Google Enhances Gemini AI with PDF Interaction and Advanced Thinking Features

Gemini : Google Enhances Gemini AI with PDF Interaction and Advanced Thinking Features

Google’s virtual AI assistant has received an exciting update: a new screen recognition feature makes Gemini even more helpful. Announced in May at Google’s developer conference, this feature is now available. As reported by sources like Android Police, the latest version of the Files by Google app allows users to ask questions about a PDF while viewing it. Previously, Gemini assisted users with features like “Questions about this screen” and “Questions about this video,” enabling them to scan YouTube videos. Now, with the latest rollout, this capability extends to PDFs, allowing users to summarize lengthy documents and quickly review multiple files.

To use this new AI feature, devices must run on Android 15, have a Gemini Advanced subscription, and set Gemini as the default assistant.

Gemini eases the workload for PDFs by offering competition to other AIs like ChatGPT. The chatbot is continuously developed and can quickly find and summarize information from Gmail and Google Drive, generate images in seconds, and use text, voice commands, photos, and the camera for assistance.

The “Questions about this PDF” update in the Google Files app simplifies working with long and complex documents. Users can not only summarize the content but also ask specific questions and get answers or create new content based on the PDF. Additionally, the feature allows combining PDF files with other documents to merge information.

Google also introduced a new AI model from the Gemini family for users with access to Google AI Studio or direct API connection: Gemini 2.0 Flash Thinking Experimental, known as Gemini 2.0 Flash-Thinking. This “experimental model” is designed to undergo a “thinking process” as part of its response. The paths of thoughts are verifiable in the response window for Gemini users, marked as experimental thoughts. This aims to provide the AI with stronger reasoning abilities than the base model Gemini 2.0 Flash and avoid errors.

Google’s new AI search has faced some challenges. However, the continuous development of features like these shows Google’s commitment to enhancing AI capabilities and user experience.

Stay updated on software and development news by subscribing to newsletters. Ensure you provide a valid email address to complete the subscription process.