Bring your towel and join one of the fastest growing data communities. Welcome to our second-generation open source orchestration platform, a completely rethought approach to dataflow automation.

Prefect Community

any one else run into something broke in the reasoning example and it seems to infinite loop now? i think it might be on my model server side related to `model_kwargs=dict(tool_choice="required")` 

Interestingly enough it seems to fail sometimes on gpt4 (mostly works) but it’ll infinite loop with any model being served w/ vLLM , the problem seems to be related to vLLM not supporting tool_choice: “required”