In a move that dramatically improves usability, Google has announced a significant enhancement to its Gemini AI chatbot: users can now upload up to 10 images or documents at once. This update marks a substantial upgrade from the previous version, where users were limited to a single file per prompt—often a frustrating constraint for those seeking richer, more complex interactions with the chatbot.
The feature, which was rolled out on a Monday update, is now live across all platforms where Gemini is available. Whether you’re accessing Gemini through its web interface or the dedicated Android and iOS apps, you can take advantage of this new functionality. Even better, the feature is supported by all current general-purpose Gemini models, ensuring that a wide range of users can immediately benefit from the change.
Josh Woodward, Vice President of Google Labs and Gemini, shared the news on his official X (formerly Twitter) account. In his announcement, Woodward highlighted the expanded upload capability and invited users to share feedback or suggestions for further enhancements. Google’s approach continues to show a clear commitment to refining its AI tools in line with user needs and expectations.
How It Works: A Streamlined Upload Experience
With the new feature, uploading multiple files is intuitive and efficient. Users can simply tap the plus icon next to the chatbot’s text field to open a file browser or photo gallery. On mobile devices, long-pressing on images or files allows for multiple selections, while on desktop, users can use the familiar Shift + click method. Repeating the process allows users to add more files until the 10-file limit is reached.
If a user tries to exceed this limit, Gemini provides a helpful error message: “Some of your files could not be uploaded because you can only upload 10 attachments at a time.” This ensures that users are clearly informed about usage boundaries without confusion.
Why This Matters: Enhancing Everyday Use
The ability to submit multiple documents in one go is more than just a convenience—it fundamentally changes how users interact with Gemini. Previously, users with complex tasks often had to rely on alternative tools like NotebookLM or manually create “Gems” to handle multiple files. Now, this can be done directly within the Gemini interface, streamlining the process and improving productivity.
This update is especially useful for professionals, students, and researchers who frequently need AI support for summarizing or comparing content across multiple sources. By reducing the friction in the input process, Google is making Gemini a more powerful and accessible tool for a variety of real-world applications.
Part of a Bigger Picture
This change is part of Google’s broader strategy to continually refine and expand the capabilities of its AI platforms. As AI becomes increasingly integrated into our daily digital experiences, usability improvements like these are essential. Not only do they make tools like Gemini more effective, but they also ensure that AI remains approachable and useful to a wider audience.
As the race for AI supremacy heats up, small but impactful updates like this could play a big role in shaping user loyalty and long-term adoption. For Google, the message is clear: Gemini isn’t just about intelligence—it’s about intelligent design.
