github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-05-23 18:41:28 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #8190] Context Length seems to be ignored in 0.5.2 but worked fine in 0.4.8 #85773

New Issue
Closed
opened 2026-05-15 10:21:33 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-15 10:21:33 -05:00
Owner
Copy Link

Originally created by @nikow on GitHub (Dec 29, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/8190

Originally assigned to: @tjbck on GitHub.

Installation Method

[Describe the method you used to install the project, e.g., git clone, Docker, pip, etc.]
I am using ghcr.io/open-webui/open-webui docker image. The problem is with main version which is 0.5.2, but it was not there with 0.4.8.

Environment

  • Open WebUI Version: 0.5.2 bug exists, but 0.4.8 worked fine

  • Ollama (if applicable): 0.5.4

  • Operating System: Docker container living on Fedora

  • Browser (if applicable): Google Chrome Version 131.0.6778.204, Firefox 132.0.1

Confirmation:

  • [ X] I have read and followed all the instructions provided in the README.md.
  • [X ] I am on the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • [X ] I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below.

Expected Behavior:

The answer gets into account context_length set by me so my AI answers are more consistent, even when slower.

Actual Behavior:

The answers are blazing fast, but lose details from previous messages quickly.

Description

Bug Summary:
When i put my context_length manually to be 32768 it seems to be ignored with new version. It makes my Single User Dungeons with AI less consistent, because it forgets details faster.

Reproduction Details

Steps to Reproduce:

  1. Start new chat with mistral-nemo:12b. It does not matter if i am using local or remote image with ollama.
  2. Go to Controls, click on Context Length and type manually value 32768.
  3. Ask AI to generate a story adventure and choose name for a character.

Additional Information

In previous version AI needed 2 minutes and 30 seconds to answer my prompts now it's instant. The problem is that it was able to keep details from my prompts for 5-7 messages and now it loses them quickly. I tested it with CPU only ollama version on my laptop and with GPU (RTX4070) version of Ollama on Windows.

Originally created by @nikow on GitHub (Dec 29, 2024). Original GitHub issue: https://github.com/open-webui/open-webui/issues/8190 Originally assigned to: @tjbck on GitHub. ## Installation Method [Describe the method you used to install the project, e.g., git clone, Docker, pip, etc.] I am using ghcr.io/open-webui/open-webui docker image. The problem is with main version which is 0.5.2, but it was not there with 0.4.8. ## Environment - **Open WebUI Version:** 0.5.2 bug exists, but 0.4.8 worked fine - **Ollama (if applicable):** 0.5.4 - **Operating System:** Docker container living on Fedora - **Browser (if applicable):** Google Chrome Version 131.0.6778.204, Firefox 132.0.1 **Confirmation:** - [ X] I have read and followed all the instructions provided in the README.md. - [X ] I am on the latest version of both Open WebUI and Ollama. - [ ] I have included the browser console logs. - [ ] I have included the Docker container logs. - [X ] I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below. ## Expected Behavior: The answer gets into account context_length set by me so my AI answers are more consistent, even when slower. ## Actual Behavior: The answers are blazing fast, but lose details from previous messages quickly. ## Description **Bug Summary:** When i put my context_length manually to be 32768 it seems to be ignored with new version. It makes my Single User Dungeons with AI less consistent, because it forgets details faster. ## Reproduction Details **Steps to Reproduce:** 1. Start new chat with mistral-nemo:12b. It does not matter if i am using local or remote image with ollama. 3. Go to Controls, click on Context Length and type manually value 32768. 4. Ask AI to generate a story adventure and choose name for a character. ## Additional Information In previous version AI needed 2 minutes and 30 seconds to answer my prompts now it's instant. The problem is that it was able to keep details from my prompts for 5-7 messages and now it loses them quickly. I tested it with CPU only ollama version on my laptop and with GPU (RTX4070) version of Ollama on Windows.
GiteaMirror commented 2026-05-15 10:21:37 -05:00
Author
Owner
Copy Link

@tjbck commented on GitHub (Dec 30, 2024):

Good catch! Fixed on dev and will be released with 0.5.3 shortly!

<!-- gh-comment-id:2564886166 --> @tjbck commented on GitHub (Dec 30, 2024): Good catch! Fixed on dev and will be released with 0.5.3 shortly!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#85773
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?