rahulkaushal.hashnode.devBuild Your First RAG Pipeline from ScratchYou have probably heard people say "just build a RAG app" as if it is obvious. But nobody walks you through the whole thing, from loading a real PDF to getting a real answer out of an LLM, step by steJan 19·16 min read
rahulkaushal.hashnode.devHow AI Finds What You Actually MeanSo. You have heard the word "embedding" thrown around about forty times in AI tutorials. You have nodded along politely. You still have no idea what it actually is. That ends today. This post is goingJan 12·19 min read
rahulkaushal.hashnode.devThe Modern LLM Engineering Stack, Explained SimplySo you want to build AI apps. Cool. But every tutorial you open looks like it was written by a robot for other robots. Words like "vector embeddings," "RAG pipeline," "orchestration layer" get thrown Jan 5·14 min read
rahulkaushal.hashnode.devDon't Hold the Chef Hostage: A Production Guide to Async FastAPIYou've read the docs. You know async def is for async things and def is for sync things. You ship the app. Everything looks fine in development. Then it goes to production. Traffic picks up. Requests Nov 9, 2025·17 min read
rahulkaushal.hashnode.devWhy Your FastAPI DB Pool Never Fails in Dev (And Explodes in Prod)Your FastAPI app is humming in dev. Endpoints respond in under 50ms, tests pass, the team is happy. You ship to prod. Traffic climbs past 80 concurrent users and suddenly... your database pool is exhausted, requests are hanging, and your monitoring s...Nov 2, 2025·9 min read
