AttributeError: 'OllamaLLM' object has no attribute '__pydantic_private__'

[0xD4rky]

when using OllamaLLM to serve models when generating the synthetic datasets using Distilabel, I am facing this issue and even changing the versions of ollama and pydantic doesn't help me. Please have a look into this.

Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/distilabel/llms/base.py", line 501, in __del__
    if self._new_event_loop:
       ^^^^^^^^^^^^^^^^^^^^
  File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pydantic/main.py", line 970, in __getattr__
    return self.__pydantic_private__[item]  # type: ignore
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pydantic/main.py", line 988, in __getattr__
    return super().__getattribute__(item)  # Raises AttributeError if appropriate
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'OllamaLLM' object has no attribute '__pydantic_private__'

[dameikle]

Thanks for reporting this @0xD4rky. Can you share the pipeline you are using with us?

I've tried a few locally on the develop branch and have been successful.