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

from Gradio_UI import GradioUI

# Below is an example of a tool that does nothing. Amaze us with your creativity !
@tool
def capture_website_screenshot(url: str, full_page: bool = False) -> str:
    """Captures a screenshot of a specified webpage.
    Args:
        url: The URL of the website to screenshot
        full_page: Whether to capture the entire page or just the viewport
    """
    import os
    import tempfile
    from selenium import webdriver
    from selenium.webdriver.chrome.options import Options
    from datetime import datetime
    
    try:
        # Create a temporary file path for the screenshot
        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
        temp_dir = tempfile.gettempdir()
        screenshot_path = os.path.join(temp_dir, f"screenshot_{timestamp}.png")
        
        # Configure Chrome options
        chrome_options = Options()
        chrome_options.add_argument("--headless")  # Run in headless mode
        chrome_options.add_argument("--disable-gpu")
        chrome_options.add_argument("--no-sandbox")
        chrome_options.add_argument("--disable-dev-shm-usage")
        chrome_options.add_argument("--window-size=1920,1080")
        
        # Initialize the WebDriver
        driver = webdriver.Chrome(options=chrome_options)
        
        # Navigate to the URL
        driver.get(url)
        
        # Wait for page to load (you might need to adjust this)
        driver.implicitly_wait(5)
        
        if full_page:
            # Get the total height of the page
            total_height = driver.execute_script("return document.body.scrollHeight")
            # Set the window size to capture everything
            driver.set_window_size(1920, total_height)
            
        # Take the screenshot
        driver.save_screenshot(screenshot_path)
        
        # Close the browser
        driver.quit()
        
        return f"Screenshot captured successfully and saved to: {screenshot_path}"
        
    except Exception as e:
        return f"Error capturing screenshot: {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=[final_answer, capture_website_screenshot], ## 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()