I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Git Clone
Open WebUI Version
v0.6.26
Ollama Version (if applicable)
No response
Operating System
Webapp Linux
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
Pasting documents into the prompt does not work
Actual Behavior
When add document Error : NoneType object has no attribute encore
I try download new model and save its the same problem
With v0.6.25 the same problem
Steps to Reproduce
1 Add document to prompt error
Logs & Screenshots
Additional Information
No response
Originally created by @zic04 on GitHub (Aug 28, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17005
### 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
v0.6.26
### Ollama Version (if applicable)
_No response_
### Operating System
Webapp Linux
### 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
Pasting documents into the prompt does not work
### Actual Behavior
When add document Error : NoneType object has no attribute encore
I try download new model and save its the same problem
With v0.6.25 the same problem
### Steps to Reproduce
1 Add document to prompt error
### Logs & Screenshots
<img width="391" height="73" alt="Image" src="https://github.com/user-attachments/assets/a02d87a7-abe4-4b1b-b15d-bf5b04c2b93f" />
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-04-25 07:33:39 -05:00
<!-- gh-comment-id:3334471423 -->
@maurerle commented on GitHub (Sep 25, 2025):
I still have this issue - what is the duplicate this is referring to?
Eventually: https://github.com/open-webui/open-webui/issues/15535
Which also does not have a code solution..
I have placed my model in /backend/data/cache/embedding/models
and executed the following code inside the Docker container.
I used the upskyy/bge-m3-korean model from Sentence Transformers, so the path looks like this:
/backend/data/cache/embedding/models/upskyy/bge-m3-korean/snapshots/
from sentence_transformer import SentenceTransformer
m=SentenceTransformer(/backend/data/cache/embedding/models/upskyy/bge-m3/korean/snapshots/<HASH>)
print(m.get_sentence_embedding_dimension())
It works successfully. It print out 1024
And—I also tried copying all files from the snapshot folder into a single-level folder
(bge-m3-korean) under both /app/backend/data/cache/embedding/models
and /app/backend/data/cache/embedding/ just in case.
But I still get the same error.
Anyone have solved this issue?
<!-- gh-comment-id:3495363978 -->
@UESENPAI commented on GitHub (Nov 6, 2025):
I have placed my model in /backend/data/cache/embedding/models
and executed the following code inside the Docker container.
I used the upskyy/bge-m3-korean model from Sentence Transformers, so the path looks like this:
/backend/data/cache/embedding/models/upskyy/bge-m3-korean/snapshots/<HASH>
```
from sentence_transformer import SentenceTransformer
m=SentenceTransformer(/backend/data/cache/embedding/models/upskyy/bge-m3/korean/snapshots/<HASH>)
print(m.get_sentence_embedding_dimension())
```
It works successfully. It print out 1024
And—I also tried copying all files from the snapshot folder into a single-level folder
(bge-m3-korean) under both /app/backend/data/cache/embedding/models
and /app/backend/data/cache/embedding/ just in case.
But I still get the same error.
Anyone have solved this issue?
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 @zic04 on GitHub (Aug 28, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17005
Check Existing Issues
Installation Method
Git Clone
Open WebUI Version
v0.6.26
Ollama Version (if applicable)
No response
Operating System
Webapp Linux
Browser (if applicable)
Firefox
Confirmation
README.md.Expected Behavior
Pasting documents into the prompt does not work
Actual Behavior
When add document Error : NoneType object has no attribute encore
I try download new model and save its the same problem
With v0.6.25 the same problem
Steps to Reproduce
1 Add document to prompt error
Logs & Screenshots
Additional Information
No response
@zic04 commented on GitHub (Aug 28, 2025):
@maurerle commented on GitHub (Sep 25, 2025):
I still have this issue - what is the duplicate this is referring to?
Eventually: https://github.com/open-webui/open-webui/issues/15535
Which also does not have a code solution..
@UESENPAI commented on GitHub (Nov 6, 2025):
I have placed my model in /backend/data/cache/embedding/models
and executed the following code inside the Docker container.
I used the upskyy/bge-m3-korean model from Sentence Transformers, so the path looks like this:
/backend/data/cache/embedding/models/upskyy/bge-m3-korean/snapshots/
It works successfully. It print out 1024
And—I also tried copying all files from the snapshot folder into a single-level folder
(bge-m3-korean) under both /app/backend/data/cache/embedding/models
and /app/backend/data/cache/embedding/ just in case.
But I still get the same error.
Anyone have solved this issue?