Image and PDF OCR support was added in version 3.3.5, making it easy to extract text, generate captions, and create alt text for accessibility.
PDF Support
The AI Assistant can read and interpret PDF files attached to your documents. What you can do with PDFs:- Generate summaries of entire documents
- Ask questions about the content
- Extract key points or insights
- Pull out specific information
- Research papers and articles
- Reports and whitepapers
- Documentation and manuals
- Meeting notes and presentations
Image Support
The AI Assistant works especially well with images and provides fast results for visual content.Supported image formats
- PNG
- JPG
- JPEG
- GIF
- WEBP
What you can do with images
- Generate captions – Create descriptive captions for your images
- Get summaries – Understand what the image shows
- Create detailed descriptions – Generate thorough interpretations
- Improve accessibility – Generate alt text for screen readers
- Extract text – Pull text from screenshots or photos of documents
- Documentation and guides
- Meeting whiteboards and diagrams
- Screenshots of UI or designs
- Charts and graphs
- Accessibility compliance (alt text generation)
Using OCR features
The Assistant will process the content and provide results instantly.
Code blocks
In addition to images and PDFs, the AI Assistant can also help with code blocks:- Explain what code does
- Help debug issues
- Clarify logic or structure
- Suggest improvements
Tips for best results
For images:- Use clear, high-resolution images when possible
- Ensure text in images is legible
- Crop out unnecessary content for more focused results
- Smaller PDFs process faster
- Well-formatted PDFs with clear text work best
- Consider splitting very large PDFs into sections
- Include context about what the code should do
- Specify the programming language if not obvious
- Ask specific questions for better answers