[GH-ISSUE #21611] issue: intermittent "Model not found" errors #35066

New Issue

Closed

opened 2026-04-25 09:16:16 -05:00 by GiteaMirror · 3 comments

GiteaMirror commented 2026-04-25 09:16:16 -05:00

Owner

Copy Link

Originally created by @m1g32 on GitHub (Feb 19, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/21611

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

v0.7.2

Ollama Version (if applicable)

No response

Operating System

kubernetes 1.32

Browser (if applicable)

No response

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

• The specified model should always be found and used consistently for all tasks.
• Both the main response generation and follow-up tasks (follow-up question and chat title generation) should reliably access the same model without intermittent lookup failures.
• Model discovery and caching mechanisms should behave consistently, regardless of how many custom models exist.

Actual Behavior

• We receive intermittent “model not found” errors, even though the model definitely exists.
• This occurs in two scenarios:
  1. During generation of the main response, where no response is produced and only the “model not found” error is returned.
  2. During follow-up tasks (in generate_follow_ups for follow-up question and chat title generation). In these cases, the main response is generated successfully using the model, but the follow-up tasks fail with “model not found” for the same model.

Steps to Reproduce

1. Deploy Open WebUI v0.7.2 using Docker on Kubernetes.
2. Start the service and add a connection providing several base-models
3. [Add several hundred custom models]
4. Configure MODELS_CACHE_TTL to 300 seconds.
5. Leave “Cache Base Model List” enabled or disabled (issue occurs in both cases).
6. Do not define any local or external task model in the admin settings.
7. Configure connections either via explicit model IDs or via auto-discovery (both exhibit the issue).
8. Generate a response using any available model.
9. Observe that intermittently either:
   – The main response generation fails with “model not found”, or
   – The main response succeeds but follow-up tasks (follow-up question or chat title generation) fail with “model not found” for the same model.
10. Repeat the same steps; the issue appears randomly and is not tied to a specific model

Logs & Screenshots

| ERROR | open_webui.routers.tasks:generate_follow_ups:314 - Exception occurred
Traceback (most recent call last):

File "", line 1, in
File "/usr/local/lib/python3.11/multiprocessing/spawn.py", line 122, in spawn_main
exitcode = _main(fd, parent_sentinel)
│ │ └ 4
│ └ 21
└ <function _main at 0x7f35a7606160>
File "/usr/local/lib/python3.11/multiprocessing/spawn.py", line 135, in _main
return self._bootstrap(parent_sentinel)
│ │ └ 4
│ └ <function BaseProcess._bootstrap at 0x7f35a7973740>
└
File "/usr/local/lib/python3.11/multiprocessing/process.py", line 314, in _bootstrap
self.run()
│ └ <function BaseProcess.run at 0x7f35a7972ca0>
└
File "/usr/local/lib/python3.11/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
│ │ │ │ │ └ {'config': <uvicorn.config.Config object at 0x7f35a7602d50>, 'target': <bound method Process.target of <uvicorn.supervisors.m...
│ │ │ │ └
│ │ │ └ ()
│ │ └
│ └ <function subprocess_started at 0x7f35a6b74cc0>
└
File "/usr/local/lib/python3.11/site-packages/uvicorn/_subprocess.py", line 80, in subprocess_started
target(sockets=sockets)
│ └ [<socket.socket fd=3, family=2, type=1, proto=0, laddr=('0.0.0.0', 8080)>]
└ <bound method Process.target of <uvicorn.supervisors.multiprocess.Process object at 0x7f35a689ce50>>
File "/usr/local/lib/python3.11/site-packages/uvicorn/supervisors/multiprocess.py", line 64, in target
return self.real_target(sockets)
│ │ └ [<socket.socket fd=3, family=2, type=1, proto=0, laddr=('0.0.0.0', 8080)>]
│ └ <bound method Server.run of <uvicorn.server.Server object at 0x7f35a689cf90>>
└ <uvicorn.supervisors.multiprocess.Process object at 0x7f35a689ce50>
File "/usr/local/lib/python3.11/site-packages/uvicorn/server.py", line 67, in run
return asyncio_run(self.serve(sockets=sockets), loop_factory=self.config.get_loop_factory())
│ │ │ │ │ │ └ <function Config.get_loop_factory at 0x7f35a6af0180>
│ │ │ │ │ └ <uvicorn.config.Config object at 0x7f35a7602d50>
│ │ │ │ └ <uvicorn.server.Server object at 0x7f35a689cf90>
│ │ │ └ [<socket.socket fd=3, family=2, type=1, proto=0, laddr=('0.0.0.0', 8080)>]
│ │ └ <function Server.serve at 0x7f35a6b57a60>
│ └ <uvicorn.server.Server object at 0x7f35a689cf90>
└ <function asyncio_run at 0x7f35a6bd0ae0>
File "/usr/local/lib/python3.11/site-packages/uvicorn/_compat.py", line 30, in asyncio_run
return runner.run(main)
│ │ └ <coroutine object Server.serve at 0x7f35a686cb80>
│ └ <function Runner.run at 0x7f35a6ec94e0>
└ <asyncio.runners.Runner object at 0x7f35a7a9e550>
File "/usr/local/lib/python3.11/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
│ │ │ └ <Task pending name='Task-1' coro=<Server.serve() running at /usr/local/lib/python3.11/site-packages/uvicorn/server.py:71> wai...
│ │ └ <cyfunction Loop.run_until_complete at 0x7f35a685be80>
│ └ <uvloop.Loop running=True closed=False debug=False>
└ <asyncio.runners.Runner object at 0x7f35a7a9e550>

