tools/search_tools.py

from langchain_core.tools import tool
from langchain_community.document_loaders import WikipediaLoader
from langchain_community.document_loaders import ArxivLoader
# Search engine specifically for LLMs
# from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_tavily import TavilySearch


@tool
def web_search(query: str) -> str:
    """Search Tavily for a query and return maximum 3 results.
    
    Args:
        query: The search query."""
    # print(f"Web search query:::::::::::: {query}")
    search_docs = TavilySearch(max_results=3).invoke({"query":query})
    formatted_search_docs = "\n\n---\n\n".join(
        [
            f'<Document source="{doc["url"]}" page="{doc["title"]}"/>\n{doc["content"]}\n</Document>'
            for doc in search_docs['results']
        ])
    # print(f"Web search result:::::::::::: {formatted_search_docs}")
    return {"web_results": formatted_search_docs}

@tool
def wiki_search(query: str) -> str:
    """Search Wikipedia for a query and return maximum 2 results.
    
    Args:
        query: The search query."""
    
    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
    formatted_search_docs = "\n\n---\n\n".join(
        [
            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
            for doc in search_docs
        ])
    
    return {"wiki_results": formatted_search_docs}

@tool
def arvix_search(query: str) -> str:
    """Search Arxiv for a query and return maximum 3 result.
    
    Args:
        query: The search query."""
    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
    formatted_search_docs = "\n\n---\n\n".join(
        [
            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
            for doc in search_docs
        ])
    return {"arvix_results": formatted_search_docs}