Python: Token usage from Azure OpenAI streaming chat completion #8996
Labels
ai connector
Anything related to AI connectors
python
Pull requests for the Python Semantic Kernel
sk team issue
A tag to denote issues that where created by the Semantic Kernel team (i.e., not the community)
Currently, OpenAI provides the functionality to return token usage through their Streaming Chat Completion API. However, this feature has not yet been incorporated into Azure OpenAI. Upon experimenting with the
stream_options
parameter with the OpenAI Python SDK, I noticed that using this parameter may lead to errors when using the latest Azure OpenAI GA API version: 2024-06-01.This issue has been created to monitor their progress, enabling us to implement the feature within our Azure OpenAI connector as soon as the Azure team integrates support for this functionality.
The text was updated successfully, but these errors were encountered: