[Help](https://revise.io/help)›PDF Scanner

# PDF Scanner

## High Quality PDF Content Extraction

Revise can import PDF documents using multi-modal LLMs. Unlike traditional PDF text extraction, this approach actually "reads" your PDF like a human would, preserving formatting, tables, and document structure with high accuracy.

### How To Import PDFs

Click on theImportbutton in the header to choose a PDF file to import.

Please be patient. The content extraction process can take a while, especially for complex PDFs with a lot of content. When the extraction is finished, Revise will show you the final, completely editable document!

Note: PDF import is currently limited to documents 20 pages or less, and using this feature requires a free account.

### What Gets Preserved

- Text formatting - Bold, italic, underline, and other text styles
- Headings - Document hierarchy and heading levels
- Tables - Full table structure with rows and columns
- Lists - Bulleted and numbered lists
- Code blocks - Preserves code formatting when detected

### Limitations

- Images - Embedded images in PDFs are not currently imported (only the text content)
- Complex layouts - Multi-column layouts or unusual formatting may be simplified
- Large PDFs - Documents over 20 pages will be truncated to the first 50 pages

### Other Import Methods

Revise also supports importing Word documents (.docx), Markdown (.md), and plain text (.txt) files. These file formats are parsed much more quickly.