Class GoogleVertexAIMultimodalEmbeddings

constructor

• new GoogleVertexAIMultimodalEmbeddings(
      fields?: GoogleVertexAIMultimodalEmbeddingsParams,
  ): GoogleVertexAIMultimodalEmbeddings

  Parameters

  • Optionalfields: GoogleVertexAIMultimodalEmbeddingsParams

  Returns GoogleVertexAIMultimodalEmbeddings

model

embedDocuments

• embedDocuments(documents: string[]): Promise<number[][]>

  Generates embeddings for multiple text documents.

  Parameters

  • documents: string[]

    An array of text documents.

  Returns Promise<number[][]>

  A promise that resolves to an array of text document embeddings.

embedImage

• embedImage(images: Buffer<ArrayBufferLike>[]): Promise<number[][]>

  Generates embeddings for multiple images.

  Parameters

  • images: Buffer<ArrayBufferLike>[]

    An array of images.

  Returns Promise<number[][]>

  A promise that resolves to an array of image embeddings.

embedImageQuery

• embedImageQuery(image: Buffer): Promise<number[]>

  Generates embeddings for a single image.

  Parameters

  • image: Buffer

    A single image.

  Returns Promise<number[]>

  A promise that resolves to an image embedding.

embedMedia

• embedMedia(media: GoogleVertexAIMedia[]): Promise<MediaEmbeddings[]>

  Generates embeddings for multiple media instances.

  Parameters

  • media: GoogleVertexAIMedia[]

    An array of media instances.

  Returns Promise<MediaEmbeddings[]>

  A promise that resolves to an array of media embeddings.

embedMediaQuery

• embedMediaQuery(media: GoogleVertexAIMedia): Promise<MediaEmbeddings>

  Generates embeddings for a single media instance.

  Parameters

  • media: GoogleVertexAIMedia

    A single media instance.

  Returns Promise<MediaEmbeddings>

  A promise that resolves to a media embedding.

embedQuery

• embedQuery(document: string): Promise<number[]>

  Generates embeddings for a single text document.

  Parameters

  • document: string

    A single text document.

  Returns Promise<number[]>

  A promise that resolves to a text document embedding.

mediaToInstance

• mediaToInstance(
      media: GoogleVertexAIMedia,
  ): GoogleVertexAIMultimodalEmbeddingsInstance

  Converts media (text or image) to an instance that can be used for generating embeddings.

  Parameters

  • media: GoogleVertexAIMedia

    The media (text or image) to be converted.

  Returns GoogleVertexAIMultimodalEmbeddingsInstance

  An instance of media that can be used for generating embeddings.

responseToEmbeddings

• responseToEmbeddings(
      response: GoogleVertexAILLMResponse<
          GoogleVertexAIMultimodalEmbeddingsResults,
      >,
  ): MediaEmbeddings[]

  Converts the response from Google Vertex AI to embeddings.

  Parameters

  • response: GoogleVertexAILLMResponse<GoogleVertexAIMultimodalEmbeddingsResults>

    The response from Google Vertex AI.

  Returns MediaEmbeddings[]

  An array of media embeddings.