github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-05-08 04:16:03 -05:00
Code Issues 1.3k Packages Projects Releases 126 Wiki Activity

[GH-ISSUE #16896] issue: HybridSearch ZeroDivisionError: division by zero #33619

New Issue
Closed
opened 2026-04-25 07:31:21 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-25 07:31:21 -05:00
Owner
Copy Link

Originally created by @Schwenn2002 on GitHub (Aug 25, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16896

Check Existing Issues

  • I have searched the existing issues and discussions.
  • I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

v0.6.25

Ollama Version (if applicable)

ollama 0.11.6

Operating System

Ubuntu 24.04

Browser (if applicable)

chrome

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 expected result is that documents are displayed from the RAG and the API returns corresponding chunks.``

Actual Behavior

I get an error when querying RAG (http status 400) and in the Docker log there is an error for the hybrid search.

Test via the API:
/api/v1/retrieval/query/Collection

{
  "collection_names": [
    "3ce4b804-6c65-46c2-b93c-b6aec5345742"
  ],
  "query": "XXX some Text XXX",
  "k": 10,
  "k_reranker": 10,
  "r": 0.8,
  "hybrid": false,
  "hybrid_bm25_weight": 0.6
}

Steps to Reproduce

Go to the URL /docs#/retrieval/query_collection_handler_api_v1_retrieval_query_collection_post and execute a test API query.

Logs & Screenshots

██████╗ ██████╗ ███████╗███╗ ██╗ ██╗ ██╗███████╗██████╗ ██╗ ██╗██╗
██╔═══██╗██╔══██╗██╔════╝████╗ ██║ ██║ ██║██╔════╝██╔══██╗██║ ██║██║
██║ ██║██████╔╝█████╗ ██╔██╗ ██║ ██║ █╗ ██║█████╗ ██████╔╝██║ ██║██║
██║ ██║██╔═══╝ ██╔══╝ ██║╚██╗██║ ██║███╗██║██╔══╝ ██╔══██╗██║ ██║██║
╚██████╔╝██║ ███████╗██║ ╚████║ ╚███╔███╔╝███████╗██████╔╝╚██████╔╝██║
╚═════╝ ╚═╝ ╚══════╝╚═╝ ╚═══╝ ╚══╝╚══╝ ╚══════╝╚═════╝ ╚═════╝ ╚═╝

v0.6.25 - building the best AI user interface.

https://github.com/open-webui/open-webui

Fetching 22 files: 100%|██████████| 22/22 [00:00<00:00, 75697.04it/s]
Fetching 13 files: 100%|██████████| 13/13 [00:00<00:00, 46843.60it/s]
INFO: Started server process [1]
INFO: Waiting for application startup.
2025-08-25 14:29:34.620 | ERROR | open_webui.retrieval.utils:query_doc_with_hybrid_search:193 - Error querying doc 3ce4b804-6c65-46c2-b93c-b6aec5345742 with hybrid search: division by zero
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 0x7487f3740a40>
└ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)>
File "/usr/local/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
self.run()
│ └ <function Thread.run at 0x7487f3740720>
└ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)>
File "/usr/local/lib/python3.11/threading.py", line 982, in run
self._target(*self._args, **self._kwargs)
│ │ │ │ │ └ {}
│ │ │ │ └ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)>
│ │ │ └ (<weakref at 0x7484756ad3f0; to 'ThreadPoolExecutor' at 0x748477acb050>, <_queue.SimpleQueue object at 0x748475569f30>, None,...
│ │ └ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)>
│ └ <function _worker at 0x7487f2814a40>
└ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)>
File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 83, in _worker
work_item.run()
│ └ <function _WorkItem.run at 0x7487f2814b80>
└ <concurrent.futures.thread._WorkItem object at 0x748477aaea50>
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 0x748477aaea50>
│ │ │ └ ('3ce4b804-6c65-46c2-b93c-b6aec5345742', 'Liegt ein IKT-Managementrahmen vor')
│ │ └ <concurrent.futures.thread._WorkItem object at 0x748477aaea50>
│ └ <function query_collection_with_hybrid_search..process_query at 0x7484756ce520>
└ <concurrent.futures.thread._WorkItem object at 0x748477aaea50>

File "/app/backend/open_webui/retrieval/utils.py", line 364, in process_query
result = query_doc_with_hybrid_search(
└ <function query_doc_with_hybrid_search at 0x7484ec289b20>

File "/app/backend/open_webui/retrieval/utils.py", line 130, in query_doc_with_hybrid_search
bm25_retriever = BM25Retriever.from_texts(
│ └ <classmethod(<function BM25Retriever.from_texts at 0x7484ec288400>)>
└ <class 'langchain_community.retrievers.bm25.BM25Retriever'>

