feat: Is it possible to automatically use specific models for Image Recognition? #4477

Closed
opened 2025-11-11 15:55:03 -06:00 by GiteaMirror · 0 comments
Owner

Originally created by @PeterTucker on GitHub (Mar 18, 2025).

Check Existing Issues

  • I have searched the existing issues and discussions.

Problem Description

Hi guys,
Had a question regarding image recognition with file uploading.

I have a docker setup running multiple services as followed:

Open WebUI
Ollama-Chat - Using Mistral Nemo 
Ollama-Vision - Using LLAVA

Is there anyway to configure Open WebUI so that I can chat with Mistral, then when I upload a file use LLAVA for Image Recognition, without having to switch back and forth between the models every time?

Thanks!

Desired Solution you'd like

A way to be able to automatically use a Vision Model for File Upload, instead of having to constantly switch between models.

Alternatives Considered

No response

Additional Context

No response

Originally created by @PeterTucker on GitHub (Mar 18, 2025). ### Check Existing Issues - [x] I have searched the existing issues and discussions. ### Problem Description Hi guys, Had a question regarding image recognition with file uploading. I have a docker setup running multiple services as followed: ``` Open WebUI Ollama-Chat - Using Mistral Nemo Ollama-Vision - Using LLAVA ``` Is there anyway to configure Open WebUI so that I can chat with Mistral, then when I upload a file use LLAVA for Image Recognition, without having to switch back and forth between the models every time? Thanks! ### Desired Solution you'd like A way to be able to automatically use a Vision Model for File Upload, instead of having to constantly switch between models. ### Alternatives Considered _No response_ ### Additional Context _No response_
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#4477