Anthropic Introduces PDF Image Understanding With Claude 3.5 Sonnet AI Model

Claude can now understand complex PDFs filled with charts and graphics.

Written by Akash Dutta, Edited by Siddharth Suvarna | Updated: 4 November 2024 16:30 IST

Highlights

The PDF image understanding feature is available in open beta currently
Earlier, Claude could understand the text in PDF files
Claude can also answer queries based on these images

The Claude AI feature is available to all users

Photo Credit: Anthropic

Anthropic released another new artificial intelligence (AI) feature for its chatbot Claude on Friday. The feature, dubbed PDF image understanding, now allows Claude to see and process images embedded within PDF files including charts and graphics. This capability has been added to the recently released Claude 3.5 Sonnet AI model. The company claims that this ability will allow the chatbot to accurately understand complex documents and offer better analysis of the data. The Anthropic application packaging interface (API) also supports PDF inputs. This feature is available in beta.

Anthropic Releases PDF Image Understanding for Claude

In its support documents, Anthropic detailed the new PDF support feature. The image understanding capability in PDF has been added to the Claude 3.5 Sonnet version 20241022, and it can process images in PDF as well as support PDF inputs.

Breaking down the first capability, Claude can now see and process images, charts, and graphics added to a PDF to perform a deeper analysis of the document. Once done, users can ask the AI queries about the particular images and it can answer with relevant information.

Claude AI is Now Available As a Desktop App on Mac and Windows

So far, Claude accepted images as input and could answer queries about them, however, it could not process images attached to a document. With this feature, Anthropic now allows users to get responses about PDFs in greater detail. The feature is likely aimed at the enterprise users of the chatbot who use it to analyse sales and marketing documents as well as other such files.

Claude 3.5 Sonnet now also accepts PDF as an input, which means users can now upload PDF files directly and let users ask queries about them. This brings Claude's capabilities on par with Google's NotebookLM, which is a dedicated platform for PDF and other file types.

Currently, the maximum file size of a PDF uploaded to Claude can be 32MB with a maximum page count of 1,000. Additionally, the chatbot cannot process PDFs which are password-protected or have encryption on them. Anthropic will make the feature available on Amazon Bedrock and Google Vertex AI soon.

For the latest tech news and reviews, follow Gadgets 360 on X, Facebook, WhatsApp, Threads and Google News. For the latest videos on gadgets and tech, subscribe to our YouTube channel. If you want to know everything about top influencers, follow our in-house Who'sThat360 on Instagram and YouTube.