Replies: 5 comments
-
Thank you so much for reaching out! Currently we only support uploading images and text files at the beginning of a chat. We have it on our plan to support arbitrary file upload during execution (it would be only a Change in the react frontend mostly), if you'd like to help in making this contribution I'm more than happy to guide you. Otherwise, I'll let you know once we implement this. There are no real blockers to get this working. |
Beta Was this translation helpful? Give feedback.
-
Really love the direction Magentic UI is heading — clean, thoughtful, and very brand-aware. As someone building a food-focused concept called Checker breakfast Menu, strong UI systems like this are incredibly valuable, especially when visual storytelling is at the core of the brand. For a food experience that's centered around bold, crave able menus and aesthetic-first recipe drops, having a design language that balances vibe and usability is huge. I’ve been exploring lightweight systems like this to shape content and presentation, especially for mobile-heavy audiences coming from social. |
Beta Was this translation helpful? Give feedback.
-
It would mostly be backend code rather than agent orchestration in addition to minimal frontend changes. |
Beta Was this translation helpful? Give feedback.
-
Good news! The latest release 0.1.0 supports arbitrary file uploads, please try it out and let us know what you think! |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Hi team, first of all — amazing project.
I’m experimenting with Magentic-UI locally via Docker and Azure OpenAI (GPT-4o), and I’m wondering if it would be possible (or advisable) to support file uploads during an active chat session — e.g., by dragging a file directly into the chat interface, and having FileSurfer or another agent immediately use or summarize it.
This would unlock a lot of real-world use cases where users want to drop in PDFs, .txt files or images while talking to the bot.
Is there a recommended way to implement this or would it require modifications to the agent orchestration and frontend React code?
Thanks in advance!
Beta Was this translation helpful? Give feedback.
All reactions