Class GoogleVertexAIMultimodalEmbeddings

Class for generating embeddings for text and images using Google's Vertex AI. It extends the Embeddings base class and implements the GoogleVertexAIMultimodalEmbeddingsParams interface.

Hierarchy (view full)

Toolkit
- GoogleVertexAIMultimodalEmbeddings

Implements

GoogleVertexAIMultimodalEmbeddingsParams

Index

Constructors

Properties

Methods

embedDocuments embedImage embedImageQuery embedMedia embedMediaQuery embedQuery mediaToInstance responseToEmbeddings

Constructors

constructor

new GoogleVertexAIMultimodalEmbeddings(fields?): GoogleVertexAIMultimodalEmbeddings
Parameters
- Optional fields: GoogleVertexAIMultimodalEmbeddingsParams
Returns GoogleVertexAIMultimodalEmbeddings
Overrides Embeddings.constructor
- Defined in langchain/src/experimental/multimodal_embeddings/googlevertexai.ts:86

Properties

model

model: string = "multimodalembedding@001"

Model to use

Methods

embedDocuments

embedDocuments(documents): 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.
- Defined in langchain/src/experimental/multimodal_embeddings/googlevertexai.ts:200

embedImage

embedImage(images): Promise<number[][]>
Generates embeddings for multiple images.
Parameters
- images: Buffer[]
  An array of images.
Returns Promise<number[][]>
A promise that resolves to an array of image embeddings.
- Defined in langchain/src/experimental/multimodal_embeddings/googlevertexai.ts:178

embedImageQuery

embedImageQuery(image): 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.
- Defined in langchain/src/experimental/multimodal_embeddings/googlevertexai.ts:189

embedMedia

embedMedia(media): 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.
- Defined in langchain/src/experimental/multimodal_embeddings/googlevertexai.ts:146

embedMediaQuery

embedMediaQuery(media): 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.
- Defined in langchain/src/experimental/multimodal_embeddings/googlevertexai.ts:156

embedQuery

embedQuery(document): 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.
- Defined in langchain/src/experimental/multimodal_embeddings/googlevertexai.ts:211

mediaToInstance

mediaToInstance(media): 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.
- Defined in langchain/src/experimental/multimodal_embeddings/googlevertexai.ts:107

responseToEmbeddings

responseToEmbeddings(response): 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.
- Defined in langchain/src/experimental/multimodal_embeddings/googlevertexai.ts:130

Generated using TypeDoc