You can upload documents, spreadsheets, photos, videos, and more to Gemini Apps to get answers, summaries, and insights about your content.
What you need
- If you’re signed in to a work or school Google Account:
- To upload files from Google Drive, access to apps in Gemini must be enabled by your organization’s Workspace administrator.
- Learn more about using Gemini Apps with a work or school account or how to enable access to apps in Gemini Apps.
- To use this feature, you must be signed in to Gemini Apps. Learn how to sign in to Gemini Apps.
Upload files & code
- On your computer, go to gemini.google.com.
- In the text box at the bottom, enter your question or prompt.
- Click Add files
.
- To upload a supported file from your device: click Files
.
- To add a code folder: click Import Code
Upload folder.
- To add a GitHub repository: click Import Code
and enter the GitHub repository or branch URL. Learn more about adding GitHub repositories.
- To add a supported file from your Google Drive: click Drive
.
- To add files from your Drive, you need to have Gemini Apps Activity on and connect Google Workspace to Gemini Apps. If it’s not connected, you'll get the option to connect it. Learn about your Gemini Apps and Google Workspace data.
- To upload a supported file from your device: click Files
- Click Submit
.
File types & upload limits
- Gemini Apps support most file types.
- Up to 10 files can be uploaded in the same prompt.
- Each video can be up to 2 GB. All other supported file types can be up to 100 MB.
- Total video length can be up to 5 minutes. Upgrade to Google AI Pro or Google AI Ultra to extend total upload length to 1 hour.
- One code folder, or one GitHub repository, with up to 5,000 files and a maximum size of 100 MB, can be added to a chat. Learn more about adding GitHub repositories.
- ZIP files can contain up to 10 files.
Learn more about files you upload
Important: These resources are only for users with a personal account. If you’re using a work or school account, learn more about how your data is protected.
Create a chart based on your data
You can ask the Gemini web app to create a chart based on your uploaded spreadsheet(s), zoom in to explore the chart, and customize the chart for your needs.
Customize a chart
- Below the chart, click Edit
.
- Choose how you want the chart to change. For example, you can edit things like the chart type and labels.
- Click Update.
Learn how to modify responses, export responses, and share your chats from Gemini Apps.
File upload error messages
“You’ve reached your limit for chats with files”There are rolling limits for how much you can upload and analyze files in a period of time. After some time, the limit will reset, and you will be able to upload and analyze files again.
If you would like to upload and analyze more files, try again later or upgrade to Google AI Pro or Google AI Ultra for higher usage limits.If you try to upload a file that is too large, Gemini may provide a response that misses connections or details throughout the content. This is most relevant for prompts that require attention to many details scattered throughout large file(s).
For better results, upload smaller files with less content, or upgrade to Google AI Pro or Google AI Ultra for a larger 1 million token context window.
Important: If you use Deep Think, there is a 192 thousand token window. Learn more about using Deep Think.
If you’re using Gemini Apps with a work or school Google Account, you might get a message that you’ve exceeded the context window for uploading and analyzing files.
What is a context window?
When you upload files to Gemini Apps, it needs to "read" the content to provide useful insights or answers. The context window is like the reading capacity. It determines how much content can be understood together at one time.
What does it mean when my prompt exceeds the context window?
A larger context window allows Gemini to read and comprehend more. For example, with a 1M token context window, Gemini can understand up to 1,500 pages of text or 30,000 lines of code.
If you exceed the context window, this could lead to responses that don’t take into account all the content provided or miss connections or details throughout the content. This is most relevant for prompts that require attention to many details scattered throughout large files.