AAAbbas Afsharfarniainabbas-code.hashnode.dev·8h ago · 8 min readLean AI: Stop Wasting Tokens and Start Building Smarter LLM Apps 🚀Most AI applications have a token problem. Not because tokens are inherently expensive, but because many applications send far more context than the model actually needs. Massive system prompts. Entir00
ARAhmad Raafatinbuilt-properly.hashnode.dev·16h ago · 21 min readMulti-Tenancy Is the Real Agent Platform Problem Overview What I have seen when building agent platforms is that most agent demos work because there is only one tenant. One user, one memory store, one tool set, one trace, one notebook, and one happy10
SSsatyam sahuinthebuildersnotebook.hashnode.dev·2h ago · 30 min readBuilding an Offline “Life Memorizer” with Gemini 2.0 & Qdrant EdgeOriginally published on Medium. Reposted here for the Hashnode community. Consider this. You are trying to find where you left an item, like your wallet or keys, inside your own house. You know you s00
Mmofuteqinblog.mofuteq.space·7h ago · 4 min readYour Users Ask One Question, Your Retriever Searches AnotherA user types a question into your RAG system. Before anything is retrieved, a decision gets made: what string do we actually search with? In a lot of systems, nobody made that decision on purpose. The00
MPMohana Priya Rinmona23.hashnode.dev·1d ago · 2 min readWhy I chose Qdrant over ChromaDB in my RAG SystemWhen I started building Nexus — my multi-source RAG system — one of the first real decisions I had to make was picking a vector database. It sounds like a small choice. It isn't. First, why do you eve00
TATrustgate AIintrustgateai.hashnode.dev·1d ago · 5 min readRAG poisoning: how one document can hijack your AI agentMost teams securing an LLM app start by filtering the user's prompt. It's the obvious move: untrusted input goes in, so you scan it for jailbreaks and injection attempts. The problem is that the most 00
MMMihai Marinescuinfeaturingcode.com·3d ago · 31 min readRAG From First Principles: How a PDF Becomes a Searchable AnswerAs a disclaimer, my project was created without spending any money on tokens at Voyage, Grok or Clerk for auth - meaning all the implementation was done on their free tier. The principles remain the s37JSZ
MGManav Guptainmanavgupta.hashnode.dev·3d ago · 8 min readHow quantization keeps vector search in RAMI've been building a RAG system over a terabyte of scanned engineering manuals tens of millions of pages, chunked into roughly six million searchable pieces. At that scale the interesting problems sto00
DPDevesh Parmarinbackend-bytes.hashnode.dev·3d ago · 9 min readHow Google Photos Finds Your Memories: And What Breaks When Vector Search Goes WrongYou typed "Spiti Valley 2026" and Google Photos found it instantly, with no tags, no albums, no manual sorting. Here's the engineering behind that magic, and what happens when it fails. The Magic Yo00
SRSukalyan Royinsukalyanroy.hashnode.dev·3d ago · 12 min readDiscovering RAGs 3: More on Agentic Rags and Project updatesIn the previous part, we explored Agentic RAG as an evolution of the traditional Retrieval-Augmented Generation pipeline:https://sukalyanroy.hashnode.dev/discovering-rags-2-what-is-agentic-rag A littl00
