> ## Documentation Index
> Fetch the complete documentation index at: https://www.anything.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Uploads

> Let users upload files to your app. Images, documents, audio, video.

Describe an upload feature and the agent builds it. When a user uploads a file, your app sends it to a cloud storage service and gets back a URL. If you need to display or reference that file again, the agent writes code to save the URL to a [database](/apps/databases).

```
Add a profile picture uploader that saves the URL to /[UsersDB]
```

```
Let users drag and drop PDFs into the page and save them to /[DocumentsDB]
```

```
Add an image upload button that shows a preview after uploading
```

## Supported formats

Images (PNG, JPG, HEIC, GIF, WebP, SVG), PDFs, audio, video, and most common document formats. Files can be up to 10 MB.

## Passing files to AI

Upload a file and pass it to one of Anything's [built-in integrations](/apps/integrations) for processing. Add the integration with a `/` slash command in your prompt.

```
Let users upload photos and use /[GPT-4 Vision] to describe what's in them
```

```
Upload audio files and use /[Audio Transcription] to turn them into text
```

```
Upload a PDF and use /[PDF Parser] to extract the text
```

## Handling large files

The 10 MB limit covers most uploads. If users might try uploading something larger, tell the agent to check the file size and show an error.

```
Show an error if the uploaded file is larger than 5 MB
```

```
Resize uploaded images to a max width of 1200px before saving
```