File "/usr/local/lib/python3.11/site-packages/langchain_community/retrievers/bm25.py", line 64, in from_texts
vectorizer = BM25Okapi(texts_processed, **bm25_params)
│ │ └ {}
│ └ []
└ <class 'rank_bm25.BM25Okapi'>
File "/usr/local/lib/python3.11/site-packages/rank_bm25.py", line 83, in init
super().init(corpus, tokenizer)
│ └ None
└ []
File "/usr/local/lib/python3.11/site-packages/rank_bm25.py", line 27, in init
nd = self._initialize(corpus)
│ │ └ []
│ └ <function BM25._initialize at 0x7484755f0cc0>
└ <rank_bm25.BM25Okapi object at 0x7484755e1a90>
File "/usr/local/lib/python3.11/site-packages/rank_bm25.py", line 52, in _initialize
self.avgdl = num_doc / self.corpus_size
│ │ │ │ └ 0
│ │ │ └ <rank_bm25.BM25Okapi object at 0x7484755e1a90>
│ │ └ 0
│ └ 0
└ <rank_bm25.BM25Okapi object at 0x7484755e1a90>

ZeroDivisionError: division by zero
2025-08-25 14:29:34.622 | ERROR | open_webui.retrieval.utils:process_query:377 - Error when querying the collection with hybrid_search: division by zero
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 0x7487f3740a40>
└ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)>
File "/usr/local/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
self.run()
│ └ <function Thread.run at 0x7487f3740720>
└ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)>
File "/usr/local/lib/python3.11/threading.py", line 982, in run
self._target(*self._args, **self._kwargs)
│ │ │ │ │ └ {}
│ │ │ │ └ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)>
│ │ │ └ (<weakref at 0x7484756ad3f0; to 'ThreadPoolExecutor' at 0x748477acb050>, <_queue.SimpleQueue object at 0x748475569f30>, None,...
│ │ └ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)>
│ └ <function _worker at 0x7487f2814a40>
└ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)>
File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 83, in _worker
work_item.run()
│ └ <function _WorkItem.run at 0x7487f2814b80>
└ <concurrent.futures.thread._WorkItem object at 0x748477aaea50>
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 0x748477aaea50>
│ │ │ └ ('3ce4b804-6c65-46c2-b93c-b6aec5345742', 'Liegt ein IKT-Managementrahmen vor')
│ │ └ <concurrent.futures.thread._WorkItem object at 0x748477aaea50>
│ └ <function query_collection_with_hybrid_search..process_query at 0x7484756ce520>
└ <concurrent.futures.thread._WorkItem object at 0x748477aaea50>

File "/app/backend/open_webui/retrieval/utils.py", line 364, in process_query
result = query_doc_with_hybrid_search(
└ <function query_doc_with_hybrid_search at 0x7484ec289b20>

File "/app/backend/open_webui/retrieval/utils.py", line 194, in query_doc_with_hybrid_search
raise e

File "/app/backend/open_webui/retrieval/utils.py", line 130, in query_doc_with_hybrid_search
bm25_retriever = BM25Retriever.from_texts(
│ └ <classmethod(<function BM25Retriever.from_texts at 0x7484ec288400>)>
└ <class 'langchain_community.retrievers.bm25.BM25Retriever'>

File "/usr/local/lib/python3.11/site-packages/langchain_community/retrievers/bm25.py", line 64, in from_texts
vectorizer = BM25Okapi(texts_processed, **bm25_params)
│ │ └ {}
│ └ []
└ <class 'rank_bm25.BM25Okapi'>
File "/usr/local/lib/python3.11/site-packages/rank_bm25.py", line 83, in init
super().init(corpus, tokenizer)
│ └ None
└ []
File "/usr/local/lib/python3.11/site-packages/rank_bm25.py", line 27, in init
nd = self._initialize(corpus)
│ │ └ []
│ └ <function BM25._initialize at 0x7484755f0cc0>
└ <rank_bm25.BM25Okapi object at 0x7484755e1a90>
File "/usr/local/lib/python3.11/site-packages/rank_bm25.py", line 52, in _initialize
self.avgdl = num_doc / self.corpus_size
│ │ │ │ └ 0
│ │ │ └ <rank_bm25.BM25Okapi object at 0x7484755e1a90>
│ │ └ 0
│ └ 0
└ <rank_bm25.BM25Okapi object at 0x7484755e1a90>

