Class VectaraStore

constructor

• new VectaraStore(args: VectaraLibArgs): VectaraStore

  Parameters

  • args: VectaraLibArgs

  Returns VectaraStore

FilterType

lc_aliases

• get lc_aliases(): { [key: string]: string }

  Returns { [key: string]: string }

lc_secrets

• get lc_secrets(): { [key: string]: string }

  Returns { [key: string]: string }

_vectorstoreType

• _vectorstoreType(): string

  Returns string

addDocuments

• addDocuments(documents: Document[]): Promise<string[]>

  Adds documents to the Vectara store.

  Parameters

  • documents: Document[]

    An array of Document objects to add to the Vectara store.

  Returns Promise<string[]>

  A Promise that resolves to an array of document IDs indexed in Vectara.

addFiles

• addFiles(
      files: VectaraFile[],
      metadatas?: undefined | Record<string, unknown>,
  ): Promise<string[]>

  Vectara provides a way to add documents directly via their API. This API handles pre-processing and chunking internally in an optimal manner. This method is a wrapper to utilize that API within LangChain.

  Parameters

  • files: VectaraFile[]

    An array of VectaraFile objects representing the files and their respective file names to be uploaded to Vectara.

  • metadatas: undefined | Record<string, unknown> = undefined

  Returns Promise<string[]>

  A Promise that resolves to the number of successfully uploaded files.

addVectors

• addVectors(_vectors: number[][], _documents: Document[]): Promise<void>

  Throws an error, as this method is not implemented. Use addDocuments instead.

  Parameters

  • _vectors: number[][]

    Not used.

  • _documents: Document[]

    Not used.

  Returns Promise<void>

  Does not return a value.

deleteDocuments

• deleteDocuments(ids: string[]): Promise<void>

  Method to delete data from the Vectara corpus.

  Parameters

  • ids: string[]

  Returns Promise<void>

  Promise that resolves when the deletion is complete.

getJsonHeader

• getJsonHeader(): Promise<VectaraCallHeader>

  Returns a header for Vectara API calls.

  Returns Promise<VectaraCallHeader>

  A Promise that resolves to a VectaraCallHeader object.

similaritySearch

• similaritySearch(
      query: string,
      k?: number,
      filter?: VectaraFilter,
  ): Promise<Document[]>

  Performs a similarity search and returns documents.

  Parameters

  • query: string

    The query string for the similarity search.

  • Optionalk: number

    Optional. The number of results to return. Default is 10.

  • Optionalfilter: VectaraFilter

    Optional. A VectaraFilter object to refine the search results.

  Returns Promise<Document[]>

  A Promise that resolves to an array of Document objects.

similaritySearchVectorWithScore

• similaritySearchVectorWithScore(
      _query: number[],
      _k: number,
      _filter?: VectaraFilter,
  ): Promise<[Document, number][]>

  Throws an error, as this method is not implemented. Use similaritySearch or similaritySearchWithScore instead.

  Parameters

  • _query: number[]

    Not used.

  • _k: number

    Not used.

  • Optional_filter: VectaraFilter

    Not used.

  Returns Promise<[Document, number][]>

  Does not return a value.

similaritySearchWithScore

• similaritySearchWithScore(
      query: string,
      k?: number,
      filter?: VectaraFilter,
  ): Promise<[Document, number][]>

  Performs a similarity search and returns documents along with their scores.

  Parameters

  • query: string

    The query string for the similarity search.

  • Optionalk: number

    Optional. The number of results to return. Default is 10.

  • Optionalfilter: VectaraFilter

    Optional. A VectaraFilter object to refine the search results.

  Returns Promise<[Document, number][]>

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

vectaraQuery

• vectaraQuery(
      query: string,
      k: number,
      vectaraFilterObject: VectaraFilter,
      summary?: VectaraSummary,
  ): Promise<SummaryResult>

  Performs a Vectara API call based on the arguments provided.

  Parameters

  • query: string

    The query string for the similarity search.

  • k: number

    Optional. The number of results to return. Default is 10.

  • vectaraFilterObject: VectaraFilter
  • summary: VectaraSummary = ...

  Returns Promise<SummaryResult>

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

StaticfromDocuments

• fromDocuments(
      docs: Document[],
      _embeddings: EmbeddingsInterface,
      args: VectaraLibArgs,
  ): Promise<VectaraStore>

  Creates a VectaraStore instance from documents.

  Parameters

  • docs: Document[]

    An array of Document objects.

  • _embeddings: EmbeddingsInterface

    Not used.

  • args: VectaraLibArgs

    A VectaraLibArgs object for initializing the VectaraStore instance.

  Returns Promise<VectaraStore>

  A Promise that resolves to a VectaraStore instance.

StaticfromTexts

• fromTexts(
      texts: string[],
      metadatas: object | object[],
      _embeddings: EmbeddingsInterface,
      args: VectaraLibArgs,
  ): Promise<VectaraStore>

  Creates a VectaraStore instance from texts.

  Parameters

  • texts: string[]

    An array of text strings.

  • metadatas: object | object[]

    Metadata for the texts. Can be a single object or an array of objects.

  • _embeddings: EmbeddingsInterface

    Not used.

  • args: VectaraLibArgs

    A VectaraLibArgs object for initializing the VectaraStore instance.

  Returns Promise<VectaraStore>

  A Promise that resolves to a VectaraStore instance.