Originally created by @Polak149 on GitHub (Oct 8, 2025).
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
v0.6.33
Ollama Version (if applicable)
v0.12.3
Operating System
Ubuntu 22.04
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
When enabling the Knowledge Base, all sources should be processed through embedding, the same way as when adding files via Upload File.
The model should use vector representations of the sources instead of loading entire documents into the context.
Actual Behavior
When enabling the Knowledge Base, embedding is skipped.
Instead, all sources are loaded in full into the context.
This leads to heavy context usage and reduced quality of responses.
Workaround: If you first upload a file through Upload File (embedding works correctly) and then, in a following message, add the Knowledge Base, embedding is applied to it as well.
Steps to Reproduce
Run the latest version of OpenWebUI.
Enable the Knowledge Base in a conversation.
Notice that Knowledge Base sources are loaded entirely without embedding.
(Optional) Try the workaround: first upload a file via Upload File, then in the next message add the Knowledge Base → in this case embedding works.
Logs & Screenshots
Attached knowledge without "single file" first - embedding not working
Attached knowledge with "single file" first - embedding not working
Additional Information
Issue appeared after updating to the latest version.
Possible cause: bug in the initialization of embedding when attaching the Knowledge Base.
Originally created by @Polak149 on GitHub (Oct 8, 2025).
### 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
v0.6.33
### Ollama Version (if applicable)
v0.12.3
### Operating System
Ubuntu 22.04
### 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
- When enabling the Knowledge Base, all sources should be processed through embedding, the same way as when adding files via Upload File.
- The model should use vector representations of the sources instead of loading entire documents into the context.
### Actual Behavior
- When enabling the Knowledge Base, embedding is skipped.
- Instead, all sources are loaded in full into the context.
- This leads to heavy context usage and reduced quality of responses.
- Workaround: If you first upload a file through Upload File (embedding works correctly) and then, in a following message, add the Knowledge Base, embedding is applied to it as well.
### Steps to Reproduce
- Run the latest version of OpenWebUI.
- Enable the Knowledge Base in a conversation.
- Notice that Knowledge Base sources are loaded entirely without embedding.
- (Optional) Try the workaround: first upload a file via Upload File, then in the next message add the Knowledge Base → in this case embedding works.
### Logs & Screenshots
Attached knowledge without "single file" first - embedding not working
<img width="1056" height="487" alt="Image" src="https://github.com/user-attachments/assets/bcc8a28f-42d0-445b-91b2-60371a3c6ba7" />
Attached knowledge with "single file" first - embedding not working
<img width="1058" height="834" alt="Image" src="https://github.com/user-attachments/assets/92e84b1b-09fa-4288-9afe-cef5bb1cac56" />
### Additional Information
- Issue appeared after updating to the latest version.
- Possible cause: bug in the initialization of embedding when attaching the Knowledge Base.
GiteaMirror
added the bug label 2025-11-11 17:01:48 -06:00
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @Polak149 on GitHub (Oct 8, 2025).
Check Existing Issues
Installation Method
Docker
Open WebUI Version
v0.6.33
Ollama Version (if applicable)
v0.12.3
Operating System
Ubuntu 22.04
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
Actual Behavior
Steps to Reproduce
Logs & Screenshots
Attached knowledge without "single file" first - embedding not working


Attached knowledge with "single file" first - embedding not working
Additional Information
@rgaricano commented on GitHub (Oct 8, 2025):
duplicated: https://github.com/open-webui/open-webui/issues/18133