ZeroDivisionError: division by zero
2025-08-25 14:29:34.623 | ERROR | open_webui.routers.retrieval:query_collection_handler:2189 - Hybrid search failed for all collections. Using Non-hybrid search as fallback.
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 0x7487f3740a40>
└ <WorkerThread(AnyIO worker thread, started 128106283116224)>
File "/usr/local/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
self.run()
│ └ <function WorkerThread.run at 0x7484762d2700>
└ <WorkerThread(AnyIO worker thread, started 128106283116224)>
File "/usr/local/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 967, in run
result = context.run(func, *args)
│ │ │ └ ()
│ │ └ functools.partial(<function query_collection_handler at 0x7484ec31c220>, user=UserModel(id='4dcd7332-88b8-4ba4-b910-db56289de...
│ └ <method 'run' of '_contextvars.Context' objects>
└ <_contextvars.Context object at 0x748477aace40>

File "/app/backend/open_webui/routers/retrieval.py", line 2149, in query_collection_handler
return query_collection_with_hybrid_search(
└ <function query_collection_with_hybrid_search at 0x7484ec289e40>

File "/app/backend/open_webui/retrieval/utils.py", line 400, in query_collection_with_hybrid_search
raise Exception(

Exception: Hybrid search failed for all collections. Using Non-hybrid search as fallback.

