github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-07-27 17:04:57 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

issue: Title Generation for chat is triggered every time i send a message. #5037

New Issue
Closed
opened 2025-11-11 16:10:24 -06:00 by GiteaMirror · 0 comments
GiteaMirror commented 2025-11-11 16:10:24 -06:00
Owner
Copy Link
Copy Source

Originally created by @Simi5599 on GitHub (May 5, 2025).

Check Existing Issues

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

Installation Method

Docker

Open WebUI Version

0.6.5

Ollama Version (if applicable)

No response

Operating System

Windows 11

Browser (if applicable)

Firefox 138.0.1

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

The system should call the title generation feature only for the first message.

Actual Behavior

When interacting with a model, title generation is currently triggered for every message sent during the conversation. Specifically:

  • The system invokes the title generation process each time a new message is sent.
  • The model used for this task is the one configured in ADMIN SETTINGS → INTERFACE.

This approach leads to:

  • Excessive token usage, as the title generation model is called redundantly.
  • Resource waste, particularly when long conversations involve frequent back-and-forth messages.

We should restrict title generation to execute only once, specifically during the first message exchange of a conversation. Subsequent messages should bypass this process unless explicitly reinitialized by the user.

Steps to Reproduce

  1. Set a custom model for title generation via ADMIN SETTINGS -> INTERFACE
  2. Use a model

Logs & Screenshots

Sending screenshot now. I am using OpenRouter.

BEFORE THE SWITCH TO A LOCAL MODEL (Title Generation Request Is made for each call):

Image

AFTER THE SWITCH TO A LOCAL MODEL (The request is now made only with the working model):

Image

Additional Information

No response

Originally created by @Simi5599 on GitHub (May 5, 2025). ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version 0.6.5 ### Ollama Version (if applicable) _No response_ ### Operating System Windows 11 ### Browser (if applicable) Firefox 138.0.1 ### 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 The system should call the title generation feature only for the first message. ### Actual Behavior When interacting with a model, title generation is currently triggered for every message sent during the conversation. Specifically: - The system invokes the title generation process each time a new message is sent. - The model used for this task is the one configured in ADMIN SETTINGS → INTERFACE. This approach leads to: - Excessive token usage, as the title generation model is called redundantly. - Resource waste, particularly when long conversations involve frequent back-and-forth messages. We should restrict title generation to execute only once, specifically during the first message exchange of a conversation. Subsequent messages should bypass this process unless explicitly reinitialized by the user. ### Steps to Reproduce 1. Set a custom model for title generation via ADMIN SETTINGS -> INTERFACE 2. Use a model ### Logs & Screenshots Sending screenshot now. I am using OpenRouter. BEFORE THE SWITCH TO A LOCAL MODEL (Title Generation Request Is made for each call): ![Image](https://github.com/user-attachments/assets/6b919760-62c4-403b-9058-394b73cb033f) AFTER THE SWITCH TO A LOCAL MODEL (The request is now made only with the working model): ![Image](https://github.com/user-attachments/assets/f1e93240-702c-4ffe-8fe5-39103672718f) ### Additional Information _No response_
GiteaMirror added the bug label 2025-11-11 16:10:24 -06:00
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 labels bug
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#5037