issue: v0.6.13 update 400: Open WebUI: Server Connection Error with Google AI API #5411

Closed
opened 2025-11-11 16:20:18 -06:00 by GiteaMirror · 1 comment
Owner

Originally created by @VideoFX on GitHub (May 31, 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

v0.6.13

Ollama Version (if applicable)

newest

Operating System

Ubuntu 22.04

Browser (if applicable)

Chrome newest

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

Everything works in v0.6.11 as expected.

Actual Behavior

Update to v0.6.13 is broken, even on fresh install.

Steps to Reproduce

1.) Start with a new install of Ubuntu 22.04, 100% new and updated/upgraded with apt-get.
2.) Install Docker
3.) Run Open WebUI
4.) Enter Google AI URL and key

https://generativelanguage.googleapis.com/v1beta/openai

5.) Successful connection, and models loaded.
6.) ask Hello World in chat window

Logs & Screenshots

Image

Additional Information

This happened after v0.6.12 on old installs, so I wanted to try this in a new environment. The error is still there. I tested this today.

Revert to v0.6.11, and it works.

Originally created by @VideoFX on GitHub (May 31, 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 v0.6.13 ### Ollama Version (if applicable) newest ### Operating System Ubuntu 22.04 ### Browser (if applicable) Chrome newest ### 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 Everything works in v0.6.11 as expected. ### Actual Behavior Update to v0.6.13 is broken, even on fresh install. ### Steps to Reproduce 1.) Start with a new install of Ubuntu 22.04, 100% new and updated/upgraded with apt-get. 2.) Install Docker 3.) Run Open WebUI 4.) Enter Google AI URL and key https://generativelanguage.googleapis.com/v1beta/openai 5.) Successful connection, and models loaded. 6.) ask Hello World in chat window ### Logs & Screenshots ![Image](https://github.com/user-attachments/assets/07583f4a-0f7a-48c6-b9c3-8a5160b25aa5) ### Additional Information This happened after v0.6.12 on old installs, so I wanted to try this in a new environment. The error is still there. I tested this today. Revert to v0.6.11, and it works.
GiteaMirror added the bug label 2025-11-11 16:20:18 -06:00
Author
Owner

@Jorgeruiz97 commented on GitHub (Jun 1, 2025):

This is also being discussed at https://github.com/open-webui/open-webui/discussions/14542. Adding it for reference.

The bug was introduced at v0.6.12.

@Jorgeruiz97 commented on GitHub (Jun 1, 2025): This is also being discussed at https://github.com/open-webui/open-webui/discussions/14542. Adding it for reference. The bug was introduced at v0.6.12.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#5411