​
ArxivToolkit

class ArxivToolkit(BaseToolkit):
A toolkit for interacting with the arXiv API to search and download academic papers.

​
init

def __init__(self, timeout: Optional[float] = None):
Initializes the ArxivToolkit and sets up the arXiv client.

​
_get_search_results

def _get_search_results(
    self,
    query: str,
    paper_ids: Optional[List[str]] = None,
    max_results: Optional[int] = 5
):
Retrieves search results from the arXiv API based on the provided query and optional paper IDs. Parameters:
  • query (str): The search query string used to search for papers on arXiv.
  • paper_ids (List[str], optional): A list of specific arXiv paper IDs to search for. (default: :obj:None)
  • max_results (int, optional): The maximum number of search results to retrieve. (default: :obj:5)
Returns: Generator: A generator that yields results from the arXiv search query, which includes metadata about each paper matching the query.

​
search_papers

def search_papers(
    self,
    query: str,
    paper_ids: Optional[List[str]] = None,
    max_results: Optional[int] = 5
):
Searches for academic papers on arXiv using a query string and optional paper IDs. Parameters:
  • query (str): The search query string.
  • paper_ids (List[str], optional): A list of specific arXiv paper IDs to search for. (default: :obj:None)
  • max_results (int, optional): The maximum number of search results to return. (default: :obj:5)
Returns: List[Dict[str, str]]: A list of dictionaries, each containing information about a paper, including title, published date, authors, entry ID, summary, and extracted text from the paper.

​
download_papers

def download_papers(
    self,
    query: str,
    paper_ids: Optional[List[str]] = None,
    max_results: Optional[int] = 5,
    output_dir: Optional[str] = './'
):
Downloads PDFs of academic papers from arXiv based on the provided query. Parameters:
  • query (str): The search query string.
  • paper_ids (List[str], optional): A list of specific arXiv paper IDs to download. (default: :obj:None)
  • max_results (int, optional): The maximum number of search results to download. (default: :obj:5)
  • output_dir (str, optional): The directory to save the downloaded PDFs. Defaults to the current directory.
Returns: str: Status message indicating success or failure.

​
get_tools

def get_tools(self):
Returns: List[FunctionTool]: A list of FunctionTool objects representing the functions in the toolkit.