[GH-ISSUE #17706] issue: too many results (more then top-k) when using multiple knowledge based with a model #18374

Open
opened 2026-04-20 00:36:02 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @guenhter on GitHub (Sep 24, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17706

Check Existing Issues

  • 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

Git Clone

Open WebUI Version

v0.6.30

Ollama Version (if applicable)

No response

Operating System

Ubuntu 24.04

Browser (if applicable)

No response

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

I only get Top K results when working with several knowledge based configured on the a custom model.

Actual Behavior

It gets top-k results per knowledge base.

Steps to Reproduce

  1. set top-k in the Documents Settings to 1 (for easier testing)
  2. Create two knowledge bases with 1 document each
  3. Create a new model and select both knowledge bases
  4. Chat to the new model
  5. --> you see now, that it lists two references even though the Top-K is 1, so it should have picked only one chunk of one single document.

Logs & Screenshots

Additional Information

No response

Originally created by @guenhter on GitHub (Sep 24, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/17706 ### 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 Git Clone ### Open WebUI Version v0.6.30 ### Ollama Version (if applicable) _No response_ ### Operating System Ubuntu 24.04 ### Browser (if applicable) _No response_ ### 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 I only get Top K results when working with several knowledge based configured on the a custom model. ### Actual Behavior It gets top-k results per knowledge base. ### Steps to Reproduce 1. set top-k in the Documents Settings to 1 (for easier testing) 2. Create two knowledge bases with 1 document each 3. Create a new model and select both knowledge bases 4. Chat to the new model 5. --> you see now, that it lists two references even though the Top-K is 1, so it should have picked only one chunk of one single document. ### Logs & Screenshots - ### Additional Information _No response_
GiteaMirror added the bug label 2026-04-20 00:36:02 -05:00
Author
Owner

@vaclcer commented on GitHub (Oct 10, 2025):

I was asking the same thing and got pretty good explanation here https://github.com/open-webui/open-webui/discussions/14428#discussioncomment-13794532

If that's a bug or a feature, I do not know... But there are many factors at play.

It surely makes number of final results unpredictable, hence making it difficult to work with a limited context of reranking model and generation model down the line.

<!-- gh-comment-id:3392232802 --> @vaclcer commented on GitHub (Oct 10, 2025): I was asking the same thing and got pretty good explanation here https://github.com/open-webui/open-webui/discussions/14428#discussioncomment-13794532 If that's a bug or a feature, I do not know... But there are many factors at play. It surely makes number of final results unpredictable, hence making it difficult to work with a limited context of reranking model and generation model down the line.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#18374