error when I using the Function Call

I am following this tutorial to use function call with qwen2:0.5b https://github.com/abetlen/llama-cpp-python/blob/main/examples/notebooks/Functions.ipynb

I used this command to start a serve inside container

python3 -m llama_cpp.server --model /app/vlm_weights/Qwen2-0___5B-Instruct-GGUF/qwen2-0_5b-instruct-fp16.gguf --n_gpu_layers -1

then I can successfully using following code

import openai
import json
from pydantic import BaseModel
import instructor

client = openai.OpenAI(
    api_key="sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",  # can be anything
    base_url="http://127.0.0.1:8000/v1",  # NOTE: Replace with IP address and port of your llama-cpp-python server
)

# Enables `response_model`
client = instructor.patch(client=client)

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

user = client.chat.completions.create(
    model="gpt-3.5-turbo",
    response_model=UserDetail,
    messages=[
        {"role": "user", "content": "Extract Jason is 25 years old"},
    ],
)

assert isinstance(user, UserDetail)
assert user.name == "Jason"
assert user.age == 25

print(user)

with output

root@ubuntu:/app/inside_container/llama_python_demo# python3 client.py 
name='Jason' age=25

but when I using Text Classification example with code

import openai
import json
from pydantic import BaseModel
import enum

client = openai.OpenAI(
    api_key="sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",  # can be anything
    base_url="http://127.0.0.1:8000/v1",  # NOTE: Replace with IP address and port of your llama-cpp-python server
)

class Labels(str, enum.Enum):
    """Enumeration for single-label text classification."""

    SPAM = "spam"
    NOT_SPAM = "not_spam"

class SinglePrediction(BaseModel):
    """
    Class for a single class label prediction.
    """

    class_label: Labels

def classify(data: str) -> SinglePrediction:
    """Perform single-label classification on the input text."""
    return client.chat.completions.create(
        model="gpt-3.5-turbo-0613",
        response_model=SinglePrediction,
        messages=[
            {
                "role": "user",
                "content": f"Classify the following text: {data}",
            },
        ],
    )  # type: ignore

prediction = classify("Hello there I'm a Nigerian prince and I want to give you money")
assert prediction.class_label == Labels.SPAM
print(prediction)

with bug

root@ubuntu:/app/inside_container/llama_python_demo# python3 client.py 
Traceback (most recent call last):
  File "/app/inside_container/llama_python_demo/client.py", line 41, in <module>
    prediction = classify("Hello there I'm a Nigerian prince and I want to give you money")
  File "/app/inside_container/llama_python_demo/client.py", line 29, in classify
    return client.chat.completions.create(
  File "/usr/local/lib/python3.10/dist-packages/openai/_utils/_utils.py", line 274, in wrapper
    return func(*args, **kwargs)
TypeError: Completions.create() got an unexpected keyword argument 'response_model'

Can anyone help me look at it?

abetlen / llama-cpp-python

error when I using the Function Call #1747