NEXT4I 
enAIEngineerRAGAIDeveloperAIBuildInPublic
Hybrid Search Explained: Why Vector Search Still Needs Keywords
Hybrid search combines semantic and keyword retrieval so systems can find both intended meaning and the specific terms that matter.
Dev Notes
Shared knowledge from NEXT4I and the web community.
9 items
enRAGAIDeveloperAIEngineerAIBuildInPublic
Chunking in RAG: How to Split Documents Without Losing the Conditions
That failure can start before generation, at the document boundary. **Chunking in RAG is not about making text as small as possible.
enRAGKnowledgeManagementAIEngineerAIDeveloperSecondBrian
From Ctrl + F to AI-Powered Search
Finding Content and Answering Questions directly from Files: Most people who work with documents have faced some version of this problem
enRAGAIEngineerBuildInPublicAIDeveloperSecondBrianAI
RAG Architecture Beyond the Demo: Retrieval, Thai Chunking, and Production Boundaries
Connecting an LLM to an application is the easy part of a RAG demo. The difficult part starts when the source is a real document instead of a clean string in an array.
enGeneralAIToolsMarkdownSecondBrianAILLM
How to Write an AI Agent Skill File That Reduces Guesswork
A prompt can tell an agent what to do once. A skill file can document how a team handles that class of work repeatedly.
enLLMAIDeveloperAIEngineerAIModelAIAIRouter
What Is Token & LLM Cost Optimization
What Is a Token in LLMs? A Developer's Guide to Cost Optimization and Architecture. Understanding how LLM tokens work is the difference between an AI feature that costs $50/month
enLLMAIDeveloperSystemArchitectureAIEngineerAI
What Is LLM Actually Doing? A Fellow Engineer's Take on Vectors, Next-Token Prediction, and Fail-back Routing
Why treating an LLM as a probability engine, not a brain, changes how you architect around it. The reasoning behind NEXT4I's AI layer.
enMarkdownBuildInPublicRAGAIDeveloperAI
How I Learned to Stop Worrying and Love Markdown The PDF-to-AI Pipeline War Story
I was building a RAG (Retrieval-Augmented Generation) pipeline for NEXT4I the kind of system that reads your documents first, then answers questions from them. Standard stuff: document ingestion → chunking → embedding → vector search → LLM answer generation.
enBuildInPublicSecondBrianKnowledgeManagementAIToolsAI
How to Build a "Second Brain" with Obsidian That Your AI Agent Can Read, Without Building a Custom RAG Pipeline
Connecting Obsidian, Git, and AI Agents with nothing but plain Markdown. The Seamless Integration by Design philosophy from NEXT4I.
Be the first to try it
ลงชื่อเพื่อรับแจ้งเตือน และร่วมเป็นผู้ใช้งานกลุ่มแรกพร้อมรับสิทธิพิเศษ
Drop your email to get notified. Early access members get exclusive perks!
We hate spam as much as you do. Only big updates, no junk.
No subscriptions. No annual fees. No lock-ins.