InAI Exploration JourneybyFlorian June·4d agoInfinity-Parser2: Document Parsing That Goes Beyond Text Recognition to Understand StructureIn a previous article, I introduced the principles behind Infinity-Parser (Rethinking Scanned Document Parsing with Layout-Aware RL — AI…A response icon1A response icon1
InLevel Up CodingbyMd Monsur ali·Oct 28OCR-Apps: How I Built a Self-Hosted Document Intelligence Pipeline That Turns PDFs and Images Into…How I built a GPU-accelerated document intelligence system that converts complex PDFs, scanned documents, and images into structured…
InOpen IntelligencebyDr. Fadi Shaar·Oct 18OpenDataLoader PDF: Parse 100+ Pages per Second Without a GPUAn open-source approach to extracting structured document content and generating accessible, tagged PDFs on ordinary hardware.
Sidhanttiwari·Oct 3Building a RAG Pipeline That Actually Works on Real DocumentsIn Part 1, we covered the architecture and stack decisions. This part covers the retrieval pipeline — specifically how to make it work on…
InAI Exploration JourneybyFlorian June·Sep 30MinerU-Popo: Fixing the Hidden Flaw in PDF ParsingModern OCR can produce impressive page-level results, but real documents do not think in pages. They think in chapters, sections…
InArtificial Intelligence in Plain EnglishbyAyesha Mughal·Sep 15How I Parse and Organize 50+ Page Technical PDFs in Minutes Using AILast month a client sent me a 62 page PRD for an AI agent integration project. No summary, no table of contents that actually matched the…A response icon1A response icon1
InAI Exploration JourneybyFlorian June·Aug 15MinerU2.5-Pro: Teaching a 1.2B Model to Parse Like a GiantIn my earlier articles, I already covered the core idea behind MinerU (From Big Picture to Details: MinerU 2.5 Redefines Document Parsing).
Patilshubham·Jul 26Parsing PDFs for AI Search: Why We Use MiniLM to Generate the EmbeddingsIn the last two posts in this series, I covered why we self-host our LLM instead of routing documents to a public AI API, and how we use…
InAI Exploration JourneybyFlorian June·Jun 19The Three Paradigms Shaping Modern OCRAnyone who has worked with PDFs, forms, or scanned reports knows this feeling: extracting text is easy until structure starts to matter.A response icon1A response icon1
InAI Exploration JourneybyFlorian June·Jun 14MegaRAG: Stop Chunking Blindly, Start Reading Like a HumanIf you have ever built a RAG system for real documents, you probably know the feeling: the model finds the right page, but still misses the…A response icon2A response icon2
