[GH-ISSUE #18536] issue: qdrant since version v1.15.4 it is not working with Open WebUI

Originally created by @YetheSamartaka on GitHub (Oct 23, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/18536 ### 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 Docker ### Open WebUI Version 0.6.34 ### Ollama Version (if applicable) - ### Operating System Debian 12 ### Browser (if applicable) All ### 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 Requests towards qdrant are working as supposed ### Actual Behavior Since version v1.15.4 it is not working with Open WebUI. When I tried this or the version above (v1.15.5), it was not working, but reverting to version v1.15.3 solved the issue. Nothing else has changed. First use of knowledge from Open WebUI is working but the second one (same question) is not working at all. ### Steps to Reproduce 1. Have Open WebUI with latest 0.6.34 version running and connected to qdrant 2. Use collection and ask a question and observe that the first such request is working 3. Try asking the same question in a new chat and the request is not even send towards qdrant ### Logs & Screenshots none, it is as if request was never created in the first place, but when i stop the conversation from generating, it logs the stop conversation print with debug mode enabled. ### Additional Information When reverted to version 1.15.3, there is no such issue. Any other changes are not present. I was upgrading from 1.15.1 when i found this out

GiteaMirror commented

2026-04-25 08:04:33 -05:00

Owner

Originally created by @YetheSamartaka on GitHub (Oct 23, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/18536

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

Docker

Open WebUI Version

0.6.34

Ollama Version (if applicable)

Operating System

Debian 12

Browser (if applicable)

All

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

Requests towards qdrant are working as supposed

Actual Behavior

Since version v1.15.4 it is not working with Open WebUI. When I tried this or the version above (v1.15.5), it was not working, but reverting to version v1.15.3 solved the issue. Nothing else has changed.

First use of knowledge from Open WebUI is working but the second one (same question) is not working at all.

Steps to Reproduce

Have Open WebUI with latest 0.6.34 version running and connected to qdrant
Use collection and ask a question and observe that the first such request is working
Try asking the same question in a new chat and the request is not even send towards qdrant

Logs & Screenshots

none, it is as if request was never created in the first place, but when i stop the conversation from generating, it logs the stop conversation print with debug mode enabled.

Additional Information

When reverted to version 1.15.3, there is no such issue. Any other changes are not present. I was upgrading from 1.15.1 when i found this out

GiteaMirror added the bug label 2026-04-25 08:04:33 -05:00

GiteaMirror closed this issue

[GH-ISSUE #18536] issue: qdrant since version v1.15.4 it is not working with Open WebUI #34156