github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-07-16 06:03:26 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #16126] issue: Download from Huggingface broken, Openwebui completely crashes afterwards #17788

New Issue
Closed
opened 2026-04-19 23:40:21 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-19 23:40:21 -05:00
Owner
Copy Link

Originally created by @LumenYoung on GitHub (Jul 29, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16126

Check Existing Issues

  • I have searched the existing issues and discussions.
  • I am using the latest version of Open WebUI.

Installation Method

Git Clone

Open WebUI Version

v0.6.18

Ollama Version (if applicable)

No response

Operating System

Linux, running inside container

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 specifying model like intfloat/multilingual-e5-large-instruct for embedding model for the RAG setup or Qwen/Qwen3-Embedding-0.6B, the whole service crashes and any attempt to restart the service or recreate the container cannot bring back the service, the initial error is following even though the OFFLINE_MODE is explicitly set to false on my instance.

message(2).txt

Moreover, using model like jinaai/jina-embeddings-v4 would download fine but the inference would give the following error message when attempting to index. But this won't crash the service like above problem, but RAG is not working:

message(1).txt

Further investigation on this second type of problem reveal the following error message:


ERROR [open_webui.routers.retrieval] CrossEncoder: Unrecognized configuration class <class 'transformers.models.qwen2_vl.configuration_qwen2_vl.Qwen2VLConfig'> for this kind of AutoModel: AutoModelForSequenceClassification.
Model type should be one of AlbertConfig, ArceeConfig, BartConfig, BertConfig, BigBirdConfig, BigBirdPegasusConfig, BioGptConfig, BloomConfig, CamembertConfig, CanineConfig, LlamaConfig, ConvBertConfig, CTRLConfig, Data2VecTextConfig, DebertaConfig, DebertaV2Config, DiffLlamaConfig, DistilBertConfig, ElectraConfig, ErnieConfig, ErnieMConfig, EsmConfig, FalconConfig, FlaubertConfig, FNetConfig, FunnelConfig, GemmaConfig, Gemma2Config, GlmConfig, Glm4Config, GPT2Config, GPT2Config, GPTBigCodeConfig, GPTNeoConfig, GPTNeoXConfig, GPTJConfig, HeliumConfig, IBertConfig, JambaConfig, JetMoeConfig, LayoutLMConfig, LayoutLMv2Config, LayoutLMv3Config, LEDConfig, LiltConfig, LlamaConfig, LongformerConfig, LukeConfig, MarkupLMConfig, MBartConfig, MegaConfig, MegatronBertConfig, MiniMaxConfig, MistralConfig, MixtralConfig, MobileBertConfig, ModernBertConfig, MPNetConfig, MptConfig, MraConfig, MT5Config, MvpConfig, NemotronConfig, NezhaConfig, NystromformerConfig, OpenLlamaConfig, OpenAIGPTConfig, OPTConfig, PerceiverConfig, PersimmonConfig, PhiConfig, Phi3Config, PhimoeConfig, PLBartConfig, QDQBertConfig, Qwen2Config, Qwen2MoeConfig, Qwen3Config, Qwen3MoeConfig, ReformerConfig, RemBertConfig, RobertaConfig, RobertaPreLayerNormConfig, RoCBertConfig, RoFormerConfig, SmolLM3Config, SqueezeBertConfig, StableLmConfig, Starcoder2Config, T5Config, T5GemmaConfig, TapasConfig, TransfoXLConfig, UMT5Config, XLMConfig, XLMRobertaConfig, XLMRobertaXLConfig, XLNetConfig, XmodConfig, YosoConfig, ZambaConfig, Zamba2Config.

Actual Behavior

The service either crashes completely in case 1 (Qwen/Qwen3-Embedding-0.6B) or rag doesn't work in case 2 (jinaai/jina-embeddings-v4).

Steps to Reproduce

  1. start a new openwebui instance with main tag
  2. set the embedding model for the document to either of the model above
  3. in case 1, it crashes directly now. in case 2, it would download the model fine, but you will see error message once you start indexing file or do rag.

