[GH-ISSUE #8682] Can't use Ollama for embedding #53880

Closed
opened 2026-05-05 15:29:03 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @frenzybiscuit on GitHub (Jan 19, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/8682

I'm trying to use Ollama for embedding. I've pulled mxbai-embed-large with Ollama pull and now I'm running the following:

OLLAMA_HOST=192.168.0.10 OLLAMA_FLASH_ATTENTION=1 OLLAMA_KV_CACHE_TYPE=Q4 ollama serve

However, open-webui continues to error out when trying to upload a pdf to the chat.

See attached image.

Installation is linux x86_64 with python and CUDA 12.7 with a RTX 3090.

Image
Originally created by @frenzybiscuit on GitHub (Jan 19, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/8682 I'm trying to use Ollama for embedding. I've pulled mxbai-embed-large with Ollama pull and now I'm running the following: `OLLAMA_HOST=192.168.0.10 OLLAMA_FLASH_ATTENTION=1 OLLAMA_KV_CACHE_TYPE=Q4 ollama serve` However, open-webui continues to error out when trying to upload a pdf to the chat. See attached image. Installation is linux x86_64 with python and CUDA 12.7 with a RTX 3090. <img width="1919" alt="Image" src="https://github.com/user-attachments/assets/b1c2a588-7d41-4c58-b6bf-4f467deeeba2" />
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#53880