Local LLM을 넘어 OCR-RAG-Inference 통합 파이프라인 기반의 Full-Local AI 아키텍처 구축
Why “Local Document AI” Is Really an OCR + RAG + Local Inference Problem
Why “Local Document AI” Is Really an OCR + RAG + Local Inference Problem
How We Built a Federal Court Rules Database
From Scans to Structured Data: Converting Medical Reports to JSON with Pydantic & LLMs
LLM wiki for the historical research
Stop Guessing Your Health: Building an Autonomous AI Nutritionist Crew with CrewAI and GPT-4o
Vision Models for OCR: When They Beat Tesseract and When They Don't
I built a tool to analyze lease agreements and uncover hidden costs before signing
I shipped my first AI iOS app in 24 days. Apple rejected it 4 times. Here's what I learned.
Vintage chatbot lives in the past like an elderly relative
I built a free PDF toolkit that properly handles Arabic documents
I Built CrabPDF: a Privacy-First PDF Editor That Runs Locally in the Browser
Why OCR Alone Fails in Real-World Documents
Claude Code Billing Alert, Workflow Enhancements & Open-Source OCR Benchmarks
Finn 💰 — A Personal Finance Assistant That Lives in WhatsApp
Document Parsing vs Document Understanding: What’s the Difference?
LLM OCR Benchmarks, Claude Code Context Issues, & Cloud GPU Pricing Tool
3.7만 개 아티클의 구조화 파이프라인을 통한 백과사전 디지털 복원
From Pixels to Prescriptions: Building a Smart Drug-Drug Interaction (DDI) Scanner with GPT-4o and OCR
OpenAI now lets you screenshot your privacy in the foot
Article: Redesigning Banking PDF Table Extraction: A Layered Approach with Java