Raw response is not present when the response model is an Iterable

[jacobtohahn]

Discussed in #365

^{Originally posted by chrishiste January 25, 2024}
Describe the bug
When using the instructor library, there seems to be an issue with the raw response not being available when the response model is an Iterable.

To Reproduce

from typing import Iterable

import instructor
from openai import OpenAI
from pydantic import BaseModel


client = instructor.patch(OpenAI())


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


users = client.chat.completions.create(
    model="gpt-3.5-turbo",
    response_model=Iterable[UserDetail],
    messages=[
        {"role": "user", "content": "Give me 3 users"},
    ],
)

print(users) # [UserDetail(name='Alice', age=25), UserDetail(name='Bob', age=30), UserDetail(name='Charlie', age=35)]
assert users._raw_response is not None # AttributeError: 'list' object has no attribute '_raw_response'

Expected behavior
The expected behavior is that the raw response should be available and accessible.

Extracting Tasks using Iterable in the docs makes it seem as if this is supposed to work in general with models (regardless of if they also include the raw response).

The issue happens due to create_with_completion() in client.py attempting to access _raw_response when the response_model is an Iterable (i.e., a list), resulting in the error AttributeError: 'list' object has no attribute '_raw_response'.

[jacobtohahn]

For now a viable workaround is to create a class to hold the Iterable:

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


class Users(BaseModel):
    users: List[User]
    
# Instead of response_model = List[User], use:
# response_model = Users