Working with files in ChatGPT
Source: OpenAI Blog
Uploading files
ChatGPT allows you to upload and work with files directly in your conversations. This lets you analyze spreadsheets, edit documents, summarize PDFs, or work with images without leaving the chat.
Start a chat with ChatGPT.
Upload your file by opening the tools menu and selecting Add photos or files (supported formats include CSV, XLSX, PDF, DOCX, JPEG, PNG, TXT, and more).
Ask a question or give a task, for example:
- “Summarize the main findings in this report and call out any risks or open questions.”
- “Visualize this sales data by region and highlight the biggest changes month over month.”
- “Rewrite this document to be clearer and more concise, while keeping the same tone.”
- “Extract the key dates and owners from this PDF into a simple table.”
Experiment in chat by requesting specific views (like tables or charts), or download ChatGPT‑generated outputs (such as updated spreadsheets or PDFs).
Using apps
Some versions of ChatGPT let you use apps, which give the model access to third‑party tools so you can bring external context into the conversation.
- Go to Settings → Apps to find an app to connect to.
- Complete the authentication and permissions flow.
- Apps appear in the Tools panel during chats, or you can invoke them with
@or/.
Learn more about available apps (opens in a new window)
Using apps for work (opens in a new window)
Note: For Enterprise workspaces, your organization’s admin controls which apps are available. If you don’t see the option to connect an app, check with your admin. Data accessed through apps is not used to train OpenAI models by default.