internet_search_tool.py

from duckduckgo_search import DDGS
from utils import clean_text
from langchain_core.tools import tool

@tool
def internet_search(query: str, max_results: int = 10) -> list[dict]:
    """
    Search the Internet for the given query and return a list of results.

    Args:
        query (str): The search query string.
        max_results (int, optional): Maximum number of search results to return. Default is 10.

    Returns:
        list[dict]: A list of dictionaries containing search results. Each dictionary typically includes:
                    - 'title': The title of the result.
                    - 'href': The URL of the result.
                    - 'body': A short snippet or description.
    
    Raises:
        ValueError: If the query is empty or only whitespace.
    """
    if not query.strip():
        raise ValueError("Query must not be empty.")

    results = []
    with DDGS() as ddgs:
        for r in ddgs.text(query):
            results.append(r)
            if len(results) >= max_results:
                break
    return results

if __name__ == "__main__":
    query = 'Alexandre Gazola'
    try:        
        results = internet_search.invoke(
            {
            "query": query, 
            "max_results": 5
            }
         )
        
        for i, result in enumerate(results, 1):
            print(f"\nResult {i}:")
            print(f"Title: {clean_text(result.get('title'))}")
            print(f"URL: {clean_text(result.get('href'))}")
            print(f"Snippet: {clean_text(result.get('body'))}")
    except ValueError as e:
        print(f"Error: {e}")