Try Gemini 1.5 models, the latest multimodal models in Vertex AI, and see what you can build with up to a 2M token context window. Try Gemini 1.5 models, the latest multimodal models in Vertex AI, and see what you can build with up to a 2M token context window.

Interface VertexInit (1.3.1)

Params used to initialize the Vertex SDK.

Package

@google-cloud/vertexai

Properties

apiEndpoint

apiEndpoint?: string;

Optional. The base Vertex AI endpoint to use for the request. If not provided, the default regionalized endpoint (i.e. us-central1-aiplatform.googleapis.com) will be used.

googleAuthOptions

googleAuthOptions?: GoogleAuthOptions;

Optional. The Authentication options provided by google-auth-library. Complete list of authentication options is documented in the GoogleAuthOptions interface: https://github.com/googleapis/google-auth-library-nodejs/blob/main/src/auth/googleauth.ts.

location

location?: string;

Optional. The Google Cloud project location. If not provided, SDK will firtly try to resolve it from runtime environment. If no location resolved from runtime environment, SDK will use default value us-central1.

project

project?: string;

Optional. The Google Cloud project ID. It is not the numeric project name. If not provided, SDK will try to resolve it from runtime environment. If still not cannot resovle project ID, SDK will throw exception.