mineru-4.0.9-released
refactoringhq/tolariamineru-4.0.9-releasedSep 28, 2026by myhloli
Upgrading?
AI Summary
Improves PDF text extraction accuracy by rebuilding inter-word spacing to prevent English word merging and optimizes render subprocess handling for better concurrent task performance.
Key Highlights
- Native PDF text extraction rebuilds inter-word spacing to fix word merging
- PDF render subprocess supports non-exclusive reuse for concurrent tasks
- Dependency update: Require docvortex>=0.5.4
Full Release Notes
## 更新内容 / What's Changed **优化 / Improvements** - PDF 原生文本提取：重建词间空格，修复空格丢失导致的英文单词黏连，并保护代码 span 与相邻文本的间距 / Native PDF text extraction: rebuild inter-word spacing to fix lost spaces merging English words, with code-span spacing protection - PDF render 子进程支持非独占复用，并发任务不再排队等待 render worker / PDF render subprocess now supports non-exclusive reuse, so concurrent tasks no longer wait for an available render worker **依赖 / Dependencies** - docvortex 提升至 0.5.4（0.5.2 → 0.5.4）/ Require docvortex>=0.5.4 (0.5.2 → 0.5.4) **Full Changelog**: https://github.com/opendatalab/MinerU/compare/mineru-4.0.8-released...mineru-4.0.9-released
Related Repositories
openclaw/openclaw★ 392,714
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
nilbuild/developer-roadmap★ 370,095
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
morluto/rea★ 360,153
Reverse engineer anything with agents, from app behavior down to native binaries.
anomalyco/opencode★ 219,855
The open source coding agent.
n8n-io/n8n★ 208,278
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.