File Attachments

You can attach files to your messages so the AI can read, analyze, and work with their contents.

Attaching files

There are two ways to attach a file:

  • Drag and drop: Drag a file from your computer directly onto the chat input area.
  • Click to browse: Click the attachment icon (paperclip) in the chat input area to open a file picker.

Attached files appear as thumbnails above the message input before you send. You can remove an attachment by clicking the X on its thumbnail.

Supported file types

Magus can extract text from a wide range of file formats:

  • Documents: PDF, Word (.doc, .docx), RTF, EPUB, OpenDocument (.odt)
  • Spreadsheets: Excel (.xls, .xlsx), CSV, OpenDocument (.ods)
  • Presentations: PowerPoint (.ppt, .pptx)
  • Images: JPEG, PNG, GIF, WebP, TIFF, BMP, SVG (text extraction via OCR)
  • Web and data formats: HTML, XML, JSON, YAML, Markdown
  • Plain text: .txt and other text-based files

Size limits

  • Per file: Up to 50 MB per attachment.
  • Per message: Up to 5 files per message.

If a file exceeds the size limit, you’ll see an error message and the file won’t be attached.

What the AI can do with attachments

Once a file is attached and you send your message, the AI has access to the contents. You can ask it to:

  • Summarize a document or extract key points.
  • Answer questions based on the file’s content.
  • Analyze data in a spreadsheet or CSV.
  • Review and explain code files.
  • Describe or edit images (when using a model that supports vision).
  • Compare multiple attached files side by side.

The AI reads the full content of text-based files. For images, it uses vision capabilities to understand and describe what’s in the image.

Files in the conversation

Files you’ve attached are listed in the Files tab of the right panel. You can view and re-reference files from previous messages in the same conversation by clicking on them there.