mirror of
https://github.com/open-webui/open-webui.git
synced 2026-07-17 08:21:12 -05:00
[GH-ISSUE #17702] feat: Feature Request: Support Direct Video Input for Multimodal Models Instead of Treating as Files #89111
No Assignees
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: github-starred/open-webui#89111
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @EchocCCCC on GitHub (Sep 24, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17702
Check Existing Issues
Problem Description
Currently, when using a multimodal model, I would like to directly import videos so that the model can understand the visuals and content of the video (similar to how images are currently handled — converted to Base64 and attached to the conversation).
However, video files currently seem to be treated as regular files, and the model does not actually interpret the video content — it only sees a file path.
Desired Solution you'd like
This does not match my expectations for multimodal capabilities:
Images: can be converted to Base64 and understood by the model
Audio/Video: currently seem to be unsupported for direct interpretation
Alternatives Considered
No response
Additional Context
No response