Class VertexAIEmbeddings

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

Hierarchy

GoogleEmbeddings
- VertexAIEmbeddings

Index

Constructors

Properties

Methods

buildAbstractedClient buildApiKey buildApiKeyClient buildClient embedDocuments embedQuery

Constructors

constructor

new VertexAIEmbeddings(fields): VertexAIEmbeddings
Parameters
- fields: GoogleVertexAIEmbeddingsInput
Returns VertexAIEmbeddings
Overrides GoogleEmbeddings.constructor
- Defined in libs/langchain-google-vertexai-web/src/embeddings.ts:20

Properties

caller

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.

model

model: string

Methods

buildAbstractedClient

buildAbstractedClient(fields?): GoogleAbstractedClient
Parameters
- Optionalfields: GoogleConnectionParams<WebGoogleAuthOptions>
Returns GoogleAbstractedClient
Inherited from GoogleEmbeddings.buildAbstractedClient
- Defined in libs/langchain-google-webauth/dist/embeddings.d.ts:15

buildApiKey

buildApiKey(fields?): undefined | string
Parameters
- Optionalfields: GoogleConnectionParams<WebGoogleAuthOptions>
Returns undefined | string
Inherited from GoogleEmbeddings.buildApiKey
- Defined in libs/langchain-google-common/dist/embeddings.d.ts:54

buildApiKeyClient

buildApiKeyClient(apiKey): GoogleAbstractedClient
Parameters
- apiKey: string
Returns GoogleAbstractedClient
Inherited from GoogleEmbeddings.buildApiKeyClient
- Defined in libs/langchain-google-common/dist/embeddings.d.ts:53

buildClient

buildClient(fields?): GoogleAbstractedClient
Parameters
- Optionalfields: GoogleConnectionParams<WebGoogleAuthOptions>
Returns GoogleAbstractedClient
Inherited from GoogleEmbeddings.buildClient
- Defined in libs/langchain-google-common/dist/embeddings.d.ts:55

embedDocuments

embedDocuments(documents): 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.
Parameters
- documents: string[]
  An array of documents to be embedded.
Returns Promise<number[][]>
A promise that resolves to a 2D array of embeddings for each document.
Inherited from GoogleEmbeddings.embedDocuments
- Defined in libs/langchain-google-common/dist/embeddings.d.ts:64

embedQuery

embedQuery(document): 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.
Parameters
- document: string
  A document to be embedded.
Returns Promise<number[]>
A promise that resolves to an embedding for the document.
Inherited from GoogleEmbeddings.embedQuery
- Defined in libs/langchain-google-common/dist/embeddings.d.ts:72