I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Docker
Open WebUI Version
v0.6.22 - v0.6.25
Ollama Version (if applicable)
No response
Operating System
Ubuntu 22.04
Browser (if applicable)
Chrome, Brave, Edge
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
Choose a follow-up prompt
Actual Behavior
Follow-up prompts rarely get appended to chat
Steps to Reproduce
I am uncertain of how to recreate the issue ... maybe disabling all Ollama endpoints in admin settings/connections
I was hoping a newer version would clear up the intermittent problem.
I am testing LM Studio as an openai connection and the logs show the follow-up prompts get generated, but they rarely appear in the chat session no matter the browser [Chrome, Brave, Edge].
Logs & Screenshots
LM Studio log:
2025-08-22 12:14:14 [DEBUG]
Received request: POST to /v1/chat/completions with body {
"model": "qwen/qwen3-4b-2507",
"messages": [
{
"role": "user",
"content": "### Task:\nSuggest 3-5 relevant follow-up questions... ...re! 👋 How can I assist you today?\n</chat_history>"
}
],
"stream": false
}
2025-08-22 12:14:14 [INFO]
[LM STUDIO SERVER] Running chat completion on conversation with 1 messages.
___ useless log data removed from here ____
2025-08-22 12:14:17 [INFO]
[qwen/qwen3-4b-2507] Generated prediction: {
"id": "chatcmpl-ddzmv5q8eya48y6ln116jg",
"object": "chat.completion",
"created": 1755879254,
"model": "qwen/qwen3-4b-2507",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "[\n "What are some common mistakes people make when starting a new project?",\n "Can you give me examples of how to set realistic goals?",\n "How can I stay motivated when progress feels slow?",\n "What tools or resources do you recommend for project planning?"\n]",
"reasoning_content": "",
"tool_calls": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 262,
"completion_tokens": 57,
"total_tokens": 319
},
"stats": {},
"system_fingerprint": "qwen/qwen3-4b-2507"
}
Browser console log:
Failed to load resource: the server responded with a status of 500 ()
All other generators work as expected.
Follow Up is enabled.
Originally created by @cma2t3r on GitHub (Aug 22, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16834
### 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
v0.6.22 - v0.6.25
### Ollama Version (if applicable)
_No response_
### Operating System
Ubuntu 22.04
### Browser (if applicable)
Chrome, Brave, Edge
### 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
Choose a follow-up prompt
### Actual Behavior
Follow-up prompts rarely get appended to chat
### Steps to Reproduce
I am uncertain of how to recreate the issue ... maybe disabling all Ollama endpoints in admin settings/connections
I was hoping a newer version would clear up the intermittent problem.
I am testing LM Studio as an openai connection and the logs show the follow-up prompts get generated, but they rarely appear in the chat session no matter the browser [Chrome, Brave, Edge].
### Logs & Screenshots
<img width="1036" height="747" alt="Image" src="https://github.com/user-attachments/assets/7c5ffe05-6fa3-4d14-aed3-be3602301737" />
LM Studio log:
2025-08-22 12:14:14 [DEBUG]
Received request: POST to /v1/chat/completions with body {
"model": "qwen/qwen3-4b-2507",
"messages": [
{
"role": "user",
"content": "### Task:\nSuggest 3-5 relevant follow-up questions... <Truncated in logs> ...re! 👋 How can I assist you today?\n</chat_history>"
}
],
"stream": false
}
2025-08-22 12:14:14 [INFO]
[LM STUDIO SERVER] Running chat completion on conversation with 1 messages.
