Class Typesense

constructor

• new Typesense(
      embeddings: EmbeddingsInterface,
      config: TypesenseConfig,
  ): Typesense

  Parameters

  • embeddings: EmbeddingsInterface
  • config: TypesenseConfig

  Returns Typesense

FilterType

_documentsToTypesenseRecords

• _documentsToTypesenseRecords(
      documents: Document[],
      vectors: number[][],
  ): Record<string, unknown>[]

  Transform documents to Typesense records.

  Parameters

  • documents: Document[]
  • vectors: number[][]

  Returns Record<string, unknown>[]

  Typesense records.

_typesenseRecordsToDocuments

• _typesenseRecordsToDocuments(
      typesenseRecords:
          | undefined
          | { document?: Record<string, unknown>; vector_distance: number }[],
  ): [Document, number][]

  Transform the Typesense records to documents.

  Parameters

  • typesenseRecords: undefined | { document?: Record<string, unknown>; vector_distance: number }[]

  Returns [Document, number][]

  documents

_vectorstoreType

• _vectorstoreType(): string

  Returns string

addDocuments

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

  Add documents to the vector store. Will be updated if in the metadata there is a document with the same id if is using the default import function. Metadata will be added in the columns of the schema based on metadataColumnNames.

  Parameters

  • documents: Document[]

    Documents to add.

  Returns Promise<void>

addVectors

• addVectors(vectors: number[][], documents: Document[]): Promise<void>

  Adds vectors to the vector store.

  Parameters

  • vectors: number[][]

    Vectors to add.

  • documents: Document[]

    Documents associated with the vectors.

  Returns Promise<void>

deleteDocuments

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

  Delete documents from the vector store.

  Parameters

  • documentIds: string[]

    ids of the documents to delete

  Returns Promise<void>

similaritySearchVectorWithScore

• similaritySearchVectorWithScore(
      vectorPrompt: number[],
      k?: number,
      filter?: Partial<MultiSearchRequestSchema>,
  ): Promise<[Document, number][]>

  Search for similar documents with their similarity score.

  Parameters

  • vectorPrompt: number[]

    vector to search for

  • Optionalk: number

    amount of results to return

  • filter: Partial<MultiSearchRequestSchema> = {}

  Returns Promise<[Document, number][]>

  similar documents with their similarity score

StaticfromDocuments

• fromDocuments(
      docs: Document[],
      embeddings: EmbeddingsInterface,
      config: TypesenseConfig,
  ): Promise<Typesense>

  Create a vector store from documents.

  Parameters

  • docs: Document[]

    documents

  • embeddings: EmbeddingsInterface

    embeddings

  • config: TypesenseConfig

    Typesense configuration

  Returns Promise<Typesense>

  Typesense vector store

  Warning

  You can omit this method, and only use the constructor and addDocuments.

StaticfromTexts

• fromTexts(
      texts: string[],
      metadatas: object[],
      embeddings: EmbeddingsInterface,
      config: TypesenseConfig,
  ): Promise<Typesense>

  Create a vector store from texts.

  Parameters

  • texts: string[]
  • metadatas: object[]
  • embeddings: EmbeddingsInterface
  • config: TypesenseConfig

  Returns Promise<Typesense>

  Typesense vector store