LlamaIndex 出了个新工具 LiteParse v2.1，专门把 PDF 转成 Markdown，速度最快，准确率还吊打同类开源方案，免费直接用。
LlamaIndex 推出 LiteParse v2.1，号称全球最快的 PDF 转 Markdown 解析器。在 olmOCR0-bench、opendataloader-bench 和 ParseBench 三个标准化基准上，其准确率超过 pymupdf4llm、opendataloader、pdf-inspector、markitdown 等所有开源无模型解析器。该工具完全开源（Apache 2.0）且免费，支持 CLI、Rust、Node、Python 和 WASM 调用，也可作为一键 Agent Skill 安装。
We built the fastest PDF -> markdown parser in the world 🚀⚡️ AND it’s more accurate than any other...
We built the fastest PDF -> markdown parser in the world 🚀⚡️ AND it’s more accurate than any other open-source, model-free parser (pymupdf4llm, opendataloader, pdf-inspector, markitdown) on 3 standardized benchmarks: olmOCR0-bench, opendataloader-bench, ParseBench Introducing LiteParse v2.1. The v2 base version was already the fastest document->text parser on the planet, and with this new release we’ve introduced markdown. It is fully open-source (Apache 2.0) and free, is usable from CLI/Rust/Node/Python/WASM, and is also installable as a one-click agent skill. Check it out: llamaindex.ai/blog/markdown-… 2 Come check out LiteParse: github.com/run-llama/lite… 8 Your browser does not support the video tag. 🔗 View on Twitter 💬 7 🔄 9 ❤️ 24 👀 2319 📊 16 ⚡
- IT之家06-17 13:52原文