大模型
x.com ·
@jerryjliu0
Jerry Liu 发布开源文档分类与切分库 DocJev
Jerry Liu 介绍开源库 DocJev，用于文档分类与子文档边界切分：输入文档和自然语言类别规则即可预测类别或切分点，声称比 gpt-5.6-luna 快 6 倍且精度相当。支持 liteparse（免费开源文本解析器，适合数字化文档）和 LlamaParse（基于 VLM，适合复杂文档但增加预处理延迟）两种 OCR 后端，并给出 GitHub 与 LlamaParse 链接。性能对比为作者自述，尚无独立验证。
AI推荐理由 作者发布开源文档分类/切分库 DocJev，给出自然语言类别规则即可分类或切分，并声称比 gpt-5.6-luna 快 6 倍且精度相当，支持 liteparse 与 LlamaParse 两种 OCR 后端，附 GitHub 链接。属于开发者可验证的一手工具发布，对文档处理与 Agent 数据管线有实际用途；但性能对比为作者自述、无第三方复现，且发布时间为存储时间，不能视为新发布。
72
浏览 55,409
点赞 820
评论 31
转发 68
正文
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: https://github.com/jerryjliu/docjev
If you want to dive deeper into liteparse or LlamaParse check the links below:
liteparse: https://github.com/run-llama/liteparse
LlamaParse: https://cloud.llamaindex.ai/