Lagent Logo
latest

Get Started

  • Overview
  • Installation
  • Quickstart

Tutorials

  • Action

Switch Language

  • English
  • 简体中文

API Reference

  • lagent.actions
    • Submodules
      • action_executor
      • arxiv_search
      • base_action
      • bing_map
      • builtin_actions
      • google_scholar_search
      • google_search
      • ipython_interpreter
      • parser
      • ppt
      • python_interpreter
    • Package Contents
  • lagent.agents
  • lagent.llms
  • lagent.utils
  • lagent.schema
  • lagent.version
Lagent
  • lagent.actions
  • arxiv_search
  • Edit on GitHub

arxiv_search

Module Contents

Classes

ArxivSearch

Search information from Arxiv.org. Useful for when you need to answer questions about Physics, Mathematics, Computer Science, Quantitative Biology, Quantitative Finance, Statistics, Electrical Engineering, and Economics from scientific articles on arxiv.org.

class lagent.actions.arxiv_search.ArxivSearch(top_k_results=3, max_query_len=300, doc_content_chars_max=1500, description=None, parser=JsonParser, enable=True)

Bases: lagent.actions.base_action.BaseAction

Search information from Arxiv.org. Useful for when you need to answer questions about Physics, Mathematics, Computer Science, Quantitative Biology, Quantitative Finance, Statistics, Electrical Engineering, and Economics from scientific articles on arxiv.org.

Parameters:
  • top_k_results (int) –

  • max_query_len (int) –

  • doc_content_chars_max (int) –

  • description (Optional[dict]) –

  • parser (Type[lagent.actions.parser.BaseParser]) –

  • enable (bool) –

get_arxiv_article_information(query)

Run Arxiv search and get the article meta information.

Parameters:

query (str) – the content of search query

Returns:

article information
  • content (str): a list of 3 arxiv search papers

Return type:

dict

Previous Next

© Copyright 2020-2030, InternLM. Revision d943beca.

Built with Sphinx using a theme provided by Read the Docs.