Google has added another useful feature to the Gemini side panel in Google Drive. The generative AI chatbot can now analyze and extract valuable data from images uploaded to your drive storage.
For the uninitiated, it"s been more than a year since the Gemini side panel landed on Google Drive and other Workspace apps. You can already use the side panel to summarize documents, deal with PDFs, more recently, ask questions about video files. The Gemini side panel can also take natural language commands and move files into folders.
The latest addition lets you throw prompts and ask questions about what"s present in an image. You can ask the chatbot to summarize an image, generate alternate text, extract text written from the image, or write a story about it. For instance, you can ask Gemini to fetch data from a restaurant bill and present it in a table.
Google notes that the feature works best for images with heavy text and documents, such as receipts, invoices, and contracts. Its rollout to eligible users has begun, and it will take a few weeks to complete. You can access the Gemini side panel by clicking on the "Ask Gemini" button in the top-right corner of the screen after opening an image.
Gemini"s image analysis support in Google Drive will be available to different Workspace tiers, including Business Standard/Plus, Enterprise Standard/Plus, Google One AI Premium, and those who have purchased Gemini add-ons. Note that image support is currently available only in English.
This adds to the stream of new features and changes Google has introduced in Drive in recent months. Google Drive now lets you edit uploaded videos directly in a browser, displays thumbnail previews in videos, shows summaries for file changes, allows you to ask questions about specific files, and features a redesigned user interface in its desktop app.