github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-07-27 17:04:57 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

issue: Model can't access web search results despite seemingly successfully retrieving them #5672

New Issue
Closed
opened 2025-11-11 16:28:35 -06:00 by GiteaMirror · 3 comments
GiteaMirror commented 2025-11-11 16:28:35 -06:00
Owner
Copy Link
Copy Source

Originally created by @mateocovacho on GitHub (Jun 30, 2025).

Originally assigned to: @jackthgu on GitHub.

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

v0.6.15

Ollama Version (if applicable)

No response

Operating System

Debian

Browser (if applicable)

Firefox

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

Give an answer with the web search results taken into context

Actual Behavior

The models answer as if it expects a response but is given a blank one

However, it has access to the query result URLs, so a issue with the search engine can be ruled out

Steps to Reproduce

Activate websearch
Set it to duckduckgo or Searxng

Logs & Screenshots

Image

Additional Information

No response

Originally created by @mateocovacho on GitHub (Jun 30, 2025). Originally assigned to: @jackthgu on GitHub. ### 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 v0.6.15 ### Ollama Version (if applicable) _No response_ ### Operating System Debian ### Browser (if applicable) Firefox ### 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 Give an answer with the web search results taken into context ### Actual Behavior The models answer as if it expects a response but is given a blank one However, it has access to the query result URLs, so a issue with the search engine can be ruled out ### Steps to Reproduce Activate websearch Set it to duckduckgo or Searxng ### Logs & Screenshots ![Image](https://github.com/user-attachments/assets/6160afad-d79b-4c76-9ed5-d04d69b9684f) ### Additional Information _No response_
GiteaMirror added the bug label 2025-11-11 16:28:35 -06:00
GiteaMirror commented 2025-11-11 16:28:38 -06:00
Author
Owner
Copy Link
Copy Source

@mateocovacho commented on GitHub (Jun 30, 2025):

No special console logs btw

@mateocovacho commented on GitHub (Jun 30, 2025): No special console logs btw
GiteaMirror commented 2025-11-11 16:28:38 -06:00
Author
Owner
Copy Link
Copy Source

@jackthgu commented on GitHub (Jul 1, 2025):

Hello, @mateocovacho

regarding the web-search issue you reported, I suspect two main causes:

  1. The model’s context window is too small, so some content is omitted.
  2. After obtaining URLs from the search engine, the crawler’s return visit to those URLs may be blocked by bot-detection mechanisms.

Based on this, please check the following:

  1. In the backend logs, look for tokens_prompt=. If it seems large, lower WEB_SEARCH_RESULT_COUNT and try again.

  2. Test the BYPASS variables:

    • BYPASS_WEB_SEARCH_WEB_LOADER=True → use only the URL snippet.
    • BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL=True → skip embedding and retrieval.

  3. Change the loader engine: modify the WEB_LOADER_ENGINE variable and test again.

  4. Run curl <document_URL>; if access is blocked, set http_proxy / https_proxy and review the WEB_SEARCH_TRUST_ENV setting.

Please try these steps and let us know the results.

Thank you.

@jackthgu commented on GitHub (Jul 1, 2025): Hello, @mateocovacho regarding the web-search issue you reported, I suspect two main causes: 1. The model’s context window is too small, so some content is omitted. 2. After obtaining URLs from the search engine, the crawler’s return visit to those URLs may be blocked by bot-detection mechanisms. Based on this, please check the following: 1. In the backend logs, look for `tokens_prompt=`. If it seems large, lower `WEB_SEARCH_RESULT_COUNT` and try again. 2. Test the BYPASS variables: * `BYPASS_WEB_SEARCH_WEB_LOADER=True` → use only the URL snippet. * `BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL=True` → skip embedding and retrieval. 3. Change the loader engine: modify the `WEB_LOADER_ENGINE` variable and test again. 4. Run `curl <document_URL>`; if access is blocked, set `http_proxy` / `https_proxy` and review the `WEB_SEARCH_TRUST_ENV` setting. Please try these steps and let us know the results. Thank you.
GiteaMirror commented 2025-11-11 16:28:39 -06:00
Author
Owner
Copy Link
Copy Source

@rgaricano commented on GitHub (Jul 1, 2025):

& add current date & time: {{CURRENT_DATETIME}} to your prompt, as I indicated in https://discord.com/channels/1170866489302188073/1389342833277669377

@rgaricano commented on GitHub (Jul 1, 2025): & add `current date & time: {{CURRENT_DATETIME}}` to your prompt, as I indicated in https://discord.com/channels/1170866489302188073/1389342833277669377
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#5672