[GH-ISSUE #11746] issue: Denial of Service (Chat generations) #16342

Closed
opened 2026-04-19 22:17:19 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @frenzybiscuit on GitHub (Mar 16, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/11746

Check Existing Issues

  • I have searched the existing issues and discussions.
  • I am using the latest version of Open WebUI.

Installation Method

Git Clone

Open WebUI Version

latest

Ollama Version (if applicable)

No response

Operating System

Debian 12

Browser (if applicable)

Firefox

Confirmation

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have listed steps to reproduce the bug in detail.

Expected Behavior

User can only generate one chat at a time

Actual Behavior

User can go through the chat list and click regenerate on every chat.

User can leave the chat while regenerating, go into another chat, regenerate that one and continue onto other chats.

This can in effect create a denial of service for the LLM backend. For local models, this could quickly prevent other people from using your service. For remote models, if your API key can only generate so many concurrent chats at once, this will overwhelm it.

Steps to Reproduce

described above

Logs & Screenshots

none

Additional Information

No response

Originally created by @frenzybiscuit on GitHub (Mar 16, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/11746 ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Git Clone ### Open WebUI Version latest ### Ollama Version (if applicable) _No response_ ### Operating System Debian 12 ### Browser (if applicable) Firefox ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have listed steps to reproduce the bug in detail. ### Expected Behavior User can only generate one chat at a time ### Actual Behavior User can go through the chat list and click regenerate on every chat. User can leave the chat while regenerating, go into another chat, regenerate that one and continue onto other chats. This can in effect create a denial of service for the LLM backend. For local models, this could quickly prevent other people from using your service. For remote models, if your API key can only generate so many concurrent chats at once, this will overwhelm it. ### Steps to Reproduce described above ### Logs & Screenshots none ### Additional Information _No response_
GiteaMirror added the bug label 2026-04-19 22:17:19 -05:00
Author
Owner

@frenzybiscuit commented on GitHub (Mar 16, 2025):

Using OpenAI backends.

<!-- gh-comment-id:2727582323 --> @frenzybiscuit commented on GitHub (Mar 16, 2025): Using OpenAI backends.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#16342