[GH-ISSUE #11190] [Feature Request]: Support adding multiple interface configurations compatible with the OpenAI API. #54803

New Issue

GiteaMirror · 2026-05-05T16:44:32-05:00

GiteaMirror commented

2026-05-05 16:44:32 -05:00

Originally created by @hzycn on GitHub (Mar 5, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/11190

Check Existing Issues

I have searched the existing issues and discussions.

Problem Description

Support adding multiple interface configurations compatible with the OpenAI API.
The usage is as follows：
1, ollama run deepseek llm
2, The first: compatible with the OpenAI API to run the rerank model.
3，The second: compatible with the OpenAI API to run the Qwen2.5-VL multimodal model.

Desired Solution you'd like

I hope to add multiple OpenAI API interface addresses so that I can use multiple locally deployed models. For example:
1, Ollama API configuration , run llm.
2, OpenAI API configuration ， run the rerank model.
3, Configuration compatible with the OpenAI API , run Qwen2.5-VL multimodal model.

Alternatives Considered

On the basis of Ollama and OpenAI API, add a configuration compatible with the OpenAI API in parallel, with the same functionality as the existing OpenAI API configuration.

Additional Context

No response

Originally created by @hzycn on GitHub (Mar 5, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/11190 ### Check Existing Issues - [x] I have searched the existing issues and discussions. ### Problem Description Support adding multiple interface configurations compatible with the OpenAI API. The usage is as follows： 1, ollama run deepseek llm 2, The first: compatible with the OpenAI API to run the rerank model. 3，The second: compatible with the OpenAI API to run the Qwen2.5-VL multimodal model. ### Desired Solution you'd like I hope to add multiple OpenAI API interface addresses so that I can use multiple locally deployed models. For example: 1, Ollama API configuration , run llm. 2, OpenAI API configuration ， run the rerank model. 3, Configuration compatible with the OpenAI API , run Qwen2.5-VL multimodal model. ### Alternatives Considered On the basis of Ollama and OpenAI API, add a configuration compatible with the OpenAI API in parallel, with the same functionality as the existing OpenAI API configuration. ### Additional Context _No response_

GiteaMirror closed this issue

2026-05-05 16:44:33 -05:00

Sign in to join this conversation.

Branches Tags

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#54803