MinerU 4.0.0 发布:分档解析与本地文档库
原标题:mineru-4.0.0-released
AI 摘要
MinerU 发布 4.0.0 大版本,围绕分档解析质量、原生多格式文档解析、面向 Agent 阅读的本地文档库以及统一 SDK/API/服务工具进行重构。新版本将原有 pipeline/vlm/hybrid 后端替换为 flash、basic、standard、advanced 四档质量,支持 PDF、Office、EPUB、HTML 等原生多格式解析,并新增 mineru 命令族与本地文档库、稳定引用定位符。该版本还引入独立模型配置、V1 HTTP API 与结构化结果多格式渲染,并包含多项破坏性变更和迁移指南。
正文节选
## What's Changed - 2026/09/16 4.0.0 Released MinerU 4.0 is a major release that rebuilds the project around **tiered parsing quality**, **native multi-format document parsing**, **a local document library for agent reading**, and **unified SDK / API / service tools**. The main updates include: - Four parsing tiers - The 3.x `pipeline` / `vlm` / `hybrid` backend selection is replaced by four quality tiers: `flash`, `basic`, `standard`, and `advanced`. - `flash` parses nati