A new feature is now available to a wide range of users of Claude 3.5 Sonnet — the model can now analyze images in PDF documents. This improvement allows for a better understanding of complex documents with diagrams and charts, which previously could not be fully represented in text format.
Claude can now view images within a PDF, in addition to text.
— Anthropic (@AnthropicAI) November 1, 2024
This helps Claude 3.5 Sonnet more accurately understand complex documents, such as those laden with charts or graphics.
Enable the feature preview: https://t.co/bJ8BjBT6zG. pic.twitter.com/VNSf547ptT
Users can enable the new feature by turning on Visual PDFs in preview mode.
“It’s a big day for PDF capabilities in Claude,” reports Anthropic. The features are already available on the web version and via the Anthropic API. Currently, Claude can analyze graphical components in PDF documents up to one hundred pages long.
For more details on how the new feature works, refer to the documentation at docs.anthropic.com.
