企业 AI 团队终于有了一个可视化的文档处理工具，能直接从 PDF 中提取结构化 JSON，做数据清洗和 RAG 管道的开发者可以直接用起来。
LlamaIndex 发布了开源项目 Parse-Flow，旨在解决企业 AI 中从 PDF 等非结构化文档提取可靠结构化数据的难题。该项目提供了一个可视化工作流设计器，集成了四个核心文档处理原语：解析、分类、分割和提取。用户可以通过拖拽步骤构建管道，实时观察事件流，底层由 LlamaAgents 工作流驱动，确保每一步可观测且错误可处理。这对于处理合同、发票、报告等复杂文档的企业 AI 应用具有重要意义。
Most AI pipelines are only as good as the data we provide them with, and that usually means PDFs or ...
Most AI pipelines are only as good as the data we provide them with, and that usually means PDFs or other unstructured documents. Contracts, invoices, reports... All have special layout, language, and context mixed together, and getting reliable structured data out of them is still one of the hardest unsolved problems in enterprise AI. Parse-Flow is an open-source project we built to tackle this head-on. It puts four document processing primitives at the center of a visual workflow designer: 📄 Parse — clean markdown and text from raw documents 🔍️ Classify — assign documents to user-defined categories ✂️ Split — segment documents into typed chunks Extract — pull structured JSON against a schema You drag steps onto a canvas, drop in a document, and watch events stream back as the pipeline runs. Under the hood it's powered by a LlamaAgents workflow that walks your flow one step at a time, making every transition observable and every failure a first-class value. 📚️ Full write-up on the architecture he llamaindex.ai/blog/designing… wGnX 👩💻 Source github.com/run-llama/pars… 7vXt9i 💬 1 🔄 1 ❤️ 4 👀 334 📊 2 ⚡