[SUPPORT] function call usage

[FanZhang91]

environment：ubuntu=20.04 + transformers=4.42.4 + openai=1.30.5 + vllm=0.5.2

I use vllm as server and openai as client and using similar code from website:https://github.com/openai/openai-cookbook/blob/main/examples/How_to_call_functions_with_chat_models.ipynb

but result show no function info to call. how to fix this problem?

---------------------------------------------------- client code info ---------------------------------------------------------
from openai import OpenAI
import json

tools = [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use. Infer this from the users location.",
},
},
"required": ["location", "format"],
},
}
},
{
"type": "function",
"function": {
"name": "get_n_day_weather_forecast",
"description": "Get an N-day weather forecast",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use. Infer this from the users location.",
},
"num_days": {
"type": "integer",
"description": "The number of days to forecast",
}
},
"required": ["location", "format", "num_days"]
},
}
},
]

openai_api_key = "xxx"
openai_api_base = "http://localhost:8000/v1/"

client = OpenAI(
api_key=openai_api_key,
base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id

messages = []
messages.append({"role": "system", "content": "Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous."})
messages.append({"role": "user", "content": "What's the weather like today"})
response = client.chat.completions.create(
model=model,
messages=messages,
tools=tools,
)
assistant_message = response.choices[0].message
messages.append(assistant_message)
print("response: ", assistant_message)

---------------------------------------------- server script-------------------------------------------------
python entrypoints/openai/api_server.py --model="xxxx/Qwen2-1.5B-Instruct" --trust-remote-code --host "localhost" --port 8000 --dtype auto

--------------------------------------------- print info --------------------------------------------------------
response: ChatCompletionMessage(content='Get out and check.', role='assistant', function_call=None, tool_calls=[])

[nelsonauner]

@FanZhang91 Please format your code with triple backticks.
What GPT model are you using? Your invocation includes --model="xxxx/Qwen2-1.5B-Instruct" which of course isn't an OpenAI model at all.

Please provide a more simple code sample that doesn't use an API server