issue: Ubuntu 24.04 docker / SSL WRONG_VERSION_NUMBER , not able to read models, AMD 780M ROCm #6521

New Issue

2025-11-11T16:58:23-06:00

GiteaMirror commented

2025-11-11 16:58:23 -06:00

Originally created by @reywang18 on GitHub (Sep 27, 2025).

Check Existing Issues

I have searched for any existing and/or related issues.
I have searched for any existing and/or related discussions.
I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

0.6.31

Ollama Version (if applicable)

0.11.10

Operating System

Ubuntu 24.04

Browser (if applicable)

local Chrome

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

From $ docker logs ID, noticed 2 most important errors.

Exception: External Error: {'message': 'Missing bearer authentication in header', 'type': 'invalid_request_error', 'param': None, 'code': None}
2025-09-27 20:24:42.411 | ERROR | open_webui.routers.ollama:send_get_request:106 - Connection error: Cannot connect to host 192.168.0.2:11434 ssl:default [[SSL: WRONG_VERSION_NUMBER] wrong version number (_ssl.c:1016)]

In my env,
~/docker$ env | grep OLL
OLLAMA_MODELS=/opt/ollama_models
OLLAMA_HOST=0.0.0.0
OLLAMA_DEBUG=1

$ ifconfig -a

enp2s0: flags=4163<UP,BROADCAST,RUNNING,MULTICAST> mtu 1500
inet 192.168.0.2 netmask 255.255.255.0 broadcast 192.168.0.255
ether 58:47:ca:74:2a:f5 txqueuelen 1000 (Ethernet)
RX packets 6302 bytes 814134 (814.1 KB)
RX errors 0 dropped 0 overruns 0 frame 0
TX packets 3811 bytes 489292 (489.2 KB)
TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0

So my issue is somwhow SSL prevents to read models.

Actual Behavior

Can't load models.

Steps to Reproduce

This is for AMD 780M GPU, ROCm enable.

docker AMD open webUI startup ROCm
$ docker pull ghcr.io/open-webui/open-webui:main

$ docker run -d -p 8080:8080 --name open-webui --device=/dev/kfd --device=/dev/dri ghcr.io/open-webui/open-webui:main

Logs & Screenshots

NA

Additional Information

NA

Originally created by @reywang18 on GitHub (Sep 27, 2025). ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version 0.6.31 ### Ollama Version (if applicable) 0.11.10 ### Operating System Ubuntu 24.04 ### Browser (if applicable) local Chrome ### 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 From $ docker logs ID, noticed 2 most important errors. Exception: External Error: {'message': 'Missing bearer authentication in header', 'type': 'invalid_request_error', 'param': None, 'code': None} 2025-09-27 20:24:42.411 | ERROR | open_webui.routers.ollama:send_get_request:106 - Connection error: Cannot connect to host 192.168.0.2:11434 ssl:default [[SSL: WRONG_VERSION_NUMBER] wrong version number (_ssl.c:1016)] In my env, ~/docker$ env | grep OLL OLLAMA_MODELS=/opt/ollama_models OLLAMA_HOST=0.0.0.0 OLLAMA_DEBUG=1 $ ifconfig -a enp2s0: flags=4163<UP,BROADCAST,RUNNING,MULTICAST> mtu 1500 **inet 192.168.0.2** netmask 255.255.255.0 broadcast 192.168.0.255 ether 58:47:ca:74:2a:f5 txqueuelen 1000 (Ethernet) RX packets 6302 bytes 814134 (814.1 KB) RX errors 0 dropped 0 overruns 0 frame 0 TX packets 3811 bytes 489292 (489.2 KB) TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0 So my issue is somwhow SSL prevents to read models. ### Actual Behavior Can't load models. ### Steps to Reproduce This is for AMD 780M GPU, ROCm enable. docker AMD open webUI startup ROCm $ docker pull ghcr.io/open-webui/open-webui:main $ docker run -d -p 8080:8080 --name open-webui --device=/dev/kfd --device=/dev/dri ghcr.io/open-webui/open-webui:main ### Logs & Screenshots NA ### Additional Information NA

GiteaMirror added the bug label 2025-11-11 16:58:23 -06:00

GiteaMirror closed this issue

2025-11-11 16:58:23 -06:00

GiteaMirror referenced this issue

2025-11-11 18:03:24 -06:00

[PR #6521] [MERGED] enh: include base model id in feedback metadata #8694

GiteaMirror referenced this issue

2026-04-20 03:47:24 -05:00

[PR #6521] [MERGED] enh: include base model id in feedback metadata #21898

GiteaMirror referenced this issue

2026-04-25 10:57:37 -05:00

[PR #6521] [MERGED] enh: include base model id in feedback metadata #37528