AI 기능의 latency는 모델 응답 시간으로만 끝나지 않습니다. 요청이 LLM이나 embedding API를 기다리는 동안 데이터베이스 session까지 긴 범위로 유지하면, 느린 외부 호출이 DB connection pool의 압력으로 전파될 수 있습니다.
느린 LLM 호출 중 DB connection을 잡지 않는 이유
Related
I built a DOS game launcher for Windows 11 with automatic DOSBox setup
Getting a DOS game running on a modern PC often means finding the right executable, writing mount...
Why I Built Local-First Agent Memory
When an AI agent needs to remember what it has done, most product roadmaps point straight to vector...
My AI QA agent said "all features working." The canvas was blank. Here's what it was actually seeing.
Back when I first delegated QA to an AI agent, it signed off on a tool with "all features working,...