github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-08-30 17:25:30 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

issue: Searching doesn't work, at all. #5052

New Issue
Closed
opened 2025-11-11 16:10:51 -06:00 by GiteaMirror · 4 comments
GiteaMirror commented 2025-11-11 16:10:51 -06:00
Owner
Copy Link
Copy Source

Originally created by @SerenoV7 on GitHub (May 5, 2025).

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

0.6.6

Ollama Version (if applicable)

No response

Operating System

Ubuntu 22.04.5 LTS x86_64 (Virtualized)

Browser (if applicable)

Zen Browser 1.12b (Firefox 138.0.1)

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 listed steps to reproduce the bug in detail.

Expected Behavior

When enabling search, the model is supposed to generate a search query and use that for the search

Actual Behavior

Instead of generating a search query, it errors out with Error: object of type 'NoneType' has no len() and searches that using whatever engine is provided (in my case duckduckgo)

Steps to Reproduce

  1. Enable Web Search in the settings
  2. Ask any model to search for anything

Logs & Screenshots

2025-05-05 20:30:28.670 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "POST /api/chat/completed HTTP/1.1" 200 - {}
2025-05-05 20:30:28.978 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-05-05 20:30:29.034 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "POST /api/v1/chats/983eb8b6-c458-46fb-b2d4-999832ea3562 HTTP/1.1" 200 - {}
2025-05-05 20:30:29.673 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-05-05 20:30:31.213 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "POST /api/v1/chats/983eb8b6-c458-46fb-b2d4-999832ea3562 HTTP/1.1" 200 - {}
2025-05-05 20:30:31.852 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
Original request body: {"model": "openrouter.google/gemini-2.0-flash-exp:free", "messages": [{"role": "user", "content": "### Task:\nAnalyze the chat history to determine the necessity of generating search queries, in the given language. By default, **prioritize generating 1-3 broad and relevant search queries** unless it is absolutely certain that no additional information is required. The aim is to retrieve comprehensive, updated, and valuable information even with minimal uncertainty. If no search is unequivocally ...
Extracted model ID: google/gemini-2.0-flash-exp:free
Sending non-streaming request to OpenRouter: {"model": "google/gemini-2.0-flash-exp:free", "messages": [{"role": "user", "content": "### Task:\nAnalyze the chat history to determine the necessity of generating search queries, in the given langua...
OpenRouter response keys: ['id', 'provider', 'model', 'object', 'created', 'choices', 'usage']
Message keys: ['role', 'content', 'refusal', 'reasoning']
Error in non_stream_response: object of type 'NoneType' has no len()
2025-05-05 20:30:34.069 | INFO     | open_webui.routers.retrieval:process_web_search:1572 - trying to web search with ('duckduckgo', "Error: object of type 'NoneType' has no len()") - {}
2025-05-05 20:30:35.006 | INFO     | duckduckgo_search.duckduckgo_search:_text_lite:274 - response: https://lite.duckduckgo.com/lite/ 200 - {}
Fetching pages: 100%|##########| 3/3 [00:00<00:00,  3.79it/s]
Original request body: {"model": "openrouter.google/gemini-2.0-flash-exp:free", "messages": [{"role": "user", "content": "### Task:\nAnalyze the chat history to determine the necessity of generating search queries, in the given language. By default, **prioritize generating 1-3 broad and relevant search queries** unless it is absolutely certain that no additional information is required. The aim is to retrieve comprehensive, updated, and valuable information even with minimal uncertainty. If no search is unequivocally ...
Extracted model ID: google/gemini-2.0-flash-exp:free
Sending non-streaming request to OpenRouter: {"model": "google/gemini-2.0-flash-exp:free", "messages": [{"role": "user", "content": "### Task:\nAnalyze the chat history to determine the necessity of generating search queries, in the given langua...
OpenRouter response keys: ['error', 'user_id']
Original request body: {"stream": true, "model": "openrouter.google/gemini-2.0-flash-exp:free", "messages": [{"role": "system", "content": "### Task:\nRespond to the user query using the provided context, incorporating inline citations in the format [id] **only when the <source> tag includes an explicit id attribute** (e.g., <source id=\"1\">).\n\n### Guidelines:\n- If you don't know the answer, clearly state that.\n- If uncertain, ask the user for clarification.\n- Respond in the same language as the user's query.\n-...
Extracted model ID: google/gemini-2.0-flash-exp:free
2025-05-05 20:30:39.703 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "POST /api/chat/completions HTTP/1.1" 200 - {}
2025-05-05 20:30:40.035 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-05-05 20:30:40.065 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "POST /api/chat/completed HTTP/1.1" 200 - {}
2025-05-05 20:30:41.037 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "POST /api/v1/chats/983eb8b6-c458-46fb-b2d4-999832ea3562 HTTP/1.1" 200 - {}
2025-05-05 20:30:41.677 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}```

