[GH-ISSUE #14305] issue: Web Search Error: Incomplete error logging when fetching Tesla.cn with empty error object #17206

Closed
opened 2026-04-19 22:55:34 -05:00 by GiteaMirror · 4 comments
Owner

Originally created by @belugaming on GitHub (May 25, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14305

Check Existing Issues

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

Installation Method

Git Clone

Open WebUI Version

0.6.10

Ollama Version (if applicable)

No response

Operating System

macOS sequoia

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 listed steps to reproduce the bug in detail.

Expected Behavior

When the web search function encounters an error while fetching content from a website:

  1. The error message should contain detailed information about what went wrong
  2. Users should be able to see meaningful error details to understand why the fetch failed
  3. The system should provide actionable information (e.g., "403 Forbidden", "Connection timeout", etc.)

Actual Behavior

The web search function shows a warning with an empty error object when failing to fetch content from Tesla.cn:

  • Error message ends with - {} (empty object)
  • No meaningful error details are provided
  • Users cannot understand why the request failed

Steps to Reproduce

  1. Open Open WebUI interface
  2. Ask a question that would trigger web search for Tesla news (e.g., "最近特斯拉的新闻有没有")
  3. Observe the system attempting to fetch from https://www.tesla.cn/blog
  4. Check the logs for the warning message
  5. Note that the error object is empty: - {}

Logs & Screenshots

2025-05-25 02:29:43.906 | WARNING | langchain_community.document_loaders.web_base:_fetch_with_rate_limit:271 - Error fetching https://www.tesla.cn/blog,⁠ skipping due to continue_on_failure=True - {}

Additional Information

  • This appears to be related to the langchain_community.document_loaders.web_base module
  • The continue_on_failure=True setting causes the system to skip failed URLs silently
  • This makes debugging web search issues difficult for users and administrators
  • Suggested improvement: Capture and log the actual exception details instead of an empty object
Originally created by @belugaming on GitHub (May 25, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/14305 ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Git Clone ### Open WebUI Version 0.6.10 ### Ollama Version (if applicable) _No response_ ### Operating System macOS sequoia ### 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 listed steps to reproduce the bug in detail. ### Expected Behavior When the web search function encounters an error while fetching content from a website: 1. The error message should contain detailed information about what went wrong 2. Users should be able to see meaningful error details to understand why the fetch failed 3. The system should provide actionable information (e.g., "403 Forbidden", "Connection timeout", etc.) ### Actual Behavior The web search function shows a warning with an empty error object when failing to fetch content from Tesla.cn: - Error message ends with `- {}` (empty object) - No meaningful error details are provided - Users cannot understand why the request failed ### Steps to Reproduce 1. Open Open WebUI interface 2. Ask a question that would trigger web search for Tesla news (e.g., "最近特斯拉的新闻有没有") 3. Observe the system attempting to fetch from https://www.tesla.cn/blog 4. Check the logs for the warning message 5. Note that the error object is empty: `- {}` ### Logs & Screenshots 2025-05-25 02:29:43.906 | WARNING | langchain_community.document_loaders.web_base:_fetch_with_rate_limit:271 - Error fetching [https://www.tesla.cn/blog,⁠ ](https://www.tesla.cn/blog,%E2%81%A0)skipping due to continue_on_failure=True - {} ### Additional Information - This appears to be related to the langchain_community.document_loaders.web_base module - The `continue_on_failure=True` setting causes the system to skip failed URLs silently - This makes debugging web search issues difficult for users and administrators - Suggested improvement: Capture and log the actual exception details instead of an empty object
GiteaMirror added the bug label 2026-04-19 22:55:34 -05:00
Author
Owner

@tth37 commented on GitHub (May 25, 2025):

This functionality is provided by langchain_community, the web loader won't log out error messages when continue on failure is set. Maybe consider creating an issue under langchain project? Or just re-implement the web loader.

<!-- gh-comment-id:2907709304 --> @tth37 commented on GitHub (May 25, 2025): This functionality is provided by langchain_community, the web loader won't log out error messages when continue on failure is set. Maybe consider creating an issue under langchain project? Or just re-implement the web loader.
Author
Owner

@belugaming commented on GitHub (May 25, 2025):

此功能由 langchain_community 提供,当设置了“失败时继续”时,Web 加载器不会输出错误消息。或许可以考虑在 langchain 项目下创建一个问题?或者干脆重新实现 Web 加载器。

Thanks, my search function doesn't work now

<!-- gh-comment-id:2907738947 --> @belugaming commented on GitHub (May 25, 2025): > 此功能由 langchain_community 提供,当设置了“失败时继续”时,Web 加载器不会输出错误消息。或许可以考虑在 langchain 项目下创建一个问题?或者干脆重新实现 Web 加载器。 Thanks, my search function doesn't work now
Author
Owner

@tth37 commented on GitHub (May 25, 2025):

#14029 #14073 Already fixed in dev, for now just disable ssl validation to avoid the error

<!-- gh-comment-id:2907740803 --> @tth37 commented on GitHub (May 25, 2025): #14029 #14073 Already fixed in dev, for now just disable ssl validation to avoid the error
Author
Owner

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

or just adjust value of WEB_SEARCH_CONCURRENT_REQUESTS env var.
langchain_community.document_loaders.web_base lib is used on web scrap ( 82716f3789/backend/open_webui/retrieval/web/utils.py ) & it have a parameter(RateLimitMixin) that is dynamically setted based on that env var (82716f3789/backend/open_webui/routers/retrieval.py (L1368) )

<!-- gh-comment-id:2907748355 --> @rgaricano commented on GitHub (May 25, 2025): or just adjust value of WEB_SEARCH_CONCURRENT_REQUESTS env var. langchain_community.document_loaders.web_base lib is used on web scrap ( https://github.com/open-webui/open-webui/blob/82716f3789147585862f56f9f18fb2a77d92ed39/backend/open_webui/retrieval/web/utils.py ) & it have a parameter(RateLimitMixin) that is dynamically setted based on that env var (https://github.com/open-webui/open-webui/blob/82716f3789147585862f56f9f18fb2a77d92ed39/backend/open_webui/routers/retrieval.py#L1368 )
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#17206