KSKreeti Sharmainkreeti1210.hashnode.dev·Apr 3 · 5 min readHow can we make our RAGs Better?Ever wondered how we can calculate the success metrics of RAGs model? How we enhance the model and on which parameters especially when we have so many models? Most frequent metrics that can come to ou00
KSKreeti Sharmainkreeti1210.hashnode.dev·Nov 10, 2025 · 1 min readUnderstanding Memoization in React Simplified Like Never Before!As I was preparing for frontend interviews, I realized that one of the trickiest concepts to explain clearly is memoization in React, especially when it comes to optimizing re-renders. So I created this visual to simplify how these three tools work t...00
KSKreeti Sharmainkreeti1210.hashnode.dev·Aug 18, 2025 · 5 min readHow Retrieval-Augmented Generation Makes AI Smarter with Personalized Law Firm DataImagine you're BENJAMIN who is just hired by a law firm PEARSON HARDMAN. Their goal? To integrate AI into their internal systems so that legal documents, case files, and client information can be retrieved effortlessly - just by asking a question. I ...01A
KSKreeti Sharmainkreeti1210.hashnode.dev·Aug 15, 2025 · 5 min readPrompting in LLMs: Talking to AI Like a ProEver chatted with ChatGPT and wondered how it knows what tone to use or how deep to go? That magic comes from prompting — the art of telling an LLM (Large Language Model) what you want and how you want it. Let’s break it down in a way that’s fun, vis...00
KSKreeti Sharmainkreeti1210.hashnode.dev·Jul 29, 2025 · 4 min readUnifying Data Fetching with GraphQL : The Upgrade Every Developers NeedPicture this: your frontend needs to render a blog post with its author's name and other authored posts. With a RESTful setup, that typically means: GET /blog/:id GET /author/:id GET /author/:id/blogs That’s three API calls just to render one vi...00
