Metadata-Version: 2.2
Name: arxa
Version: 0.1.3
Summary: A research automation tool for fetching, summarizing, and enhancing arXiv papers.
Home-page: https://github.com/binaryninja/ArxivSummarizer
Author: Jeremy Richards
Author-email: jeremy@richards.ai
Classifier: Programming Language :: Python :: 3
Description-Content-Type: text/markdown
Requires-Dist: PyPDF2
Requires-Dist: arxiv
Requires-Dist: anthropic
Requires-Dist: ollama
Requires-Dist: openai
Requires-Dist: requests
Requires-Dist: tenacity
Requires-Dist: tqdm
Requires-Dist: aiohttp
Requires-Dist: pyyaml
Requires-Dist: tiktoken
Requires-Dist: httpx<1,>=0.23.0
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: requires-dist
Dynamic: summary

# arxa

arxa is a tool to automatically generate research reviews from an arXiv paper or a local PDF. It even supports optional GitHub repository cloning and analysis if a GitHub URL is detected in the review.

## Installation

You can install via pip:

`pip install arxa`

Then run it with the command-line interface as shown below.

## Features

• Generate a review for a single arXiv paper by providing its ID:
`arxa -aid 1234.5678 -o output.md`

• Generate a review from a local PDF file:
`arxa -pdf /path/to/paper.pdf -o output.md`

• Specify the LLM backend provider and model:
`arxa -pdf /path/to/paper.pdf -o output.md -p openai -m o3-mini`

• Enable GitHub cloning (disabled by default):
`arxa -pdf /path/to/paper.pdf -o output.md -g`

• Use a configuration file for additional settings:
`arxa -c config.yaml`
