Next.js Pages Router Quickstart

The AI SDK is a powerful Typescript library designed to help developers build AI-powered applications.

In this quickstart tutorial, you'll build a simple AI-chatbot with a streaming user interface. Along the way, you'll learn key concepts and techniques that are fundamental to using the SDK in your own projects.

If you are unfamiliar with the concepts of Prompt Engineering and HTTP Streaming, you can optionally read these documents first.

Prerequisites

To follow this quickstart, you'll need:

• Node.js 18+ and pnpm installed on your local development machine.
• An OpenAI API key.

If you haven't obtained your OpenAI API key, you can do so by signing up on the OpenAI website.

Setup Your Application

Start by creating a new Next.js application. This command will create a new directory named my-ai-app and set up a basic Next.js application inside it.

pnpm create next-app@latest my-ai-app

Navigate to the newly created directory:

cd my-ai-app

Install dependencies

Install ai, @ai-sdk/react, and @ai-sdk/openai, the AI package, AI SDK's React hooks, and AI SDK's OpenAI provider respectively.

pnpm add ai@beta @ai-sdk/react@beta @ai-sdk/openai@beta zod

Configure OpenAI API key

Create a .env.local file in your project root and add your OpenAI API Key. This key is used to authenticate your application with the OpenAI service.

touch .env.local

Edit the .env.local file:

OPENAI_API_KEY=xxxxxxxxx

Replace xxxxxxxxx with your actual OpenAI API key.

Create a Route Handler

Create a Route Handler (app/api/chat/route.ts) and add the following code:

import { openai } from '@ai-sdk/openai';
import { streamText, UIMessage, convertToModelMessages } from 'ai';

// Allow streaming responses up to 30 seconds
export const maxDuration = 30;

export async function POST(req: Request) {
  const { messages }: { messages: UIMessage[] } = await req.json();

  const result = streamText({
    model: openai('gpt-4o'),
    messages: convertToModelMessages(messages),
  });

  return result.toUIMessageStreamResponse();
}

Let's take a look at what is happening in this code:

1. Define an asynchronous POST request handler and extract messages from the body of the request. The messages variable contains a history of the conversation between you and the chatbot and provides the chatbot with the necessary context to make the next generation. The messages are of UIMessage type, which are designed for use in application UI - they contain the entire message history and associated metadata like timestamps.
2. Call streamText, which is imported from the ai package. This function accepts a configuration object that contains a model provider (imported from @ai-sdk/openai) and messages (defined in step 1). You can pass additional settings to further customise the model's behaviour. The messages key expects a ModelMessage[] array. This type is different from UIMessage in that it does not include metadata, such as timestamps or sender information. To convert between these types, we use the convertToModelMessages function, which strips the UI-specific metadata and transforms the UIMessage[] array into the ModelMessage[] format that the model expects.
3. The streamText function returns a StreamTextResult. This result object contains the toUIMessageStreamResponse function which converts the result to a streamed response object.
4. Finally, return the result to the client to stream the response.

This Route Handler creates a POST request endpoint at /api/chat.

Wire up the UI

Now that you have an API route that can query an LLM, it's time to setup your frontend. The AI SDK's UI package abstract the complexity of a chat interface into one hook, useChat.

Update your root page (pages/index.tsx) with the following code to show a list of chat messages and provide a user message input:

import { useChat } from '@ai-sdk/react';
import { useState } from 'react';

export default function Chat() {
  const [input, setInput] = useState('');
  const { messages, sendMessage } = useChat();
  return (
    <div className="flex flex-col w-full max-w-md py-24 mx-auto stretch">
      {messages.map(message => (
        <div key={message.id} className="whitespace-pre-wrap">
          {message.role === 'user' ? 'User: ' : 'AI: '}
          {message.parts.map((part, i) => {
            switch (part.type) {
              case 'text':
                return <div key={`${message.id}-${i}`}>{part.text}</div>;
            }
          })}
        </div>
      ))}

      <form
        onSubmit={e => {
          e.preventDefault();
          sendMessage({ text: input });
          setInput('');
        }}
      >
        <input
          className="fixed dark:bg-zinc-900 bottom-0 w-full max-w-md p-2 mb-8 border border-zinc-300 dark:border-zinc-800 rounded shadow-xl"
          value={input}
          placeholder="Say something..."
          onChange={e => setInput(e.currentTarget.value)}
        />
      </form>
    </div>
  );
}

This page utilizes the useChat hook, which will, by default, use the POST API route you created earlier (/api/chat). The hook provides functions and state for handling user input and form submission. The useChat hook provides multiple utility functions and state variables:

• messages - the current chat messages (an array of objects with id, role, and parts properties).
• sendMessage - a function to send a message to the chat API.

The component uses local state (useState) to manage the input field value, and handles form submission by calling sendMessage with the input text and then clearing the input field.

The LLM's response is accessed through the message parts array. Each message contains an ordered array of parts that represents everything the model generated in its response. These parts can include plain text, reasoning tokens, and more that you will see later. The parts array preserves the sequence of the model's outputs, allowing you to display or process each component in the order it was generated.

