vectors to the vector store.

      Parameters

      • documents: Document[]

        The documents to be added to the vector store.

      Returns Promise<void>

      A Promise that resolves when the documents have been added.

    • Method to add vectors to the vector store. It first initializes the index if it hasn't been initialized yet, then adds the vectors to the index and the documents to the document store.

      Parameters

      • vectors: number[][]

        The vectors to be added to the vector store.

      • documents: Document[]

        The documents corresponding to the vectors.

      Returns Promise<void>

      A Promise that resolves when the vectors and documents have been added.

    • Method to delete the vector store from a directory. It deletes the hnswlib.index file, the docstore.json file, and the args.json file from the directory.

      Parameters

      • params: { directory: string }

        An object with a directory property that specifies the directory from which to delete the vector store.

      Returns Promise<void>

      A Promise that resolves when the vector store has been deleted.

    • Method to save the vector store to a directory. It saves the HNSW index, the arguments, and the document store to the directory.

      Parameters

      • directory: string

        The directory to which to save the vector store. In CloseVector, we use IndexedDB to mock the file system. Therefore, this parameter is can be treated as a key to the contents stored.

      Returns Promise<void>

      A Promise that resolves when the vector store has been saved.

    • Method to save the index to the CloseVector CDN.

      Parameters

      • options: {
            credentials?: CloseVectorCredentials;
            description?: string;
            onProgress?: (progress: { loaded: number; total: number }) => void;
            public?: boolean;
            uuid?: string;
        }
        • Optionalcredentials?: CloseVectorCredentials

          the credentials to be used to access the CloseVector API

        • Optionaldescription?: string

          a description of the index

        • OptionalonProgress?: (progress: { loaded: number; total: number }) => void

          a callback function to track the upload progress

        • Optionalpublic?: boolean

          a boolean to determine if the index should be public or private, if not provided, the index will be private. If the index is public, it can be accessed by anyone with the uuid.

        • Optionaluuid?: string

          after uploading the index to the CloseVector CDN, the uuid of the index can be obtained by instance.uuid

      Returns Promise<void>

    • Method to perform a similarity search in the vector store using a query vector. It returns the k most similar documents along with their similarity scores. An optional filter function can be provided to filter the documents.

      Parameters

      • query: number[]

        The query vector.

      • k: number

        The number of most similar documents to return.

      • Optionalfilter: (doc: Document) => boolean

        An optional filter function to filter the documents.

      Returns Promise<[Document<Record<string, unknown>>, number][]>

      A Promise that resolves to an array of tuples, where each tuple contains a document and its similarity score.

    • Returns string

    • Static method to create a new CloseVectorWeb instance from documents. It creates a new CloseVectorWeb instance, adds the documents to it, then returns the instance.

      Parameters

      • docs: Document[]

        The documents to be added to the CloseVectorWeb instance.

      • embeddings: EmbeddingsInterface

        The embeddings to be used by the CloseVectorWeb instance.

      • Optionalargs: Record<string, unknown>

        An optional configuration object for the CloseVectorWeb instance.

      • Optionalcredentials: CloseVectorCredentials

        An optional credential object for the CloseVector API.

      Returns Promise<CloseVectorWeb>

      A Promise that resolves to a new CloseVectorWeb instance.

    • Static method to create a new CloseVectorWeb instance from texts and metadata. It creates a new Document instance for each text and metadata, then calls the fromDocuments method to create the CloseVectorWeb instance.

      Parameters

      • texts: string[]

        The texts to be used to create the documents.

      • metadatas: object | object[]

        The metadata to be used to create the documents.

      • embeddings: EmbeddingsInterface

        The embeddings to be used by the CloseVectorWeb instance.

      • Optionalargs: Record<string, unknown>

        An optional configuration object for the CloseVectorWeb instance.

      • Optionalcredential: CloseVectorCredentials

        An optional credential object for the CloseVector API.

      Returns Promise<CloseVectorWeb>

      A Promise that resolves to a new CloseVectorWeb instance.

    • Returns Promise<HnswlibModule>

    • Static method to load a vector store from a directory. It reads the HNSW index, the arguments, and the document store from the directory, then creates a new CloseVectorWeb instance with these values.

      Parameters

      • directory: string

        The directory from which to load the vector store.

      • embeddings: EmbeddingsInterface

        The embeddings to be used by the CloseVectorWeb instance.

      • Optionalcredentials: CloseVectorCredentials

      Returns Promise<CloseVectorWeb>

      A Promise that resolves to a new CloseVectorWeb instance.

    • Method to load the index from the CloseVector CDN.

      Parameters

      • options: {
            credentials?: CloseVectorCredentials;
            embeddings: EmbeddingsInterface;
            onProgress?: (progress: { loaded: number; total: number }) => void;
            uuid: string;
        }
        • Optionalcredentials?: CloseVectorCredentials

          the credentials to be used to access the CloseVector API

        • embeddings: EmbeddingsInterface

          the embeddings to be used by the CloseVectorWeb instance

        • OptionalonProgress?: (progress: { loaded: number; total: number }) => void

          a callback function to track the download progress

        • uuid: string

          after uploading the index to the CloseVector CDN, the uuid of the index can be obtained by instance.uuid

      Returns Promise<CloseVectorWeb>

    • Parameters

      • texts: string[]
      • metadatas: object | object[]

      Returns Document[]