![Image](https://github.com/user-attachments/assets/7e277599-97c1-4dd5-8bdb-be3a772e36a8)

### Additional Information

I use models from OpenRouter, whenever I try to use the search feature with whatever search engine I pick, it never manages to generate a search query and just constantly searches for `Error: object of type 'NoneType' has no len()`
Originally created by @SerenoV7 on GitHub (May 5, 2025). ### 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 0.6.6 ### Ollama Version (if applicable) _No response_ ### Operating System Ubuntu 22.04.5 LTS x86_64 (Virtualized) ### Browser (if applicable) Zen Browser 1.12b (Firefox 138.0.1) ### 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 listed steps to reproduce the bug in detail. ### Expected Behavior When enabling search, the model is supposed to generate a search query and use that for the search ### Actual Behavior Instead of generating a search query, it errors out with `Error: object of type 'NoneType' has no len()` and searches that using whatever engine is provided (in my case duckduckgo) ### Steps to Reproduce 1. Enable Web Search in the settings 2. Ask any model to search for anything ### Logs & Screenshots ```2025-05-05 20:30:28.651 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-05-05 20:30:28.670 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "POST /api/chat/completed HTTP/1.1" 200 - {} 2025-05-05 20:30:28.978 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-05-05 20:30:29.034 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "POST /api/v1/chats/983eb8b6-c458-46fb-b2d4-999832ea3562 HTTP/1.1" 200 - {} 2025-05-05 20:30:29.673 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-05-05 20:30:31.213 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "POST /api/v1/chats/983eb8b6-c458-46fb-b2d4-999832ea3562 HTTP/1.1" 200 - {} 2025-05-05 20:30:31.852 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} Original request body: {"model": "openrouter.google/gemini-2.0-flash-exp:free", "messages": [{"role": "user", "content": "### Task:\nAnalyze the chat history to determine the necessity of generating search queries, in the given language. By default, **prioritize generating 1-3 broad and relevant search queries** unless it is absolutely certain that no additional information is required. The aim is to retrieve comprehensive, updated, and valuable information even with minimal uncertainty. If no search is unequivocally ... Extracted model ID: google/gemini-2.0-flash-exp:free Sending non-streaming request to OpenRouter: {"model": "google/gemini-2.0-flash-exp:free", "messages": [{"role": "user", "content": "### Task:\nAnalyze the chat history to determine the necessity of generating search queries, in the given langua... OpenRouter response keys: ['id', 'provider', 'model', 'object', 'created', 'choices', 'usage'] Message keys: ['role', 'content', 'refusal', 'reasoning'] Error in non_stream_response: object of type 'NoneType' has no len() 2025-05-05 20:30:34.069 | INFO | open_webui.routers.retrieval:process_web_search:1572 - trying to web search with ('duckduckgo', "Error: object of type 'NoneType' has no len()") - {} 2025-05-05 20:30:35.006 | INFO | duckduckgo_search.duckduckgo_search:_text_lite:274 - response: https://lite.duckduckgo.com/lite/ 200 - {} Fetching pages: 100%|##########| 3/3 [00:00<00:00, 3.79it/s] Original request body: {"model": "openrouter.google/gemini-2.0-flash-exp:free", "messages": [{"role": "user", "content": "### Task:\nAnalyze the chat history to determine the necessity of generating search queries, in the given language. By default, **prioritize generating 1-3 broad and relevant search queries** unless it is absolutely certain that no additional information is required. The aim is to retrieve comprehensive, updated, and valuable information even with minimal uncertainty. If no search is unequivocally ... Extracted model ID: google/gemini-2.0-flash-exp:free Sending non-streaming request to OpenRouter: {"model": "google/gemini-2.0-flash-exp:free", "messages": [{"role": "user", "content": "### Task:\nAnalyze the chat history to determine the necessity of generating search queries, in the given langua... OpenRouter response keys: ['error', 'user_id'] Original request body: {"stream": true, "model": "openrouter.google/gemini-2.0-flash-exp:free", "messages": [{"role": "system", "content": "### Task:\nRespond to the user query using the provided context, incorporating inline citations in the format [id] **only when the <source> tag includes an explicit id attribute** (e.g., <source id=\"1\">).\n\n### Guidelines:\n- If you don't know the answer, clearly state that.\n- If uncertain, ask the user for clarification.\n- Respond in the same language as the user's query.\n-... Extracted model ID: google/gemini-2.0-flash-exp:free 2025-05-05 20:30:39.703 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "POST /api/chat/completions HTTP/1.1" 200 - {} 2025-05-05 20:30:40.035 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-05-05 20:30:40.065 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "POST /api/chat/completed HTTP/1.1" 200 - {} 2025-05-05 20:30:41.037 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "POST /api/v1/chats/983eb8b6-c458-46fb-b2d4-999832ea3562 HTTP/1.1" 200 - {} 2025-05-05 20:30:41.677 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 81.56.30.233:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}``` ![Image](https://github.com/user-attachments/assets/7e277599-97c1-4dd5-8bdb-be3a772e36a8) ### Additional Information I use models from OpenRouter, whenever I try to use the search feature with whatever search engine I pick, it never manages to generate a search query and just constantly searches for `Error: object of type 'NoneType' has no len()`
GiteaMirror added the bug label 2025-11-11 16:10:51 -06:00
GiteaMirror commented 2025-11-11 16:10:52 -06:00
Author
Owner
Copy Link
Copy Source