Running Your Application

With that, you have built everything you need for your chatbot! To start your application, use the command:

pnpm run dev

Head to your browser and open http://localhost:3000. You should see an input field. Test it out by entering a message and see the AI chatbot respond in real-time! The AI SDK makes it fast and easy to build AI chat interfaces with Next.js.

Enhance Your Chatbot with Tools

While large language models (LLMs) have incredible generation capabilities, they struggle with discrete tasks (e.g. mathematics) and interacting with the outside world (e.g. getting the weather). This is where tools come in.

Tools are actions that an LLM can invoke. The results of these actions can be reported back to the LLM to be considered in the next response.

For example, if a user asks about the current weather, without tools, the model would only be able to provide general information based on its training data. But with a weather tool, it can fetch and provide up-to-date, location-specific weather information.

Update Your Route Handler

Let's start by giving your chatbot a weather tool. Update your Route Handler (app/api/chat/route.ts):

import { openai } from '@ai-sdk/openai';
import { streamText, UIMessage, convertToModelMessages, tool } from 'ai';
import { z } from 'zod';

// Allow streaming responses up to 30 seconds
export const maxDuration = 30;

export async function POST(req: Request) {
  const { messages }: { messages: UIMessage[] } = await req.json();

  const result = streamText({
    model: openai('gpt-4o'),
    messages: convertToModelMessages(messages),
    tools: {
      weather: tool({
        description: 'Get the weather in a location',
        inputSchema: z.object({
          location: z.string().describe('The location to get the weather for'),
        }),
        execute: async ({ location }) => ({
          location,
          temperature: 72 + Math.floor(Math.random() * 21) - 10,
        }),
      }),
    },
  });

  return result.toUIMessageStreamResponse();
}

In this updated code:

1. You import the tool function from the ai package and z from zod for schema validation.

2. You define a tools object with a weather tool. This tool:

   • Has a description that helps the model understand when to use it.
   • Defines inputSchema using a Zod schema, specifying that it requires a location string to execute this tool. The model will attempt to extract this input from the context of the conversation. If it can't, it will ask the user for the missing information.
   • Defines an execute function that simulates getting weather data (in this case, it returns a random temperature). This is an asynchronous function running on the server so you can fetch real data from an external API.

Now your chatbot can "fetch" weather information for any location the user asks about. When the model determines it needs to use the weather tool, it will generate a tool call with the necessary input. The execute function will then be automatically run, and the tool output will be added to the messages as a tool message.

Try asking something like "What's the weather in New York?" and see how the model uses the new tool.

Notice the blank response in the UI? This is because instead of generating a text response, the model generated a tool call. You can access the tool call and subsequent tool result on the client via the tool-weather part of the message.parts array.

Update the UI

To display the tool invocations in your UI, update your pages/index.tsx file:

import { useChat } from '@ai-sdk/react';
import { useState } from 'react';

export default function Chat() {
  const [input, setInput] = useState('');
  const { messages, sendMessage } = useChat();
  return (
    <div className="flex flex-col w-full max-w-md py-24 mx-auto stretch">
      {messages.map(message => (
        <div key={message.id} className="whitespace-pre-wrap">
          {message.role === 'user' ? 'User: ' : 'AI: '}
          {message.parts.map((part, i) => {
            switch (part.type) {
              case 'text':
                return <div key={`${message.id}-${i}`}>{part.text}</div>;
              case 'tool-weather':
                return (
                  <pre key={`${message.id}-${i}`}>
                    {JSON.stringify(part, null, 2)}
                  </pre>
                );
            }
          })}
        </div>
      ))}

      <form
        onSubmit={e => {
          e.preventDefault();
          sendMessage({ text: input });
          setInput('');
        }}
      >
        <input
          className="fixed dark:bg-zinc-900 bottom-0 w-full max-w-md p-2 mb-8 border border-zinc-300 dark:border-zinc-800 rounded shadow-xl"
          value={input}
          placeholder="Say something..."
          onChange={e => setInput(e.currentTarget.value)}
        />
      </form>
    </div>
  );
}

With this change, you're updating the UI to handle different message parts. For text parts, you display the text content as before. For weather tool invocations, you display a JSON representation of the tool call and its result.

Now, when you ask about the weather, you'll see the tool call and its result displayed in your chat interface.

Enabling Multi-Step Tool Calls

You may have noticed that while the tool is now visible in the chat interface, the model isn't using this information to answer your original query. This is because once the model generates a tool call, it has technically completed its generation.

To solve this, you can enable multi-step tool calls using stopWhen. By default, stopWhen is set to stepCountIs(1), which means generation stops after the first step when there are tool results. By changing this condition, you can allow the model to automatically send tool results back to itself to trigger additional generations until your specified stopping condition is met. In this case, you want the model to continue generating so it can use the weather tool results to answer your original question.