File "/app/backend/open_webui/main.py", line 1729, in process_chat
return await process_chat_response(
└ <function process_chat_response at 0x7f3418d68a40>

File "/app/backend/open_webui/utils/middleware.py", line 3677, in process_chat_response
return await response_handler(response, events)
│ │ └ []
│ └ <starlette.responses.StreamingResponse object at 0x7f33f74a8cd0>
└ <function process_chat_response..response_handler at 0x7f34142ec040>

File "/app/backend/open_webui/utils/middleware.py", line 3659, in response_handler
await background_tasks_handler()
└ <function process_chat_response..background_tasks_handler at 0x7f33f75332e0>

File "/app/backend/open_webui/utils/middleware.py", line 1963, in background_tasks_handler
res = await generate_follow_ups(
└ <function generate_follow_ups at 0x7f341aeb4860>

File "/app/backend/open_webui/routers/tasks.py", line 312, in generate_follow_ups
return await generate_chat_completion(request, form_data=payload, user=user)
│ │ │ └ UserModel(id='xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx', email='x.y@z.com', username=None, role='user', name='...
│ │ └ {'model': 'gpt-5.2', 'messages': [{'role': 'user', 'content': '### Task:\nSuggest 3-5 relevant follow-up questions or promp...
│ └ <starlette.requests.Request object at 0x7f3415046c10>
└ <function generate_chat_completion at 0x7f341b010720>

File "/app/backend/open_webui/utils/chat.py", line 194, in generate_chat_completion
raise Exception("Model not found")

Exception: Model not found

---

Traceback (most recent call last):