Logs & Screenshots

Already appended at the description

Additional Information

No response

Originally created by @LumenYoung on GitHub (Jul 29, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/16126 ### 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 v0.6.18 ### Ollama Version (if applicable) _No response_ ### Operating System Linux, running inside container ### 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 specifying model like `intfloat/multilingual-e5-large-instruct` for embedding model for the RAG setup or `Qwen/Qwen3-Embedding-0.6B`, the whole service crashes and any attempt to restart the service or recreate the container cannot bring back the service, the initial error is following even though the `OFFLINE_MODE` is explicitly set to `false` on my instance. [message(2).txt](https://github.com/user-attachments/files/21492356/message.2.txt) Moreover, using model like `jinaai/jina-embeddings-v4` would download fine but the inference would give the following error message when attempting to index. But this won't crash the service like above problem, but RAG is not working: [message(1).txt](https://github.com/user-attachments/files/21492337/message.1.txt) Further investigation on this second type of problem reveal the following error message: ``` ERROR [open_webui.routers.retrieval] CrossEncoder: Unrecognized configuration class <class 'transformers.models.qwen2_vl.configuration_qwen2_vl.Qwen2VLConfig'> for this kind of AutoModel: AutoModelForSequenceClassification. Model type should be one of AlbertConfig, ArceeConfig, BartConfig, BertConfig, BigBirdConfig, BigBirdPegasusConfig, BioGptConfig, BloomConfig, CamembertConfig, CanineConfig, LlamaConfig, ConvBertConfig, CTRLConfig, Data2VecTextConfig, DebertaConfig, DebertaV2Config, DiffLlamaConfig, DistilBertConfig, ElectraConfig, ErnieConfig, ErnieMConfig, EsmConfig, FalconConfig, FlaubertConfig, FNetConfig, FunnelConfig, GemmaConfig, Gemma2Config, GlmConfig, Glm4Config, GPT2Config, GPT2Config, GPTBigCodeConfig, GPTNeoConfig, GPTNeoXConfig, GPTJConfig, HeliumConfig, IBertConfig, JambaConfig, JetMoeConfig, LayoutLMConfig, LayoutLMv2Config, LayoutLMv3Config, LEDConfig, LiltConfig, LlamaConfig, LongformerConfig, LukeConfig, MarkupLMConfig, MBartConfig, MegaConfig, MegatronBertConfig, MiniMaxConfig, MistralConfig, MixtralConfig, MobileBertConfig, ModernBertConfig, MPNetConfig, MptConfig, MraConfig, MT5Config, MvpConfig, NemotronConfig, NezhaConfig, NystromformerConfig, OpenLlamaConfig, OpenAIGPTConfig, OPTConfig, PerceiverConfig, PersimmonConfig, PhiConfig, Phi3Config, PhimoeConfig, PLBartConfig, QDQBertConfig, Qwen2Config, Qwen2MoeConfig, Qwen3Config, Qwen3MoeConfig, ReformerConfig, RemBertConfig, RobertaConfig, RobertaPreLayerNormConfig, RoCBertConfig, RoFormerConfig, SmolLM3Config, SqueezeBertConfig, StableLmConfig, Starcoder2Config, T5Config, T5GemmaConfig, TapasConfig, TransfoXLConfig, UMT5Config, XLMConfig, XLMRobertaConfig, XLMRobertaXLConfig, XLNetConfig, XmodConfig, YosoConfig, ZambaConfig, Zamba2Config. ``` ### Actual Behavior The service either crashes completely in case 1 (`Qwen/Qwen3-Embedding-0.6B`) or rag doesn't work in case 2 (`jinaai/jina-embeddings-v4`). ### Steps to Reproduce 1. start a new openwebui instance with main tag 2. set the embedding model for the document to either of the model above 3. in case 1, it crashes directly now. in case 2, it would download the model fine, but you will see error message once you start indexing file or do rag. ### Logs & Screenshots Already appended at the description ### Additional Information _No response_
GiteaMirror added the bug label 2026-04-19 23:40:21 -05:00
GiteaMirror commented 2026-04-19 23:40:23 -05:00
Author
Owner
Copy Link

@tjbck commented on GitHub (Jul 29, 2025):

jinaai/jina-embeddings-v4 requires additional dependencies.

<!-- gh-comment-id:3133534760 --> @tjbck commented on GitHub (Jul 29, 2025): `jinaai/jina-embeddings-v4` requires additional dependencies.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#17788
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?