AI SDK Google Provider Integration

Integrate Google Generative AI (Gemini) models into your application using the Vercel AI SDK's Google provider.

What This Skill Does

This skill guides you through integrating Google's Gemini language models into your TypeScript/JavaScript application using the `@ai-sdk/google` package from Vercel's AI SDK. It supports text generation, streaming responses, and leveraging Google's powerful Gemini models.

Prerequisites

Setup Instructions

1. Install Dependencies

Install the Google provider package and the AI SDK core:

```bash

npm i @ai-sdk/google ai

```

2. Configure API Key

Set your Google AI API key as an environment variable:

```bash

.env.local or .env

GOOGLE_GENERATIVE_AI_API_KEY=your_api_key_here

```

Alternatively, pass it directly when creating the provider instance (not recommended for production).

3. Import and Initialize Provider

Create a provider instance in your code:

```typescript

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

import { generateText } from 'ai';

// Provider automatically uses GOOGLE_GENERATIVE_AI_API_KEY from env

const model = google('gemini-1.5-pro-latest');

```

4. Generate Text

Use the `generateText` function for simple text generation:

```typescript

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

import { generateText } from 'ai';

const { text } = await generateText({

model: google('gemini-1.5-pro-latest'),

prompt: 'Write a vegetarian lasagna recipe for 4 people.',

});

console.log(text);

```

5. Stream Responses (Optional)

For streaming responses in real-time applications:

```typescript

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

import { streamText } from 'ai';

const result = streamText({

model: google('gemini-1.5-flash'),

prompt: 'Explain quantum computing in simple terms.',

});

for await (const chunk of result.textStream) {

process.stdout.write(chunk);

}

```

Available Models

Common Google Gemini models:

Check [Google AI Studio](https://ai.google.dev/models/gemini) for the latest models.

Common Use Cases

**Text Generation:**

```typescript

const { text } = await generateText({

model: google('gemini-1.5-pro-latest'),

prompt: 'Your prompt here',

});

```

**Structured Output:**

```typescript

import { generateObject } from 'ai';

import { z } from 'zod';

const { object } = await generateObject({

model: google('gemini-1.5-pro-latest'),

schema: z.object({

recipe: z.string(),

ingredients: z.array(z.string()),

}),

prompt: 'Create a simple pasta recipe',

});

```

**Multi-turn Conversations:**

```typescript

const { text } = await generateText({

model: google('gemini-1.5-flash'),

messages: [

{ role: 'user', content: 'Hello!' },

{ role: 'assistant', content: 'Hi! How can I help?' },

{ role: 'user', content: 'Tell me a joke.' },

],

});

```

Important Notes

Troubleshooting

**API Key Not Found:**

Ensure `GOOGLE_GENERATIVE_AI_API_KEY` is set in your environment or `.env` file.

**Model Not Found:**

Verify the model name is correct and available in your region.

**Rate Limit Errors:**

Implement retry logic with exponential backoff or reduce request frequency.

Next Steps

After integration, explore:

Resources