Google is making its AI-powered Deep Research feature even more versatile

You can now upload your own files to Deep Research in Gemini as well as use Canvas Create to transform reports

May 21, 2025 - 01:10

Google is making its AI-powered Deep Research feature even more versatile

Google is enhancing Deep Research in Gemini with file upload support, allowing users to add their own PDFs and images as sources for its detailed reports.
This feature enables analysis of private documents like prior studies or personal photos to get in-depth, contextualized information and recommendations.
Deep Research is also integrating Canvas Create, enabling users to transform research reports into dynamic formats like interactive web pages and infographics.

AI chatbots like Google Gemini are great at quickly finding answers to your questions, but these answers can sometimes be too short or lack key background info. This is where Deep Research in Gemini comes in handy. It formulates a step-by-step plan to research the answer, often involving reading dozens of web pages to synthesize information from. It then generates a multi-page research report that has all the info you could ever want. Deep Research is a great way to learn about more complex topics that you have little familiarity with, but if you have any documents or images you want it to analyze, you’re out of luck. At least, you were before today.

At its annual Google I/O developer conference, Google announced that file upload support is coming to Deep Research. This allows you to add your own PDFs or images as sources before generating reports or asking follow-up questions. To share a file, simply click the “+” sign and select the file(s) you want to upload.