Chat with PDFs

Some language models like Anthropic's Claude Sonnet 3.5 and Google's Gemini 2.0 can understand PDFs and respond to questions about their contents. In this example, we'll show you how to build a chat interface that accepts PDF uploads.

This example requires a provider that supports PDFs, such as Anthropic's Claude 3.7, Google's Gemini 2.5, or OpenAI's GPT-4.1. Check the provider documentation for up-to-date support information.

Implementation

Server

Create a route handler that will use Anthropic's Claude model to process messages and PDFs:

app/api/chat/route.ts

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

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();
}

Client

Create a chat interface that allows uploading PDFs alongside messages:

app/page.tsx

'use client';

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

async function convertFilesToDataURLs(
  files: FileList,
): Promise<
  { type: 'file'; filename: string; mediaType: string; url: string }[]
> {
  return Promise.all(
    Array.from(files).map(
      file =>
        new Promise<{
          type: 'file';
          filename: string;
          mediaType: string;
          url: string;
        }>((resolve, reject) => {
          const reader = new FileReader();
          reader.onload = () => {
            resolve({
              type: 'file',
              filename: file.name,
              mediaType: file.type,
              url: reader.result as string, // Data URL
            });
          };
          reader.onerror = reject;
          reader.readAsDataURL(file);
        }),
    ),
  );
}

export default function Chat() {
  const [input, setInput] = useState('');

  const { messages, sendMessage } = useChat({
    transport: new DefaultChatTransport({
      api: '/api/chat',
    }),
  });

  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(message => (
        <div key={message.id} className="whitespace-pre-wrap">
          {message.role === 'user' ? 'User: ' : 'AI: '}

          {message.parts.map(part => {
            if (part.type === 'text') {
              return <div key={`${message.id}-text`}>{part.text}</div>;
            }
          })}

          <div></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={async event => {
          event.preventDefault();

          const fileParts =
            files && files.length > 0
              ? await convertFilesToDataURLs(files)
              : [];

          sendMessage({
            role: 'user',
            parts: [{ type: 'text', text: input }, ...fileParts],
          });

          setFiles(undefined);
          setInput('');

          if (fileInputRef.current) {
            fileInputRef.current.value = '';
          }
        }}
      >
        <input
          type="file"
          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={event => {
            setInput(event.target.value);
          }}
        />
      </form>
    </div>
  );
}

The code uses the useChat hook which handles the file upload and message streaming. The experimental_attachments option allows you to send files alongside messages.

Make sure to set up your environment variables with your Anthropic API key:

.env.local

ANTHROPIC_API_KEY=xxxxxxxxx

Now you can upload PDFs and ask questions about their contents. The LLM will analyze the PDF and provide relevant responses based on the document's content.