@mMabeck commented on GitHub (May 6, 2025):

Can you use the model openrouter.google/gemini-2.0-flash-exp:free normally in chat?
Otherwise try disabling search query generation in the admin settings.

@mMabeck commented on GitHub (May 6, 2025): Can you use the model openrouter.google/gemini-2.0-flash-exp:free normally in chat? Otherwise try disabling search query generation in the admin settings.
GiteaMirror commented 2025-11-11 16:10:52 -06:00
Author
Owner
Copy Link
Copy Source

@SerenoV7 commented on GitHub (May 6, 2025):

Can you use the model openrouter.google/gemini-2.0-flash-exp:free normally in chat? Otherwise try disabling search query generation in the admin settings.

Yes I can use all models from openrouter correctly in normal chat and they even work with image generation, but as soon as I try to do web search it breaks

@SerenoV7 commented on GitHub (May 6, 2025): > Can you use the model openrouter.google/gemini-2.0-flash-exp:free normally in chat? Otherwise try disabling search query generation in the admin settings. Yes I can use all models from openrouter correctly in normal chat and they even work with image generation, but as soon as I try to do web search it breaks
GiteaMirror commented 2025-11-11 16:10:52 -06:00
Author
Owner
Copy Link
Copy Source

@Classic298 commented on GitHub (May 6, 2025):

I don't really see any error messages in the logs. What RAG settings do you have set? what is your GLOBAL_LOG_LEVEL set to? It's odd that it would fail silently without logs.

@Classic298 commented on GitHub (May 6, 2025): I don't really see any error messages in the logs. What RAG settings do you have set? what is your GLOBAL_LOG_LEVEL set to? It's odd that it would fail silently without logs.
GiteaMirror commented 2025-11-11 16:10:52 -06:00
Author
Owner
Copy Link
Copy Source

@SerenoV7 commented on GitHub (May 6, 2025):

I don't really see any error messages in the logs. What RAG settings do you have set? what is your GLOBAL_LOG_LEVEL set to? It's odd that it would fail silently without logs.

Most of my settings are just the defaults that come with OpenWebUI's Docker Image so dunno what to say

@SerenoV7 commented on GitHub (May 6, 2025): > I don't really see any error messages in the logs. What RAG settings do you have set? what is your GLOBAL_LOG_LEVEL set to? It's odd that it would fail silently without logs. Most of my settings are just the defaults that come with OpenWebUI's Docker Image so dunno what to say
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 labels bug
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#5052