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
v0.6.34
Ollama Version (if applicable)
v0.12.5
Operating System
Debian 13
Browser (if applicable)
Arc
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
When running hybrid search, results are sorted through reranker.
Actual Behavior
Reranker is ignored.
Logs state error 405 method not allowed.
No config changes were made with this functioning in 0.6.32.
Steps to Reproduce
Configure v0.6.34 with hybrid search using bundled ollama with default config.
Using open-webui/open-webui:ollama image.
Logs & Screenshots
2025-10-21 03:18:42.718 | INFO | open_webui.retrieval.models.external:predict:40 - ExternalReranker:predict:model dengcao/Qwen3-Reranker-8B:f16
2025-10-21 03:18:42.718 | INFO | open_webui.retrieval.models.external:predict:41 - ExternalReranker:predict:query latest research
[GIN] 2025/10/21 - 03:18:42 | 405 | 7.921µs | 127.0.0.1 | POST "/"
2025-10-21 03:18:42.723 | ERROR | open_webui.retrieval.models.external:predict:73 - Error in external reranking: 405 Client Error: Method Not Allowed for url: http://localhost:11434/
Traceback (most recent call last):
File "/usr/local/lib/python3.11/threading.py", line 1002, in _bootstrap
self._bootstrap_inner()
│ └ <function Thread._bootstrap_inner at 0x7fb6c86c89a0>
└ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
File "/usr/local/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
self.run()
│ └ <function Thread.run at 0x7fb6c86c8680>
└ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
File "/usr/local/lib/python3.11/threading.py", line 982, in run
self._target(*self._args, **self._kwargs)
│ │ │ │ │ └ {}
│ │ │ │ └ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
│ │ │ └ (<weakref at 0x7fb5c94b31f0; to 'ThreadPoolExecutor' at 0x7fb58bdf8150>, <_queue.SimpleQueue object at 0x7fb5a9438a90>, None,...
│ │ └ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
│ └ <function _worker at 0x7fb6c77aa5c0>
└ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 83, in _worker
work_item.run()
│ └ <function _WorkItem.run at 0x7fb6c77aa700>
└ <concurrent.futures.thread._WorkItem object at 0x7fb5ead074d0>
File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
│ │ │ │ │ └ {}
│ │ │ │ └ <concurrent.futures.thread._WorkItem object at 0x7fb5ead074d0>
│ │ │ └ ('ca9366c0-09d1-47d4-ba5f-39f33c12bb8d', 'latest research on ketamine therapy safety')
│ │ └ <concurrent.futures.thread._WorkItem object at 0x7fb5ead074d0>
│ └ <function query_collection_with_hybrid_search..process_query at 0x7fb610df2ca0>
└ <concurrent.futures.thread._WorkItem object at 0x7fb5ead074d0>
File "/app/backend/open_webui/retrieval/utils.py", line 415, in process_query
result = query_doc_with_hybrid_search(
└ <function query_doc_with_hybrid_search at 0x7fb612da1760>
File "/app/backend/open_webui/retrieval/utils.py", line 211, in query_doc_with_hybrid_search
result = compression_retriever.invoke(query)
│ │ └ 'latest research on ketamine therapy safety'
│ └ <function BaseRetriever.invoke at 0x7fb612f8a2a0>
└ ContextualCompressionRetriever(base_compressor=RerankCompressor(embedding_function=<function chat_completion_files_handler.<l...
File "/usr/local/lib/python3.11/site-packages/langchain_core/retrievers.py", line 263, in invoke
result = self._get_relevant_documents(
│ └ <function ContextualCompressionRetriever._get_relevant_documents at 0x7fb612f8a020>
└ ContextualCompressionRetriever(base_compressor=RerankCompressor(embedding_function=<function chat_completion_files_handler.<l...
File "/usr/local/lib/python3.11/site-packages/langchain/retrievers/contextual_compression.py", line 46, in _get_relevant_documents
compressed_docs = self.base_compressor.compress_documents(
│ │ └ <function RerankCompressor.compress_documents at 0x7fb612da2200>
│ └ RerankCompressor(embedding_function=<function chat_completion_files_handler.... at 0x7fb61025...