Update Your Route Handler

Modify your app/api/chat/route.ts file to include the stopWhen condition:

import { openai } from '@ai-sdk/openai';
import {
  streamText,
  UIMessage,
  convertToModelMessages,
  tool,
  stepCountIs,
} from 'ai';
import { z } from 'zod';

export const maxDuration = 30;

export async function POST(req: Request) {
  const { messages }: { messages: UIMessage[] } = await req.json();

  const result = streamText({
    model: openai('gpt-4o'),
    messages: convertToModelMessages(messages),
    stopWhen: stepCountIs(5),
    tools: {
      weather: tool({
        description: 'Get the weather in a location (fahrenheit)',
        inputSchema: z.object({
          location: z.string().describe('The location to get the weather for'),
        }),
        execute: async ({ location }) => {
          const temperature = Math.round(Math.random() * (90 - 32) + 32);
          return {
            location,
            temperature,
          };
        },
      }),
    },
  });

  return result.toUIMessageStreamResponse();
}

Head back to the browser and ask about the weather in a location. You should now see the model using the weather tool results to answer your question.

By setting stopWhen: stepCountIs(5), you're allowing the model to use up to 5 "steps" for any given generation. This enables more complex interactions and allows the model to gather and process information over several steps if needed. You can see this in action by adding another tool to convert the temperature from Celsius to Fahrenheit.

Add another tool

Update your app/api/chat/route.ts file to add a new tool to convert the temperature from Fahrenheit to Celsius:

import { openai } from '@ai-sdk/openai';
import {
  streamText,
  UIMessage,
  convertToModelMessages,
  tool,
  stepCountIs,
} from 'ai';
import { z } from 'zod';

export const maxDuration = 30;

export async function POST(req: Request) {
  const { messages }: { messages: UIMessage[] } = await req.json();

  const result = streamText({
    model: openai('gpt-4o'),
    messages: convertToModelMessages(messages),
    stopWhen: stepCountIs(5),
    tools: {
      weather: tool({
        description: 'Get the weather in a location (fahrenheit)',
        inputSchema: z.object({
          location: z.string().describe('The location to get the weather for'),
        }),
        execute: async ({ location }) => {
          const temperature = Math.round(Math.random() * (90 - 32) + 32);
          return {
            location,
            temperature,
          };
        },
      }),
      convertFahrenheitToCelsius: tool({
        description: 'Convert a temperature in fahrenheit to celsius',
        inputSchema: z.object({
          temperature: z
            .number()
            .describe('The temperature in fahrenheit to convert'),
        }),
        execute: async ({ temperature }) => {
          const celsius = Math.round((temperature - 32) * (5 / 9));
          return {
            celsius,
          };
        },
      }),
    },
  });

  return result.toUIMessageStreamResponse();
}

Update Your Frontend

Update your pages/index.tsx file to render the new temperature conversion tool:

import { useChat } from '@ai-sdk/react';
import { useState } from 'react';

export default function Chat() {
  const [input, setInput] = useState('');
  const { messages, sendMessage } = useChat();
  return (
    <div className="flex flex-col w-full max-w-md py-24 mx-auto stretch">
      {messages.map(message => (
        <div key={message.id} className="whitespace-pre-wrap">
          {message.role === 'user' ? 'User: ' : 'AI: '}
          {message.parts.map((part, i) => {
            switch (part.type) {
              case 'text':
                return <div key={`${message.id}-${i}`}>{part.text}</div>;
              case 'tool-weather':
              case 'tool-convertFahrenheitToCelsius':
                return (
                  <pre key={`${message.id}-${i}`}>
                    {JSON.stringify(part, null, 2)}
                  </pre>
                );
            }
          })}
        </div>
      ))}

      <form
        onSubmit={e => {
          e.preventDefault();
          sendMessage({ text: input });
          setInput('');
        }}
      >
        <input
          className="fixed dark:bg-zinc-900 bottom-0 w-full max-w-md p-2 mb-8 border border-zinc-300 dark:border-zinc-800 rounded shadow-xl"
          value={input}
          placeholder="Say something..."
          onChange={e => setInput(e.currentTarget.value)}
        />
      </form>
    </div>
  );
}

This update handles the new tool-convertFahrenheitToCelsius part type, displaying the temperature conversion tool calls and results in the UI.

Now, when you ask "What's the weather in New York in celsius?", you should see a more complete interaction:

1. The model will call the weather tool for New York.
2. You'll see the tool output displayed.
3. It will then call the temperature conversion tool to convert the temperature from Fahrenheit to Celsius.
4. The model will then use that information to provide a natural language response about the weather in New York.

This multi-step approach allows the model to gather information and use it to provide more accurate and contextual responses, making your chatbot considerably more useful.

This simple example demonstrates how tools can expand your model's capabilities. You can create more complex tools to integrate with real APIs, databases, or any other external systems, allowing the model to access and process real-world data in real-time. Tools bridge the gap between the model's knowledge cutoff and current information.

Where to Next?

You've built an AI chatbot using the AI SDK! From here, you have several paths to explore:

• To learn more about the AI SDK, read through the documentation.
• If you're interested in diving deeper with guides, check out the RAG (retrieval-augmented generation) and multi-modal chatbot guides.
• To jumpstart your first AI project, explore available templates.