I have searched the existing issues and discussions.
Problem Description
Currently, when editing a previous message in a chat thread, there is no way to attach or upload a new file alongside the edited input. This limits the ability to fully revise a prompt if the updated version also depends on a supplementary file—for example, uploading a new CSV, PDF, or image for the model to reference within the same context.
This seems to not be possible with any of the LLM Interfaces be it Anthropic, OpenAI etc. and I really can not understand why.
Desired Solution you'd like
I'd like to see support for attaching a new file when editing a previous message inside a chat thread. Ideally:
The user could click “Edit” on a previous message
Add new or updated text
And also drag/drop or select a new file to be uploaded as part of the same edit
This would allow replacing past prompts and files in one cohesive step
Alternatives Considered
Currently, the only alternatives are:
Follow up prompt
a. Edit the message first;
b. Then, in a new message, upload the required file and reference the edited text;
c. This creates disjointed context and lacks cohesion, especially if the goal is to re-run an earlier message with updated content + an updated file.
Recreate (only similar) history
a. New chat with same prompts
b. OR rerun the previous prompt to be able to upload files from a "new" response
These workarounds both do not lead to exactly the desired outcome and cost needless extra computing resources
Additional Context
Other AI UIs also currently lack file support in edit mode.
Being one of the most extensible and community-driven platforms, Open WebUI could be the first interface to implement this much needed enhancement.
Thanks again for all the fantastic work on this project!
Originally created by @riendril on GitHub (Jun 2, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14596
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
### Problem Description
Currently, when editing a previous message in a chat thread, there is no way to attach or upload a new file alongside the edited input. This limits the ability to fully revise a prompt if the updated version also depends on a supplementary file—for example, uploading a new CSV, PDF, or image for the model to reference within the same context.
This seems to not be possible with any of the LLM Interfaces be it Anthropic, OpenAI etc. and I really can not understand why.
### Desired Solution you'd like
I'd like to see support for attaching a new file when editing a previous message inside a chat thread. Ideally:
- The user could click “Edit” on a previous message
- Add new or updated text
- And also drag/drop or select a new file to be uploaded as part of the same edit
This would allow replacing past prompts and files in one cohesive step
### Alternatives Considered
Currently, the only alternatives are:
1. Follow up prompt
a. Edit the message first;
b. Then, in a new message, upload the required file and reference the edited text;
c. This creates disjointed context and lacks cohesion, especially if the goal is to re-run an earlier message with updated content + an updated file.
2. Recreate (only similar) history
a. New chat with same prompts
b. OR rerun the previous prompt to be able to upload files from a "new" response
These workarounds both do not lead to exactly the desired outcome and cost needless extra computing resources
### Additional Context
Other AI UIs also currently lack file support in edit mode.
Being one of the most extensible and community-driven platforms, Open WebUI could be the first interface to implement this much needed enhancement.
Thanks again for all the fantastic work on this project!
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @riendril on GitHub (Jun 2, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14596
Check Existing Issues
Problem Description
Currently, when editing a previous message in a chat thread, there is no way to attach or upload a new file alongside the edited input. This limits the ability to fully revise a prompt if the updated version also depends on a supplementary file—for example, uploading a new CSV, PDF, or image for the model to reference within the same context.
This seems to not be possible with any of the LLM Interfaces be it Anthropic, OpenAI etc. and I really can not understand why.
Desired Solution you'd like
I'd like to see support for attaching a new file when editing a previous message inside a chat thread. Ideally:
This would allow replacing past prompts and files in one cohesive step
Alternatives Considered
Currently, the only alternatives are:
a. Edit the message first;
b. Then, in a new message, upload the required file and reference the edited text;
c. This creates disjointed context and lacks cohesion, especially if the goal is to re-run an earlier message with updated content + an updated file.
a. New chat with same prompts
b. OR rerun the previous prompt to be able to upload files from a "new" response
These workarounds both do not lead to exactly the desired outcome and cost needless extra computing resources
Additional Context
Other AI UIs also currently lack file support in edit mode.
Being one of the most extensible and community-driven platforms, Open WebUI could be the first interface to implement this much needed enhancement.
Thanks again for all the fantastic work on this project!