In a notable update to the Files by Google app, Gemini, Google’s advanced AI assistant, now boasts the ability to recognise when a PDF is open on your screen, enabling users to directly query the file’s contents.
According to The Verge, this feature is part of a broader rollout of context-aware capabilities in Gemini, designed to enhance the way users interact with their digital files.
The functionality has begun rolling out to Gemini Advanced subscribers, The Verge reports. When users view a PDF within the Files by Google app, they can summon Gemini and tap a new button labelled “Ask about this PDF.” This option allows users to pose specific questions about the PDF’s contents, similar to how one would engage with a conversational AI like ChatGPT.
This feature significantly improves how users interact with their files. For instance, you could open a PDF–be it a research paper, eBook, or report–and seamlessly ask Gemini, “What’s the summary of this document?” or “Can you explain this section?” The assistant responds with a detailed summary or clarifications, much like having a personal assistant interpret the file for you.
Google had first teased this functionality during its I/O developer conference in May 2024, and it is now becoming available to Gemini Advanced subscribers. While currently limited to this group, the feature is expected to expand to a broader audience in the future.
The PDF recognition capability is part of Google’s efforts to make Gemini more context-aware across various media. Previously, Gemini allowed users to ask questions about web pages and YouTube videos. Now, it can interpret content displayed on a device’s screen, opening up new possibilities for mobile users.
For apps or files that do not yet support Gemini’s context-aware functionality, the assistant can still help by capturing a screenshot of the screen and offering to answer questions based on it. For instance, while reading an article in a web browser or watching a YouTube video, users can tap on “Ask about this screen” to have Gemini analyse the content and respond.
This interactive feature positions Gemini as more than just an assistant; it becomes a highly intuitive tool for navigating digital content across devices.
To access this new functionality, users need a subscription to Gemini Advanced, Google’s premium AI assistant service. While the feature is still being rolled out, it marks a significant advancement in how digital assistants can interpret and interact with content, streamlining information retrieval and daily tasks.
Integrating AI-driven tools like these into widely used apps, such as Files by Google, reflects a growing trend of digital assistants becoming indispensable for productivity and content management. Whether reviewing a report, reading a PDF for work, or navigating complex information, Gemini’s capabilities are designed to make the process faster, more efficient, and interactive.
