tools.py

from smolagents import DuckDuckGoSearchTool
from smolagents import Tool
import random
from huggingface_hub import list_models
import requests
from bs4 import BeautifulSoup
import openpyxl
import wikipedia
import pandas as pd

class MediaTool(Tool):
    name = "media_tool"
    description = "Used for deciphering video and audio files."
    inputs = {
        "filename": {
            "type": "string",
            "description": "The name of the media file to transcribe."
        }
    }
    output_type = "string"

    def forward(self, filename: str):
        print(f"called MediaTool with {filename}")
        return "This tool hasn't been implemented yet. Please return 0 if the task cannot be solved without knowing the contents of this file."

class WikipediaTool(Tool):
    name = "wikipedia_api"
    description = "Returns the contents of a wikipedia article through a direct API call."
    inputs = {
        "title": {
            "type": "string",
            "description": "The title of the wikipedia article to retrieve."
        }
    }
    output_type = "string"

    def forward(self, title: str):
        print(f"called WikipediaTool with {title}")
        try:
            page = wikipedia.page(title)
            content = page.content[:3000]
            return content
        except Exception as e:
            return f"ERROR: {e}"

class ExcelTool(Tool):
    name = "read_excel"
    description = "Returns the contents of an Excel file as a Pandas dataframe."
    inputs = {
        "filename": {
            "type": "string",
            "description": "The name of the Excel file to read."
        }
    }
    output_type = "string"

    def forward(self, filename: str):
        print(f"called ExcelTool with {filename}")
        try:
            df = pd.read_excel(filename, engine = "openpyxl")
            return df
        except Exception as e:
            return f"ERROR: {e}"

class WebscraperTool(Tool):
    name = "webscraper"
    description = "Returns the page's html content from the input url."
    inputs = {
        "url": {
            "type": "string",
            "description": "The link of the web page to scrape."
        }
    }
    output_type = "string"

    def forward(self, url: str):
        print(f"called WebscraperTool with {url}")
        try:
            response = requests.get(url, stream=True)
            if response.status_code == 200:
                soup = BeautifulSoup(response.content, 'html.parser')
                html_text = soup.get_text()
                return html_text
            else:
                return "Website cannot be reached."
        except Exception as e:
            return f"ERROR: {e}"

# Initialize the DuckDuckGo search tool
class InternetSearchTool(Tool):
    name = "internet_search"
    description = "Searches the internet for the answer to any question input. Returns a long batch of textual information related to the query."
    inputs = {
        "question": {
            "type": "string",
            "description": "The question to retrieve an answer for."
        }
    }
    output_type = "string"

    def forward(self, question: str):
        print(f"called InternetSearchTool with {question}")
        try:
            search_tool = DuckDuckGoSearchTool()
            result = search_tool(question)
            return result
        except Exception as e:
            return f"ERROR: {e}"

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)}"