-
2025/06/13 2.0.0发布
- MinerU 2.0 是一次从架构到功能的全面重构与升级，带来了更简洁的设计、更强的性能以及更灵活的使用体验。
- 全新架构：MinerU 2.0 在代码结构和交互方式上进行了深度重构，显著提升了系统的易用性、可维护性与扩展能力。
- 去除第三方依赖限制：彻底移除对
pymupdf的依赖，推动项目向更开放、合规的开源方向迈进。 - 开箱即用，配置便捷：无需手动编辑 JSON 配置文件，绝大多数参数已支持命令行或 API 直接设置。
- 模型自动管理：新增模型自动下载与更新机制，用户无需手动干预即可完成模型部署。
- 离线部署友好：提供内置模型下载命令，支持完全断网环境下的部署需求。
- 代码结构精简：移除数千行冗余代码，简化类继承逻辑，显著提升代码可读性与开发效率。
- 统一中间格式输出：采用标准化的
middle_json格式，兼容多数基于该格式的二次开发场景，确保生态业务无缝迁移。
- 去除第三方依赖限制：彻底移除对
- 全新模型：MinerU 2.0 集成了我们最新研发的小参数量、高性能多模态文档解析模型，实现端到端的高速、高精度文档理解。
- 小模型，大能力：模型参数不足 1B，却在解析精度上超越传统 72B 级别的视觉语言模型（VLM）。
- 多功能合一：单模型覆盖多语言识别、手写识别、版面分析、表格解析、公式识别、阅读顺序排序等核心任务。
- 极致推理速度：在单卡 NVIDIA 4090 上通过
sglang加速，达到峰值吞吐量超过 10,000 token/s，轻松应对大规模文档处理需求。 - 在线体验：您可在我们的huggingface demo上在线体验该模型：体验链接
- 不兼容变更说明:为提升整体架构合理性与长期可维护性，本版本包含部分不兼容的变更：
- Python 包名从
magic-pdf更改为mineru，命令行工具也由magic-pdf改为mineru，请同步更新脚本与调用命令。 - 出于对系统模块化设计与生态一致性的考虑，MinerU 2.0 已不再内置 LibreOffice 文档转换模块。如需处理 Office 文档，建议通过独立部署的 LibreOffice 服务先行转换为 PDF 格式，再进行后续解析操作。
- Python 包名从
- 全新架构：MinerU 2.0 在代码结构和交互方式上进行了深度重构，显著提升了系统的易用性、可维护性与扩展能力。
- MinerU 2.0 是一次从架构到功能的全面重构与升级，带来了更简洁的设计、更强的性能以及更灵活的使用体验。
-
2025/06/13 2.0.0 Released
- MinerU 2.0 represents a comprehensive reconstruction and upgrade from architecture to functionality, delivering a more streamlined design, enhanced performance, and more flexible user experience.
- New Architecture: MinerU 2.0 has been deeply restructured in code organization and interaction methods, significantly improving system usability, maintainability, and extensibility.
- Removal of Third-party Dependency Limitations: Completely eliminated the dependency on
pymupdf, moving the project toward a more open and compliant open-source direction. - Ready-to-use, Easy Configuration: No need to manually edit JSON configuration files; most parameters can now be set directly via command line or API.
- Automatic Model Management: Added automatic model download and update mechanisms, allowing users to complete model deployment without manual intervention.
- Offline Deployment Friendly: Provides built-in model download commands, supporting deployment requirements in completely offline environments.
- Streamlined Code Structure: Removed thousands of lines of redundant code, simplified class inheritance logic, significantly improving code readability and development efficiency.
- Unified Intermediate Format Output: Adopted standardized
middle_jsonformat, compatible with most secondary development scenarios based on this format, ensuring seamless ecosystem business migration.
- Removal of Third-party Dependency Limitations: Completely eliminated the dependency on
- New Model: MinerU 2.0 integrates our latest small-parameter, high-performance multimodal document parsing model, achieving end-to-end high-speed, high-precision document understanding.
- Small Model, Big Capabilities: With parameters under 1B, yet surpassing traditional 72B-level vision-language models (VLMs) in parsing accuracy.
- Multiple Functions in One: A single model covers multilingual recognition, handwriting recognition, layout analysis, table parsing, formula recognition, reading order sorting, and other core tasks.
- Ultimate Inference Speed: Achieves peak throughput exceeding 10,000 tokens/s through
sglangacceleration on a single NVIDIA 4090 card, easily handling large-scale document processing requirements. - Online Experience: You can experience this model online on our Hugging Face demo: Experience Link
- Incompatible Changes Notice: To improve overall architectural rationality and long-term maintainability, this version contains some incompatible changes:
- Python package name changed from
magic-pdftomineru, and the command-line tool changed frommagic-pdftomineru. Please update your scripts and command calls accordingly. - For modular system design and ecosystem consistency considerations, MinerU 2.0 no longer includes the LibreOffice document conversion module. If you need to process Office documents, we recommend converting them to PDF format through an independently deployed LibreOffice service before proceeding with subsequent parsing operations.
- Python package name changed from
- New Architecture: MinerU 2.0 has been deeply restructured in code organization and interaction methods, significantly improving system usability, maintainability, and extensibility.
- MinerU 2.0 represents a comprehensive reconstruction and upgrade from architecture to functionality, delivering a more streamlined design, enhanced performance, and more flexible user experience.
New Contributors
- @seedclaimer made their first contribution in #2536
- @AdrianWangs made their first contribution in #2578
Full Changelog: magic_pdf-1.3.12-released...mineru-2.0.0-released