Spaces:
Sleeping
Sleeping
| from langchain_core.tools import tool | |
| from langchain_community.document_loaders import ArxivLoader | |
| from langchain_community.retrievers import WikipediaRetriever | |
| def arxiv_search(query: str) -> str: | |
| """ | |
| Search Arxiv for academic papers based on a query and return summaries of top results. | |
| Args: | |
| query (str): The search query for Arxiv. | |
| Returns: | |
| str: Summary of the top few relevant papers from Arxiv. | |
| """ | |
| try: | |
| loader = ArxivLoader(query=query, load_max_docs=2) | |
| documents = loader.load() | |
| if not documents: | |
| return "No relevant papers found on Arxiv." | |
| # Format and return top paper summaries | |
| results = [] | |
| for doc in documents: | |
| title = doc.metadata.get("Title", "No Title") | |
| published = doc.metadata.get("Published", "Unknown date") | |
| url = doc.metadata.get("entry_id", "No URL") | |
| summary = doc.page_content[:500] # limit summary length | |
| results.append(f"Title: {title}\nPublished: {published}\nURL: {url}\nSummary: {summary}\n") | |
| return "\n---\n".join(results) | |
| except Exception as e: | |
| return f"An error occurred while searching Arxiv: {str(e)}" | |
| def wikipedia_search(query: str) -> str: | |
| """ | |
| Search Wikipedia for a given query and return a summary of the top result. | |
| Args: | |
| query (str): The search term. | |
| Returns: | |
| str: A summary of the most relevant Wikipedia entry. | |
| """ | |
| wikipedia_retriever = WikipediaRetriever(load_max_docs=1) | |
| documents = wikipedia_retriever.get_relevant_documents(query) | |
| if not documents: | |
| return "No relevant Wikipedia articles found." | |
| formatted_search_docs = "\n\n---\n\n".join( | |
| [ | |
| f'<Document source="{doc.metadata["source"]}" title="{doc.metadata.get("title", "")}"/>\n{doc.metadata["summary"]}\n</Document>' | |
| for doc in documents | |
| ]) | |
| # Return the content of the top document | |
| return formatted_search_docs | |