-
Notifications
You must be signed in to change notification settings - Fork 232
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
chat/completions api suport vioce input/output #296
base: main
Are you sure you want to change the base?
Conversation
* CreateChatCompletionRequest updated * CreateChatCompletionResponse updated * add example: /example/chat-audio
* CreateChatCompletionRequest updated * CreateChatCompletionResponse updated * add example: /example/chat-audio
Thank you for PR! +1 for including example. On an initial scan, it looks like some of the types may already exist in the repo, do you mind double checking that the types are not defined twice? |
Hi, thank you for your reply. I have checked the whole project, i did not find any data structure that exactly matches my code. Would you please point them out for me? Thanks very much. |
There are bunch of refactors that requires here, names are not matching spec. Also why is there a builder pattern on a response object? Also example contain type which is not present? For these reasons I cannot accept this PR as it is. |
My initial comment was because types are confusing between Chat and Audio APIS. It's addressed in v0.27.0. For this PR you're welcome to update the example, I'll happily accept the example. For mp3 file for input you can copy it from other speech to text example in the repo. |
chat/completions api suport vioce input/output
CreateChatCompletionRequest updated
CreateChatCompletionResponse updated
add example: /example/chat-audio