mirror of
https://github.com/open-webui/open-webui.git
synced 2026-08-03 20:02:57 -05:00
Open webui cant use o1-model #2107
No Assignees
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: github-starred/open-webui#2107
Reference in New Issue
Block a user
Originally created by @123hi123 on GitHub (Sep 18, 2024).
Bug Report
Installation Method
I installed Open WebUI using Docker(GPU version) by pulling the official Docker image and running it according to the provided documentation.
Environment
Confirmation:
Expected Behavior
I expect to be able to use the
o1-modelwithin Open WebUI seamlessly, allowing for model loading and inference without any errors.Actual Behavior
When attempting to use the
o1-modelin Open WebUI, the system fails to recognize the model and displays an error message. The model fails to load, rendering the related functionalities unusable.Description
Bug Summary:
Unable to use the
o1-modelin Open WebUI as the system does not recognize or load the model, causing related features to fail.Reproduction Details
Steps to Reproduce:
Pull and run the Open WebUI Docker image using the following commands:
Place the
o1-modelin the designated models directory within the Docker container.Navigate to the models management page in Open WebUI.
Attempt to add the
o1-model.Observe that the system displays an error message and fails to load the model.
Logs and Screenshots
Browser Console Logs:
Docker Container Logs:
Screenshots/Screen Recordings (if applicable):
Additional Information
I have verified that the
o1-modelfiles are correctly placed in the models directory and that other models are functioning correctly within Open WebUI. The issue only occurs when attempting to use theo1-model. I suspect that the problem might be related to the model file format or version incompatibility.@TianzeWang commented on GitHub (Sep 18, 2024):
Likewise. Same issue.
@crzroot commented on GitHub (Sep 19, 2024):
Yes, I am too
@bahuzh commented on GitHub (Sep 19, 2024):
Unsupported value: 'stream' does not support true with this model. Only the default (false) value is supported.
https://platform.openai.com/docs/guides/reasoning/beta-limitations
@123hi123 commented on GitHub (Sep 19, 2024):
I see so can we shut down the stream mode manually?
@fangyuan99 commented on GitHub (Sep 19, 2024):
The same need
@tjbck commented on GitHub (Sep 19, 2024):
Stream Chat Response toggle option has been added to Settings > Interface in dev!
@123hi123 commented on GitHub (Sep 19, 2024):
what version you are
my show below and i try close the most likey one but still not work 'Fluidly stream large external response chunks'
@fangyuan99 commented on GitHub (Sep 19, 2024):
His should be a development version, not yet release
@123hi123 commented on GitHub (Sep 19, 2024):
ok but is can i think add this to workplace will be better fulfill way
just a little suggestion
@hxt365 commented on GitHub (Jan 16, 2025):
o1 model still can't not use stream, needed to disable stream response for this specific model
@123hi123 commented on GitHub (Jan 16, 2025):
Ya , now the o1 works will in my owu
If you turn off the stream the o1 will work nice in o1 series