issue: UI isn't clear that RAG_EMBEDDING_MODEL has to be a HF name/id #3574

New Issue

2025-11-11T15:34:10-06:00

GiteaMirror commented

2025-11-11 15:34:10 -06:00

Originally created by @Ezbaze on GitHub (Feb 5, 2025).

Installation Method

pipx

Environment

Open WebUI Version: v0.5.7
Operating System: Windows 11
Browser (if applicable): Chrome

Confirmation:

I have read and followed all the instructions provided in the README.md.
I am on 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 the exact steps to reproduce the bug in the "Steps to Reproduce" section below.

Expected Behavior:

I have embeding models downloaded in Ollama, I was expecting those to be used when changing the deafult embeding model. Or the settings page could state that the embeding model has to be from HF.

Actual Behavior:

It saves the RAG_EMBEDDING_MODEL setting but it fails to downlad / use the model. It casues Web Searches to fail etc.

Description

Bug Summary:
The RAG_EMBEDDING_MODEL setting requires a HF model name/id. It won't use the embeding models downloaded in Ollama.

Reproduction Details

Steps to Reproduce:

Change the Embeding Model to any Embeding Model downloaded with Ollama (eg. mxbai-embed-large:latest)
Save

Logs and Screenshots

Docker Container Logs:

ERROR [open_webui.retrieval.utils] Cannot determine model snapshot path: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'sentence-transformers/mxbai-embed-large:latest'.
Traceback (most recent call last):
  File "C:\Users\ezba\pipx\venvs\open-webui\Lib\site-packages\open_webui\retrieval\utils.py", line 417, in get_model_path
    model_repo_path = snapshot_download(**snapshot_kwargs)
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ezba\pipx\venvs\open-webui\Lib\site-packages\huggingface_hub\utils\_validators.py", line 106, in _inner_fn
    validate_repo_id(arg_value)
  File "C:\Users\ezba\pipx\venvs\open-webui\Lib\site-packages\huggingface_hub\utils\_validators.py", line 160, in validate_repo_id
    raise HFValidationError(
huggingface_hub.errors.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'sentence-transformers/mxbai-embed-large:latest'.
WARNI [sentence_transformers.SentenceTransformer] No sentence-transformers model found with name sentence-transformers/mxbai-embed-large:latest. Creating a new one with mean pooling.

Additional Information

None

Originally created by @Ezbaze on GitHub (Feb 5, 2025). ## Installation Method pipx ## Environment - **Open WebUI Version:** v0.5.7 - **Operating System:** Windows 11 - **Browser (if applicable):** Chrome **Confirmation:** - [x] I have read and followed all the instructions provided in the README.md. - [x] I am on 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 the exact steps to reproduce the bug in the "Steps to Reproduce" section below. ## Expected Behavior: I have embeding models downloaded in Ollama, I was expecting those to be used when changing the deafult embeding model. Or the settings page could state that the embeding model has to be from HF. ## Actual Behavior: It saves the `RAG_EMBEDDING_MODEL` setting but it fails to downlad / use the model. It casues Web Searches to fail etc. ## Description **Bug Summary:** The `RAG_EMBEDDING_MODEL` setting requires a HF model name/id. It won't use the embeding models downloaded in Ollama. ## Reproduction Details **Steps to Reproduce:** 1. Change the Embeding Model to any Embeding Model downloaded with Ollama (eg. mxbai-embed-large:latest) 2. Save ## Logs and Screenshots **Docker Container Logs:** ``` ERROR [open_webui.retrieval.utils] Cannot determine model snapshot path: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'sentence-transformers/mxbai-embed-large:latest'. Traceback (most recent call last): File "C:\Users\ezba\pipx\venvs\open-webui\Lib\site-packages\open_webui\retrieval\utils.py", line 417, in get_model_path model_repo_path = snapshot_download(**snapshot_kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\ezba\pipx\venvs\open-webui\Lib\site-packages\huggingface_hub\utils\_validators.py", line 106, in _inner_fn validate_repo_id(arg_value) File "C:\Users\ezba\pipx\venvs\open-webui\Lib\site-packages\huggingface_hub\utils\_validators.py", line 160, in validate_repo_id raise HFValidationError( huggingface_hub.errors.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'sentence-transformers/mxbai-embed-large:latest'. WARNI [sentence_transformers.SentenceTransformer] No sentence-transformers model found with name sentence-transformers/mxbai-embed-large:latest. Creating a new one with mean pooling. ``` ## Additional Information None

GiteaMirror closed this issue

2025-11-11 15:34:10 -06:00

GiteaMirror referenced this issue

2026-04-19 20:05:22 -05:00

[GH-ISSUE #3574] The txt2img function cannot be used #13311

GiteaMirror referenced this issue

2026-04-25 03:23:05 -05:00

[GH-ISSUE #3574] The txt2img function cannot be used #28839

GiteaMirror referenced this issue

2026-05-05 13:12:44 -05:00

[GH-ISSUE #3574] The txt2img function cannot be used #51977

GiteaMirror referenced this issue