[GH-ISSUE #12387] feat: how to deploy the self-trained llava multimodal, like the openai compatible api #87317

Closed
opened 2026-05-15 11:46:16 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @nouise on GitHub (Apr 3, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/12387

Check Existing Issues

  • I have searched the existing issues and discussions.

Problem Description

I want to deploy the LLaVA multimodal model on my own machine. However, Ollama seems to only support the official version. How can I package my custom multimodal large model into an OpenAI-style API and make it accessible to all users?
The current issue is an error: "str has no attribute 'get'".

Desired Solution you'd like

how to fix the bug

Alternatives Considered

No response

Additional Context

No response

Originally created by @nouise on GitHub (Apr 3, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/12387 ### Check Existing Issues - [x] I have searched the existing issues and discussions. ### Problem Description I want to deploy the LLaVA multimodal model on my own machine. However, Ollama seems to only support the official version. How can I package my custom multimodal large model into an OpenAI-style API and make it accessible to all users? The current issue is an error: "str has no attribute 'get'". ### Desired Solution you'd like how to fix the bug ### 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#87317