Class TigrisVectorStore

constructor

• new TigrisVectorStore(
      embeddings: EmbeddingsInterface,
      args: TigrisLibArgs,
  ): TigrisVectorStore

  Parameters

  • embeddings: EmbeddingsInterface
  • args: TigrisLibArgs

  Returns TigrisVectorStore

Optionalindex

_vectorstoreType

• _vectorstoreType(): string

  Returns string

addDocuments

• addDocuments(
      documents: Document[],
      options?: string[] | { ids?: string[] },
  ): Promise<void>

  Method to add an array of documents to the Tigris database.

  Parameters

  • documents: Document[]

    An array of Document instances to be added to the Tigris database.

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

    Optional parameter that can either be an array of string IDs or an object with a property 'ids' that is an array of string IDs.

  Returns Promise<void>

  A Promise that resolves when the documents have been added to the Tigris database.

addVectors

• addVectors(
      vectors: number[][],
      documents: Document[],
      options?: string[] | { ids?: string[] },
  ): Promise<void>

  Method to add vectors to the Tigris database.

  Parameters

  • vectors: number[][]

    An array of vectors to be added to the Tigris database.

  • documents: Document[]

    An array of Document instances corresponding to the vectors.

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

    Optional parameter that can either be an array of string IDs or an object with a property 'ids' that is an array of string IDs.

  Returns Promise<void>

  A Promise that resolves when the vectors have been added to the Tigris database.

similaritySearchVectorWithScore

• similaritySearchVectorWithScore(
      query: number[],
      k: number,
      filter?: object,
  ): Promise<[Document, number][]>

  Method to perform a similarity search in the Tigris database and return the k most similar vectors along with their similarity scores.

  Parameters

  • query: number[]

    The query vector.

  • k: number

    The number of most similar vectors to return.

  • Optionalfilter: object

    Optional filter object to apply during the search.

  Returns Promise<[Document, number][]>

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

StaticfromDocuments

• fromDocuments(
      docs: Document[],
      embeddings: EmbeddingsInterface,
      dbConfig: TigrisLibArgs,
  ): Promise<TigrisVectorStore>

  Static method to create a new instance of TigrisVectorStore from an array of Document instances.

  Parameters

  • docs: Document[]

    An array of Document instances to be added to the Tigris database.

  • embeddings: EmbeddingsInterface

    An instance of Embeddings to be used for embedding the documents.

  • dbConfig: TigrisLibArgs

    An instance of TigrisLibArgs to be used for configuring the Tigris database.

  Returns Promise<TigrisVectorStore>

  A Promise that resolves to a new instance of TigrisVectorStore.

StaticfromExistingIndex

• fromExistingIndex(
      embeddings: EmbeddingsInterface,
      dbConfig: TigrisLibArgs,
  ): Promise<TigrisVectorStore>

  Static method to create a new instance of TigrisVectorStore from an existing index.

  Parameters

  • embeddings: EmbeddingsInterface

    An instance of Embeddings to be used for embedding the documents.

  • dbConfig: TigrisLibArgs

    An instance of TigrisLibArgs to be used for configuring the Tigris database.

  Returns Promise<TigrisVectorStore>

  A Promise that resolves to a new instance of TigrisVectorStore.

StaticfromTexts

• fromTexts(
      texts: string[],
      metadatas: object | object[],
      embeddings: EmbeddingsInterface,
      dbConfig: TigrisLibArgs,
  ): Promise<TigrisVectorStore>

  Static method to create a new instance of TigrisVectorStore from an array of texts.

  Parameters

  • texts: string[]

    An array of texts to be converted into Document instances and added to the Tigris database.

  • metadatas: object | object[]

    Either an array of metadata objects or a single metadata object to be associated with the texts.

  • embeddings: EmbeddingsInterface

    An instance of Embeddings to be used for embedding the texts.

  • dbConfig: TigrisLibArgs

    An instance of TigrisLibArgs to be used for configuring the Tigris database.

  Returns Promise<TigrisVectorStore>

  A Promise that resolves to a new instance of TigrisVectorStore.