└ ContextualCompressionRetriever(base_compressor=RerankCompressor(embedding_function=<function chat_completion_files_handler.<l...
File "/app/backend/open_webui/retrieval/utils.py", line 1053, in compress_documents
scores = self.reranking_function(
│ └ <function chat_completion_files_handler.... at 0x7fb610370ea0>
└ RerankCompressor(embedding_function=<function chat_completion_files_handler.... at 0x7fb61025...
File "/app/backend/open_webui/utils/middleware.py", line 892, in
lambda sentences: request.app.state.RERANKING_FUNCTION(
│ │ └ <property object at 0x7fb6c51584f0>
│ └ <starlette.requests.Request object at 0x7fb6104c2310>
└ [('latest research on ketamine therapy safety', "\n\n\n\n## Embracing Neurodiversity in Psychedel...
File "/app/backend/open_webui/retrieval/utils.py", line 510, in
return lambda sentences, user=None: reranking_function.predict(
│ │ └ <function ExternalReranker.predict at 0x7fb6112cef20>
│ └ <open_webui.retrieval.models.external.ExternalReranker object at 0x7fb6087be1d0>
└ [('latest research on ketamine therapy safety', "\n\n\n\n## Embracing Neurodiversity in Psychedel...
File "/app/backend/open_webui/retrieval/models/external.py", line 62, in predict
r.raise_for_status()
│ └ <function Response.raise_for_status at 0x7fb6c534afc0>
└ <Response [405]>
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1026, in raise_for_status
raise HTTPError(http_error_msg, response=self)
│ │ └ <Response [405]>
│ └ '405 Client Error: Method Not Allowed for url: http://localhost:11434/'
└ <class 'requests.exceptions.HTTPError'>
requests.exceptions.HTTPError: 405 Client Error: Method Not Allowed for url: http://localhost:11434/
2025-10-21 03:18:42.734 | WARNING | open_webui.retrieval.utils:compress_documents:1089 - No valid scores found, check your reranking function. Returning original documents.
Additional Information
Full context mode works as expected.
Problem wasn't evident initially when upgrading to v0.6.34 (may or may have been present), but was definitely noticeable when resetting and reindexing knowledgebase. There were no issues connecting to the embedded model with the same ollama instance.
Originally created by @98h398hrpohpoai on GitHub (Oct 21, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/18477
### 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
v0.6.34
### Ollama Version (if applicable)
v0.12.5
### Operating System
Debian 13
### Browser (if applicable)
Arc
### 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
When running hybrid search, results are sorted through reranker.
### Actual Behavior
Reranker is ignored.
Logs state error 405 method not allowed.
No config changes were made with this functioning in 0.6.32.
### Steps to Reproduce
Configure v0.6.34 with hybrid search using bundled ollama with default config.
Using open-webui/open-webui:ollama image.
### Logs & Screenshots
2025-10-21 03:18:42.718 | INFO | open_webui.retrieval.models.external:predict:40 - ExternalReranker:predict:model dengcao/Qwen3-Reranker-8B:f16
2025-10-21 03:18:42.718 | INFO | open_webui.retrieval.models.external:predict:41 - ExternalReranker:predict:query latest research
[GIN] 2025/10/21 - 03:18:42 | 405 | 7.921µs | 127.0.0.1 | POST "/"
2025-10-21 03:18:42.723 | ERROR | open_webui.retrieval.models.external:predict:73 - Error in external reranking: 405 Client Error: Method Not Allowed for url: http://localhost:11434/
Traceback (most recent call last):
File "/usr/local/lib/python3.11/threading.py", line 1002, in _bootstrap
self._bootstrap_inner()
│ └ <function Thread._bootstrap_inner at 0x7fb6c86c89a0>
└ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
File "/usr/local/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
self.run()
│ └ <function Thread.run at 0x7fb6c86c8680>
└ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
File "/usr/local/lib/python3.11/threading.py", line 982, in run
self._target(*self._args, **self._kwargs)
│ │ │ │ │ └ {}
│ │ │ │ └ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
│ │ │ └ (<weakref at 0x7fb5c94b31f0; to 'ThreadPoolExecutor' at 0x7fb58bdf8150>, <_queue.SimpleQueue object at 0x7fb5a9438a90>, None,...
