@Marvin is the JSONSerializer class supposed to be able to serialize pydantic

BaseModel

objects? When I run this code snippet:

from pydantic import BaseModel
from prefect.serializers import JSONSerializer
 
class M(BaseModel):
    f1: str
    f2: int
 
m = M(f1="model", m2=1234)
ser = JSONSerializer(dumps_kwargs={"sort_keys": True})
ser.dumps(((m,), {}))

I get this error:

python3.10/site-packages/pydantic/v1/json.py:90, in pydantic_encoder(obj)
     88     return encoder(obj)
     89 else:  # We have exited the for loop without finding a suitable encoder
---> 90     raise TypeError(f"Object of type '{obj.__class__.__name__}' is not JSON serializable")

TypeError: Object of type 'M' is not JSON serializable

The Prefect's JSONSerializer should be able to serialize Pydantic

BaseModel

objects as it adds support for all types supported by Pydantic. However, you might be running into issues because of the way you're trying to serialize the Pydantic model. When you're trying to serialize a Pydantic model, you should first convert it to a dictionary using the

.dict()

method, like so:

ser.dumps(((m.dict(),), {}))

This is because the JSONSerializer expects a JSON serializable object, and a Pydantic model is not directly serializable - it needs to be converted to a dictionary first. Here's the corrected code:

from pydantic import BaseModel
from prefect.serializers import JSONSerializer
 
class M(BaseModel):
    f1: str
    f2: int
 
m = M(f1="model", f2=1234)
ser = JSONSerializer(dumps_kwargs={"sort_keys": True})
ser.dumps(((m.dict(),), {}))

This should serialize your Pydantic model without any issues.

okay, but according to this PR: https://github.com/PrefectHQ/prefect/pull/7048 it looks like the intention here was to make

BaseModel

instances serializable with JSON