def get_current_temperature(location: str, unit: str):
    """
    Get the current temperature at a location.

    Args:
        location: The location to get the temperature for, in the format "City, Country"
        unit: The unit to return the temperature in. (choices: ["celsius", "fahrenheit"])
    """
    return 22.  # A real function should probably actually get the temperature!

def get_current_wind_speed(location: str):
    """
    Get the current wind speed in km/h at a given location.

    Args:
        location: The location to get the wind speed for, in the format "City, Country"
    """
    return 6.  # A real function should probably actually get the wind speed!

tools = [get_current_temperature, get_current_wind_speed]

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

checkpoint = "NousResearch/Hermes-2-Pro-Llama-3-8B"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint, dtype="auto", device_map="auto")

messages = [
  {"role": "system", "content": "You are a bot that responds to weather queries. You should reply with the unit used in the queried location."},
  {"role": "user", "content": "Hey, what's the temperature in Paris right now?"}
]

inputs = tokenizer.apply_chat_template(messages, tools=tools, add_generation_prompt=True, return_dict=True, return_tensors="pt")
outputs = model.generate(**inputs.to(model.device), max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):]))

<tool_call>
{"arguments": {"location": "Paris, France", "unit": "celsius"}, "name": "get_current_temperature"}
</tool_call><|im_end|>

tool_call = {"name": "get_current_temperature", "arguments": {"location": "Paris, France", "unit": "celsius"}}
messages.append({"role": "assistant", "tool_calls": [{"type": "function", "function": tool_call}]})

messages.append({"role": "tool", "content": "22"})  # Note that the returned content is always a string!

inputs = tokenizer.apply_chat_template(messages, tools=tools, add_generation_prompt=True, return_dict=True, return_tensors="pt")
out = model.generate(**inputs.to(model.device), max_new_tokens=128)
print(tokenizer.decode(out[0][len(inputs["input_ids"][0]):]))

The temperature in Paris, France right now is 22°C.<|im_end|>

from transformers.utils import get_json_schema

def multiply(a: float, b: float):
    """
    A function that multiplies two numbers

    Args:
        a: The first number to multiply
        b: The second number to multiply
    """
    return a * b

schema = get_json_schema(multiply)
print(schema)

{
  "type": "function",
  "function": {
    "name": "multiply",
    "description": "A function that multiplies two numbers",
    "parameters": {
      "type": "object",
      "properties": {
        "a": {
          "type": "number",
          "description": "The first number to multiply"
        },
        "b": {
          "type": "number",
          "description": "The second number to multiply"
        }
      },
      "required": ["a", "b"]
    }
  }
}

# A simple function that takes no arguments
current_time = {
  "type": "function",
  "function": {
    "name": "current_time",
    "description": "Get the current local time as a string.",
    "parameters": {
      'type': 'object',
      'properties': {}
    }
  }
}

# A more complete function that takes two numerical arguments
multiply = {
  'type': 'function',
  'function': {
    'name': 'multiply',
    'description': 'A function that multiplies two numbers',
    'parameters': {
      'type': 'object',
      'properties': {
        'a': {
          'type': 'number',
          'description': 'The first number to multiply'
        },
        'b': {
          'type': 'number', 'description': 'The second number to multiply'
        }
      },
      'required': ['a', 'b']
    }
  }
}

model_input = tokenizer.apply_chat_template(
    messages,
    tools = [current_time, multiply]
)