LangChain Reference home page

GitHub
Main Docs

Google

Node

Overview
Chat Models
LLMs
Embeddings

⌘I

LangChain Assistant

Ask a question to get started

Enter to send•Shift+Enter new line

Menu

Overview Chat Models LLMs Embeddings

Language

Theme

JavaScript@langchain/google-vertexai-webindexVertexAIEmbeddings

Class●Since v0.2

VertexAIEmbeddings

Copy

class VertexAIEmbeddings

Bases

GoogleEmbeddings

Used in Docs

Embedding model integrations
Vector store integrations
VertexAIEmbeddings integration

Constructors

Properties

Methods

View source on GitHub

property

caller: AsyncCaller

The async caller should be used by subclasses to make any async calls, which will thus benefit from the concurrency and retry logic.

property

dimensions: number

Used to specify output embedding size. If set, output embeddings will be truncated to the size specified.

property

lc_serializable: boolean

property

model: string

Model to use

aiStudioResponseToValues→ number[][]

buildAbstractedClient→ GoogleAbstractedClient

buildApiKey→ string | undefined

buildApiKeyClient→ GoogleAbstractedClient

buildClient→ GoogleAbstractedClient

buildParameters→ VertexEmbeddingsParameters

embedDocuments→ Promise<number[][]>

Takes an array of documents as input and returns a promise that resolves to a 2D array of embeddings for each document. It splits the documents into chunks and makes requests to the Google Vertex AI API to generate embeddings.

embedQuery→ Promise<number[]>

Takes a document as input and returns a promise that resolves to an embedding for the document. It calls the embedDocuments method with the document as the input.

responseToValues→ number[][]

vertexResponseToValues→ number[][]

lc_name→ string

Integration with a Google Vertex AI embeddings model using the "@langchain/google-webauth" package for auth.