New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Request] 支持多个 oneapi 同时存在 #2253
Comments
👀 @sxjeru Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible. |
🥰 Description of requirementsIt is known that there is oneapi that is compatible with OpenAI API, and it is hoped that multiple oneapi can coexist. In order to avoid unnecessary confusion with OpenAI, a separate oneapi area can be created. Each API can set Key, interface address, and model independently. 🧐 SolutionSee above. 📝 Supplementary informationNo response |
相关 #1985 |
Related #1985 |
在 #2040 中支持 |
我覺得大可不必, 你自己部署一個OneAPI中繼所有OneAPI/OpenAI API就行了 |
I don’t think it’s necessary. Just deploy a OneAPI to relay all OneAPI/OpenAI APIs yourself. |
感谢提供另外的解决方案,各有优缺点可言。 |
Thanks for the other solutions, each has its pros and cons. |
@ckt1031 不考虑 oneapi,仅考虑提供允许添加自定义的 OpenAI 兼容 API 对于很多场景来说会有比较好的灵活度。例如某些小的Provider 只要兼容 openai 的接口规范,用户就可以将这个 provider 添加到自己的配置中 |
@ckt1031 Do not consider oneapi, only consider providing an OpenAI compatible API that allows adding customization, which will have better flexibility for many scenarios. For example, as long as some small providers are compatible with openai's interface specifications, users can add this provider to their own configuration. |
🥰 需求描述
已知存在兼容 OpenAI API 的 oneapi,希望能实现多 oneapi 共存。
为了避免与 OpenAI 产生不必要的混淆,另可单独出一个 oneapi 区域。
每个 API 均能单独设置 Key、接口地址、模型。
若存在模型重复,可以考虑简单报错,或者负载均衡。
🧐 解决方案
见上。
📝 补充信息
No response
The text was updated successfully, but these errors were encountered: