Hierarchy

  • VectorStore
    • AstraDBVectorStore

Constructors

Properties

FilterType: CollectionFilter
caller: AsyncCaller
embeddings: EmbeddingsInterface

Embeddings interface for generating vector embeddings from text queries, enabling vector-based similarity searches.

Methods

  • Method that adds documents to AstraDB.

    Parameters

    • documents: Document<Record<string, any>>[]

      Array of documents to add to AstraDB.

    • Optionaloptions: string[]

      Optional ids for the documents.

    Returns Promise<void>

    Promise that resolves the documents have been added.

  • Method to save vectors to AstraDB.

    Parameters

    • vectors: number[][]

      Vectors to save.

    • documents: Document<Record<string, any>>[]

      The documents associated with the vectors.

    • Optionaloptions: string[]

    Returns Promise<void>

    Promise that resolves when the vectors have been added.

  • Creates a VectorStoreRetriever instance with flexible configuration options.

    Parameters

    • OptionalkOrFields: number | Partial<VectorStoreRetrieverInput<AstraDBVectorStore>>

      If a number is provided, it sets the k parameter (number of items to retrieve).

      • If an object is provided, it should contain various configuration options.
    • Optionalfilter: CollectionFilter

      Optional filter criteria to limit the items retrieved based on the specified filter type.

    • Optionalcallbacks: Callbacks

      Optional callbacks that may be triggered at specific stages of the retrieval process.

    • Optionaltags: string[]

      Tags to categorize or label the VectorStoreRetriever. Defaults to an empty array if not provided.

    • Optionalmetadata: Record<string, unknown>

      Additional metadata as key-value pairs to add contextual information for the retrieval process.

    • Optionalverbose: boolean

      If true, enables detailed logging for the retrieval process. Defaults to false.

    Returns VectorStoreRetriever<AstraDBVectorStore>

    • A configured VectorStoreRetriever instance based on the provided parameters.

    Basic usage with a k value:

    const retriever = myVectorStore.asRetriever(5);
    

    Usage with a configuration object:

    const retriever = myVectorStore.asRetriever({
    k: 10,
    filter: myFilter,
    tags: ['example', 'test'],
    verbose: true,
    searchType: 'mmr',
    searchKwargs: { alpha: 0.5 },
    });
  • Create a new collection in your Astra DB vector database and then connects to it. If the collection already exists, it will connect to it as well.

    Returns Promise<void>

    Promise that resolves if connected to the collection.

  • Return documents selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to the query AND diversity among selected documents.

    Parameters

    • query: string

      Text to look up documents similar to.

    • options: MaxMarginalRelevanceSearchOptions<CollectionFilter>

    Returns Promise<Document<Record<string, any>>[]>

    • List of documents selected by maximal marginal relevance.
  • Searches for documents similar to a text query by embedding the query and performing a similarity search on the resulting vector.

    Parameters

    • query: string

      Text query for finding similar documents.

    • Optionalk: number

      Number of similar results to return. Defaults to 4.

    • Optionalfilter: CollectionFilter

      Optional filter based on FilterType.

    • Optional_callbacks: Callbacks

      Optional callbacks for monitoring search progress

    Returns Promise<DocumentInterface<Record<string, any>>[]>

    A promise resolving to an array of DocumentInterface instances representing similar documents.

  • Method that performs a similarity search in AstraDB and returns and similarity scores.

    Parameters

    • query: number[]

      Query vector for the similarity search.

    • k: number

      Number of top results to return.

    • Optionalfilter: CollectionFilter

      Optional filter to apply to the search.

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

    Promise that resolves with an array of documents and their scores.

  • Searches for documents similar to a text query by embedding the query, and returns results with similarity scores.

    Parameters

    • query: string

      Text query for finding similar documents.

    • Optionalk: number

      Number of similar results to return. Defaults to 4.

    • Optionalfilter: CollectionFilter

      Optional filter based on FilterType.

    • Optional_callbacks: Callbacks

      Optional callbacks for monitoring search progress

    Returns Promise<[DocumentInterface<Record<string, any>>, number][]>

    A promise resolving to an array of tuples, each containing a document and its similarity score.

  • Returns Serialized

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

    Parameters

    • docs: Document<Record<string, any>>[]

      The Documents to use.

    • embeddings: EmbeddingsInterface

      The embeddings to use.

    • dbConfig: AstraLibArgs

      The arguments for the AstraDBVectorStore.

    Returns Promise<AstraDBVectorStore>

    Promise that resolves with a new instance of AstraDBVectorStore.

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

    Parameters

    • texts: string[]

      The texts to use.

    • metadatas: object | object[]

      The metadata associated with the texts.

    • embeddings: EmbeddingsInterface

      The embeddings to use.

    • dbConfig: AstraLibArgs

      The arguments for the AstraDBVectorStore.

    Returns Promise<AstraDBVectorStore>

    Promise that resolves with a new instance of AstraDBVectorStore.