v2.7.5
Fixes
- PDF rendering timeout detection now works reliably under all conditions
Unclaimed project
Are you a maintainer of MinerU? Claim this project to take control of your public changelog and roadmap.
Changelog
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
Last updated about 2 months ago
Fixes
2026/01/30 2.7.4 Release
2026/01/30 2.7.4 发布
Full Changelog: https://github.com/opendatalab/MinerU/compare/mineru-2.7.2-released...mineru-2.7.3-released
2026/01/23 2.7.2 Release
2026/01/23 2.7.2 发布
2026/01/06 2.7.1 Release
2026/01/06 2.7.1 发布
vlm acceleration engine dependencies. Using uv pip install mineru[all] during installation will install all optional backend dependencies.hybrid backend, which combines the advantages of pipeline and vlm backends. Built on vlm, it integrates some capabilitie...Full Changelog: https://github.com/opendatalab/MinerU/compare/mineru-2.6.7-released...mineru-2.6.8-released
Full Changelog: https://github.com/opendatalab/MinerU/compare/mineru-2.6.6-released...mineru-2.6.7-released
mineru-api tool optimizations
mineru-api interface parameters to improve API documentation readability.MINERU_API_ENABLE_FASTAPI_DOCS to control whether the auto-generated interface documentation page is enabled (enabled by default).2025/11/26 2.6.5 Release
2025/11/26 2.6.5 发布
vlm-lmdeploy-engine支持，使用方式与vlm-vllm-(async)engine类似，但使用lmdeploy作为推理...AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Stable Diffusion web UI
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A feature-rich command-line audio/video downloader