issue: Chat response is not working

[navilg]

Check Existing Issues

• 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

Docker

Open WebUI Version

v0.6.41

Ollama Version (if applicable)

No response

Operating System

Ubuntu 22.04

Browser (if applicable)

Firefox 145.0.1

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

Model should stream its response for user prompt

Actual Behavior

When I send my prompt, Model does not respond and just stay in loading mode. This happened after I upgraded to 0.6.41.

Steps to Reproduce

1. Upgrade OpenWebUI to 0.6.41
2. Connect to model using OpenAI-compatible API
3. Send user prompt in chat
4. See screenshot attached

Logs & Screenshots

2025-12-20T15:56:37.672279419Z 2025-12-20 15:56:37.672 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /ollama/api/version HTTP/1.1" 200

2025-12-20T15:56:37.770095735Z 2025-12-20 15:56:37.769 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /api/v1/users/user/settings HTTP/1.1" 200

2025-12-20T15:56:40.280132787Z 2025-12-20 15:56:40.279 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /api/v1/chats/d08c0083-bdd3-441c-924c-9a7f0ee20489 HTTP/1.1" 200

2025-12-20T15:56:40.345846281Z 2025-12-20 15:56:40.345 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /api/v1/chats/fed4823a-5b91-4498-9f85-c92d9c8e1b8e HTTP/1.1" 200

2025-12-20T15:56:41.203435415Z 2025-12-20 15:56:41.203 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /api/usage HTTP/1.1" 200

2025-12-20T15:56:43.083379703Z 2025-12-20 15:56:43.083 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /_app/immutable/chunks/24Apm04j.js HTTP/1.1" 404

2025-12-20T15:56:44.772183117Z 2025-12-20 15:56:44.771 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /ollama/api/version HTTP/1.1" 200

2025-12-20T15:56:45.881641940Z 2025-12-20 15:56:45.881 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /api/version/updates HTTP/1.1" 200

2025-12-20T15:57:12.379574507Z 2025-12-20 15:57:12.379 | INFO     | open_webui.routers.openai:get_all_models:476 - get_all_models()

2025-12-20T15:57:14.261935775Z 2025-12-20 15:57:14.261 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /api/models HTTP/1.1" 200

2025-12-20T15:57:19.664814553Z 2025-12-20 15:57:19.664 | INFO     | open_webui.routers.openai:get_all_models:476 - get_all_models()

2025-12-20T15:57:21.567715268Z 2025-12-20 15:57:21.567 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /api/models HTTP/1.1" 200

2025-12-20T15:57:22.123056384Z 2025-12-20 15:57:22.122 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /_app/version.json HTTP/1.1" 304

2025-12-20T15:57:56.490006864Z 2025-12-20 15:57:56.489 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "POST /api/v1/chats/new HTTP/1.1" 200

2025-12-20T15:57:56.615739167Z 2025-12-20 15:57:56.615 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200

2025-12-20T15:57:56.699574888Z 2025-12-20 15:57:56.699 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /api/v1/folders/ HTTP/1.1" 200

2025-12-20T15:57:56.712728595Z 2025-12-20 15:57:56.712 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "POST /api/v1/chats/c64b2337-af07-41df-a198-6e8545ca1def HTTP/1.1" 200

2025-12-20T15:57:56.814651904Z 2025-12-20 15:57:56.814 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200

2025-12-20T15:57:56.921939617Z 2025-12-20 15:57:56.921 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /api/v1/folders/ HTTP/1.1" 200

2025-12-20T15:57:56.935672568Z 2025-12-20 15:57:56.935 | INFO     | open_webui.routers.openai:get_all_models:476 - get_all_models()

2025-12-20T15:57:56.936688417Z 2025-12-20 15:57:56.936 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "POST /api/chat/completions HTTP/1.1" 200

2025-12-20T15:57:57.039601774Z 2025-12-20 15:57:57.039 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200

2025-12-20T15:57:57.217414780Z 2025-12-20 15:57:57.217 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 129.159.228.200:0 - "GET /api/v1/folders/ HTTP/1.1" 200

2025-12-20T15:58:42.650619214Z 2025-12-20 15:58:42.650 | INFO     | open_webui.routers.openai:get_all_models:476 - get_all_models()

2025-12-20T15:58:48.575625077Z 2025-12-20 15:58:48.575 | INFO     | open_webui.routers.openai:get_all_models:476 - get_all_models()

Additional Information

No response

[owui-terminator[bot]]

🔍 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. #19777 issue:
   by Yaute7 • Dec 05, 2025 • bug

2. #20019 issue:
   by j63440490 • Dec 17, 2025 • bug

3. #19987 issue: There is a lack of visual consistency between the home page and the chat interface.
   by i-iooi-i • Dec 16, 2025 • bug

4. #19877 issue:
   by dotmobo • Dec 11, 2025 • bug

5. #19861 issue:
   by QuitHub • Dec 10, 2025 • bug

Show 5 more related issues

6. #19864 issue:
   by Haervwe • Dec 10, 2025 • bug

7. #19563 issue:
   by naruto7g • Nov 28, 2025 • bug

8. #19085 issue: Chat UI loads forever instead of showing error
   by TamKej • Nov 10, 2025 • bug

9. #18999 issue: Unable to load chat history
   by i-iooi-i • Nov 07, 2025 • bug

10. #19481 issue: admin panel not working
    by kybeq • Nov 25, 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.

[OctoberRust2000]

@navilg Did you manage to fix your issue?

I'm facing similar problem. The response from my FastAPI chat endpoint is not visible in the OWUI chat.
I followed the OpenAI documentation for it:
https://developers.openai.com/api/reference/resources/chat/subresources/completions/methods/create
and hardcoded the response for simplicity but still wasn't able to make it work. Here's my endopint:

@fastapi.post("/v1/chat/completions")
async def run_agent(request: Request):
    try:
        content = '''{
            "object": "chat.completion",
            "id": "''' + str(uuid.uuid4()) + '''",
            "model": "Steelbite - Brave websearch",
            "created": ''' + str(int(time.time())) + ''',        
            
            "system_fingerprint": "fp_50cad350e4",
            "choices": [
                {
                    "index": 0,
                    "message": {
                        "content": "The response from agent",
                        "role": "assistant",
                        "refusal": null
                    },
                    "finish_reason": "stop",
                    "logprobs": null
                }
            ],
            "usage": {
                "total_tokens": 31,
                "completion_tokens": 18,
                "prompt_tokens": 13
            }
        }'''
        
        return content
    except Exception as e:
        print(e)
        raise HTTPException(status_code=500, detail=str(e))

OWUI is successfully retrieving models from my endpoint below, but struggling with chat completions.

@fastapi.get("/v1/models")
async def list_models():

[OctoberRust2000]

Changing the return method did the trick:

return Response(content=content, headers={'content-type': 'application/json'})