Being able to upload files for analysis and summarization can help make your basic chatbot into a much more capable digital assistant. Google announced on Wednesday that the ability to upload files to its Gemini AI is now available on iOS and Android, but only if you have a Gemini Advanced subscription.
File uploads came to the desktop in May, as part of the Gemini 1.5 Pro roll-out. However, if you used Gemini on your mobile device, you’d have to navigate to gemini.google.com in order to use the feature, instead of staying directly in the app. That is no longer the case. Once the app update hits your phone, look for the plus (+) icon in the bottom left corner of the Gemini screen. Tapping on that opens a menu where you can choose the source of the documents you want to upload.
Gemini can work with plain text files (TXT), a variety of document files (DOC, DOCX, PDF, RTF, DOT, DOTX, HWP, HWPX) as well as anything made in Google Docs; tabular data files (CSV, TSV), and spreadsheet files (XLS, XLSX) including spreadsheets created in Google Sheets. Take note that you’ll be able to upload as many as 10 files at a time with each file being as much as 100 MB.
Unfortunately, the ability to upload files remains firmly paywalled and unavailable to free tier users (who are only able to upload images for analysis). You will need a Gemini Advanced subscription to use the newly available feature (both on desktop and on mobile). Gemini Advanced will cost you $20 per month (after the free introductory month) and offers the new 1.5 Pro model with its 1 million token context window, as well as priority access to new features, Gemini integration in Google Worksuite, and 2 TB of storage. You can sign up for Gemini advanced by clicking on the “Try Gemini Advanced!” radio button in the upper right corner of the desktop screen.
Source: 9to5Google
