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 scrapes webpages for content!
@tool
def smart_webpage_scraper(url: str, selector: str = None) -> str:
    """Intelligently scrapes webpage content with anti-detection measures.
    Args:
        url: The webpage URL to scrape
        selector: Optional CSS selector for specific content
    """
    import requests
    from bs4 import BeautifulSoup
    import time
    import random
    
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
        'Accept-Language': 'en-US,en;q=0.5',
        'Accept-Encoding': 'gzip, deflate',
        'Connection': 'keep-alive'
    }
    
    try:
        # Add random delay to avoid detection
        time.sleep(random.uniform(1, 3))
        
        response = requests.get(url, headers=headers, timeout=15)
        response.raise_for_status()
        
        soup = BeautifulSoup(response.content, 'html.parser')
        
        # Remove script and style elements
        for script in soup(["script", "style"]):
            script.decompose()
        
        if selector:
            elements = soup.select(selector)
            if elements:
                return '\n'.join([elem.get_text().strip() for elem in elements])
            else:
                return f"No elements found with selector: {selector}"
        
        # Get main content, avoid headers/footers
        main_content = soup.find('main') or soup.find('article') or soup.find('div', class_='content') or soup.body
        
        if main_content:
            text = main_content.get_text(separator='\n', strip=True)
            # Limit output and clean up
            lines = [line.strip() for line in text.split('\n') if line.strip()]
            return '\n'.join(lines[:100])  # First 100 meaningful lines
        
        return "Could not extract meaningful content"
        
    except requests.exceptions.RequestException as e:
        return f"Network error accessing {url}: {str(e)}"
    except Exception as e:
        return f"Parsing error for {url}: {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], ## 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()