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

@tool
def get_bbc_headline(section: str = "news") -> str:
    """Extracts the main headline from BBC website sections.
    
    Args:
        section: BBC section to check - 'news', 'sport', 'business', 'technology'
    """
    import requests
    from bs4 import BeautifulSoup
    import time
    
    # Map sections to URLs
    bbc_urls = {
        "news": "https://www.bbc.co.uk/news",
        "sport": "https://www.bbc.co.uk/sport", 
        "business": "https://www.bbc.co.uk/news/business",
        "technology": "https://www.bbc.co.uk/news/technology",
        "world": "https://www.bbc.co.uk/news/world"
    }
    
    if section not in bbc_urls:
        return f"Invalid section. Available: {', '.join(bbc_urls.keys())}"
    
    url = bbc_urls[section]
    
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
        'Accept-Language': 'en-GB,en;q=0.5',
        'Cache-Control': 'no-cache'
    }
    
    try:
        response = requests.get(url, headers=headers, timeout=10)
        response.raise_for_status()
        
        soup = BeautifulSoup(response.content, 'html.parser')
        
        # BBC headline selectors (they change frequently, so multiple fallbacks)
        headline_selectors = [
            'h1[data-testid="headline"]',  # Current BBC format
            'h1.gs-u-mt0',                 # Alternative format
            '.media__title',               # Story format
            'h1',                          # Generic fallback
            '.gs-c-promo-heading__title'   # Promo heading
        ]
        
        main_headline = None
        
        # Try each selector until we find a headline
        for selector in headline_selectors:
            headlines = soup.select(selector)
            if headlines:
                # Get the first meaningful headline
                for headline in headlines:
                    text = headline.get_text().strip()
                    if len(text) > 10:  # Filter out short/empty headlines
                        main_headline = text
                        break
                if main_headline:
                    break
        
        if main_headline:
            # Get timestamp for context
            timestamp = time.strftime("%Y-%m-%d %H:%M:%S UTC")
            return f"BBC {section.title()} - Main Headline ({timestamp}):\n{main_headline}"
        else:
            return f"Could not extract headline from BBC {section} section. Site structure may have changed."
            
    except requests.exceptions.RequestException as e:
        return f"Error accessing BBC {section}: {str(e)}"
    except Exception as e:
        return f"Error parsing BBC {section}: {str(e)}"

# Test function to validate the tool works
def test_bbc_headline_tool():
    """Test the BBC headline extraction on multiple sections"""
    sections = ["news", "sport", "business"]
    
    print("🔍 Testing BBC Headline Extraction")
    print("=" * 40)
    
    for section in sections:
        print(f"\n📰 Testing {section.upper()} section...")
        result = get_bbc_headline(section)
        print(f"Result: {result[:100]}...")
        
    print("\n✅ Test completed")

if __name__ == "__main__":
    test_bbc_headline_tool()

@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()