[GH-ISSUE #16493] issue: gpt5 - [Object Object] error - docker deployment - on portainer - older models work as expected #104923

New Issue

2026-05-18T02:44:15-05:00

GiteaMirror commented

2026-05-18 02:44:15 -05:00

Originally created by @javapapo on GitHub (Aug 11, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16493

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

ghcr.io/open-webui/open-webui:v0.6.22@sha256:6c8e6aa1d7fa3e71ea0d01f1b52a63757ca837ab6268c52c7db55d9981b0f363

Ollama Version (if applicable)

0.11.4

Operating System

Ubuntu 22.04

Browser (if applicable)

Firefox

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

Selecting gpt5 on a new chat - throws Object-Object error on the chat., Gpt4 and older work as expected

Actual Behavior

Gpt5 seems not to work?

Steps to Reproduce

The installation is a vanilla docker-compose one, on portainer. OpenWebui works as expected with previous OpenAI models, the new GPT5 does not.

Logs & Screenshots

Additional Information

No response

Originally created by @javapapo on GitHub (Aug 11, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/16493 ### 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 ghcr.io/open-webui/open-webui:v0.6.22@sha256:6c8e6aa1d7fa3e71ea0d01f1b52a63757ca837ab6268c52c7db55d9981b0f363 ### Ollama Version (if applicable) 0.11.4 ### Operating System Ubuntu 22.04 ### Browser (if applicable) Firefox ### 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 Selecting gpt5 on a new chat - throws Object-Object error on the chat., Gpt4 and older work as expected ### Actual Behavior Gpt5 seems not to work? ### Steps to Reproduce The installation is a vanilla docker-compose one, on portainer. OpenWebui works as expected with previous OpenAI models, the new GPT5 does not. ### Logs & Screenshots <img width="1210" height="304" alt="Image" src="https://github.com/user-attachments/assets/2d47044c-60ae-425c-ba7d-88f4fa944343" /> <img width="1173" height="811" alt="Image" src="https://github.com/user-attachments/assets/9cd60e8b-a1e9-4ebc-ae37-f68825dc0878" /> ### Additional Information _No response_

GiteaMirror added the bug label 2026-05-18 02:44:15 -05:00

GiteaMirror closed this issue

2026-05-18 02:44:16 -05:00

GiteaMirror commented

2026-05-18 02:44:18 -05:00

@DevInsilicon commented on GitHub (Aug 11, 2025):

Same issue here

@DevInsilicon commented on GitHub (Aug 11, 2025): Same issue here

GiteaMirror commented

2026-05-18 02:44:18 -05:00

@tjbck commented on GitHub (Aug 13, 2025):

Unable to reproduce from our end, however we do get this error message:

@tjbck commented on GitHub (Aug 13, 2025): Unable to reproduce from our end, however we do get this error message: <img width="1108" height="316" alt="Image" src="https://github.com/user-attachments/assets/780eadda-6858-4c72-b882-e6f1dc8a4c86" />

Sign in to join this conversation.

Branches Tags

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#104923