AI

Multi-Modal Chatbot

In this guide, you will build a multi-modal AI-chatbot capable of understanding both images and PDFs.

Multi-modal refers to the ability of the chatbot to understand and generate responses in multiple formats, such as text, images, PDFs, and videos. In this example, we will focus on sending images and PDFs and generating text-based responses.

Different AI providers have varying levels of multi-modal support, for example:

  • OpenAI (GPT-4o): Supports image input
  • Anthropic (Sonnet 3.5): Supports image and PDF input
  • Google (Gemini 2.0): Supports image and PDF input

For a complete list of providers that support both image and PDF inputs, visit the providers documentation.

We'll first build a chatbot capable of generating responses based on an image input using OpenAI, then show how to switch providers to handle PDFs.

Prerequisites

To follow this quickstart, you'll need:

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

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

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

Create Your Application

Start by creating a new Next.js application. This command will create a new directory named multi-modal-chatbot and set up a basic Next.js application inside it.

Be sure to select yes when prompted to use the App Router. If you are looking for the Next.js Pages Router quickstart guide, you can find it here.

pnpm create next-app@latest multi-modal-chatbot

Navigate to the newly created directory:

cd multi-modal-chatbot

Install dependencies

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

The AI SDK is designed to be a unified interface to interact with any large language model. This means that you can change model and providers with just one line of code! Learn more about available providers and building custom providers in the providers section.

pnpm
npm
yarn
pnpm add ai @ai-sdk/react @ai-sdk/openai

Make sure you are using ai version 3.2.27 or higher.

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:

.env.local
OPENAI_API_KEY=xxxxxxxxx

Replace xxxxxxxxx with your actual OpenAI API key.

The AI SDK's OpenAI Provider will default to using the OPENAI_API_KEY environment variable.

Implementation Plan

To build a multi-modal chatbot, you will need to:

  • Create a Route Handler to handle incoming chat messages and generate responses.
  • Wire up the UI to display chat messages, provide a user input, and handle submitting new messages.
  • Add the ability to upload images and attach them alongside the chat messages.

Create a Route Handler

Create a route handler, app/api/chat/route.ts and add the following code:

app/api/chat/route.ts
import { openai } from '@ai-sdk/openai';
import { streamText, Message } from 'ai';


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


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


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


  return result.toDataStreamResponse();
}

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.
  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.
  3. The streamText function returns a StreamTextResult. This result object contains the toDataStreamResponse 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 a Route Handler that can query a large language model (LLM), it's time to setup your frontend. AI SDK UI abstracts the complexity of a chat interface into one hook, useChat.

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

app/page.tsx
'use client';


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


export default function Chat() {
  const { messages, input, handleInputChange, handleSubmit } = useChat();
  return (
    <div className="flex flex-col w-full max-w-md py-24 mx-auto stretch">
      {messages.map(m => (
        <div key={m.id} className="whitespace-pre-wrap">
          {m.role === 'user' ? 'User: ' : 'AI: '}
          {m.content}
        </div>
      ))}


      <form
        onSubmit={handleSubmit}
        className="fixed bottom-0 w-full max-w-md mb-8 border border-gray-300 rounded shadow-xl"
      >
        <input
          className="w-full p-2"
          value={input}
          placeholder="Say something..."
          onChange={handleInputChange}
        />
      </form>
    </div>
  );
}

Make sure you add the "use client" directive to the top of your file. This allows you to add interactivity with Javascript.

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 content properties).
  • input - the current value of the user's input field.
  • handleInputChange and handleSubmit - functions to handle user interactions (typing into the input field and submitting the form, respectively).
  • status - the status of the API request.

Add Image Upload

To make your chatbot multi-modal, let's add the ability to upload and send images to the model. There are two ways to send attachments alongside a message with the useChat hook: by providing a FileList object or a list of URLs to the handleSubmit function. In this guide, you will be using the FileList approach as it does not require any additional setup.

Update your root page (app/page.tsx) with the following code:

app/page.tsx
'use client';


import { useChat } from '@ai-sdk/react';
import { useRef, useState } from 'react';
import Image from 'next/image';


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


  const [files, setFiles] = useState<FileList | undefined>(undefined);
  const fileInputRef = useRef<HTMLInputElement>(null);


  return (
    <div className="flex flex-col w-full max-w-md py-24 mx-auto stretch">
      {messages.map(m => (
        <div key={m.id} className="whitespace-pre-wrap">
          {m.role === 'user' ? 'User: ' : 'AI: '}
          {m.content}
          <div>
            {m?.experimental_attachments
              ?.filter(attachment =>
                attachment?.contentType?.startsWith('image/'),
              )
              .map((attachment, index) => (
                <Image
                  key={`${m.id}-${index}`}
                  src={attachment.url}
                  width={500}
                  height={500}
                  alt={attachment.name ?? `attachment-${index}`}
                />
              ))}
          </div>
        </div>
      ))}


