ac_tools.py

from smolagents import Tool
import time
import random
from duckduckgo_search import DDGS


class DuckDuckGoSearchToolWH(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
        self.USER_AGENTS = [
            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
            "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:122.0) Gecko/20100101 Firefox/122.0",
            "Mozilla/5.0 (Macintosh; Intel Mac OS X 13_0) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.1 Safari/605.1.15",
            "Mozilla/5.0 (Linux; Android 11; Pixel 5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Mobile Safari/537.36",
            "Mozilla/5.0 (iPhone; CPU iPhone OS 16_0 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.0 Mobile/15E148 Safari/604.1"
        ]
        self.kwargs = kwargs
        self.kwargs.pop('headers', None)


    def forward(self, query: str) -> str:
        headers = {"User-Agent": random.choice(self.USER_AGENTS)}
        self.ddgs = DDGS(headers=headers, **self.kwargs)
        time.sleep(2.0)
        results = self.ddgs.text(query, max_results=self.max_results)
        if not results:
            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)