langgraph_dir/custom_tools.py

from langchain_core.tools import tool
from huggingface_hub import InferenceClient

# --- Basic operations --- #

@tool
def multiply(a: float, b: float) -> float:
    """Multiplies two numbers.

    Args:
        a (float): the first number
        b (float): the second number
    """
    return a * b


@tool
def add(a: float, b: float) -> float:
    """Adds two numbers.

    Args:
        a (float): the first number
        b (float): the second number
    """
    return a + b


@tool
def subtract(a: float, b: float) -> int:
    """Subtracts two numbers.

    Args:
        a (float): the first number
        b (float): the second number
    """
    return a - b


@tool
def divide(a: float, b: float) -> float:
    """Divides two numbers.

    Args:
        a (float): the first float number
        b (float): the second float number
    """
    if b == 0:
        raise ValueError("Cannot divided by zero.")
    return a / b


@tool
def modulus(a: int, b: int) -> int:
    """Get the modulus of two numbers.

    Args:
        a (int): the first number
        b (int): the second number
    """
    return a % b


@tool
def power(a: float, b: float) -> float:
    """Get the power of two numbers.

    Args:
        a (float): the first number
        b (float): the second number
    """
    return a**b


# --- Functions --- #

@tool
def query_image(query: str, image_url: str) -> str:
    """Ask anything about an image using a Vision Language Model

    Args:
        query (str): the query about the image, e.g. how many persons are on the image?
        image_url (str): the URL to the image
    """

    client = InferenceClient(provider="nebius")
    try:
        completion = client.chat.completions.create(
            # model="google/gemma-3-27b-it",
            model="Qwen/Qwen2.5-VL-72B-Instruct",
            messages=[
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "text",
                            "text": query
                        },
                        {
                            "type": "image_url",
                            "image_url": {
                                "url": image_url
                            }
                        }
                    ]
                }
            ],
            max_tokens=512,
        )
        return completion.choices[0].message

    except Exception as e:
        return f"query_image failed: {e}"

@tool
def automatic_speech_recognition(file_url: str) -> str:
    """Transcribe an audio file to text

    Args:
        file_url (str): the URL to the audio file
    """
    client = InferenceClient(provider="fal-ai")
    try:
        return client.automatic_speech_recognition(file_url, model="openai/whisper-large-v3")
    except Exception as e:
        return f"automatic_speech_recognition failed: {e}"