Mistral

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

Vercel AI SDK provides a set of utilities to make it easy to use Mistral's APIs and models. In this guide, we'll walk through how to use the utilities to create a chat bot and a text completion app.

Guide: Mistral Chatbot

Create a Next.js app

Create a Next.js application and install ai and @mistralai/mistralai, the Vercel AI SDK and Mistral API client respectively.

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

Add your Mistral API Key to `.env`

Create a .env file in your project root and add your Mistral API Key:

MISTRAL_API_KEY=xxxxxxxxx

Create a Route Handler

Create a Next.js Route Handler that we'll use to generate a chat completion via Mistral that we'll then stream back to our Next.js.

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 { MistralStream, StreamingTextResponse } from 'ai';

import MistralClient from '@mistralai/mistralai';

const mistral = new MistralClient(process.env.MISTRAL_API_KEY || '');

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

  const response = mistral.chatStream({
    model: 'mistral-small',
    maxTokens: 1000,
    messages,
  });

  // Convert the response into a friendly text-stream. The Mistral client responses are
  // compatible with the Vercel AI SDK MistralStream adapter.
  const stream = MistralStream(response);

  // 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 Mistral to the MistralStream. This method 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 className="mx-auto w-full max-w-md py-24 flex flex-col stretch">
      {messages.map(m => (
        <div key={m.id} className="whitespace-pre-wrap">
          {m.role === 'user' ? 'User: ' : 'AI: '}
          {m.content}
        </div>
      ))}
      <form onSubmit={handleSubmit}>
        <input
          className="fixed bottom-0 w-full max-w-md p-2 mb-8 border border-gray-300 rounded shadow-xl"
          value={input}
          placeholder="Say something..."
          onChange={handleInputChange}
        />
      </form>
    </div>
  );
}

Guide: Text Completion

Use the Completion API

Similar to the Chatbot example above, we'll create a Next.js Route Handler that generates a text completion via the Mistral api that we'll then stream back to our Next.js. It accepts a POST request with a prompt string:

import MistralClient from '@mistralai/mistralai';
import { MistralStream, StreamingTextResponse } from 'ai';

const mistral = new MistralClient(process.env.MISTRAL_API_KEY || '');

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

  // Ask Mistral for a streaming completion given the prompt
  const response = mistral.chatStream({
    model: 'mistral-small',
    maxTokens: 1000,
    messages: [{ role: 'user', content: prompt }],
  });

  // Convert the response into a friendly text-stream
  const stream = MistralStream(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,
    error,
  } = useCompletion({
    api: '/api/completion',
  });
  return (
    <div className="mx-auto w-full max-w-md py-24 flex flex-col stretch">
      <h4 className="text-xl font-bold text-gray-900 md:text-xl pb-4">
        useCompletion Example
      </h4>
      {error && (
        <div className="fixed top-0 left-0 w-full p-4 text-center bg-red-500 text-white">
          {error.message}
        </div>
      )}
      <output>{completion}</output>
      <form
        onSubmit={handleSubmit}
        className="fixed w-full max-w-xl bottom-0 mb-8 items-stretch flex"
      >
        <input
          className="border border-gray-300 rounded m-2 shadow-xl p-2 flex-grow"
          value={input}
          placeholder="Say something..."
          onChange={handleInputChange}
        />
        <button
          disabled={isLoading}
          type="submit"
          className="inline-block bg-gray-100 hover:bg-gray-300 text-gray-700 font-semibold hover:text-white py-2 px-4 border border-gray-300 hover:border-transparent rounded m-2 disabled:opacity-50"
        >
          Send
        </button>
        <button
          disabled={!isLoading}
          type="button"
          onClick={stop}
          className="inline-block bg-gray-100 hover:bg-gray-300 text-gray-700 font-semibold hover:text-white py-2 px-4 border border-gray-300 hover:border-transparent rounded m-2 disabled:opacity-50"
        >
          Stop
        </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 MistralStream 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 = MistralStream(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 stream completes
      // You can use this to save the final completion to your database
      await saveCompletionToDatabase(completion);
    },
  });
  // Respond with the stream
  return new StreamingTextResponse(stream);
}