LlamaIndex这次把文档解析的三种场景都做了：高精度的、低成本大批量的、还有低延迟实时的。有LlamaParse和开源LiteParse，不同需求直接用对应的就行。
LlamaIndex推出LlamaParse和LiteParse，分别针对文档解析的三个关键场景：高精度解析要求99%+准确率，面向金融和保险等监管行业，价格不敏感；低成本高吞吐解析支持代理批量处理大量文档；低延迟低成本解析适配用户临时上传大量文件（如1000个PDF给Claude Cowork）的代理循环。LlamaParse覆盖成本-精度模式，LiteParse为开源项目，可路由至VLM深度解析模式。所有测试结果可在ParseBench查看。
Fully solving document parsing includes covering every point on the Pareto curve of accuracy, cost, ...
Fully solving document parsing includes covering every point on the Pareto curve of accuracy, cost, and latency: 1️⃣ High-accuracy parsing - requires 99%+ accuracy, price insensitive. Especially relevant in regulated industries like financial service and insurance. 2️⃣ Low cost, high volume parsing - requires inhaling a massive volume of documents as context for agents. Can run offline in a batch setting. 3️⃣Low latency and low cost parsing - these are use cases where the user is uploading a massive volume of files ad-hoc and in the agent loop (e.g. uploading 1k pdfs to claude cowork). Requires an extremely fast pass to make sense of the docs before a deeper dive LlamaParse covers the cost-accuracy modes for document OCR with our document agent harness. LiteParse, our OSS project, is designed to be in the agent loop, and can route to deeper VLM-enabled modes. I talked about this and other topics during the @aiDotEngineer talk today. Stay tuned for the slides! In the meantime, check out our full set of parsing results on ParseBench: parsebench.ai LlamaParse: cloud.llamaindex.ai LiteParse: github.com/run-llama/lite… 💬 0 🔄 0 ❤️ 0 👀 51 ⚡