File "", line 1, in
File "/usr/local/lib/python3.11/multiprocessing/spawn.py", line 122, in spawn_main
exitcode = _main(fd, parent_sentinel)
│ │ └ 4
│ └ 21
└ <function _main at 0x7ff7c1bc2160>
File "/usr/local/lib/python3.11/multiprocessing/spawn.py", line 135, in _main
return self._bootstrap(parent_sentinel)
│ │ └ 4
│ └ <function BaseProcess._bootstrap at 0x7ff7c1f2f740>
└
File "/usr/local/lib/python3.11/multiprocessing/process.py", line 314, in _bootstrap
self.run()
│ └ <function BaseProcess.run at 0x7ff7c1f2eca0>
└
File "/usr/local/lib/python3.11/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
│ │ │ │ │ └ {'config': <uvicorn.config.Config object at 0x7ff7c1bbed50>, 'target': <bound method Process.target of <uvicorn.supervisors.m...
│ │ │ │ └
│ │ │ └ ()
│ │ └
│ └ <function subprocess_started at 0x7ff7c1130cc0>
└
File "/usr/local/lib/python3.11/site-packages/uvicorn/_subprocess.py", line 80, in subprocess_started
target(sockets=sockets)
│ └ [<socket.socket fd=3, family=2, type=1, proto=0, laddr=('0.0.0.0', 8080)>]
└ <bound method Process.target of <uvicorn.supervisors.multiprocess.Process object at 0x7ff7c0e58e50>>
File "/usr/local/lib/python3.11/site-packages/uvicorn/supervisors/multiprocess.py", line 64, in target
return self.real_target(sockets)
│ │ └ [<socket.socket fd=3, family=2, type=1, proto=0, laddr=('0.0.0.0', 8080)>]
│ └ <bound method Server.run of <uvicorn.server.Server object at 0x7ff7c0e58f90>>
└ <uvicorn.supervisors.multiprocess.Process object at 0x7ff7c0e58e50>
File "/usr/local/lib/python3.11/site-packages/uvicorn/server.py", line 67, in run
return asyncio_run(self.serve(sockets=sockets), loop_factory=self.config.get_loop_factory())
│ │ │ │ │ │ └ <function Config.get_loop_factory at 0x7ff7c10ac180>
│ │ │ │ │ └ <uvicorn.config.Config object at 0x7ff7c1bbed50>
│ │ │ │ └ <uvicorn.server.Server object at 0x7ff7c0e58f90>
│ │ │ └ [<socket.socket fd=3, family=2, type=1, proto=0, laddr=('0.0.0.0', 8080)>]
│ │ └ <function Server.serve at 0x7ff7c1113a60>
│ └ <uvicorn.server.Server object at 0x7ff7c0e58f90>
└ <function asyncio_run at 0x7ff7c118cae0>
File "/usr/local/lib/python3.11/site-packages/uvicorn/_compat.py", line 30, in asyncio_run
return runner.run(main)
│ │ └ <coroutine object Server.serve at 0x7ff7c0e28b80>
│ └ <function Runner.run at 0x7ff7c14854e0>
└ <asyncio.runners.Runner object at 0x7ff7c0f4ead0>
File "/usr/local/lib/python3.11/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
│ │ │ └ <Task pending name='Task-1' coro=<Server.serve() running at /usr/local/lib/python3.11/site-packages/uvicorn/server.py:71> wai...
│ │ └ <cyfunction Loop.run_until_complete at 0x7ff7c0e17e80>
│ └ <uvloop.Loop running=True closed=False debug=False>
└ <asyncio.runners.Runner object at 0x7ff7c0f4ead0>

File "/app/backend/open_webui/main.py", line 1710, in process_chat
form_data, metadata, events = await process_chat_payload(
│ │ └ <function process_chat_payload at 0x7ff6333b49a0>
│ └ {'user_id': '51ef38bd-45f6-46e0-877c-3089c393add3', 'chat_id': 'bfaa226a-db9e-49d7-909a-e8428d037823', 'message_id': 'ee665e7...
└ {'stream': True, 'model': 'gpt-5.2', 'messages': [{'role': 'user', 'content': 'I want to research xyz ...

File "/app/backend/open_webui/utils/middleware.py", line 1581, in process_chat_payload
form_data = await chat_web_search_handler(
└ <function chat_web_search_handler at 0x7ff6333b44a0>

File "/app/backend/open_webui/utils/middleware.py", line 771, in chat_web_search_handler
res = await generate_queries(
└ <function generate_queries at 0x7ff635488fe0>

File "/app/backend/open_webui/routers/tasks.py", line 533, in generate_queries
raise e

