Class that provides an interface to a Neon Postgres database. It extends the VectorStore base class and implements methods for adding documents and vectors, performing similarity searches, and ensuring the existence of a table in the database.

Hierarchy

  • VectorStore
    • NeonPostgres

Constructors

Properties

FilterType: Metadata
contentColumnName: string
embeddings: EmbeddingsInterface
filter?: Metadata
idColumnName: string
metadataColumnName: string
neonConnectionString: string
tableName: string
vectorColumnName: string

Methods

  • Method to add documents to the vector store. It converts the documents into vectors, and adds them to the store.

    Parameters

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

      Array of Document instances.

    • Optionaloptions: {
          ids?: string[];
      }

      Optional arguments for adding documents

      • Optionalids?: string[]

    Returns Promise<string[]>

    Promise that resolves when the documents have been added.

  • Method to add vectors to the vector store. It converts the vectors into rows and inserts them into the database.

    Parameters

    • vectors: number[][]

      Array of vectors.

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

      Array of Document instances.

    • Optionaloptions: {
          ids?: string[];
      }

      Optional arguments for adding documents

      • Optionalids?: string[]

    Returns Promise<string[]>

    Promise that resolves when the vectors have been added.

  • Parameters

    • OptionalkOrFields: number | Partial<VectorStoreRetrieverInput<NeonPostgres>>
    • Optionalfilter: Metadata
    • Optionalcallbacks: Callbacks
    • Optionaltags: string[]
    • Optionalmetadata: Record<string, unknown>
    • Optionalverbose: boolean

    Returns VectorStoreRetriever<NeonPostgres>

  • Method to delete documents from the vector store. It deletes the documents that match the provided ids.

    Parameters

    • params: {
          deleteAll?: boolean;
          ids?: string[];
      }
      • OptionaldeleteAll?: boolean
      • Optionalids?: string[]

    Returns Promise<void>

    Promise that resolves when the documents have been deleted.

  • Method to ensure the existence of the table to store vectors in the database. It creates the table if it does not already exist.

    Returns Promise<void>

    Promise that resolves when the table has been ensured.

  • 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<Metadata>
    • _callbacks: undefined | Callbacks

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

    • List of documents selected by maximal marginal relevance.
  • Constructs the SQL query for inserting rows into the specified table.

    Parameters

    • rows: (string | Record<string, any>)[][]

      The rows of data to be inserted, consisting of values and records.

    • useIdColumn: boolean

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

    The complete SQL INSERT INTO query string.

  • Parameters

    • query: string
    • Optionalk: number
    • Optionalfilter: Metadata
    • Optional_callbacks: Callbacks

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

  • Method to perform a similarity search in the vector store. It returns the k most similar documents to the query vector, along with their similarity scores.

    Parameters

    • query: number[]

      Query vector.

    • k: number

      Number of most similar documents to return.

    • Optionalfilter: Metadata

      Optional filter to apply to the search.

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

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

  • Parameters

    • query: string
    • Optionalk: number
    • Optionalfilter: Metadata
    • Optional_callbacks: Callbacks

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

  • Returns Serialized

  • Static method to create a new NeonPostgres instance from an array of Document instances. It adds the documents to the store.

    Parameters

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

      Array of Document instances.

    • embeddings: EmbeddingsInterface

      Embeddings instance.

    • dbConfig: NeonPostgresArgs

      NeonPostgreseArgs instance.

    Returns Promise<NeonPostgres>

    Promise that resolves with a new instance of NeonPostgres.

  • Static method to create a new NeonPostgres instance from an array of texts and their metadata. It converts the texts into Document instances and adds them to the store.

    Parameters

    • texts: string[]

      Array of texts.

    • metadatas: object | object[]

      Array of metadata objects or a single metadata object.

    • embeddings: EmbeddingsInterface

      Embeddings instance.

    • dbConfig: NeonPostgresArgs

      NeonPostgresArgs instance.

    Returns Promise<NeonPostgres>

    Promise that resolves with a new instance of NeonPostgresArgs.