LiteParse v2 解决了 PDF 解析慢、依赖大模型的痛点，做文档处理或 AI Agent 的开发者可以直接用，速度比同类快一个量级。
LlamaIndex 创始人 Jerry Liu 宣布推出 LiteParse v2，用 Rust 完全重写，成为全球最快的 PDF 解析器。它基于网格投影算法，无需 LLM 即可将复杂页面布局（含文本和表格）转换为结构清晰的文本，支持 50+ 文档类型，可直接在 AI Agent 中使用。相比 pymupdf、pypdf 等开源方案，LiteParse v2 在速度和准确性上均占优。核心步骤包括文本行分组、锚点识别、对齐渲染等，详情可查看官方博客。
The secret to LiteParse lies in the grid projection algorithm. We project a complex page layout with...
The secret to LiteParse lies in the grid projection algorithm. We project a complex page layout with text and tables into well-structured text, that humans can read and agents can understanding. This contains of a few core steps (no LLMs!): 1. Grouping text fragments to lines 2. Identify left,center,right anchors 3. Snap each text item to an anchor 4. Handle flowing paragraphs separately 5. Render each text item in a carefully tuned order so that each piece of text aligns to a grid column 6. Post-processing For more details check out this great blog post we wrote a month ago! llamaindex.ai/blog/how-litep… Jerry Liu @jerryjliu0 We've created the world's fastest PDF parser ⚡️ And it's more accurate than any other open-source, model-free PDF parser out there (pymupdf, pypdf, markitdown, pdftotext, opendataloader, pymupdf4llm) Introducing LiteParse v2 - we rewrote the entire library into Rust and adapted it as native packages for Python and Node. It supports 50+ different document types, can be triggered directly or installable directly within your favorite AI agent. Blog: llamaindex.ai/blog/liteparse… Repo: github.com/run-llama/lite… 🔗 View Quoted Tweet 💬 1 🔄 1 ❤️ 1 👀 247 📊 2 ⚡