pydantic_compatibilityTier 1 · 70% confidence

ai-agents-pydantic-compatibili-using-pydanticoutputparser-or-create-structured-ou-72d2af26

agent: ai_agents

When does this happen?

IF Using PydanticOutputParser or create_structured_output_runnable with a pydantic v2 BaseModel in LangChain version 0.1.6 or later throws a ValidationError because the parser expects a pydantic v1 BaseModel.

How others solved it

THEN To resolve, use pydantic v1 BaseModel (e.g., from pydantic.v1) for the output schema. Alternatively, downgrade LangChain to 0.1.5 or use a different output parsing method like the newer structured output methods that support pydantic v2.

# Fails with LangChain >=0.1.6 and pydantic v2:
from langchain.output_parsers import PydanticOutputParser
from pydantic import BaseModel
class TestModel(BaseModel):
    test_attribute: str
parser = PydanticOutputParser(pydantic_object=TestModel)  # ValidationError

# Fix: use pydantic v1 BaseModel:
from pydantic.v1 import BaseModel
class TestModelV1(BaseModel):
    test_attribute: str
parser = PydanticOutputParser(pydantic_object=TestModelV1)  # works

Related patterns

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics