I have searched for any existing and/or related issues.
I have searched for any existing and/or related discussions.
I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
I am using the latest version of Open WebUI.
Installation Method
Git Clone
Open WebUI Version
0.7.2
Ollama Version (if applicable)
0.13.5
Operating System
Ubuntu 24.04.3
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
I should see the response from the model on the screen after the model generates its response.
Actual Behavior
After upgrade from 0.6.28 to 0.7.2 when I send a chat prompt to any installed locally installed model I do not see the response on the screen unless I refresh the page. There are no console errors. I am not using Docker. All python and NPM packages were updated. This does not happen with v0.6.28, responses appear reasonably quick using a basic prompt of "say hello". I am running it on localhost, not a remote server. No add-ons were installed, only Open WebUI out of the box, default install. I've tried deepseek-coder:33b and qwen3-coder:30b from Hugging Face. I'm using nVidia 3090 with 24GB VRAM.
Steps to Reproduce
Install v0.7.2 and run it. Note that I am not using Docker, I installed manually and run it from a shell.
Open Firefox (I'm using the latest v147.01) and go to the open webui page
Select a model and send a simple chat text, wait for response.
No response comes after several minutes ( I waited as long and 5 minutes to be sure) using a simple prompt such as "say hello".
Refresh the page, the model's response appears.
Logs & Screenshots
None
Additional Information
No response
Originally created by @NTShop on GitHub (Jan 20, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20824
### 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 have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
- [x] I am using the latest version of Open WebUI.
### Installation Method
Git Clone
### Open WebUI Version
0.7.2
### Ollama Version (if applicable)
0.13.5
### Operating System
Ubuntu 24.04.3
### 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
I should see the response from the model on the screen after the model generates its response.
### Actual Behavior
After upgrade from 0.6.28 to 0.7.2 when I send a chat prompt to any installed locally installed model I do not see the response on the screen unless I refresh the page. There are no console errors. I am not using Docker. All python and NPM packages were updated. This does not happen with v0.6.28, responses appear reasonably quick using a basic prompt of "say hello". I am running it on localhost, not a remote server. No add-ons were installed, only Open WebUI out of the box, default install. I've tried deepseek-coder:33b and qwen3-coder:30b from Hugging Face. I'm using nVidia 3090 with 24GB VRAM.
### Steps to Reproduce
Install v0.7.2 and run it. Note that I am not using Docker, I installed manually and run it from a shell.
Open Firefox (I'm using the latest v147.01) and go to the open webui page
Select a model and send a simple chat text, wait for response.
No response comes after several minutes ( I waited as long and 5 minutes to be sure) using a simple prompt such as "say hello".
Refresh the page, the model's response appears.
### Logs & Screenshots
None
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-04-25 09:00:47 -05:00
@owui-terminator[bot] commented on GitHub (Jan 20, 2026):
🔍Similar Issues Found
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
#19103issue: no response from the model when ask in "channels" by silenceroom • Nov 11, 2025 • bug
#20361Issue: Large-scale model setting-related functionality fails. by shentong0722 • Jan 04, 2026 • bug
#19615issue: [TEST] Models Not Available to Users by westbrook-ai • Nov 30, 2025 • bug
#19610issue: Models not appearing for non-admin users by westbrook-ai • Nov 30, 2025 • bug
#19925issue: Model responses stop after web searches by tm-coder-484 • Dec 13, 2025 • bug
Show 5 more related issues
#20059issue: Chat response is not working by navilg • Dec 20, 2025 • bug
#19711issue: Editing function for models broken by skleffmann • Dec 03, 2025 • bug
#19899issue: openrouter Models not showing up in the model selection list. by AZComputerSolutions • Dec 12, 2025 • bug
#20286issue: Responses are duplicated for thinking models when streaming is enabled. by JadenJSJ • Dec 31, 2025 • bug
#19728issue: Blank model page when adding new or editing existing after upgrade by Skaythe • Dec 03, 2025 • bug
💡Tips:
If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
If you found a solution in any of these issues, please share it here to help others
This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
<!-- gh-comment-id:3774291601 -->
@owui-terminator[bot] commented on GitHub (Jan 20, 2026):
🔍 **Similar Issues Found**
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
1. [#19103](https://github.com/open-webui/open-webui/issues/19103) **issue: no response from the model when ask in "channels"**
*by silenceroom • Nov 11, 2025 • `bug`*
2. [#20361](https://github.com/open-webui/open-webui/issues/20361) **Issue: Large-scale model setting-related functionality fails.**
*by shentong0722 • Jan 04, 2026 • `bug`*
3. [#19615](https://github.com/open-webui/open-webui/issues/19615) **issue: [TEST] Models Not Available to Users**
*by westbrook-ai • Nov 30, 2025 • `bug`*
4. [#19610](https://github.com/open-webui/open-webui/issues/19610) **issue: Models not appearing for non-admin users**
*by westbrook-ai • Nov 30, 2025 • `bug`*
5. [#19925](https://github.com/open-webui/open-webui/issues/19925) **issue: Model responses stop after web searches**
*by tm-coder-484 • Dec 13, 2025 • `bug`*
<details>
<summary>Show 5 more related issues</summary>
6. [#20059](https://github.com/open-webui/open-webui/issues/20059) **issue: Chat response is not working**
*by navilg • Dec 20, 2025 • `bug`*
7. [#19711](https://github.com/open-webui/open-webui/issues/19711) **issue: Editing function for models broken**
*by skleffmann • Dec 03, 2025 • `bug`*
8. [#19899](https://github.com/open-webui/open-webui/issues/19899) **issue: openrouter Models not showing up in the model selection list.**
*by AZComputerSolutions • Dec 12, 2025 • `bug`*
9. [#20286](https://github.com/open-webui/open-webui/issues/20286) **issue: Responses are duplicated for thinking models when streaming is enabled.**
*by JadenJSJ • Dec 31, 2025 • `bug`*
10. [#19728](https://github.com/open-webui/open-webui/issues/19728) **issue: Blank model page when adding new or editing existing after upgrade**
*by Skaythe • Dec 03, 2025 • `bug`*
</details>
---
💡 **Tips:**
- If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
- If you found a solution in any of these issues, please share it here to help others
*This comment was generated automatically by a bot.* Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
I am unable to reproduce the reported issue. More information is warranted.
