Outdated assert using from_mistral

[ahuang11]

• [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.
• [ ] I have tried searching the documentation and have not found an answer.

What Model are you using?

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

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

Mistral recently released their new APIs. https://github.com/mistralai/client-python?tab=readme-ov-file

File ~/miniconda3/envs/lumen/lib/python3.10/site-packages/instructor/client_mistral.py:35, in from_mistral(client, mode, **kwargs)
     26 def from_mistral(
     27     client: mistralai.client.MistralClient | mistralaiasynccli.MistralAsyncClient,
     28     mode: instructor.Mode = instructor.Mode.MISTRAL_TOOLS,
     29     **kwargs: Any,
     30 ) -> instructor.Instructor | instructor.AsyncInstructor:
     31     assert mode in {
     32         instructor.Mode.MISTRAL_TOOLS,
     33     }, "Mode be one of {instructor.Mode.MISTRAL_TOOLS}"
---> 35     assert isinstance(
     36         client, (mistralai.client.MistralClient, mistralaiasynccli.MistralAsyncClient)
     37     ), "Client must be an instance of mistralai.client.MistralClient or mistralai.async_cli.MistralAsyncClient"
     39     if isinstance(client, mistralai.client.MistralClient):
     40         return instructor.Instructor(
     41             client=client,
     42             create=instructor.patch(create=client.chat, mode=mode),
   (...)
     45             **kwargs,
     46         )

AssertionError: Client must be an instance of mistralai.client.MistralClient or mistralai.async_cli.MistralAsyncClient

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

import os
import instructor

from pydantic import BaseModel
from mistralai import Mistral

# enables `response_model` in chat call
client = Mistral(api_key=os.getenv("MISTRAL_API_KEY"))

# patched_chat = instructor.patch(create=client.chat.stream_async, mode=instructor.Mode.MISTRAL_TOOLS)

patched_chat = instructor.from_mistral(client, mode=instructor.Mode.MISTRAL_TOOLS)

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

resp = await patched_chat(
    model="mistral-small-latest",
    response_model=instructor.Partial[UserDetails],
    messages=[
        {
            "role": "user",
            "content": f'Extract the following entities: "Jason is 20"',
        },
    ],
    stream=True
)
async for message in resp:
    print(message)

Expected behavior A clear and concise description of what you expected to happen.

Not crash

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

[semoal]

from mistralai import Mistral

s = Mistral(
    api_key="x",
)

client = instructor.patch(
    create=s.chat.complete_async,
    mode=instructor.mode.Mode.JSON,
)

response = await client(
    model="mistral-large-latest",
    messages=[],
    response_model=Iterable[Accounts],
)

Meanwhile, you can do it like that