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] Function calling support for minimax models #2394
Comments
Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible. |
I tried to investigate into this and found a minor discrepancy that is not compatible with OpenAI's API. The parameters of a function should be a string, not a json object. Otherwise, MiniMax will throw an error. That means, we need to serialize the object describing the parameters of a function into a string first and then serialize the |
@ifsheldon I have tried it. there is a really challange due to we pasre the response by ourself due to Minimax's strange error code. #2087 (comment) I'll consider it in the #1310 |
This issue is closed, If you have any questions, you can comment and reply. |
🎉 This issue has been resolved in version 0.157.0 🎉 The release is available on: Your semantic-release bot 📦🚀 |
@arvinxx Wow, the progress you've made are just unbelievable. Thanks a lot! |
🥰 Feature Description
Please add function calling/plugin calling for minimax models. Now plugins are disabled when a minimax model is selected. But MiniMax models and APIs support function calling. If the code calls MiniMax ChatCompletionV2 APIs, then adding function calling should be easy since the APIs are compatible with OpenAI's APIs.
🧐 Proposed Solution
Add function calling support for MiniMax models by copying and modifying the function calling support for OpenAI's models.
📝 Additional Information
No response
The text was updated successfully, but these errors were encountered: