TypeError: create_model() missing 1 required positional argument: 'model_name'

[vikyw89]

• [x ] This is actually a bug report.
• I am not getting good LLM Results
• I have tried asking for help in the community on discord or discussions and have not received a response.
• [x ] I have tried searching the documentation and have not found an answer.

What Model are you using?

• [x ] gpt-3.5-turbo
• gpt-4-turbo
• gpt-4
• Other (please specify)

Describe the bug
A clear and concise description of what the bug is.

astream partial stopped working

To Reproduce
Steps to reproduce the behavior, including code snippets of the model and the input data and openai response.

import instructor
from pydantic import BaseModel


client = instructor.from_openai(openai.OpenAI())


class User(BaseModel):
    name: str
    age: int


user_stream = client.chat.completions.create_partial(
    model="gpt-4-turbo-preview",
    messages=[
        {"role": "user", "content": "Create a user"},
    ],
    response_model=User,
)

for user in user_stream:
    print(user)
    #> name=None age=None
    #> name=None age=None
    #> name=None age=None
    #> name=None age=None
    #> name=None age=25
    #> name=None age=25
    #> name=None age=25
    #> name=None age=25
    #> name=None age=25
    #> name=None age=25
    #> name='John Doe' age=25
    # name=None age=None
    # name='' age=None
    # name='John' age=None
    # name='John Doe' age=None
    # name='John Doe' age=30
    ```
    
**Expected behavior**
A clear and concise description of what you expected to happen.

it streams

**Screenshots**
If applicable, add screenshots to help explain your problem.

def test_instructor():
    import openai
    import instructor
    from pydantic import BaseModel


    client = instructor.from_openai(openai.OpenAI())


    class User(BaseModel):
        name: str
        age: int

  user_stream = client.chat.completions.create_partial(

        model="gpt-3.5-turbo",
        messages=[
            {"role": "user", "content": "Create a user"},
        ],
        response_model=User,
    )

tests/text/test_instructor.py:15:

---

../../.cache/pypoetry/virtualenvs/llmtext-HjOqM6W8-py3.11/lib/python3.11/site-packages/instructor/client.py:135: in create_partial
response_model = instructor.Partial[response_model] # type: ignore

---

cls = <class 'instructor.dsl.partial.Partial'>, wrapped_class = <class 'test_instructor.test_instructor..User'>

def __class_getitem__(
    cls,
    wrapped_class: type[T_Model] | tuple[type[T_Model], type[MakeFieldsOptional]],
) -> type[T_Model]:
    """Convert model to one that inherits from PartialBase.

    We don't make the fields optional at this point, we just wrap them with `Partial` so the names of the nested models will be
    `Partial{ModelName}`. We want the output of `model_json_schema()` to
    reflect the name change, but everything else should be the same as the
    original model. During validation, we'll generate a true partial model
    to support partially defined fields.

    """

    make_fields_optional = None
    if isinstance(wrapped_class, tuple):
        wrapped_class, make_fields_optional = wrapped_class

    def _wrap_models(field: FieldInfo) -> tuple[object, FieldInfo]:
        tmp_field = deepcopy(field)

        annotation = field.annotation

        # Handle generics (like List, Dict, etc.)
        if get_origin(annotation) is not None:
            # Get the generic base (like List, Dict) and its arguments (like User in List[User])
            generic_base = get_origin(annotation)
            generic_args = get_args(annotation)

            # Recursively apply Partial to each of the generic arguments
            modified_args = tuple(
                (
                    Partial[arg]
                    if isinstance(arg, type) and issubclass(arg, BaseModel)
                    else arg
                )
                for arg in generic_args
            )

            # Reconstruct the generic type with modified arguments
            tmp_field.annotation = (
                generic_base[modified_args] if generic_base else None
            )
        # If the field is a BaseModel, then recursively convert it's
        # attributes to optionals.
        elif isinstance(annotation, type) and issubclass(annotation, BaseModel):
            tmp_field.annotation = Partial[annotation]
        return tmp_field.annotation, tmp_field

  return create_model(

        __model_name=(
            wrapped_class.__name__
            if wrapped_class.__name__.startswith("Partial")
            else f"Partial{wrapped_class.__name__}"
        ),
        __base__=(wrapped_class, PartialBase),
        __module__=wrapped_class.__module__,
        **{
            field_name: (
                _make_field_optional(field_info)
                if make_fields_optional is not None
                else _wrap_models(field_info)
            )
            for field_name, field_info in wrapped_class.model_fields.items()
        },
    )  # type: ignore

E TypeError: create_model() missing 1 required positional argument: 'model_name'

../../.cache/pypoetry/virtualenvs/llmtext-HjOqM6W8-py3.11/lib/python3.11/site-packages/instructor/dsl/partial.py:292: TypeError

[vikyw89]

switching pydantic version to 2.7.* fixed it, the problem happens on pydantic version 2.8.*

[ivanleomk]

hey @vikyw89 , I tried running the code snippet above and didn't get any issues. Any other ways to reproduce the error?

import instructor
from pydantic import BaseModel
import openai

client = instructor.from_openai(openai.OpenAI())


class User(BaseModel):
    name: str
    age: int


user_stream = client.chat.completions.create_partial(
    model="gpt-4-turbo-preview",
    messages=[
        {"role": "user", "content": "Create a user"},
    ],
    response_model=User,
)

for user in user_stream:
    print(user)

This was my shell output

> uv pip list | grep pydantic

pydantic                      2.7.3                                                     
pydantic-core                 2.18.4                                                    
pydantic-extra-types          2.8.0                                                     

 > python3 test.py  
 
name=None age=None
name=None age=None
name=None age=None
name=None age=None
name=None age=25
name=None age=25
name=None age=25
name='' age=25
name='John' age=25
name='John Doe' age=25
name='John Doe' age=25

[vikyw89]

Use pydantic 2.8.*

[gokturkDev]

Hi, i see that this has been closed as an issue. Will there be a fix for this?

[ivanleomk]

Hey @gokturkDev , I just released instructor 1.3.5 which fixes this! Give it a try and let me know if it works for you :)