___ useless log data removed from here ____
2025-08-22 12:14:17 [INFO]
[qwen/qwen3-4b-2507] Generated prediction: {
"id": "chatcmpl-ddzmv5q8eya48y6ln116jg",
"object": "chat.completion",
"created": 1755879254,
"model": "qwen/qwen3-4b-2507",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "[\n \"What are some common mistakes people make when starting a new project?\",\n \"Can you give me examples of how to set realistic goals?\",\n \"How can I stay motivated when progress feels slow?\",\n \"What tools or resources do you recommend for project planning?\"\n]",
"reasoning_content": "",
"tool_calls": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 262,
"completion_tokens": 57,
"total_tokens": 319
},
"stats": {},
"system_fingerprint": "qwen/qwen3-4b-2507"
}
Browser console log:
Failed to load resource: the server responded with a status of 500 ()
index.ts:189
Object
detail
:
"WebUI could not connect to Ollama"
[[Prototype]]
:
Object
### Additional Information
<img width="1035" height="393" alt="Image" src="https://github.com/user-attachments/assets/d614dfc2-2b4b-43d1-8c80-d0aa15beb62f" />
All other generators work as expected.
Follow Up is enabled.
GiteaMirror
added the bug label 2026-04-25 07:29:55 -05:00
Enabling an Ollama endpoint in admin settings/connections gets rid of the JS/AJAX error in the browser console, but still no follow-up prompts appended to chat; and the follow-up prompts aren't always generated, took multiple retries to get a follow-up to appear in the LMS log.
LM Studio log:
2025-08-22 13:16:51 [DEBUG]
Received request: POST to /v1/chat/completions with body {
"model": "qwen/qwen3-4b-2507",
"messages": [
{
"role": "user",
"content": "### Task:\nSuggest 3-5 relevant follow-up questions... ... make this as helpful as possible!\n</chat_history>"
}
],
"stream": false
}
2025-08-22 13:16:51 [INFO]
[LM STUDIO SERVER] Running chat completion on conversation with 1 messages.
___ useless log data removed from here ___
2025-08-22 13:16:54 [INFO]
[qwen/qwen3-4b-2507] Generated prediction: {
"id": "chatcmpl-zjkhylkn80bgnvun84g0bs",
"object": "chat.completion",
"created": 1755883011,
"model": "qwen/qwen3-4b-2507",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "[\n "What are some common challenges people face when starting a new project?",\n "Can you give examples of successful projects that followed a similar approach?",\n "How can I get started with setting clear goals for my project?",\n "What tools or resources would you recommend for tracking progress?"\n]",
"reasoning_content": "",
"tool_calls": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 270,
"completion_tokens": 61,
"total_tokens": 331
},
"stats": {},
"system_fingerprint": "qwen/qwen3-4b-2507"
}
<!-- gh-comment-id:3215082518 -->
@cma2t3r commented on GitHub (Aug 22, 2025):
<img width="1038" height="593" alt="Image" src="https://github.com/user-attachments/assets/e3b6f8ed-3731-4f22-b63a-65526c02cc2b" />
Enabling an Ollama endpoint in admin settings/connections gets rid of the JS/AJAX error in the browser console, but still no follow-up prompts appended to chat; and the follow-up prompts aren't always generated, took multiple retries to get a follow-up to appear in the LMS log.
LM Studio log:
2025-08-22 13:16:51 [DEBUG]
Received request: POST to /v1/chat/completions with body {
"model": "qwen/qwen3-4b-2507",
"messages": [
{
"role": "user",
"content": "### Task:\nSuggest 3-5 relevant follow-up questions... <Truncated in logs> ... make this as helpful as possible!\n</chat_history>"
}
],
"stream": false
}
2025-08-22 13:16:51 [INFO]
[LM STUDIO SERVER] Running chat completion on conversation with 1 messages.
___ useless log data removed from here ___
2025-08-22 13:16:54 [INFO]
[qwen/qwen3-4b-2507] Generated prediction: {
"id": "chatcmpl-zjkhylkn80bgnvun84g0bs",
"object": "chat.completion",
"created": 1755883011,
"model": "qwen/qwen3-4b-2507",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "[\n \"What are some common challenges people face when starting a new project?\",\n \"Can you give examples of successful projects that followed a similar approach?\",\n \"How can I get started with setting clear goals for my project?\",\n \"What tools or resources would you recommend for tracking progress?\"\n]",
"reasoning_content": "",
"tool_calls": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 270,
"completion_tokens": 61,
"total_tokens": 331
},
"stats": {},
"system_fingerprint": "qwen/qwen3-4b-2507"
}
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 @cma2t3r on GitHub (Aug 22, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16834
Check Existing Issues
Installation Method
Docker
Open WebUI Version
v0.6.22 - v0.6.25
Ollama Version (if applicable)
No response
Operating System
Ubuntu 22.04
Browser (if applicable)
Chrome, Brave, Edge
Confirmation
README.md.Expected Behavior
Choose a follow-up prompt
Actual Behavior
Follow-up prompts rarely get appended to chat
Steps to Reproduce
I am uncertain of how to recreate the issue ... maybe disabling all Ollama endpoints in admin settings/connections
I was hoping a newer version would clear up the intermittent problem.
I am testing LM Studio as an openai connection and the logs show the follow-up prompts get generated, but they rarely appear in the chat session no matter the browser [Chrome, Brave, Edge].
Logs & Screenshots
LM Studio log:
2025-08-22 12:14:14 [DEBUG]
Received request: POST to /v1/chat/completions with body {
"model": "qwen/qwen3-4b-2507",
"messages": [
{
"role": "user",
"content": "### Task:\nSuggest 3-5 relevant follow-up questions... ...re! 👋 How can I assist you today?\n</chat_history>"
}
],
"stream": false
}
2025-08-22 12:14:14 [INFO]
[LM STUDIO SERVER] Running chat completion on conversation with 1 messages.
___ useless log data removed from here ____
2025-08-22 12:14:17 [INFO]
[qwen/qwen3-4b-2507] Generated prediction: {
"id": "chatcmpl-ddzmv5q8eya48y6ln116jg",
"object": "chat.completion",
"created": 1755879254,
"model": "qwen/qwen3-4b-2507",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "[\n "What are some common mistakes people make when starting a new project?",\n "Can you give me examples of how to set realistic goals?",\n "How can I stay motivated when progress feels slow?",\n "What tools or resources do you recommend for project planning?"\n]",
"reasoning_content": "",
"tool_calls": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 262,
"completion_tokens": 57,
"total_tokens": 319
},
"stats": {},
"system_fingerprint": "qwen/qwen3-4b-2507"
}
Browser console log:
Failed to load resource: the server responded with a status of 500 ()
Object
Additional Information
All other generators work as expected.
Follow Up is enabled.
@cma2t3r commented on GitHub (Aug 22, 2025):
Enabling an Ollama endpoint in admin settings/connections gets rid of the JS/AJAX error in the browser console, but still no follow-up prompts appended to chat; and the follow-up prompts aren't always generated, took multiple retries to get a follow-up to appear in the LMS log.
LM Studio log:
2025-08-22 13:16:51 [DEBUG]
Received request: POST to /v1/chat/completions with body {
"model": "qwen/qwen3-4b-2507",
"messages": [
{
"role": "user",
"content": "### Task:\nSuggest 3-5 relevant follow-up questions... ... make this as helpful as possible!\n</chat_history>"
}
],
"stream": false
}
2025-08-22 13:16:51 [INFO]
[LM STUDIO SERVER] Running chat completion on conversation with 1 messages.
___ useless log data removed from here ___
2025-08-22 13:16:54 [INFO]
[qwen/qwen3-4b-2507] Generated prediction: {
"id": "chatcmpl-zjkhylkn80bgnvun84g0bs",
"object": "chat.completion",
"created": 1755883011,
"model": "qwen/qwen3-4b-2507",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "[\n "What are some common challenges people face when starting a new project?",\n "Can you give examples of successful projects that followed a similar approach?",\n "How can I get started with setting clear goals for my project?",\n "What tools or resources would you recommend for tracking progress?"\n]",
"reasoning_content": "",
"tool_calls": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 270,
"completion_tokens": 61,
"total_tokens": 331
},
"stats": {},
"system_fingerprint": "qwen/qwen3-4b-2507"
}