DocJev library classifies documents 6x faster than gpt-5.6-luna
it's awesome to see the reception here 🔥 one of the jev's promises is to make a lot of business o...
Free and open-source on GitHub, DocJev classifies documents 6x faster than gpt-5.6-luna at equivalent accuracy, giving developers a lightweight alternative to VLM-based pipelines like LlamaParse.
Jerry Liu, founder of LlamaIndex, announced DocJev, an open-source library built on Jev for document classification and splitting. Users supply a document with natural language category rules, and DocJev predicts either the document category or the boundaries between sub-documents. The library runs 6x faster than gpt-5.6-luna with equivalent accuracy, with speedups measured including liteparse preprocessing time. It offers two OCR backends: liteparse, a free open-source parser for digitalised documents, and LlamaParse, a VLM-based option for complex documents that adds preprocessing latency. Liu positions DocJev for lightweight business operations, leaving intelligence-heavy tasks to larger agentic systems.
it's awesome to see the reception here 🔥 one of the jev's promises is to make a lot of business o...
it's awesome to see the reception here 🔥 one of the jev's promises is to make a lot of business operations extremely lightweight and fast, while still saving intelligence-heavy tasks for larger agentic systems docjev is hyperfocused on doc classification and splitting, and it's very good at it. you can see the full visual report from the readme: github.com/jerryjliu/docj… 9 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 💬 8 🔄 1 ❤️ 26 👀 2621 📊 13 ⚡
- shao__meng09-20 23:54原文
