Google Drive just got a big AI upgrade with Gemini sidebar image analysis

The Gemini integration in Google Drive has been getting steadily more powerful, with the ability to summarize documents, chat with PDFs, and even understand the content of your videos. But until now, there’s been a big piece of the puzzle missing: your images.

Today, that changes. In a new post on the Workspace Updates blog, Google has announced that Gemini can now answer questions, extract text, and give you summaries about the images stored in your Google Drive.

More than just a picture

This is a massive upgrade to Gemini’s capabilities within Drive, bringing its powerful multimodal understanding directly to your image files. Previously, Gemini could only work with text-based content, but now it can “see” and analyze what’s in your pictures. According to Google, you can now ask Gemini to:

• Extract text from any image.
• Extract information from a receipt or invoice and put it directly into a table.
• Get an AI-generated summary of an image.
• Generate alt text for an image.
• Write a creative story based on an image.

The ability to snap a photo of a receipt, upload it to Drive, and have Gemini instantly pull the key information into a neat table is an absolute game-changer for anyone who deals with expenses.

How to use it and who gets it

Accessing the new feature is simple. When you’re in Google Drive, just double-click on an image to open the previewer, and then click the “Ask Gemini” star button in the top right corner to open the side panel and start your conversation.

For now, the feature is available in English only and works best for text-heavy images and scanned documents like contracts and receipts. It’s currently in a gradual roll-out that started on August 25th for Rapid Release domains and will begin on September 9th for most other users. It’s available to most paid Workspace subscribers, Gemini for Education add-on users, and Google One AI Premium subscribers.

This is another fantastic step in making Google Drive a truly intelligent hub for all your files. The ability to interact with the content of your images makes Gemini an even more powerful and indispensable productivity tool.