│ │ └ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
│ └ <function _worker at 0x7fb6c77aa5c0>
└ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 83, in _worker
work_item.run()
│ └ <function _WorkItem.run at 0x7fb6c77aa700>
└ <concurrent.futures.thread._WorkItem object at 0x7fb5ead074d0>
File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
│ │ │ │ │ └ {}
│ │ │ │ └ <concurrent.futures.thread._WorkItem object at 0x7fb5ead074d0>
│ │ │ └ ('ca9366c0-09d1-47d4-ba5f-39f33c12bb8d', 'latest research on ketamine therapy safety')
│ │ └ <concurrent.futures.thread._WorkItem object at 0x7fb5ead074d0>
│ └ <function query_collection_with_hybrid_search.<locals>.process_query at 0x7fb610df2ca0>
└ <concurrent.futures.thread._WorkItem object at 0x7fb5ead074d0>
File "/app/backend/open_webui/retrieval/utils.py", line 415, in process_query
result = query_doc_with_hybrid_search(
└ <function query_doc_with_hybrid_search at 0x7fb612da1760>
File "/app/backend/open_webui/retrieval/utils.py", line 211, in query_doc_with_hybrid_search
result = compression_retriever.invoke(query)
│ │ └ 'latest research on ketamine therapy safety'
│ └ <function BaseRetriever.invoke at 0x7fb612f8a2a0>
└ ContextualCompressionRetriever(base_compressor=RerankCompressor(embedding_function=<function chat_completion_files_handler.<l...
File "/usr/local/lib/python3.11/site-packages/langchain_core/retrievers.py", line 263, in invoke
result = self._get_relevant_documents(
│ └ <function ContextualCompressionRetriever._get_relevant_documents at 0x7fb612f8a020>
└ ContextualCompressionRetriever(base_compressor=RerankCompressor(embedding_function=<function chat_completion_files_handler.<l...
File "/usr/local/lib/python3.11/site-packages/langchain/retrievers/contextual_compression.py", line 46, in _get_relevant_documents
compressed_docs = self.base_compressor.compress_documents(
│ │ └ <function RerankCompressor.compress_documents at 0x7fb612da2200>
│ └ RerankCompressor(embedding_function=<function chat_completion_files_handler.<locals>.<lambda>.<locals>.<lambda> at 0x7fb61025...
└ ContextualCompressionRetriever(base_compressor=RerankCompressor(embedding_function=<function chat_completion_files_handler.<l...
File "/app/backend/open_webui/retrieval/utils.py", line 1053, in compress_documents
scores = self.reranking_function(
│ └ <function chat_completion_files_handler.<locals>.<lambda>.<locals>.<lambda> at 0x7fb610370ea0>
└ RerankCompressor(embedding_function=<function chat_completion_files_handler.<locals>.<lambda>.<locals>.<lambda> at 0x7fb61025...
File "/app/backend/open_webui/utils/middleware.py", line 892, in <lambda>
lambda sentences: request.app.state.RERANKING_FUNCTION(
│ │ └ <property object at 0x7fb6c51584f0>
│ └ <starlette.requests.Request object at 0x7fb6104c2310>
└ [('latest research on ketamine therapy safety', "<!-- image -->\n\n<!-- image -->\n\n## Embracing Neurodiversity in Psychedel...
