Mark Pollack

merged in 793052c2e96cf95230ddd8f7bbcb535abdffa397 I had a bad merge conflict somehow and ended up redoing the changes and adding a test on another branch. Sorry I forgot to add your name...

Thanks, will investigate.

Here is a recent community discussion on this topic. It isn't supported in the microsoft SDK, so until it is made available, there isn't anything we can do here. https://learn.microsoft.com/en-us/answers/questions/1805363/azure-openai-streaming-token-usage

In my experience at the model level, I agree that once you get into the details, "api compatability" is surface level. On the other hand, there is indeed a model...

I'm still not sure what to do here. Other opinions? @mxsl-gr have you tried to use Spring AI's OpenAI support to talk with this model?

Thanks for the update. I did take a look at the github project, it doesn't seem active - https://github.com/deepseek-ai/DeepSeek-V2/graphs/contributors what is your opinion. Does function calling with OpenAI 'compatability' work....

oops, didn't mean to close.

Also, llama3 has a similar commit history - minimal - I guess all the work is up front! https://github.com/meta-llama/llama3/graphs/contributors

Has been addressed, now using `OutputConverter` style suffix

Is this something that you could contribute @xenoterracide