File "/app/backend/open_webui/routers/tasks.py", line 531, in generate_queries
payload = await process_pipeline_inlet_filter(request, payload, user, models)
│ │ │ │ └ <open_webui.socket.utils.RedisDict object at 0x7ff6f9e3e610>
│ │ │ └ UserModel(id='51ef38bd-45f6-46e0-877c-3089c393add3', email='x.y@z.com', username=None, role='user', name='Emil'...
│ │ └ {'model': 'gpt-5.2', 'messages': [{'role': 'user', 'content': '### Task:\nAnalyze the chat history to determine the necessity...
│ └ <starlette.requests.Request object at 0x7ff6293e0510>
└ <function process_pipeline_inlet_filter at 0x7ff6356fe3e0>

File "/app/backend/open_webui/routers/pipelines.py", line 63, in process_pipeline_inlet_filter
model = models[model_id]
│ └ 'gpt-5.2'
└ <open_webui.socket.utils.RedisDict object at 0x7ff6f9e3e610>

File "/app/backend/open_webui/socket/utils.py", line 66, in getitem
raise KeyError(key)
└ 'gpt-5.2'

KeyError: 'gpt-5.2'

Additional Information

• This problem did not occur before updating to version 0.7.2.
• No local or external task model is defined in the settings.
• The failure appears random and inconsistent, even though the model was just accessed successfully moments earlier.
• The issue affects several different models, it is not isolated to a specific model.
• Changing the “Cache Base Model List” options had no effect.
• Explicitly setting Model IDs in Admin-panel → Connections or using auto‑discovery to include all models made no difference.
• MODELS_CACHE_TTL is set to 300 seconds.
• Our instance has several hundred custom models in addition to about 20 base models, which may be correlated with the issue.

Originally created by @m1g32 on GitHub (Feb 19, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/21611 ### 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 Docker ### Open WebUI Version v0.7.2 ### Ollama Version (if applicable) _No response_ ### Operating System kubernetes 1.32 ### Browser (if applicable) _No response_ ### 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 - The specified model should always be found and used consistently for all tasks. - Both the main response generation and follow-up tasks (follow-up question and chat title generation) should reliably access the same model without intermittent lookup failures. - Model discovery and caching mechanisms should behave consistently, regardless of how many custom models exist. ### Actual Behavior - We receive intermittent “model not found” errors, even though the model definitely exists. - This occurs in two scenarios: 1. During generation of the main response, where no response is produced and only the “model not found” error is returned. 2. During follow-up tasks (in generate_follow_ups for follow-up question and chat title generation). In these cases, the main response is generated successfully using the model, but the follow-up tasks fail with “model not found” for the same model. ### Steps to Reproduce 1. Deploy Open WebUI v0.7.2 using Docker on Kubernetes. 2. Start the service and add a connection providing several base-models 3. [Add several hundred custom models] 4. Configure MODELS_CACHE_TTL to 300 seconds. 5. Leave “Cache Base Model List” enabled or disabled (issue occurs in both cases). 6. Do not define any local or external task model in the admin settings. 7. Configure connections either via explicit model IDs or via auto-discovery (both exhibit the issue). 8. Generate a response using any available model. 9. Observe that intermittently either: – The main response generation fails with “model not found”, or – The main response succeeds but follow-up tasks (follow-up question or chat title generation) fail with “model not found” for the same model. 10. Repeat the same steps; the issue appears randomly and is not tied to a specific model ### Logs & Screenshots | ERROR | open_webui.routers.tasks:generate_follow_ups:314 - Exception occurred Traceback (most recent call last): File "<string>", line 1, in <module> File "/usr/local/lib/python3.11/multiprocessing/spawn.py", line 122, in spawn_main exitcode = _main(fd, parent_sentinel) │ │ └ 4 │ └ 21 └ <function _main at 0x7f35a7606160> File "/usr/local/lib/python3.11/multiprocessing/spawn.py", line 135, in _main return self._bootstrap(parent_sentinel) │ │ └ 4 │ └ <function BaseProcess._bootstrap at 0x7f35a7973740> └ <SpawnProcess name='SpawnProcess-4' parent=1 started> File "/usr/local/lib/python3.11/multiprocessing/process.py", line 314, in _bootstrap self.run() │ └ <function BaseProcess.run at 0x7f35a7972ca0> └ <SpawnProcess name='SpawnProcess-4' parent=1 started> File "/usr/local/lib/python3.11/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) │ │ │ │ │ └ {'config': <uvicorn.config.Config object at 0x7f35a7602d50>, 'target': <bound method Process.target of <uvicorn.supervisors.m... │ │ │ │ └ <SpawnProcess name='SpawnProcess-4' parent=1 started> │ │ │ └ () │ │ └ <SpawnProcess name='SpawnProcess-4' parent=1 started> │ └ <function subprocess_started at 0x7f35a6b74cc0> └ <SpawnProcess name='SpawnProcess-4' parent=1 started> File "/usr/local/lib/python3.11/site-packages/uvicorn/_subprocess.py", line 80, in subprocess_started target(sockets=sockets) │ └ [<socket.socket fd=3, family=2, type=1, proto=0, laddr=('0.0.0.0', 8080)>] └ <bound method Process.target of <uvicorn.supervisors.multiprocess.Process object at 0x7f35a689ce50>> File "/usr/local/lib/python3.11/site-packages/uvicorn/supervisors/multiprocess.py", line 64, in target return self.real_target(sockets) │ │ └ [<socket.socket fd=3, family=2, type=1, proto=0, laddr=('0.0.0.0', 8080)>] │ └ <bound method Server.run of <uvicorn.server.Server object at 0x7f35a689cf90>> └ <uvicorn.supervisors.multiprocess.Process object at 0x7f35a689ce50> File "/usr/local/lib/python3.11/site-packages/uvicorn/server.py", line 