github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-03-22 06:02:06 -05:00
Code Issues 308 Packages Projects Releases 100 Wiki Activity

issue: Open-WebUI sends a lot of requests #5565

New Issue
Closed
opened 2025-11-11 16:24:37 -06:00 by GiteaMirror · 4 comments
GiteaMirror commented 2025-11-11 16:24:37 -06:00
Owner
Copy Link

Originally created by @kekePower on GitHub (Jun 17, 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

0.6.15

Ollama Version (if applicable)

0.9.1

Operating System

Mageia Linux

Browser (if applicable)

Zen

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 provided every relevant configuration, setting, and environment variable used in my setup.
  • I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
  • I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
  • Start with the initial platform/version/OS and dependencies used,
  • Specify exact install/launch/configure commands,
  • List URLs visited, user input (incl. example values/emails/passwords if needed),
  • Describe all options and toggles enabled or changed,
  • Include any files or environmental changes,
  • Identify the expected and actual result at each stage,
  • Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

When I click "Send" I expect it to send the request and get the response.

Actual Behavior

When I click send it

  • requests /v1/api/models
  • requests /v1/chat/completions
  • requests /v1/models
  • requests /v1/chat/completions
  • requests /v1/models
  • requests /v1/chat/completions

This is normally hidden to the user and will, in the worst case, incur extra cost due to requesting more tokens.

Steps to Reproduce

Pull Docker image.
Run Docker image.
podman run -d -p 8080:8080 -e OLLAMA_BASE_URL=http://127.0.0.1:11434 -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:latest

Open site and chat.

Logs & Screenshots

This is for a single request, a single question.

2025/06/17 08:38:08 "GET http://xxxx/v1/models HTTP/1.1" from yyyy:38024 - 200 47371B in 276.362µs
2025/06/17 08:38:27 "POST http://xxxx/v1/chat/completions HTTP/1.1" from yyyy:38038 - 200 7950B in 18.539090039s
2025/06/17 08:38:27 "GET http://xxxx/v1/models HTTP/1.1" from yyyy:44686 - 200 47371B in 194.321µs
2025/06/17 08:38:30 "POST http://xxxx/v1/chat/completions HTTP/1.1" from yyyy:44696 - 200 288B in 2.882482785s
2025/06/17 08:38:30 "GET http://xxxx/v1/models HTTP/1.1" from yyyy:44710 - 200 47371B in 183.491µs
2025/06/17 08:38:31 "POST http://xxxx/v1/chat/completions HTTP/1.1" from yyyy:44714 - 500 134B in 239.86041ms

Additional Information

No response

Originally created by @kekePower on GitHub (Jun 17, 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 0.6.15 ### Ollama Version (if applicable) 0.9.1 ### Operating System Mageia Linux ### Browser (if applicable) Zen ### 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 **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior When I click "Send" I expect it to send the request and get the response. ### Actual Behavior When I click send it - requests /v1/api/models - requests /v1/chat/completions - requests /v1/models - requests /v1/chat/completions - requests /v1/models - requests /v1/chat/completions This is normally hidden to the user and will, in the worst case, incur extra cost due to requesting more tokens. ### Steps to Reproduce Pull Docker image. Run Docker image. podman run -d -p 8080:8080 -e OLLAMA_BASE_URL=http://127.0.0.1:11434 -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:latest Open site and chat. ### Logs & Screenshots This is for a single request, a single question. ``` 2025/06/17 08:38:08 "GET http://xxxx/v1/models HTTP/1.1" from yyyy:38024 - 200 47371B in 276.362µs 2025/06/17 08:38:27 "POST http://xxxx/v1/chat/completions HTTP/1.1" from yyyy:38038 - 200 7950B in 18.539090039s 2025/06/17 08:38:27 "GET http://xxxx/v1/models HTTP/1.1" from yyyy:44686 - 200 47371B in 194.321µs 2025/06/17 08:38:30 "POST http://xxxx/v1/chat/completions HTTP/1.1" from yyyy:44696 - 200 288B in 2.882482785s 2025/06/17 08:38:30 "GET http://xxxx/v1/models HTTP/1.1" from yyyy:44710 - 200 47371B in 183.491µs 2025/06/17 08:38:31 "POST http://xxxx/v1/chat/completions HTTP/1.1" from yyyy:44714 - 500 134B in 239.86041ms ``` ### Additional Information _No response_
GiteaMirror added the bug label 2025-11-11 16:24:37 -06:00
GiteaMirror commented 2025-11-11 16:24:39 -06:00
Author
Owner
Copy Link

@jrkropp commented on GitHub (Jun 17, 2025):

You likely have tasks enabled in settings. These run after your completion is done to generate title, tags, follow up questions etc.. You can either turn them off or choose a lightweight model as your task model.
https:/[openwebui_url]/admin/settings/interface

@jrkropp commented on GitHub (Jun 17, 2025): You likely have tasks enabled in settings. These run after your completion is done to generate title, tags, follow up questions etc.. You can either turn them off or choose a lightweight model as your task model. https:/[openwebui_url]/admin/settings/interface
GiteaMirror commented 2025-11-11 16:24:39 -06:00
Author
Owner
Copy Link

@Classic298 commented on GitHub (Jun 17, 2025):

This is expected and intended behaviour, title generation, tag generation and so forth are separate requests

@Classic298 commented on GitHub (Jun 17, 2025): This is expected and intended behaviour, title generation, tag generation and so forth are separate requests
GiteaMirror commented 2025-11-11 16:24:39 -06:00
Author
Owner
Copy Link

@kekePower commented on GitHub (Jun 17, 2025):

Thanks. It wasn't intuitive and somewhat poorly explained, but I found the settings and disabled them all as a test. This kind of degrades the functionality, so I'll experiment a bit more.

Another question. Why does it check for models all the time? Shouldn't it be using a cached list?
I see a request for models when I refresh the page, when I send a request or when I check the list of models to switch and when I continue a conversation.
These are, imho, unnecessary requests.

@kekePower commented on GitHub (Jun 17, 2025): Thanks. It wasn't intuitive and somewhat poorly explained, but I found the settings and disabled them all as a test. This kind of degrades the functionality, so I'll experiment a bit more. Another question. Why does it check for models all the time? Shouldn't it be using a cached list? I see a request for models when I refresh the page, when I send a request or when I check the list of models to switch and when I continue a conversation. These are, imho, unnecessary requests.
GiteaMirror commented 2025-11-11 16:24:39 -06:00
Author
Owner
Copy Link

@Classic298 commented on GitHub (Jun 17, 2025):

Why should it use a cached list?
Many people use Open Router or OpenAI directly and want to always have the latest version of the available models.
Models get removed, new ones get added, model IDs can change, and so forth

Edit: Or Ollama! Load in a new model, then it should show up immediately. Cached list would not be good here

@Classic298 commented on GitHub (Jun 17, 2025): Why should it use a cached list? Many people use Open Router or OpenAI directly and want to always have the latest version of the available models. Models get removed, new ones get added, model IDs can change, and so forth Edit: Or Ollama! Load in a new model, then it should show up immediately. Cached list would not be good here
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label bug
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#5565
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?