Additional Information

No response

Originally created by @Schwenn2002 on GitHub (Aug 25, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/16896 ### 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 v0.6.25 ### Ollama Version (if applicable) ollama 0.11.6 ### Operating System Ubuntu 24.04 ### Browser (if applicable) chrome ### 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 expected result is that documents are displayed from the RAG and the API returns corresponding chunks.`` ### Actual Behavior I get an error when querying RAG (http status 400) and in the Docker log there is an error for the hybrid search. Test via the API: /api/v1/retrieval/query/Collection ``` { "collection_names": [ "3ce4b804-6c65-46c2-b93c-b6aec5345742" ], "query": "XXX some Text XXX", "k": 10, "k_reranker": 10, "r": 0.8, "hybrid": false, "hybrid_bm25_weight": 0.6 } ``` ### Steps to Reproduce Go to the URL /docs#/retrieval/query_collection_handler_api_v1_retrieval_query_collection_post and execute a test API query. ### Logs & Screenshots ██████╗ ██████╗ ███████╗███╗ ██╗ ██╗ ██╗███████╗██████╗ ██╗ ██╗██╗ ██╔═══██╗██╔══██╗██╔════╝████╗ ██║ ██║ ██║██╔════╝██╔══██╗██║ ██║██║ ██║ ██║██████╔╝█████╗ ██╔██╗ ██║ ██║ █╗ ██║█████╗ ██████╔╝██║ ██║██║ ██║ ██║██╔═══╝ ██╔══╝ ██║╚██╗██║ ██║███╗██║██╔══╝ ██╔══██╗██║ ██║██║ ╚██████╔╝██║ ███████╗██║ ╚████║ ╚███╔███╔╝███████╗██████╔╝╚██████╔╝██║ ╚═════╝ ╚═╝ ╚══════╝╚═╝ ╚═══╝ ╚══╝╚══╝ ╚══════╝╚═════╝ ╚═════╝ ╚═╝ v0.6.25 - building the best AI user interface. https://github.com/open-webui/open-webui Fetching 22 files: 100%|██████████| 22/22 [00:00<00:00, 75697.04it/s] Fetching 13 files: 100%|██████████| 13/13 [00:00<00:00, 46843.60it/s] INFO: Started server process [1] INFO: Waiting for application startup. 2025-08-25 14:29:34.620 | ERROR | open_webui.retrieval.utils:query_doc_with_hybrid_search:193 - Error querying doc 3ce4b804-6c65-46c2-b93c-b6aec5345742 with hybrid search: division by zero 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 0x7487f3740a40> └ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)> File "/usr/local/lib/python3.11/threading.py", line 1045, in _bootstrap_inner self.run() │ └ <function Thread.run at 0x7487f3740720> └ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)> File "/usr/local/lib/python3.11/threading.py", line 982, in run self._target(*self._args, **self._kwargs) │ │ │ │ │ └ {} │ │ │ │ └ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)> │ │ │ └ (<weakref at 0x7484756ad3f0; to 'ThreadPoolExecutor' at 0x748477acb050>, <_queue.SimpleQueue object at 0x748475569f30>, None,... │ │ └ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)> │ └ <function _worker at 0x7487f2814a40> └ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)> File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 83, in _worker work_item.run() │ └ <function _WorkItem.run at 0x7487f2814b80> └ <concurrent.futures.thread._WorkItem object at 0x748477aaea50> 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 0x748477aaea50> │ │ │ └ ('3ce4b804-6c65-46c2-b93c-b6aec5345742', 'Liegt ein IKT-Managementrahmen vor') │ │ └ <concurrent.futures.thread._WorkItem object at 0x748477aaea50> │ └ <function query_collection_with_hybrid_search.<locals>.process_query at 0x7484756ce520> └ <concurrent.futures.thread._WorkItem object at 0x748477aaea50> File "/app/backend/open_webui/retrieval/utils.py", line 364, in process_query result = query_doc_with_hybrid_search( └ <function query_doc_with_hybrid_search at 0x7484ec289b20> > File "/app/backend/open_webui/retrieval/utils.py", line 130, in query_doc_with_hybrid_search bm25_retriever = BM25Retriever.from_texts( │ └ <classmethod(<function BM25Retriever.from_texts at 0x7484ec288400>)> └ <class 'langchain_community.retrievers.bm25.BM25Retriever'> File "/usr/local/lib/python3.11/site-packages/langchain_community/retrievers/bm25.py", line 64, in from_texts vectorizer = BM25Okapi(texts_processed, **bm25_params) │ │ └ {} │ └ [] └ <class 'rank_bm25.BM25Okapi'> File "/usr/local/lib/python3.11/site-packages/rank_bm25.py", line 83, in __init__ super().__init__(corpus, tokenizer) │ └ None └ [] File "/usr/local/lib/python3.11/site-packages/rank_bm25.py", line 27, in __init__ nd = self._initialize(corpus) │ │ └ [] │ └ <function BM25._initialize at 0x7484755f0cc0> └ <rank_bm25.BM25Okapi object at 0x7484755e1a90> File "/usr/local/lib/python3.11/site-packages/rank_bm25.py", line 52, in _initialize self.avgdl = num_doc / self.corpus_size │ │ │ │ └ 0 │ │ │ └ <rank_bm25.BM25Okapi object at 0x7484755e1a90> │ │ └ 0 │ └ 0 └ <rank_bm25.BM25Okapi object at 0x7484755e1a90> ZeroDivisionError: division by zero 2025-08-25 14:29:34.622 | ERROR | open_webui.retrieval.utils:process_query:377 - Error when querying the collection with hybrid_search: division by zero 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 0x7487f3740a40> └ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)> File "/usr/local/lib/python3.11/threading.py", line 1045, in _bootstrap_inner self.run() │ └ <function Thread.run at 0x7487f3740720> └ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)> File "/usr/local/lib/python3.11/threading.py", line 982, in run self._target(*self._args, **self._kwargs) │ │ │ │ │ └ {} │ │ │ │ └ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)> │ │ │ └ (<weakref at 0x7484756ad3f0; to 'ThreadPoolExecutor' at 0x748477acb050>, <_queue.SimpleQueue object at 0x748475569f30>, None,... │ │ └ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)> │ └ <function _worker at 0x7487f2814a40> └ <Thread(ThreadPoolExecutor-4_0, started 128105721099968)> File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 83, in _worker work_item.run() │ └ <function _WorkItem.run at 0x7487f2814b80> └ <concurrent.futures.thread._WorkItem object at 0x748477aaea50> 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 0x748477aaea50> │ │ │ └ ('3ce4b804-6c65-46c2-b93c-b6aec5345742', 'Liegt ein IKT-Managementrahmen vor') │ │ └ <concurrent.futures.thread._WorkItem object at 0x748477aaea50> │ └ <function query_collection_with_hybrid_search.<locals>.process_query at 0x7484756ce520> └ <concurrent.futures.thread._WorkItem object at 0x748477aaea50> > File "/app/backend/open_webui/retrieval/utils.py", line 364, in process_query result = query_doc_with_hybrid_search( └ <function query_doc_with_hybrid_search at 0x7484ec289b20> File "/app/backend/open_webui/retrieval/utils.py", line 194, in query_doc_with_hybrid_search raise e File "/app/backend/open_webui/retrieval/utils.py", line 130, in query_doc_with_hybrid_search bm25_retriever = BM25Retriever.from_texts( │ └ <classmethod(<function BM25Retriever.from_texts at 0x7484ec288400>)> └ <class 'langchain_community.retrievers.bm25.BM25Retriever'> File "/usr/local/lib/python3.11/site-packages/langchain_community/retrievers/bm25.py", line 64, in from_texts vectorizer = BM25Okapi(texts_processed, **bm25_params) │ │ └ {} │ └ [] └ <class 'rank_bm25.BM25Okapi'> File "/usr/local/lib/python3.11/site-packages/rank_bm25.py", line 83, in __init__ super().__init__(corpus, tokenizer) │ └ None └ [] File "/usr/local/lib/python3.11/site-packages/rank_bm25.py", line 27, in __init__ nd = self._initialize(corpus) │ │ └ [] │ └ <function BM25._initialize at 0x7484755f0cc0> └ <rank_bm25.BM25Okapi object at 0x7484755e1a90> File "/usr/local/lib/python3.11/site-packages/rank_bm25.py", line 52, in _initialize self.avgdl = num_doc / self.corpus_size │ │ │ │ └ 0 │ │ │ └ <rank_bm25.BM25Okapi object at 0x7484755e1a90> │ │ └ 0 │ └ 0 └ <rank_bm25.BM25Okapi object at 0x7484755e1a90> ZeroDivisionError: division by zero 2025-08-25 14:29:34.623 | ERROR | open_webui.routers.retrieval:query_collection_handler:2189 - Hybrid search failed for all collections. Using Non-hybrid search as fallback. 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 0x7487f3740a40> └ <WorkerThread(AnyIO worker thread, started 128106283116224)> File "/usr/local/lib/python3.11/threading.py", line 1045, in _bootstrap_inner self.run() │ └ <function WorkerThread.run at 0x7484762d2700> └ <WorkerThread(AnyIO worker thread, started 128106283116224)> File "/usr/local/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 967, in run result = context.run(func, *args) │ │ │ └ () │ │ └ functools.partial(<function query_collection_handler at 0x7484ec31c220>, user=UserModel(id='4dcd7332-88b8-4ba4-b910-db56289de... │ └ <method 'run' of '_contextvars.Context' objects> └ <_contextvars.Context object at 0x748477aace40> > File "/app/backend/open_webui/routers/retrieval.py", line 2149, in query_collection_handler return query_collection_with_hybrid_search( └ <function query_collection_with_hybrid_search at 0x7484ec289e40> File "/app/backend/open_webui/retrieval/utils.py", line 400, in query_collection_with_hybrid_search raise Exception( Exception: Hybrid search failed for all collections. Using Non-hybrid search as fallback. ### Additional Information _No response_
GiteaMirror added the bug label 2026-04-25 07:31:21 -05:00
GiteaMirror commented 2026-04-25 07:31:23 -05:00
Author
Owner
Copy Link

