Yash Bhoskar
RSS FeedExploring ideas that inspire me—and maybe you. See my work on My Profile.
Featured
-
AI harness vs. IPL harness: why your LLM needs a championship dugout
Updated:Signing for a faster model without the rest of the system is like signing a star player and playing without fielders or DRS. A breakdown of the six layers every production AI agent needs.
-
Why Your RAG Agent Gives Wrong Answers: PDF Extraction Explained
20 open-source OCR and PDF extractors for RAG and AI agents, and why the best OCR model isn't the best pipeline.
-
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 is more than chunking, embedding, retrieval, and generation. See the steps in between: parsing, reranking, and relevance checks, and where each one fails.
-
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)
Bad chunks lose answers. This post covers why agentic chunking outperforms traditional methods, and a simple corn test that shows it.
-
Docling: an AI-powered document pipeline for LLMs and RAG
Updated:Still using basic PDF parsers? Docling adds layout detection, table reconstruction, and semantic chunking for modern LLM pipelines.
-
Deep Dive into Semantic Chunking for RAG
Updated:Most RAG pipelines fail because of bad chunking, not the model. This post covers how semantic chunking, splitting text by meaning instead of size, improves retrieval accuracy.