tools.py

from smolagents import DuckDuckGoSearchTool
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin



# Initialize the DuckDuckGo search tool
search_tool = DuckDuckGoSearchTool()

# Example usage
# results = search_tool("Who's the current President of France?")
# print(results)


from smolagents import Tool
import random

class WeatherInfoTool(Tool):
    name = "weather_info"
    description = "Fetches dummy weather information for a given location."
    inputs = {
        "location": {
            "type": "string",
            "description": "The location to get weather information for."
        }
    }
    output_type = "string"

    def forward(self, location: str):
        # Dummy weather data
        weather_conditions = [
            {"condition": "Rainy", "temp_c": 15},
            {"condition": "Clear", "temp_c": 25},
            {"condition": "Windy", "temp_c": 20}
        ]
        # Randomly select a weather condition
        data = random.choice(weather_conditions)
        return f"Weather in {location}: {data['condition']}, {data['temp_c']}°C"

# # Initialize the tool
# weather_info_tool = WeatherInfoTool()


from smolagents import Tool
from huggingface_hub import list_models

class HubStatsTool(Tool):
    name = "hub_stats"
    description = "Fetches the most downloaded model from a specific author on the Hugging Face Hub."
    inputs = {
        "author": {
            "type": "string",
            "description": "The username of the model author/organization to find models from."
        }
    }
    output_type = "string"

    def forward(self, author: str):
        try:
            # List models from the specified author, sorted by downloads
            models = list(list_models(author=author, sort="downloads", direction=-1, limit=1))
            
            if models:
                model = models[0]
                return f"The most downloaded model by {author} is {model.id} with {model.downloads:,} downloads."
            else:
                return f"No models found for author {author}."
        except Exception as e:
            return f"Error fetching models for {author}: {str(e)}"

# # Initialize the tool
# hub_stats_tool = HubStatsTool()

# # Example usage
# print(hub_stats_tool("facebook")) # Example: Get the most downloaded model by Facebook


# from smolagents import CodeAgent, InferenceClientModel

# # Initialize the Hugging Face model
# model = InferenceClientModel()

# # Create Alfred with all the tools
# alfred = CodeAgent(
#     tools=[search_tool, weather_info_tool, hub_stats_tool], 
#     model=model
# )

# # Example query Alfred might receive during the gala
# response = alfred.run("What is Facebook and what's their most popular model?")

# print("🎩 Alfred's Response:")
# print(response)




class ScrapingWeb(Tool):
    name = "scraping_web"
    description = "Scraping the website to extract all text information available"
    inputs = {
        "link": {
            "type": "string",
            "description": "The link of the website to scrape"
        }
    }
    output_type = "string"

    def forward(self, link: str):
        try:
            # 1. Fetch the page
            response = requests.get(link, timeout=10)
            response.raise_for_status()  # raise HTTPError for bad status codes
        except (requests.RequestException) as e:
            print(f"Error fetching {link}: {e}")
            return None

        # 2. Parse with BeautifulSoup
        soup = BeautifulSoup(response.text, "html.parser")

        # 3. Extract the page title
        title_tag = soup.find("title")
        title = title_tag.get_text(strip=True) if title_tag else None

        # 4. Extract all visible text
        #    We’ll grab the text of each <p>, <h1>-<h6>, and <div> (if needed).
        #    For a rough “all text”, you can also do soup.get_text(), but that includes scripts/styles.
        for script_or_style in soup(["script", "style"]):
            script_or_style.decompose()
        visible_text = soup.get_text(separator="\n", strip=True)

        # 5. Extract all hyperlinks (absolute URLs)
        links = []
        for a in soup.find_all("a", href=True):
            href = a["href"]
            absolute = urljoin(link, href)
            links.append(absolute)

        return visible_text
    
        # return {
        #     "title": title,
        #     "text": visible_text,
        #     "links": links
        # }