ai-agents-pydantic-compatibili-upgrading-to-langchain-0-1-6-or-later-when-using-p-3f321f2d

THEN Downgrade to langchain 0.1.5, or define your Pydantic models using pydantic v1's BaseModel (e.g., from pydantic.v1 import BaseModel). Alternatively, use a different output parser that supports pydantic v2 or wrap your v2 models appropriately.

# Error-producing code:
# from pydantic import BaseModel  # v2
# from langchain.output_parsers import PydanticOutputParser
# class TestModel(BaseModel):
#     test_attribute: str
# parser = PydanticOutputParser(pydantic_object=TestModel)

# Workaround: use pydantic v1
from pydantic.v1 import BaseModel
from langchain.output_parsers import PydanticOutputParser
class TestModel(BaseModel):
    test_attribute: str
parser = PydanticOutputParser(pydantic_object=TestModel)
print(parser)