Google Vertex AI Provider

Learn how to use Google Vertex AI for enterprise-grade AI applications with the AI SDK.

Google Vertex AI Provider

The Google Vertex AI provider enables you to use Google’s Gemini models through Vertex AI with enterprise features like VPC, custom endpoints, and more.

Installation

npm

npm install @ai-sdk/google-vertex

pnpm add @ai-sdk/google-vertex

yarn add @ai-sdk/google-vertex

bun add @ai-sdk/google-vertex

Setup

Set up Google Cloud authentication and configure your environment:

GOOGLE_VERTEX_PROJECT=your-project-id
GOOGLE_VERTEX_LOCATION=us-central1

Usage

Basic Text Generation

import { vertex } from '@ai-sdk/google-vertex';
import { generateText } from 'ai';

const { text } = await generateText({
  model: vertex('gemini-2.0-flash'),
  prompt: 'Explain cloud computing.',
});

Streaming Responses

import { vertex } from '@ai-sdk/google-vertex';
import { streamText } from 'ai';

const result = streamText({
  model: vertex('gemini-2.0-flash'),
  prompt: 'Write about artificial intelligence.',
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

Structured Output

import { vertex } from '@ai-sdk/google-vertex';
import { generateObject } from 'ai';
import { z } from 'zod';

const { object } = await generateObject({
  model: vertex('gemini-2.0-flash'),
  schema: z.object({
    analysis: z.string(),
    sentiment: z.enum(['positive', 'negative', 'neutral']),
  }),
  prompt: 'Analyze customer feedback.',
});

Configuration

Custom Provider Instance

import { createVertex } from '@ai-sdk/google-vertex';

const vertex = createVertex({
  project: 'your-project-id',
  location: 'us-central1',
  googleAuthOptions: {
    credentials: {
      client_email: 'your-email',
      private_key: 'your-key',
    },
  },
});

Provider Options

• project: Google Cloud project ID
• location: Region for API calls (e.g., ‘us-central1’)
• googleAuthOptions: Authentication configuration

Available Models

Gemini Models

• gemini-2.0-flash - Fast and efficient
• gemini-1.5-pro - Most capable model
• gemini-1.5-flash - Balanced performance

Advanced Features

Vision

import { vertex } from '@ai-sdk/google-vertex';
import { generateText } from 'ai';
import fs from 'fs';

const result = await generateText({
  model: vertex('gemini-2.0-flash'),
  messages: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'Analyze this image.' },
        { type: 'image', image: fs.readFileSync('./image.png') },
      ],
    },
  ],
});

Code Execution

import { vertex } from '@ai-sdk/google-vertex';
import { generateText } from 'ai';

const { text } = await generateText({
  model: vertex('gemini-2.0-flash'),
  tools: {
    code_execution: vertex.tools.codeExecution({}),
  },
  prompt: 'Calculate compound interest for $10,000 at 5% over 10 years.',
});

Google Search

import { vertex } from '@ai-sdk/google-vertex';
import { generateText } from 'ai';

const { text, sources } = await generateText({
  model: vertex('gemini-2.0-flash'),
  tools: {
    google_search: vertex.tools.googleSearch({}),
  },
  prompt: 'Latest technology news.',
});

PDF Support

import { vertex } from '@ai-sdk/google-vertex';
import { generateText } from 'ai';
import fs from 'fs';

const result = await generateText({
  model: vertex('gemini-2.0-flash'),
  messages: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'Extract key information.' },
        {
          type: 'file',
          data: fs.readFileSync('./report.pdf'),
          mediaType: 'application/pdf',
        },
      ],
    },
  ],
});

Embeddings

import { vertex } from '@ai-sdk/google-vertex';
import { embed } from 'ai';

const { embedding } = await embed({
  model: vertex.embeddingModel('text-embedding-005'),
  value: 'Enterprise AI solution',
});

Available Models:

• text-embedding-005 (768 dimensions)

Image Generation

import { vertex } from '@ai-sdk/google-vertex';
import { generateImage } from 'ai';

const { image } = await generateImage({
  model: vertex.image('imagen-3.0-generate-001'),
  prompt: 'Corporate office interior',
  aspectRatio: '16:9',
});

Available Models:

• imagen-3.0-generate-001 - Enterprise image generation

Model Capabilities

Model	Vision	Tools	Structured Output
gemini-2.0-flash	✓	✓	✓
gemini-1.5-pro	✓	✓	✓
gemini-1.5-flash	✓	✓	✓

Resources

• Vertex AI Documentation
• AI SDK Documentation
• Google Cloud Console