<!-- gh-comment-id:3781820090 -->
@silentoplayz commented on GitHub (Jan 22, 2026):
I am unable to reproduce the reported issue. More information is warranted.
Copy the latest open-webui git code over the top of my existing code
npm install --force
pip install -U virtualenv
pip install -r requirements.txt -U
Then I started Open WebUI. Next, open the page in Firefox. Select model deepseek-r1:32b. Enter a chat prompt of "say hello". Waited. While waiting here's what I see in the shell console:
This is the only error in the browser console log:
10:40:59.455 Uncaught (in promise) Channels are not enabled Sidebar.svelte:374:9
Here's the response in the websocket via the browser inspector, as you can see the model responded, but the response does not appear in the browser:
42["events",{"chat_id":"921b6e39-395b-41f1-97d4-20a5ffa3089d","message_id":"72a6c2f6-9942-4fcb-8214-3958ccf0c5dd","data":{"type":"chat:completion","data":{"content":"Hello! How can I assist you with your programming or computer"}}}]
Note that I tried the same thing using Chromium browser, the same problem occurs.
Any advice on how to resolve this issue?
<!-- gh-comment-id:3785471185 -->
@NTShop commented on GitHub (Jan 22, 2026):
Here's what I did to upgrade:
- Copy the latest open-webui git code over the top of my existing code
- npm install --force
- pip install -U virtualenv
- pip install -r requirements.txt -U
Then I started Open WebUI. Next, open the page in Firefox. Select model deepseek-r1:32b. Enter a chat prompt of "say hello". Waited. While waiting here's what I see in the shell console:
2026-01-22 10:39:11.239 | INFO | open_webui.routers.ollama:get_all_models:331 - get_all_models()
2026-01-22 10:39:11.479 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "GET /api/models HTTP/1.1" 200
2026-01-22 10:39:15.122 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "POST /api/v1/chats/new HTTP/1.1" 200
2026-01-22 10:39:15.180 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-22 10:39:15.205 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "GET /api/v1/folders/ HTTP/1.1" 200
2026-01-22 10:39:15.236 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "POST /api/v1/chats/52665aef-4f78-41b7-8895-01abc212ac34 HTTP/1.1" 200
2026-01-22 10:39:15.311 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-22 10:39:15.367 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "GET /api/v1/folders/ HTTP/1.1" 200
2026-01-22 10:39:15.368 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52718 - "POST /api/chat/completions HTTP/1.1" 200
2026-01-22 10:39:15.382 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-22 10:39:15.406 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "GET /api/v1/folders/ HTTP/1.1" 200
This is the only error in the browser console log:
10:40:59.455 Uncaught (in promise) Channels are not enabled Sidebar.svelte:374:9
Here's the response in the websocket via the browser inspector, as you can see the model responded, but the response does not appear in the browser:
42["events",{"chat_id":"921b6e39-395b-41f1-97d4-20a5ffa3089d","message_id":"72a6c2f6-9942-4fcb-8214-3958ccf0c5dd","data":{"type":"chat:completion","data":{"content":"Hello! How can I assist you with your programming or computer"}}}]
Note that I tried the same thing using Chromium browser, the same problem occurs.
Any advice on how to resolve this issue?
sounds like websocket issue misconfiguration - or on reverse proxy if it's used
<!-- gh-comment-id:3785520366 -->
@Classic298 commented on GitHub (Jan 22, 2026):
Unable to reproduce here as well
sounds like websocket issue misconfiguration - or on reverse proxy if it's used
I resolved the problem by doing a completely clean install instead of copying the latest code over the top of the previous code. You can close this ticket. Thanks!
<!-- gh-comment-id:3785661430 -->
@NTShop commented on GitHub (Jan 22, 2026):
I resolved the problem by doing a completely clean install instead of copying the latest code over the top of the previous code. You can close this ticket. Thanks!