67, in run return asyncio_run(self.serve(sockets=sockets), loop_factory=self.config.get_loop_factory()) │ │ │ │ │ │ └ <function Config.get_loop_factory at 0x7f35a6af0180> │ │ │ │ │ └ <uvicorn.config.Config object at 0x7f35a7602d50> │ │ │ │ └ <uvicorn.server.Server object at 0x7f35a689cf90> │ │ │ └ [<socket.socket fd=3, family=2, type=1, proto=0, laddr=('0.0.0.0', 8080)>] │ │ └ <function Server.serve at 0x7f35a6b57a60> │ └ <uvicorn.server.Server object at 0x7f35a689cf90> └ <function asyncio_run at 0x7f35a6bd0ae0> File "/usr/local/lib/python3.11/site-packages/uvicorn/_compat.py", line 30, in asyncio_run return runner.run(main) │ │ └ <coroutine object Server.serve at 0x7f35a686cb80> │ └ <function Runner.run at 0x7f35a6ec94e0> └ <asyncio.runners.Runner object at 0x7f35a7a9e550> File "/usr/local/lib/python3.11/asyncio/runners.py", line 118, in run return self._loop.run_until_complete(task) │ │ │ └ <Task pending name='Task-1' coro=<Server.serve() running at /usr/local/lib/python3.11/site-packages/uvicorn/server.py:71> wai... │ │ └ <cyfunction Loop.run_until_complete at 0x7f35a685be80> │ └ <uvloop.Loop running=True closed=False debug=False> └ <asyncio.runners.Runner object at 0x7f35a7a9e550> File "/app/backend/open_webui/main.py", line 1729, in process_chat return await process_chat_response( └ <function process_chat_response at 0x7f3418d68a40> File "/app/backend/open_webui/utils/middleware.py", line 3677, in process_chat_response return await response_handler(response, events) │ │ └ [] │ └ <starlette.responses.StreamingResponse object at 0x7f33f74a8cd0> └ <function process_chat_response.<locals>.response_handler at 0x7f34142ec040> File "/app/backend/open_webui/utils/middleware.py", line 3659, in response_handler await background_tasks_handler() └ <function process_chat_response.<locals>.background_tasks_handler at 0x7f33f75332e0> File "/app/backend/open_webui/utils/middleware.py", line 1963, in background_tasks_handler res = await generate_follow_ups( └ <function generate_follow_ups at 0x7f341aeb4860> > File "/app/backend/open_webui/routers/tasks.py", line 312, in generate_follow_ups return await generate_chat_completion(request, form_data=payload, user=user) │ │ │ └ UserModel(id='xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx', email='x.y@z.com', username=None, role='user', name='... │ │ └ {'model': 'gpt-5.2', 'messages': [{'role': 'user', 'content': '### Task:\nSuggest 3-5 relevant follow-up questions or promp... │ └ <starlette.requests.Request object at 0x7f3415046c10> └ <function generate_chat_completion at 0x7f341b010720> File "/app/backend/open_webui/utils/chat.py", line 194, in generate_chat_completion raise Exception("Model not found") Exception: Model not found --- Traceback (most recent call last): File "<string>", line 1, in <module> File "/usr/local/lib/python3.11/multiprocessing/spawn.py", line 122, in spawn_main exitcode = _main(fd, parent_sentinel) │ │ └ 4 │ └ 21 └ <function _main at 0x7ff7c1bc2160> File "/usr/local/lib/python3.11/multiprocessing/spawn.py", line 135, in _main return self._bootstrap(parent_sentinel) │ │ └ 4 │ └ <function BaseProcess._bootstrap at 0x7ff7c1f2f740> └ <SpawnProcess name='SpawnProcess-4' parent=1 started> File "/usr/local/lib/python3.11/multiprocessing/process.py", line 314, in _bootstrap self.run() │ └ <function BaseProcess.run at 0x7ff7c1f2eca0> └ <SpawnProcess name='SpawnProcess-4' parent=1 started> File "/usr/local/lib/python3.11/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) │ │ │ │ │ └ {'config': <uvicorn.config.Config object at 0x7ff7c1bbed50>, 'target': <bound method Process.target of <uvicorn.supervisors.m... │ │ │ │ └ <SpawnProcess name='SpawnProcess-4' parent=1 started> │ │ │ └ () │ │ └ <SpawnProcess name='SpawnProcess-4' parent=1 started> │ └ <function subprocess_started at 0x7ff7c1130cc0> └ <SpawnProcess name='SpawnProcess-4' parent=1 started> File "/usr/local/lib/python3.11/site-packages/uvicorn/_subprocess.py", line 80, in subprocess_started target(sockets=sockets) │ └ [<socket.socket fd=3, family=2, type=1, proto=0, laddr=('0.0.0.0', 8080)>] └ <bound method Process.target of <uvicorn.supervisors.multiprocess.Process object