File "/app/backend/open_webui/retrieval/utils.py", line 510, in <lambda>
return lambda sentences, user=None: reranking_function.predict(
│ │ └ <function ExternalReranker.predict at 0x7fb6112cef20>
│ └ <open_webui.retrieval.models.external.ExternalReranker object at 0x7fb6087be1d0>
└ [('latest research on ketamine therapy safety', "<!-- image -->\n\n<!-- image -->\n\n## Embracing Neurodiversity in Psychedel...
> File "/app/backend/open_webui/retrieval/models/external.py", line 62, in predict
r.raise_for_status()
│ └ <function Response.raise_for_status at 0x7fb6c534afc0>
└ <Response [405]>
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1026, in raise_for_status
raise HTTPError(http_error_msg, response=self)
│ │ └ <Response [405]>
│ └ '405 Client Error: Method Not Allowed for url: http://localhost:11434/'
└ <class 'requests.exceptions.HTTPError'>
requests.exceptions.HTTPError: 405 Client Error: Method Not Allowed for url: http://localhost:11434/
2025-10-21 03:18:42.734 | WARNING | open_webui.retrieval.utils:compress_documents:1089 - No valid scores found, check your reranking function. Returning original documents.
<img width="2387" height="909" alt="Image" src="https://github.com/user-attachments/assets/a05885ab-1db0-4598-9857-9d2b11be7eea" />
### Additional Information
Full context mode works as expected.
Problem wasn't evident initially when upgrading to v0.6.34 (may or may have been present), but was definitely noticeable when resetting and reindexing knowledgebase. There were no issues connecting to the embedded model with the same ollama instance.
GiteaMirror
added the bug label 2026-05-05 20:48:21 -05:00
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 @98h398hrpohpoai on GitHub (Oct 21, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/18477
Check Existing Issues
Installation Method
Docker
Open WebUI Version
v0.6.34
Ollama Version (if applicable)
v0.12.5
Operating System
Debian 13
Browser (if applicable)
Arc
Confirmation
README.md.Expected Behavior
When running hybrid search, results are sorted through reranker.
Actual Behavior
Reranker is ignored.
Logs state error 405 method not allowed.
No config changes were made with this functioning in 0.6.32.
Steps to Reproduce
Configure v0.6.34 with hybrid search using bundled ollama with default config.
Using open-webui/open-webui:ollama image.
Logs & Screenshots
2025-10-21 03:18:42.718 | INFO | open_webui.retrieval.models.external:predict:40 - ExternalReranker:predict:model dengcao/Qwen3-Reranker-8B:f16
2025-10-21 03:18:42.718 | INFO | open_webui.retrieval.models.external:predict:41 - ExternalReranker:predict:query latest research
[GIN] 2025/10/21 - 03:18:42 | 405 | 7.921µs | 127.0.0.1 | POST "/"
2025-10-21 03:18:42.723 | ERROR | open_webui.retrieval.models.external:predict:73 - Error in external reranking: 405 Client Error: Method Not Allowed for url: http://localhost:11434/
Traceback (most recent call last):
File "/usr/local/lib/python3.11/threading.py", line 1002, in _bootstrap
self._bootstrap_inner()
│ └ <function Thread._bootstrap_inner at 0x7fb6c86c89a0>
└ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
File "/usr/local/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
self.run()
│ └ <function Thread.run at 0x7fb6c86c8680>
└ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
File "/usr/local/lib/python3.11/threading.py", line 982, in run
self._target(*self._args, **self._kwargs)
│ │ │ │ │ └ {}
│ │ │ │ └ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
│ │ │ └ (<weakref at 0x7fb5c94b31f0; to 'ThreadPoolExecutor' at 0x7fb58bdf8150>, <_queue.SimpleQueue object at 0x7fb5a9438a90>, None,...
