Google Chrome adds Gemini AI-powered PDF summarization and visual context features

Google is expanding Gemini, its AI assistant, within the Chrome browser. A new "Summarize with Gemini" button in the built‑in PDF viewer lets users generate a concise summary of a PDF and ask follow‑up questions through a side‑panel chat. The feature is currently being tested in Chrome Beta, with no public rollout date announced.

In addition, Gemini can now detect the content that users are viewing on a web page. By automatically reading highlighted text, clicked elements, or visible screen regions, the assistant can answer queries, explain diagrams, interpret images, and compare products without requiring manual copy‑and‑paste or screenshots. This contextual integration is also in testing and aims to streamline workflow directly inside the browser.