Multimodal Attachments

Let users send images, audio, video, and documents to the AI alongside their messages.

You have a working CopilotChat and want users to attach files (images, PDFs, audio, video) that the AI can see and respond to. By the end of this guide, your chat will support drag-and-drop file attachments with previews, lightbox viewing, and multimodal AI responses.

Quick start

Add attachments to your CopilotChat component:

page.tsx
import { CopilotChat } from "@copilotkit/react-core/v2";

<CopilotChat
  agentId="my-agent"
  attachments={{ enabled: true }}
/>

That's it. Users can now click the attachment button or drag-and-drop files into the chat. The files are sent as part of the message content to your agent.

Configuration

The attachments prop accepts an AttachmentsConfig object:

<CopilotChat
  attachments={{
    enabled: true,
    // Omit `accept` to allow all file types (default: "*/*").
    // Restrict with a MIME filter if needed:
    accept: "image/*,audio/*,video/*,application/pdf",
    maxSize: 10 * 1024 * 1024,      // 10MB limit (default: 20MB)
  }}
/>
OptionTypeDefaultDescription
enabledbooleannoneEnable file attachments in the chat input.
acceptstring"*/*"MIME type filter. Supports patterns like "image/*", ".pdf,.docx", or comma-separated lists.
maxSizenumber20 * 1024 * 1024Maximum file size in bytes.
maxConcurrentUploadsnumber1How many files upload at the same time. See Upload concurrency.
onUpload(file: File) => AttachmentUploadResult | Promise<...>noneCustom upload handler. See Custom upload handler.
onUploadFailed(error: AttachmentUploadError) => voidnoneCalled when a file fails validation or upload. See Handling upload errors.

Supported file types

Attachments are categorized by modality based on their MIME type:

ModalityMIME typesPreviewAI support
Imageimage/*Thumbnail with lightboxSupported by most vision-capable models (GPT-4o, Claude, etc.)
Audioaudio/*Audio playerModel-dependent
Videovideo/*Thumbnail with play button + lightboxModel-dependent
DocumentEverything elseFile icon + name; PDF and text get lightbox previewSent as file content. Model support varies

Not all models support all modalities. Model support for each file type depends on the model provider. For the details, see your provider's docs. If the agent run fails, the onError callback on CopilotChat receives the error.

Custom upload handler

By default, files are read as base64 and sent inline. For large files or production apps, you'll want to upload to your own storage and pass a URL instead.

onUpload returns an AttachmentUploadResult, a discriminated union with two variants:

<CopilotChat
  attachments={{
    enabled: true,
    onUpload: async (file) => {
      const dataUrl = await new Promise<string>((resolve, reject) => {
        const reader = new FileReader();
        reader.onload = () => resolve(reader.result as string);
        reader.onerror = () => reject(reader.error);
        reader.readAsDataURL(file);
      });
      const base64 = dataUrl.split(",")[1];
      return {
        type: "data",
        value: base64,
        mimeType: file.type,
      };
    },
  }}
/>

Adding metadata

You can attach custom metadata to any upload. It's included in the InputContent part sent to the agent and accessible via metadata on the content part.

onUpload: async (file) => {
  const url = await uploadToStorage(file);
  return {
    type: "url",
    value: url,
    mimeType: file.type,
    metadata: {
      uploadedBy: currentUser.id,
      category: "support-ticket",
    },
  };
},

The filename is always included in metadata automatically. You don't need to add it yourself.

Upload concurrency

When a user attaches several files at once, they upload one at a time by default. Every picked file shows in the attachment queue immediately, whether or not its upload has started.

Set maxConcurrentUploads to upload several together. Raise it when your upload endpoint handles parallel requests:

<CopilotChat
  attachments={{
    enabled: true,
    maxConcurrentUploads: 3, // three files at a time
    onUpload: async (file) => ({ type: "url", value: await uploadToStorage(file), mimeType: file.type }),
  }}
/>

The limit covers every upload in flight, not each batch: if a paste lands while a dropped selection is still uploading, both share the same slots. Infinity lifts the limit entirely.

Above 1, your onUpload handler may be called concurrently, so it must not rely on the previous file having finished.

Handling upload errors

Use onUploadFailed to react when a file is rejected or an upload fails, for example to show a toast:

<CopilotChat
  attachments={{
    enabled: true,
    accept: "image/*",
    maxSize: 5 * 1024 * 1024, // 5MB
    onUploadFailed: (error) => {
      // error.reason: "file-too-large" | "invalid-type" | "upload-failed"
      // error.file: the original File object
      // error.message: human-readable description
      toast.error(error.message);
    },
  }}
/>
ReasonWhen it fires
invalid-typeFile doesn't match the accept filter.
file-too-largeFile exceeds maxSize.
upload-failedThe onUpload handler threw, or the default base64 reader failed.

For errors that happen after the message is sent (e.g., the model doesn't support the file type), use the onError callback on CopilotChat:

<CopilotChat
  attachments={{ enabled: true }}
  onError={(event) => {
    console.error(`[${event.code}]`, event.error.message);
  }}
/>

How it works

When a user attaches files and sends a message, CopilotKit:

  1. Reads each file (via the default base64 reader or your onUpload handler)
  2. Builds an array of InputContent parts: text, plus one part per attachment
  3. Adds the message to the agent with content: [{ type: "text", ... }, { type: "image", source: ... }, ...]
  4. The agent receives the multimodal content via the AG-UI protocol and forwards it to the model

The attachments are part of the standard AG-UI InputContent schema, so any AG-UI-compatible agent (BuiltInAgent, LangGraph, custom) can receive them.

How is this guide?