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
v0.6.28
Ollama Version (if applicable)
No response
Operating System
AWS Kubernetes
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
Requests to POST /api/embeddings should return a 200 response and embeddings
Actual Behavior
Returns a 500 response. Server has an error that model cannot be found.
Steps to Reproduce
Set up LiteLLM with a Bedrock embedding model. We are using amazon.titan-embed-text-v2:0
Connect Open WebUI to use LiteLLM as a model provider.
Call /api/embeddings with a request body:
{
"model": "amazon.titan-embed-text-v2:0",
"input": "This is a test."
}
Logs & Screenshots
Server log:
open-webui File "/app/backend/open_webui/utils/embeddings.py", line 67, in generate_embeddings
open-webui raise Exception("Model not found")
Additional Information
The embedding model is listed at /openai/models but not /api/models.
The embedding model works fine for RAG in workspaces.
Originally created by @maxmealy on GitHub (Sep 18, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17584
### 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
v0.6.28
### Ollama Version (if applicable)
_No response_
### Operating System
AWS Kubernetes
### 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
Requests to POST /api/embeddings should return a 200 response and embeddings
### Actual Behavior
Returns a 500 response. Server has an error that model cannot be found.
### Steps to Reproduce
1. Set up LiteLLM with a Bedrock embedding model. We are using amazon.titan-embed-text-v2:0
2. Connect Open WebUI to use LiteLLM as a model provider.
4. Call /api/embeddings with a request body:
```
{
"model": "amazon.titan-embed-text-v2:0",
"input": "This is a test."
}
```
### Logs & Screenshots
Server log:
```
open-webui File "/app/backend/open_webui/utils/embeddings.py", line 67, in generate_embeddings
open-webui raise Exception("Model not found")
```
### Additional Information
- The embedding model is listed at /openai/models but not /api/models.
- The embedding model works fine for RAG in workspaces.
- Another user commented on the PR that added this feature that they were having the same issue when using a model provider that wasn't Ollama - https://github.com/open-webui/open-webui/pull/14667#issuecomment-3133563562
GiteaMirror
added the bug label 2026-04-25 07:44:31 -05:00
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 @maxmealy on GitHub (Sep 18, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17584
Check Existing Issues
Installation Method
Docker
Open WebUI Version
v0.6.28
Ollama Version (if applicable)
No response
Operating System
AWS Kubernetes
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
Requests to POST /api/embeddings should return a 200 response and embeddings
Actual Behavior
Returns a 500 response. Server has an error that model cannot be found.
Steps to Reproduce
Logs & Screenshots
Server log:
Additional Information
@tjbck commented on GitHub (Sep 19, 2025):
Unable to reproduce from our end, keep us updated.