tools.py

import re
import time
from typing import Any

from smolagents import tool, Tool
import duckduckgo_search
import wikipediaapi


class FinalAnswerTool(Tool):
    name = "final_answer"
    description = "Provides a final answer to the given problem."
    inputs = {'answer': {'type': 'string', 'description': 'The final answer to the problem'}}
    output_type = "string"

    def forward(self, answer: str) -> str:
        """
        Submits the final answer to the user.
        """
        print(f"Final Answer: {answer}")
        return answer

class DuckDuckGoSearchTool(Tool):
    name = "web_search"
    description = "Performs a duckduckgo web search based on your query (think a Google search) then returns the top search results."
    inputs = {'query': {'type': 'string', 'description': 'The search query to perform.'}}
    output_type = "string"

    def __init__(self, max_results=10, **kwargs):
        super().__init__()
        self.max_results = max_results
        try:
            from duckduckgo_search import DDGS
        except ImportError as e:
            raise ImportError(
                "You must install package `duckduckgo_search` to run this tool: for instance run `pip install duckduckgo-search`."
            ) from e
        self.ddgs = DDGS(**kwargs)

    def forward(self, query: str) -> str:
        max_retries = 3
        retry_delay = 2  # seconds
        
        for attempt in range(max_retries):
            try:
                results = self.ddgs.text(query, max_results=self.max_results)
                if len(results) == 0:
                    raise Exception("No results found! Try a less restrictive/shorter query.")
                postprocessed_results = [f"[{result['title']}]({result['href']})\n{result['body']}" for result in results]
                return "## Search Results\n\n" + "\n\n".join(postprocessed_results)
                
            except Exception as e:
                error_msg = str(e)
                if "202" in error_msg or "rate" in error_msg.lower() or "ratelimit" in error_msg.lower():
                    if attempt < max_retries - 1:
                        print(f"Rate limit hit, retrying in {retry_delay} seconds... (attempt {attempt + 1}/{max_retries})")
                        time.sleep(retry_delay)
                        retry_delay *= 2  # Exponential backoff
                        continue
                    else:
                        return "## Search Results\n\nRate limit exceeded. Please try again later or use a different search strategy."
                else:
                    # For non-rate-limit errors, don't retry
                    raise e
        
        return "## Search Results\n\nFailed to get search results after multiple attempts."
    
class VisitWebpageTool(Tool):
    name = "visit_webpage"
    description = "Visits a webpage at the given url and reads its content as a markdown string. Use this to browse webpages."
    inputs = {'url': {'type': 'string', 'description': 'The url of the webpage to visit.'}}
    output_type = "string"

    def forward(self, url: str) -> str:
        try:
            import requests
            from markdownify import markdownify
            from requests.exceptions import RequestException

            from smolagents.utils import truncate_content
        except ImportError as e:
            raise ImportError(
                "You must install packages `markdownify` and `requests` to run this tool: for instance run `pip install markdownify requests`."
            ) from e
        try:
            # Send a GET request to the URL with a 20-second timeout
            response = requests.get(url, timeout=20)
            response.raise_for_status()  # Raise an exception for bad status codes

            # Convert the HTML content to Markdown
            markdown_content = markdownify(response.text).strip()

            # Remove multiple line breaks
            markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content)

            return truncate_content(markdown_content, 10000)

        except requests.exceptions.Timeout:
            return "The request timed out. Please try again later or check the URL."
        except RequestException as e:
            return f"Error fetching the webpage: {str(e)}"
        except Exception as e:
            return f"An unexpected error occurred: {str(e)}"

    def __init__(self, *args, **kwargs):
        self.is_initialized = False

class WikipediaSearchTool(Tool):
    name = "wikipedia_search"
    description = "Searches Wikipedia for a given query and returns the summary of the most relevant page. Use this for questions about specific facts, people, places, or events."
    inputs = {'query': {'type': 'string', 'description': 'The search query to perform.'}}
    output_type = "string"

    def __init__(self, **kwargs):
        super().__init__(**kwargs)
        self.wiki_wiki = wikipediaapi.Wikipedia(
            language='en',
            user_agent='SmolAgents-Course-Assignment/1.0'
        )

    def forward(self, query: str) -> str:
        """
        Searches Wikipedia for a given query and returns the summary of the most relevant page.
        Use this for questions about specific facts, people, places, or events.
        """
        try:
            page = self.wiki_wiki.page(query)
            if page.exists():
                return f"Title: {page.title}\nSummary: {page.summary}"
            else:
                return f"Could not find a Wikipedia page for '{query}'."
        except Exception as e:
            return f"An error occurred while searching Wikipedia: {e}"