llama_index 开源文档分类工具 DocJev，分类或拆分文档 6 倍快于 GPT-5.6

Doc + Jev => DocJev @llama_index 团队最新开源文档分类与拆分工具 DocJev，给它一个 PDF/DOCX/PPTX 和一份用自然语言写的类别规则，它可以告诉你这份文...

Doc + Jev => DocJev @llama_index 团队最新开源文档分类与拆分工具 DocJev，给它一个 PDF/DOCX/PPTX 和一份用自然语言写的类别规则，它可以告诉你这份文档属于哪个类别，或者把一份“文件包”按边界拆成若干子文档并给出各自页码范围。 开源地址： github.com/jerryjliu/docj… 核心架构：解析与决策分离 1. 解析层（OCR/文本化）：默认用 liteparse，本地原生 Python 解析器，免费、无 API 费用；可选 LlamaParse，基于 VLM，擅长复杂版式，分 Cost Effective / Agentic / Agentic Plus 三档，支持版本锁定和缓存。DOCX/PPTX 需借助 LibreOffice 先渲染成 PDF。 2. 决策层（Jev）：把归一化后的页文本发给 Jev 托管服务，返回类别、概率和分布。 这个分离带来两个直接好处：解析结果可复用（parse 一次，classify/split 多次，metrics.decision_ms 可单独看推理耗时）；换 OCR 后端不影响决策逻辑。“6 倍速度”的对比是包含 liteparse 解析时间的全链路数字。 Jerry Liu @jerryjliu0 Introducing DocJev - a lightning-fast OSS library for document classification and splitting with jev ⚡️ Give a document alongside some natural language category rules. Jev will predict the document category (classify) or the boundaries between sub-documents (split). It is 6x faster than gpt-5.6-luna with equivalent accuracy. You can choose between different OCR backends: liteparse: the fastest/most accurate free+OSS text parser out there. Perfect for digitalized documents. The speedups vs. luna above are inclusive of liteparse times. LlamaParse: the most advanced VLM-based solution for complex docs. Using this will of course add latency on document preprocessing. But it’s a good option if you want to cache the digitalized representations of documents for a variety of downstream tasks. Check it out: github.com/jerryjliu/docj… If you want to dive deeper into liteparse or LlamaParse check the links below: liteparse: github.com/run-llama/lite… LlamaParse: cloud.llamaindex.ai Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 0 👀 146 📊 1 ⚡