at 0x7ff7c0e58e50>> File "/usr/local/lib/python3.11/site-packages/uvicorn/supervisors/multiprocess.py", line 64, in target return self.real_target(sockets) │ │ └ [<socket.socket fd=3, family=2, type=1, proto=0, laddr=('0.0.0.0', 8080)>] │ └ <bound method Server.run of <uvicorn.server.Server object at 0x7ff7c0e58f90>> └ <uvicorn.supervisors.multiprocess.Process object at 0x7ff7c0e58e50> File "/usr/local/lib/python3.11/site-packages/uvicorn/server.py", line 67, in run return asyncio_run(self.serve(sockets=sockets), loop_factory=self.config.get_loop_factory()) │ │ │ │ │ │ └ <function Config.get_loop_factory at 0x7ff7c10ac180> │ │ │ │ │ └ <uvicorn.config.Config object at 0x7ff7c1bbed50> │ │ │ │ └ <uvicorn.server.Server object at 0x7ff7c0e58f90> │ │ │ └ [<socket.socket fd=3, family=2, type=1, proto=0, laddr=('0.0.0.0', 8080)>] │ │ └ <function Server.serve at 0x7ff7c1113a60> │ └ <uvicorn.server.Server object at 0x7ff7c0e58f90> └ <function asyncio_run at 0x7ff7c118cae0> File "/usr/local/lib/python3.11/site-packages/uvicorn/_compat.py", line 30, in asyncio_run return runner.run(main) │ │ └ <coroutine object Server.serve at 0x7ff7c0e28b80> │ └ <function Runner.run at 0x7ff7c14854e0> └ <asyncio.runners.Runner object at 0x7ff7c0f4ead0> File "/usr/local/lib/python3.11/asyncio/runners.py", line 118, in run return self._loop.run_until_complete(task) │ │ │ └ <Task pending name='Task-1' coro=<Server.serve() running at /usr/local/lib/python3.11/site-packages/uvicorn/server.py:71> wai... │ │ └ <cyfunction Loop.run_until_complete at 0x7ff7c0e17e80> │ └ <uvloop.Loop running=True closed=False debug=False> └ <asyncio.runners.Runner object at 0x7ff7c0f4ead0> File "/app/backend/open_webui/main.py", line 1710, in process_chat form_data, metadata, events = await process_chat_payload( │ │ └ <function process_chat_payload at 0x7ff6333b49a0> │ └ {'user_id': '51ef38bd-45f6-46e0-877c-3089c393add3', 'chat_id': 'bfaa226a-db9e-49d7-909a-e8428d037823', 'message_id': 'ee665e7... └ {'stream': True, 'model': 'gpt-5.2', 'messages': [{'role': 'user', 'content': 'I want to research xyz ... File "/app/backend/open_webui/utils/middleware.py", line 1581, in process_chat_payload form_data = await chat_web_search_handler( └ <function chat_web_search_handler at 0x7ff6333b44a0> > File "/app/backend/open_webui/utils/middleware.py", line 771, in chat_web_search_handler res = await generate_queries( └ <function generate_queries at 0x7ff635488fe0> File "/app/backend/open_webui/routers/tasks.py", line 533, in generate_queries raise e File "/app/backend/open_webui/routers/tasks.py", line 531, in generate_queries payload = await process_pipeline_inlet_filter(request, payload, user, models) │ │ │ │ └ <open_webui.socket.utils.RedisDict object at 0x7ff6f9e3e610> │ │ │ └ UserModel(id='51ef38bd-45f6-46e0-877c-3089c393add3', email='x.y@z.com', username=None, role='user', name='Emil'... │ │ └ {'model': 'gpt-5.2', 'messages': [{'role': 'user', 'content': '### Task:\nAnalyze the chat history to determine the necessity... │ └ <starlette.requests.Request object at 0x7ff6293e0510> └ <function process_pipeline_inlet_filter at 0x7ff6356fe3e0> File "/app/backend/open_webui/routers/pipelines.py", line 63, in process_pipeline_inlet_filter model = models[model_id] │ └ 'gpt-5.2' └ <open_webui.socket.utils.RedisDict object at 0x7ff6f9e3e610> File "/app/backend/open_webui/socket/utils.py", line 66, in __getitem__ raise KeyError(key) └ 'gpt-5.2' KeyError: 'gpt-5.2' ### Additional Information - This problem did not occur before updating to version 0.7.2. - No local or external task model is defined in the settings. - The failure appears random and inconsistent, even though the model was just accessed successfully moments earlier. - The issue affects several different models, it is not isolated to a specific model. - Changing the “Cache Base Model List” options had no effect. - Explicitly setting Model IDs in Admin-panel → Connections or using auto‑discovery to include all models made no difference. - MODELS_CACHE_TTL is set to 300 seconds. - Our instance has several hundred custom models in addition to about 20 base models, which may be correlated with the issue.