      <form
        className="fixed bottom-0 w-full max-w-md p-2 mb-8 border border-gray-300 rounded shadow-xl space-y-2"
        onSubmit={event => {
          handleSubmit(event, {
            experimental_attachments: files,
          });


          setFiles(undefined);


          if (fileInputRef.current) {
            fileInputRef.current.value = '';
          }
        }}
      >
        <input
          type="file"
          className=""
          onChange={event => {
            if (event.target.files) {
              setFiles(event.target.files);
            }
          }}
          multiple
          ref={fileInputRef}
        />
        <input
          className="w-full p-2"
          value={input}
          placeholder="Say something..."
          onChange={handleInputChange}
        />
      </form>
    </div>
  );
}

In this code, you:

  1. Create state to hold the files and create a ref to the file input field.
  2. Display the "uploaded" files in the UI.
  3. Update the onSubmit function, to call the handleSubmit function manually, passing the the files as an option using the experimental_attachments key.
  4. Add a file input field to the form, including an onChange handler to handle updating the files state.

Running Your Application

With that, you have built everything you need for your multi-modal 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 and a button to upload an image.

Upload an image and ask the model to describe what it sees. Watch as the model's response is streamed back to you!

Working with PDFs

To enable PDF support, you can switch to a provider that handles PDFs like Google's Gemini or Anthropic's Claude. Here's how to modify the code to use Anthropic:

  1. First install the Anthropic provider:
pnpm add @ai-sdk/anthropic
  1. Update your environment variables:
.env.local
OPENAI_API_KEY=xxxxxxxxx
ANTHROPIC_API_KEY=xxxxxxxxx
  1. Modify your route handler:
app/api/chat/route.ts
import { openai } from '@ai-sdk/openai';
import { anthropic } from '@ai-sdk/anthropic';
import { streamText } from 'ai';


export const maxDuration = 30;


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


  // check if user has sent a PDF
  const messagesHavePDF = messages.some(message =>
    message.experimental_attachments?.some(
      a => a.contentType === 'application/pdf',
    ),
  );


  const result = streamText({
    model: messagesHavePDF
      ? anthropic('claude-3-5-sonnet-latest')
      : openai('gpt-4o'),
    messages,
  });


  return result.toDataStreamResponse();
}

Now your chatbot can process both images and PDFs! You automatically route PDF requests to Claude Sonnet 3.5 and image requests to OpenAI's gpt-4o model.

Finally, to display PDFs in your chat interface, update the message rendering code in your frontend to show PDF attachments in an <iframe>:

app/page.tsx
'use client';


import { useChat } from '@ai-sdk/react';
import { useRef, useState } from 'react';
import Image from 'next/image';


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


  const [files, setFiles] = useState<FileList | undefined>(undefined);
  const fileInputRef = useRef<HTMLInputElement>(null);


  return (
    <div className="flex flex-col w-full max-w-md py-24 mx-auto stretch">
      {messages.map(m => (
        <div key={m.id} className="whitespace-pre-wrap">
          {m.role === 'user' ? 'User: ' : 'AI: '}
          {m.content}
          <div>
            {m?.experimental_attachments
              ?.filter(
                attachment =>
                  attachment?.contentType?.startsWith('image/') ||
                  attachment?.contentType?.startsWith('application/pdf'),
              )
              .map((attachment, index) =>
                attachment.contentType?.startsWith('image/') ? (
                  <Image
                    key={`${m.id}-${index}`}
                    src={attachment.url}
                    width={500}
                    height={500}
                    alt={attachment.name ?? `attachment-${index}`}
                  />
                ) : attachment.contentType?.startsWith('application/pdf') ? (
                  <iframe
                    key={`${m.id}-${index}`}
                    src={attachment.url}
                    width={500}
                    height={600}
                    title={attachment.name ?? `attachment-${index}`}
                  />
                ) : null,
              )}
          </div>
        </div>
      ))}


      <form
        className="fixed bottom-0 w-full max-w-md p-2 mb-8 border border-gray-300 rounded shadow-xl space-y-2"
        onSubmit={event => {
          handleSubmit(event, {
            experimental_attachments: files,
          });


          setFiles(undefined);


          if (fileInputRef.current) {
            fileInputRef.current.value = '';
          }
        }}
      >
        <input
          type="file"
          className=""
          onChange={event => {
            if (event.target.files) {
              setFiles(event.target.files);
            }
          }}
          multiple
          ref={fileInputRef}
        />
        <input
          className="w-full p-2"
          value={input}
          placeholder="Say something..."
          onChange={handleInputChange}
        />
      </form>
    </div>
  );
}

Try uploading a PDF and asking questions about its contents.

When switching providers, be sure to check the provider documentation for specific file size limits and supported file types.

Where to Next?

You've built a multi-modal AI chatbot using the AI SDK! Experiment and extend the functionality of this application further by exploring tool calling or introducing more granular control over AI and UI states.

If you are looking to leverage the broader capabilities of LLMs, Vercel AI SDK Core provides a comprehensive set of lower-level tools and APIs that will help you unlock a wider range of AI functionalities beyond the chatbot paradigm.