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @NTShop on GitHub (Jan 20, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20824
Check Existing Issues
Installation Method
Git Clone
Open WebUI Version
0.7.2
Ollama Version (if applicable)
0.13.5
Operating System
Ubuntu 24.04.3
Browser (if applicable)
Firefox
Confirmation
README.md.Expected Behavior
I should see the response from the model on the screen after the model generates its response.
Actual Behavior
After upgrade from 0.6.28 to 0.7.2 when I send a chat prompt to any installed locally installed model I do not see the response on the screen unless I refresh the page. There are no console errors. I am not using Docker. All python and NPM packages were updated. This does not happen with v0.6.28, responses appear reasonably quick using a basic prompt of "say hello". I am running it on localhost, not a remote server. No add-ons were installed, only Open WebUI out of the box, default install. I've tried deepseek-coder:33b and qwen3-coder:30b from Hugging Face. I'm using nVidia 3090 with 24GB VRAM.
Steps to Reproduce
Install v0.7.2 and run it. Note that I am not using Docker, I installed manually and run it from a shell.
Open Firefox (I'm using the latest v147.01) and go to the open webui page
Select a model and send a simple chat text, wait for response.
No response comes after several minutes ( I waited as long and 5 minutes to be sure) using a simple prompt such as "say hello".
Refresh the page, the model's response appears.
Logs & Screenshots
None
Additional Information
No response
@owui-terminator[bot] commented on GitHub (Jan 20, 2026):
🔍 Similar Issues Found
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
#19103 issue: no response from the model when ask in "channels"
by silenceroom • Nov 11, 2025 •
bug#20361 Issue: Large-scale model setting-related functionality fails.
by shentong0722 • Jan 04, 2026 •
bug#19615 issue: [TEST] Models Not Available to Users
by westbrook-ai • Nov 30, 2025 •
bug#19610 issue: Models not appearing for non-admin users
by westbrook-ai • Nov 30, 2025 •
bug#19925 issue: Model responses stop after web searches
by tm-coder-484 • Dec 13, 2025 •
bugShow 5 more related issues
#20059 issue: Chat response is not working
by navilg • Dec 20, 2025 •
bug#19711 issue: Editing function for models broken
by skleffmann • Dec 03, 2025 •
bug#19899 issue: openrouter Models not showing up in the model selection list.
by AZComputerSolutions • Dec 12, 2025 •
bug#20286 issue: Responses are duplicated for thinking models when streaming is enabled.
by JadenJSJ • Dec 31, 2025 •
bug#19728 issue: Blank model page when adding new or editing existing after upgrade
by Skaythe • Dec 03, 2025 •
bug💡 Tips:
This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
@tjbck commented on GitHub (Jan 22, 2026):
@silentoplayz @micahdbak able to reproduce?
@silentoplayz commented on GitHub (Jan 22, 2026):
I am unable to reproduce the reported issue. More information is warranted.
@micahdbak commented on GitHub (Jan 22, 2026):
I am also unable to reproduce.
@NTShop commented on GitHub (Jan 22, 2026):
Here's what I did to upgrade:
Then I started Open WebUI. Next, open the page in Firefox. Select model deepseek-r1:32b. Enter a chat prompt of "say hello". Waited. While waiting here's what I see in the shell console:
2026-01-22 10:39:11.239 | INFO | open_webui.routers.ollama:get_all_models:331 - get_all_models()
2026-01-22 10:39:11.479 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "GET /api/models HTTP/1.1" 200
2026-01-22 10:39:15.122 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "POST /api/v1/chats/new HTTP/1.1" 200
2026-01-22 10:39:15.180 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-22 10:39:15.205 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "GET /api/v1/folders/ HTTP/1.1" 200
2026-01-22 10:39:15.236 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "POST /api/v1/chats/52665aef-4f78-41b7-8895-01abc212ac34 HTTP/1.1" 200
2026-01-22 10:39:15.311 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-22 10:39:15.367 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "GET /api/v1/folders/ HTTP/1.1" 200
2026-01-22 10:39:15.368 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52718 - "POST /api/chat/completions HTTP/1.1" 200
2026-01-22 10:39:15.382 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-22 10:39:15.406 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 127.0.0.1:52706 - "GET /api/v1/folders/ HTTP/1.1" 200
This is the only error in the browser console log:
10:40:59.455 Uncaught (in promise) Channels are not enabled Sidebar.svelte:374:9
Here's the response in the websocket via the browser inspector, as you can see the model responded, but the response does not appear in the browser:
42["events",{"chat_id":"921b6e39-395b-41f1-97d4-20a5ffa3089d","message_id":"72a6c2f6-9942-4fcb-8214-3958ccf0c5dd","data":{"type":"chat:completion","data":{"content":"Hello! How can I assist you with your programming or computer"}}}]
Note that I tried the same thing using Chromium browser, the same problem occurs.
Any advice on how to resolve this issue?
@Classic298 commented on GitHub (Jan 22, 2026):
Unable to reproduce here as well
sounds like websocket issue misconfiguration - or on reverse proxy if it's used
@NTShop commented on GitHub (Jan 22, 2026):
I resolved the problem by doing a completely clean install instead of copying the latest code over the top of the previous code. You can close this ticket. Thanks!