@rgaricano commented on GitHub (Aug 25, 2025):

That error happend when hybrid search return a empty sets or malformed similarity scores in your specific collection data.
Probably because it doesn't found any doc with relevance in the range of the indicated in the request.

By the way, I made a PR for fix hybrid param because it is not handled correctly: if the request have "hybrid": "false" the hybrid search should be ignored (regardless of other parameters).

PR for fix both: https://github.com/open-webui/open-webui/pull/16901

<!-- gh-comment-id:3220717518 --> @rgaricano commented on GitHub (Aug 25, 2025): That error happend when hybrid search return a empty sets or malformed similarity scores in your specific collection data. Probably because it doesn't found any doc with relevance in the range of the indicated in the request. By the way, I made a PR for fix hybrid param because it is not handled correctly: if the request have "hybrid": "false" the hybrid search should be ignored (regardless of other parameters). PR for fix both: https://github.com/open-webui/open-webui/pull/16901
GiteaMirror commented 2026-04-25 07:31:23 -05:00
Author
Owner
Copy Link

@mahenning commented on GitHub (Aug 26, 2025):

The error points to BM25, which happens before the similarity scores. The line self.avgdl = num_doc / self.corpus_size throws it (related: https://github.com/run-llama/llama_index/issues/9024).
This means that the size of the input text is 0 (no text). Is the document scanned or something? Can you test with another document?

<!-- gh-comment-id:3223080188 --> @mahenning commented on GitHub (Aug 26, 2025): The error points to BM25, which happens before the similarity scores. The line `self.avgdl = num_doc / self.corpus_size` throws it (related: [https://github.com/run-llama/llama_index/issues/9024](https://github.com/run-llama/llama_index/issues/9024)). This means that the size of the input text is 0 (no text). Is the document scanned or something? Can you test with another document?
GiteaMirror commented 2026-04-25 07:31:25 -05:00
Author
Owner
Copy Link

@tjbck commented on GitHub (Aug 26, 2025):

This will occur when there aren't any documents, addressed in dev to display an error message.

<!-- gh-comment-id:3226055498 --> @tjbck commented on GitHub (Aug 26, 2025): This will occur when there aren't any documents, addressed in dev to display an error message.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
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
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#33619
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?