Pydantic V1 support

[maxschulz-COL]

Is your feature request related to a problem? Please describe.
First of all, I love this library, it's just SO cool!!

I would love to implement it in conjunction with the OS library I am helping to develop (https://github.com/mckinsey/vizro), which still uses Pydantic V1 for the near future...

Describe the solution you'd like
Instructor also work with Pydantic V1 base models

Describe alternatives you've considered
We should upgrade to V2, and eventually we will :) Just cannot do it just yet

I didn't check the source code on whether this is a crazy effort or even feasible, but thought I'd better ask :)!

[jxnl]

Yeah, there's no way to go backwards. We use a lot of the newer features

[maxschulz-COL]

@jxnl One more question that I am wondering: What would be other key differences of instructor vs e.g. using the langchain pydantic output parser.

The main difference visible to me is the retry capability, which can be maybe added to a langchain approach.

I am wondering e.g. what the additional features of V2 are that you are using. Would V2 also be more powerful to parse more complex nested outputs? Or would it be better at using OS models that do not reliable even return a valid JSON?

In our case, we are still thinking of whether it's easier to use langchain (as it support pydantic V1) or upgrade to pydantic V2 to make use of instructor.

Any quick notes would be much appreciated 🙏 !