src/agent/tools/web_tools.py

from langchain_core.tools import tool
from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
from langchain_community.tools import TavilySearchResults


@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 formatted_search_docs


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


@tool
def scientific_paper_search(query: str) -> str:
    """Search Arxiv for scientific papers and publications and return maximum 3 results.
    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 title="{doc.metadata.get("Title", "")}" authors="{doc.metadata.get("Authors", "")}" published="{doc.metadata.get("Published", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
            for doc in search_docs
        ]
    )
    return formatted_search_docs


# Export all web tools
web_tools = [web_search, scientific_paper_search]