GiteaMirror added the bug label 2026-04-25 09:16:16 -05:00

GiteaMirror closed this issue 2026-04-25 09:16:17 -05:00

GiteaMirror commented 2026-04-25 09:16:18 -05:00

Author

Owner

Copy Link

@Classic298 commented on GitHub (Feb 19, 2026):

Yes this might be due to the new models not being properly synced across all workers. Simply restart Open WebUI then it should work just fine

<!-- gh-comment-id:3928196558 --> @Classic298 commented on GitHub (Feb 19, 2026): Yes this might be due to the new models not being properly synced across all workers. Simply restart Open WebUI then it should work just fine

GiteaMirror commented 2026-04-25 09:16:18 -05:00

Author

Owner

Copy Link

@m1g32 commented on GitHub (Feb 19, 2026):

Yes this might be due to the new models not being properly synced across all workers. Simply restart Open WebUI then it should work just fine

We are using a multi-worker deployment, this issue still appears even after restarting all pods.

<!-- gh-comment-id:3928313551 --> @m1g32 commented on GitHub (Feb 19, 2026): > Yes this might be due to the new models not being properly synced across all workers. Simply restart Open WebUI then it should work just fine We are using a multi-worker deployment, this issue still appears even after restarting all pods.

GiteaMirror commented 2026-04-25 09:16:19 -05:00

Author

Owner

Copy Link

@Classic298 commented on GitHub (Feb 19, 2026):

Ok in that case cannot really reproduce.
I could reproduce as long as i don't restart the server, but once I do, it works.

Seems the model list is not properly synced with redis

<!-- gh-comment-id:3928539477 --> @Classic298 commented on GitHub (Feb 19, 2026): Ok in that case cannot really reproduce. I could reproduce as long as i don't restart the server, but once I do, it works. Seems the model list is not properly synced with redis

Sign in to join this conversation.

No Branch/Tag Specified

Branches Tags

main

dev

v0.9.2

v0.9.1

v0.9.0

v0.8.12

v0.8.11

v0.8.10

v0.8.9

v0.8.8

v0.8.7

v0.8.6

v0.8.5

v0.8.4

v0.8.3

v0.8.2

v0.8.1

v0.8.0

v0.7.2

v0.7.1

v0.7.0

v0.6.43

v0.6.42

v0.6.41

v0.6.40

v0.6.39

v0.6.38

v0.6.37

v0.6.36

v0.6.35

v0.6.34

v0.6.33

v0.6.32

v0.6.31

v0.6.30

v0.6.29

v0.6.28

v0.6.27

v0.6.26

v0.6.25

v0.6.24

v0.6.23

v0.6.22

v0.6.21

v0.6.20

v0.6.19

v0.6.18

v0.6.17

v0.6.16

v0.6.15

v0.6.14

v0.6.13

v0.6.12

v0.6.11

v0.6.10

v0.6.9

v0.6.8

v0.6.7

v0.6.6

v0.6.5

v0.6.4

v0.6.3

v0.6.2

v0.6.1

v0.6.0

v0.5.20

v0.5.19

v0.5.18

v0.5.17

v0.5.16

v0.5.15

v0.5.14

v0.5.13

v0.5.12

v0.5.11

v0.5.10

v0.5.9

v0.5.8

v0.5.7

v0.5.6

v0.5.5

v0.5.4

v0.5.3

v0.5.2

v0.5.1

v0.5.0

v0.4.8

v0.4.7

v0.4.6

v0.4.5

v0.4.4

v0.4.3

v0.4.2

v0.4.1

v0.4.0

v0.3.35

v0.3.34

v0.3.33

v0.3.32

v0.3.31

v0.3.30

v0.3.29

v0.3.28

v0.3.27

v0.3.26

v0.3.25

v0.3.24

v0.3.23

v0.3.22

v0.3.21

v0.3.20

v0.3.19

v0.3.18

v0.3.17

v0.3.16

v0.3.15

v0.3.14

v0.3.13

v0.3.12

v0.3.11

v0.3.10

v0.3.9

v0.3.8

v0.3.7

v0.3.6

v0.3.5

v0.3.4

v0.3.3

v0.3.2

v0.3.1

v0.3.0

v0.2.5

v0.2.4

v0.2.3

v0.2.2

v0.2.1

v0.2.0

v0.1.125

v0.1.124

v0.1.123

v0.1.122

v0.1.121

v0.1.120

v0.1.119

v0.1.118

v0.1.117

v0.1.116

v0.1.115

v0.1.114

v0.1.113

v0.1.112

v0.1.111

v0.1.110

v0.1.109

v0.1.108

v0.1.107

v0.1.106

v0.1.105

v0.1.104

v0.1.103

v0.1.102

Labels

Clear labels

bug

confirmed

confirmed issue

core

documentation

enhancement

good first issue

help wanted

non-core

pull-request

Mirrored from GitHub Pull Request

python

question

testing wanted

No Label bug

Milestone

No items

No Milestone

Projects

Clear projects

No project

Assignees

Clear assignees

GiteaMirror ninjasurge

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#35066