Yash Bhoskar
RSS FeedExploring ideas that inspire me—and maybe you. See my work on My Profile.
Featured
-
Test prod
Prod test
-
An Evening, An agent, and The Ganesh Utsav
Updated:Pune’s Ganesh Utsav is easy to celebrate, but not always easy to navigate. So I built a simple, ad-free guide to help people find Ganpatis, aartis, and routes—right when they need them.
-
RAG Is Not Just Chunking → Embedding → Retrieval → Generation
Updated:RAG isn't just chunking, embedding, retrieval & generation. Discover the hidden steps — parsing, reranking, relevancy — that make or break your RAG pipeline.
-
Wait, how many P's are in "strawperry"?
Updated:Why AI gets letter counts wrong and what it tells us about artificial vs human brains.
-
Agentic Chunking - Why Your RAG Pipeline Is Quietly Failing (And How to Fix It)
Stop losing answers to bad chunks. Learn why agentic chunking beats every traditional RAG method — and why corn proves it.
-
Docling - AI-Powered Document Pipeline for LLMs & RAG
Updated:Still using basic PDF parsers? Docling brings AI-powered document understanding, layout detection, and smart chunking — built for modern LLM workflows.
-
Deep Dive into Semantic Chunking for RAG
Updated:Most RAG pipelines fail not because of the model, but because of bad chunking. In this deep dive, we explore semantic chunking and how splitting text by meaning instead of size can dramatically improve retrieval accuracy.