-
Notifications
You must be signed in to change notification settings - Fork 3.2k
feat: add endpoint type support for cherryin provider #11367
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
base: main
Are you sure you want to change the base?
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Note
This review was translated by Claude.
Can it run properly? The code looks fine. Additionally, you need to increment the version number and publish a new npm package.
Original Content
能跑通吗 看代码没问题,另外还需要版本号+1,再发个npm包
|
Note This issue/comment/review was translated by Claude. It works, but there might be a potential issue. Previously, models that were not from Anthropic and Gemini would use the response API, but now with endpoint type-based judgment, most of them will use the chat API. The version number can be changed first. Should the package be released before or after the merge? Original Content可以跑,但是可能有个潜在问题,之前不是anthropic和gemini的模型都会用response api,现在根据endpoint type判断的话大多走的是chat api 版本号可以先改,包是merge前发还是merge后发 |
|
Note This issue/comment/review was translated by Claude. It works, but there might be a potential issue. Previously, models that were not from Anthropic and Gemini would use the response API, but now with endpoint type-based judgment, most of them will use the chat API. The version number can be changed first. Should the package be released before or after the merge? Release it before merge. If there are issues, we can still fix them in this PR. Original Content可以跑,但是可能有个潜在问题,之前不是anthropic和gemini的模型都会用response api,现在根据endpoint type判断的话大多走的是chat api 版本号可以先改,包是merge前发还是merge后发 merge前发吧 有问题还能在这个pr里改 |
What this PR does
Before this PR:
The cherryin-provider creates a chat model based on the model name.
After this PR:
The chat model is created based on the endpoint type. If the endpoint type is not specified, it falls back to using the model name.