paper-wiki 0.3.0

Deep paper reading wiki: search, summarize, and analyze arXiv papers into a three-layer markdown wiki

paper-wiki

Deep paper reading wiki: search, summarize, and analyze arXiv papers into a three-layer markdown wiki.

Features

• Search arXiv papers via deepxiv API (SDK auto-installed)
• Download paper PDFs
• Generate per-section Chinese summaries using LLM
• Produce a full paper analysis with 5 dimensions:
  • ELI5 (小学生也能懂)
  • Core innovations (核心创新点)
  • Test datasets & metrics (测试集与指标)
  • Core weaknesses (核心缺点)
  • Future directions (后期演进方向)

Three-Layer Wiki

wiki/{arxiv_id}/
├── README.md           # Layer 1: full summary + 5 analysis aspects
├── sections/           # Layer 2: per-section Chinese summaries
│   ├── 01_introduction.md
│   ├── 02_method.md
│   └── ...
└── paper.pdf           # Layer 3: original PDF

Install

pip install paper-wiki

Prerequisites

• OpenAI-compatible API endpoint

Quick Start

# Configure API
export OPENAI_API_KEY=sk-xxx
export OPENAI_BASE_URL=https://api.openai.com/v1
export OPENAI_MODEL=gpt-4o

# Process a paper by arXiv ID
paper-wiki process 2409.05591

# Or by URL
paper-wiki process https://arxiv.org/pdf/2604.27393

# Search and interactively select
paper-wiki search "RAG long context"

# Search and auto-select first result
paper-wiki search "transformer memory" --first

# List processed papers
paper-wiki list

Configuration

Create a .env file in your working directory:

OPENAI_API_KEY=sk-xxx
OPENAI_BASE_URL=https://api.openai.com/v1
OPENAI_MODEL=gpt-4o

License

MIT