│ │ └ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
│ └ <function _worker at 0x7fb6c77aa5c0>
└ <Thread(ThreadPoolExecutor-29_2, started 140419274876608)>
File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 83, in _worker
work_item.run()
│ └ <function _WorkItem.run at 0x7fb6c77aa700>
└ <concurrent.futures.thread._WorkItem object at 0x7fb5ead074d0>
File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
│ │ │ │ │ └ {}
│ │ │ │ └ <concurrent.futures.thread._WorkItem object at 0x7fb5ead074d0>
│ │ │ └ ('ca9366c0-09d1-47d4-ba5f-39f33c12bb8d', 'latest research on ketamine therapy safety')
│ │ └ <concurrent.futures.thread._WorkItem object at 0x7fb5ead074d0>
│ └ <function query_collection_with_hybrid_search..process_query at 0x7fb610df2ca0>
└ <concurrent.futures.thread._WorkItem object at 0x7fb5ead074d0>
File "/app/backend/open_webui/retrieval/utils.py", line 415, in process_query
result = query_doc_with_hybrid_search(
└ <function query_doc_with_hybrid_search at 0x7fb612da1760>
File "/app/backend/open_webui/retrieval/utils.py", line 211, in query_doc_with_hybrid_search
result = compression_retriever.invoke(query)
│ │ └ 'latest research on ketamine therapy safety'
│ └ <function BaseRetriever.invoke at 0x7fb612f8a2a0>
└ ContextualCompressionRetriever(base_compressor=RerankCompressor(embedding_function=<function chat_completion_files_handler.<l...
File "/usr/local/lib/python3.11/site-packages/langchain_core/retrievers.py", line 263, in invoke
result = self._get_relevant_documents(
│ └ <function ContextualCompressionRetriever._get_relevant_documents at 0x7fb612f8a020>
└ ContextualCompressionRetriever(base_compressor=RerankCompressor(embedding_function=<function chat_completion_files_handler.<l...
File "/usr/local/lib/python3.11/site-packages/langchain/retrievers/contextual_compression.py", line 46, in _get_relevant_documents
compressed_docs = self.base_compressor.compress_documents(
│ │ └ <function RerankCompressor.compress_documents at 0x7fb612da2200>
│ └ RerankCompressor(embedding_function=<function chat_completion_files_handler.... at 0x7fb61025...
└ ContextualCompressionRetriever(base_compressor=RerankCompressor(embedding_function=<function chat_completion_files_handler.<l...
File "/app/backend/open_webui/retrieval/utils.py", line 1053, in compress_documents
scores = self.reranking_function(
│ └ <function chat_completion_files_handler.... at 0x7fb610370ea0>
└ RerankCompressor(embedding_function=<function chat_completion_files_handler.... at 0x7fb61025...
File "/app/backend/open_webui/utils/middleware.py", line 892, in
lambda sentences: request.app.state.RERANKING_FUNCTION(
│ │ └ <property object at 0x7fb6c51584f0>
│ └ <starlette.requests.Request object at 0x7fb6104c2310>
└ [('latest research on ketamine therapy safety', "\n\n\n\n## Embracing Neurodiversity in Psychedel...
File "/app/backend/open_webui/retrieval/utils.py", line 510, in
return lambda sentences, user=None: reranking_function.predict(
│ │ └ <function ExternalReranker.predict at 0x7fb6112cef20>
│ └ <open_webui.retrieval.models.external.ExternalReranker object at 0x7fb6087be1d0>
└ [('latest research on ketamine therapy safety', "\n\n\n\n## Embracing Neurodiversity in Psychedel...
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1026, in raise_for_status
raise HTTPError(http_error_msg, response=self)
│ │ └ <Response [405]>
│ └ '405 Client Error: Method Not Allowed for url: http://localhost:11434/'
└ <class 'requests.exceptions.HTTPError'>
requests.exceptions.HTTPError: 405 Client Error: Method Not Allowed for url: http://localhost:11434/
2025-10-21 03:18:42.734 | WARNING | open_webui.retrieval.utils:compress_documents:1089 - No valid scores found, check your reranking function. Returning original documents.
Additional Information
Full context mode works as expected.
Problem wasn't evident initially when upgrading to v0.6.34 (may or may have been present), but was definitely noticeable when resetting and reindexing knowledgebase. There were no issues connecting to the embedded model with the same ollama instance.