MinerU on recca0120 Tech Noteshttps://recca0120.github.io/en/tags/mineru/Recent content in MinerU on recca0120 Tech NotesHugo -- gohugo.ioenFri, 24 Apr 2026 21:00:00 +0800MinerU in Practice: Turning PDFs into RAG-Ready Markdownhttps://recca0120.github.io/en/2026/04/24/mineru-pdf-to-markdown/Fri, 24 Apr 2026 21:00:00 +0800https://recca0120.github.io/en/2026/04/24/mineru-pdf-to-markdown/Feeding PDFs to LLMs breaks formulas, tables, and multi-column layouts. I ran MinerU 2.5 on an academic PDF — formulas became LaTeX, tables became HTML, reading order preserved, and it runs on CPU.<![CDATA[Feeding PDFs to LLMs breaks formulas, tables, and multi-column layouts. I ran MinerU 2.5 on an academic PDF — formulas became LaTeX, tables became HTML, reading order preserved, and it runs on CPU.
Featured image]]>MinerUPDFRAGOCRLLMAI