app.py

from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
import datetime
import requests
import pytz
import yaml
from tools.final_answer import FinalAnswerTool
import cv2
import numpy as np

from Gradio_UI import GradioUI

# Below is an example of a tool that does nothing. Amaze us with your creativity !
@tool
def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
    #Keep this format for the description / args / args description but feel free to modify the tool
    """A tool that does nothing yet 
    Args:
        arg1: the first argument
        arg2: the second argument
    """
    return "What magic will you build ?"

@tool
def simple_object_detection(image_path: str, confidence_threshold: float) -> str:
    """
    A tool that performs simple object detection on an image using MobileNet SSD with error handling.
    
    Args:
        image_path: Path to the input image.
        confidence_threshold: Minimum confidence (e.g., 0.2) to filter weak detections.
    
    Returns:
        A string indicating the location of the saved processed image or an error message.
    """
    try:
        # List of class labels MobileNet SSD was trained on
        classes = ["background", "aeroplane", "bicycle", "bird", "boat",
                   "bottle", "bus", "car", "cat", "chair", "cow",
                   "diningtable", "dog", "horse", "motorbike", "person",
                   "pottedplant", "sheep", "sofa", "train", "tvmonitor"]

        # Paths to the pre-trained model files (ensure these files are downloaded)
        prototxt_path = "MobileNetSSD_deploy.prototxt.txt"
        model_path = "MobileNetSSD_deploy.caffemodel"
        
        # Load the pre-trained model from disk
        net = cv2.dnn.readNetFromCaffe(prototxt_path, model_path)
        
        # Load the image and get its dimensions
        image = cv2.imread(image_path)
        if image is None:
            return f"Error: Image at {image_path} could not be loaded."
        (h, w) = image.shape[:2]
        
        # Prepare the image as a blob for the network
        blob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 
                                     scalefactor=0.007843, size=(300, 300), 
                                     mean=127.5)
        
        # Pass the blob through the network to obtain detections
        net.setInput(blob)
        detections = net.forward()
        
        # Loop over the detections and draw bounding boxes for those above the threshold
        for i in range(0, detections.shape[2]):
            confidence = detections[0, 0, i, 2]
            if confidence > confidence_threshold:
                idx = int(detections[0, 0, i, 1])
                # Compute bounding box coordinates
                box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
                (startX, startY, endX, endY) = box.astype("int")
                
                # Draw the bounding box and label on the image
                label = f"{classes[idx]}: {confidence * 100:.2f}%"
                cv2.rectangle(image, (startX, startY), (endX, endY), (0, 255, 0), 2)
                y = startY - 10 if startY - 10 > 10 else startY + 20
                cv2.putText(image, label, (startX, y),
                            cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
        
        # Save the output image
        output_path = "output.jpg"
        cv2.imwrite(output_path, image)
        
        return f"Processed image saved as {output_path}"
    
    except Exception as e:
        return f"An error occurred: {str(e)}"


@tool
def get_current_time_in_timezone(timezone: str) -> str:
    """A tool that fetches the current local time in a specified timezone.
    Args:
        timezone: A string representing a valid timezone (e.g., 'America/New_York').
    """
    try:
        # Create timezone object
        tz = pytz.timezone(timezone)
        # Get current time in that timezone
        local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
        return f"The current local time in {timezone} is: {local_time}"
    except Exception as e:
        return f"Error fetching time for timezone '{timezone}': {str(e)}"


final_answer = FinalAnswerTool()

# If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
# model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 

model = HfApiModel(
max_tokens=2096,
temperature=0.5,
model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
custom_role_conversions=None,
)


# Import tool from Hub
image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)


with open("prompts.yaml", 'r') as stream:
    prompt_templates = yaml.safe_load(stream)
    
agent = CodeAgent(
    model=model,
    tools=[DuckDuckGoSearchTool(), simple_object_detection, get_current_time_in_timezone, final_answer], ## add your tools here (don't remove final answer)
    max_steps=6,
    verbosity_level=1,
    grammar=None,
    planning_interval=None,
    name=None,
    description=None,
    prompt_templates=prompt_templates
)


GradioUI(agent).launch()