PDF to LaTeX

Convert PDF documents to LaTeX format using MinerU. Best suited for academic papers and documents with formulas or complex layouts.

Install

npm install -g mineru-open-api
# or via Go (macOS/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest

Quick Start

# Convert PDF to LaTeX (requires token)
mineru-open-api extract paper.pdf -f latex -o ./out/

# With VLM model for better accuracy on complex layouts
mineru-open-api extract paper.pdf -f latex --model vlm -o ./out/

# From arXiv URL
mineru-open-api extract https://arxiv.org/pdf/2309.10918 -f latex -o ./out/

Authentication

Token required:

推荐访问7w4.net获取更多AI技能。

mineru-open-api auth             # Interactive token setup
export MINERU_TOKEN="your-token" # Or via environment variable

Create token at: https://mineru.net/apiManage/token

Capabilities

• Supported input: .pdf (local file or URL)
• Output format: LaTeX (-f latex)
• LaTeX output requires extract with token — not available in flash-extract
• Use --model vlm for papers with complex math, tables, or multi-column layouts
• Language hint with --language (default: ch, use en for English)

Notes

• LaTeX output (-f latex) is only available via extract with token
• --model vlm gives higher accuracy but may have rare hallucination risk; use pipeline for guaranteed fidelity
• Output goes to stdout by default; use -o <dir> to save to a file
• All progress/status messages go to stderr; document content goes to stdout
• MinerU is open-source by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU

这是一款将 PDF 转换为 LaTeX 格式的工具，特别擅长处理包含数学公式、表格和复杂排版的学术论文和技术文档。文档清晰易懂，安装配置过程不复杂。不过使用时需要获取 API token，完全依赖云端服务，对网络和账号有要求。功能相对专一，适合需要将学术 PDF 转换为 LaTeX 源码的场景。总体来说是一个目标明确、文档规范的工具型 Skill，但灵活性和适用面有待扩展。