Skip to main content

Switch to Vertex AI

Switching from Gemini API to Vertex AI Integration

I have a Node.js application that formerly used the pure Gemini API. I switched to using the Vertex AI integration.

In order to achieve this, you need to set up your environment to use Application Default Credentials (ADC) and specify your Google Cloud project ID.

#!/bin/bash

export GOOGLE_CLOUD_PROJECT=<my-project-id>
bash <(curl -sSL \
https://storage.googleapis.com/cloud-samples-data/adc/setup_adc.sh)

Then it stores the service credentials in a file:

${HOME}/.config/gcloud/application_default_credentials.json

Which contains:

{
  "account": "",
  "client_id": "....apps.googleusercontent.com",
  "client_secret": "...",
  "quota_project_id": "gen-lang-client-0123456",
  "refresh_token": "1//OlP1frQqGdZVykkPbFRWzVUBo1s",
  "type": "authorized_user",
  "universe_domain": "googleapis.com"
}

Then you can use the following code to generate content using the Vertex AI integration:

const {GoogleGenAI} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION = process.env.GOOGLE_CLOUD_LOCATION || 'global';

async function generateContent(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,    // This enables Vertex AI integration
    project: projectId,
    location: location,
  });

  const response = await client.models.generateContent({
    model: 'gemini-3-flash-preview',
    contents: 'How does AI work?',
  });

  console.log(response.text);

  return response.text;
}

How Token Renewal is Managed?

The renewal process is handled automatically by Google's underlying authentication libraries (google-auth-library) without requiring any additional code or manual intervention

Automatic Token Refresh on Request:

  • OAuth access tokens used by Google APIs are short-lived (usually expiring after 1 hour).
  • Every time you run your TypeScript code and call client.models.generateContent(...), the SDK loads the credentials from the ADC JSON file.
  • The library automatically exchanges the long-lived refresh_token for a fresh access_token by calling Google's OAuth 2.0 token endpoint.
  • Even if you do not run your script for weeks, the SDK will transparently request a new access token the moment you invoke the function.

When might the refresh_token itself expire?

While access tokens refresh automatically, the underlying refresh_token can become invalid if:

  • You changed your Google Account password.
  • You manually revoked access for the Google Cloud SDK / Google Auth in your Google Account security settings.
  • Your organization's Google Workspace session policies enforce maximum token lifetimes or session re-authentication.
  • The refresh token remains unused for an extended period (typically 6 months).

What to do if the credentials ever expire?

If the refresh token itself is invalidated, the SDK will throw an invalid_grant or authentication error. To re-authorize, simply run:

gcloud auth application-default login

Or re-run your setup script: This will open a browser window to authenticate and update your application_default_credentials.json with a new refresh token.

Popular posts from this blog

Undefined global vim

Defining vim as global outside of Neovim When developing plugins for Neovim, particularly in Lua, developers often encounter the "Undefined global vim" warning. This warning can be a nuisance and disrupt the development workflow. However, there is a straightforward solution to this problem by configuring the Lua Language Server Protocol (LSP) to recognize 'vim' as a global variable. Getting "Undefined global vim" warning when developing Neovim plugin While developing Neovim plugins using Lua, the Lua language server might not recognize the 'vim' namespace by default. This leads to warnings about 'vim' being an undefined global variable. These warnings are not just annoying but can also clutter the development environment with unnecessary alerts, potentially hiding other important warnings or errors. Defining vim as global in Lua LSP configuration to get rid of the warning To resolve the "Undefined global vi...
Read more

LazyGit AI Commit Message

Having AI‑generated commit messages directly integrated into LazyGit If you use LazyGit every day, you already know how it turns Git from a chore into something you can actually enjoy. But there is one part of the workflow that still tends to feel a bit tedious: writing good commit messages. In this post, I show how to plug OpenAI models directly into LazyGit using a tiny one‑file BASH script, so you can get AI‑generated commit messages based on your actual diffs, without waiting for external tools to catch up with the new OpenAI Responses API . The result is a minimal, focused tool you can drop into your setup today: lgaicm . It behaves like a mini aichat that does exactly one thing: generate commit messages from Git diffs, optimized for LazyGit. Why AI‑generated commit messages in LazyGit? Commit messages matter. They are the stor...
Read more

CopilotChat GlobFile Configuration

CopilotChat GlobFile Configuration Want to feed multiple files into GitHub Copilot Chat from Neovim without listing each one manually? Let's add a tiny feature that does exactly that: a file glob that includes full file contents . In this post, we'll walk through what CopilotChat.nvim offers out of the box, why the missing piece matters, and how to implement a custom #file_glob:<pattern> function to include the contents of all files matching a glob. Using Copilot Chat with Neovim CopilotChat.nvim brings GitHub Copilot's chat right into your editing flow. No context switching, no browser hopping — just type your prompt in a Neovim buffer and let the AI help you refactor code, write tests, or explain tricky functions. You can open the chat (for example) with a command like :CopilotChat , then provide extra context using built-in functions. That “extra context” is where the magic really happens. Built-in functio...
Read more