Closed CSalle closed 4 months ago
Hi, @CSalle! That's interesting. I've just run the example and, for me, it ran fine. I did a quick search and it seems that this is pydantic's way of saying the input doesn't conform.
Maybe the model doesn't give the expected output? Are you using a different model?
llm = ChatOpenAI(model_name="gpt-3.5-turbo")
This is the model in the code. Is this what you are using? Have you tried other models?
Hi Ben,
Thanks for getting back. After some hours of trying stuff, downgrading the version of Pydantic to 1.10 did the trick. I was using Pydantic 2 and it seems this runs into some issues.
After that, I didn't even need the arbitrary_types_allowed trick.
Thanks a lot, I'll close the issue :)
Good to hear, @CSalle! Thanks for updating. FYI - my version of pydantic is 1.10.13.
Hi,
While trying to run the Openresume CV example, I am getting the following error:
"RuntimeError: no validator found for <class 'main.Resume'>, see
arbitrary_types_allowed
in Config"I managed to perform a small hack by enabling arbitrary types as a decorator on top of each class (@pydantic.dataclasses.dataclass(config=Config), where Config is a class that sets arbitrary_types_allowed = True). However this seems to run into parsing errors where the data type is not correct.
Any ideas? Thanks in advance!