tools/browse.py

import copy
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_community.document_loaders import WikipediaLoader
from langchain_community.document_loaders import ArxivLoader
from langchain_core.tools import tool
def format_search_docs(search_docs):
    """Format search documents into a consistent string format.
    
    Args:
        search_docs: List of document objects with metadata and page_content.
        
    Returns:
        Formatted string with document sources and content.
    """
    return "\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
        ]
    )

@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 = format_search_docs(search_docs)
    return {"wiki_results": 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 = format_search_docs(search_docs)
    return {"web_results": formatted_search_docs}

@tool
def arxiv_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()
    truncated_docs = []
    for doc in search_docs:
        doc_copy = copy.copy(doc)
        doc_copy.page_content = doc.page_content[:1000]
        truncated_docs.append(doc_copy)
    
    formatted_search_docs = format_search_docs(truncated_docs)
    return {"arxiv_results": formatted_search_docs}