mirror of
https://github.com/open-webui/open-webui.git
synced 2026-03-10 07:43:10 -05:00
Slow chat completion for subsequent prompts #4040
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 @vexvec on GitHub (Feb 22, 2025).
Bug Report
Installation Method
k8s (Following docker deployment guideline)
Environment
**Open WebUI Version: 0.5.16
**Ollama (if applicable): 0.5.11
**Operating System: debian
**Browser (if applicable): Chrome, Chromium 132
Confirmation:
Expected Behavior:
A smoth chat experience like directly with ollama console.
Actual Behavior:
Usually the first prompt executes normally, subsequent requests have a significant delay before text is even written.
Description
Bug Summary:
OpenWebUI introduces a significant delay for answering chat prompts after the first response.
Reproduction Details
Steps to Reproduce:
1 .Make a prompt
2. Wait for answer
3. Make another prompt in the same chat
4. Wait minutes until you see the response
Logs and Screenshots
Browser Console Logs:
[Include relevant browser console logs, if applicable]
Docker Container Logs:
[Include relevant Docker container logs, if applicable]
Screenshots/Screen Recordings (if applicable):
[Attach any relevant screenshots to help illustrate the issue]
Additional Information
If I do the same using ollama console chat this delay does not occur.