Google

It is recommended to use the AI SDK Google Generative AI Provider instead of the legacy Google provider.

Vercel AI SDK provides a set of utilities to make it easy to use Google's Generative AI SDK that enables you to build apps using Google Gemini. In this guide, we'll walk through how to use the utilities to create a chat bot and a text completion app.

Guide: Chat Bot

Create a Next.js app

Create a Next.js application and install ai:

pnpm dlx create-next-app my-ai-app
cd my-ai-app
pnpm install ai @google/generative-ai

Add your Google API Key to `.env`

Create a .env file in your project root and add your API Key for the Google AI SDK:

GOOGLE_API_KEY=xxxxxxx

Create a Route Handler

Create a Next.js Route Handler that generates a response to a series of messages via Google's Generative AI SDK, and returns the response as a streaming text response.

For this example, we'll create a route handler at app/api/chat/route.ts that accepts a POST request with a messages array of strings:

import { GoogleGenerativeAI } from '@google/generative-ai';
import { GoogleGenerativeAIStream, Message, StreamingTextResponse } from 'ai';

const genAI = new GoogleGenerativeAI(process.env.GOOGLE_API_KEY || '');

// convert messages from the Vercel AI SDK Format to the format
// that is expected by the Google GenAI SDK
const buildGoogleGenAIPrompt = (messages: Message[]) => ({
  contents: messages
    .filter(message => message.role === 'user' || message.role === 'assistant')
    .map(message => ({
      role: message.role === 'user' ? 'user' : 'model',
      parts: [{ text: message.content }],
    })),
});

export async function POST(req: Request) {
  // Extract the `prompt` from the body of the request
  const { messages } = await req.json();

  const geminiStream = await genAI
    .getGenerativeModel({ model: 'gemini-pro' })
    .generateContentStream(buildGoogleGenAIPrompt(messages));

  // Convert the response into a friendly text-stream
  const stream = GoogleGenerativeAIStream(geminiStream);

  // Respond with the stream
  return new StreamingTextResponse(stream);
}

Vercel AI SDK provides 2 utility helpers to make the above seamless: First, we pass the streaming response we receive from Google's Generative AI SDK to GoogleGenerativeAIStream. This utility class decodes/extracts the text tokens in the response and then re-encodes them properly for simple consumption. We can then pass that new stream directly to StreamingTextResponse. This is another utility class that extends the normal Node/Edge Runtime Response class with the default headers you probably want (hint: 'Content-Type': 'text/plain; charset=utf-8' is already set for you).

Wire up the UI

Create a Client component with a form that we'll use to gather the prompt from the user and then stream back the completion from. By default, the useChat hook will use the POST Route Handler we created above (it defaults to /api/chat). You can override this by passing a api prop to useChat({ api: '...'}).

'use client';

import { useChat } from 'ai/react';

export default function Chat() {
  const { messages, input, handleInputChange, handleSubmit } = useChat();

  return (
    <div>
      {messages.map(m => (
        <div key={m.id}>
          {m.role === 'user' ? 'User: ' : 'AI: '}
          {m.content}
        </div>
      ))}

      <form onSubmit={handleSubmit}>
        <input
          value={input}
          placeholder="Say something..."
          onChange={handleInputChange}
        />
      </form>
    </div>
  );
}

Guide: Text Completion

Use the Completion API

Similar to the Chat Bot example above, we'll create a Next.js Route Handler that generates a text completion via the same Google Generative AI SDK that we'll then stream back to our Next.js. It accepts a POST request with a prompt string:

import { GoogleGenerativeAI } from '@google/generative-ai';
import { GoogleGenerativeAIStream, StreamingTextResponse } from 'ai';

const genAI = new GoogleGenerativeAI(process.env.GOOGLE_API_KEY || '');

export async function POST(req: Request) {
  // Extract the `prompt` from the body of the request
  const { prompt } = await req.json();

  // Ask Google Generative AI for a streaming completion given the prompt
  const response = await genAI
    .getGenerativeModel({ model: 'gemini-pro' })
    .generateContentStream({
      contents: [{ role: 'user', parts: [{ text: prompt }] }],
    });

  // Convert the response into a friendly text-stream
  const stream = GoogleGenerativeAIStream(response);

  // Respond with the stream
  return new StreamingTextResponse(stream);
}

Wire up the UI

We can use the useCompletion hook to make it easy to wire up the UI. By default, the useCompletion hook will use the POST Route Handler we created above (it defaults to /api/completion). You can override this by passing a api prop to useCompletion({ api: '...'}).

'use client';

import { useCompletion } from 'ai/react';

export default function Completion() {
  const {
    completion,
    input,
    stop,
    isLoading,
    handleInputChange,
    handleSubmit,
  } = useCompletion();

  return (
    <div className="mx-auto w-full max-w-md py-24 flex flex-col stretch">
      <form onSubmit={handleSubmit}>
        <label>
          Say something...
          <input
            className="fixed w-full max-w-md bottom-0 border border-gray-300 rounded mb-8 shadow-xl p-2"
            value={input}
            onChange={handleInputChange}
          />
        </label>
        <output>Completion result: {completion}</output>
        <button type="button" onClick={stop}>
          Stop
        </button>
        <button disabled={isLoading} type="submit">
          Send
        </button>
      </form>
    </div>
  );
}

Guide: Save to Database After Completion

It’s common to want to save the result of a completion to a database after streaming it back to the user. The GoogleGenerativeAIStream adapter accepts a couple of optional callbacks that can be used to do this.

export async function POST(req: Request) {
  // ...

  // Convert the response into a friendly text-stream
  const stream = GoogleGenerativeAIStream(response, {
    onStart: async () => {
      // This callback is called when the stream starts
      // You can use this to save the prompt to your database
      await savePromptToDatabase(prompt);
    },
    onToken: async (token: string) => {
      // This callback is called for each token in the stream
      // You can use this to debug the stream or save the tokens to your database
      console.log(token);
    },
    onCompletion: async (completion: string) => {
      // This callback is called when the completion is ready
      // You can use this to save the final completion to your database
      await saveCompletionToDatabase(completion);
    },
  });

  // Respond with the stream
  return new StreamingTextResponse(response);
}