AAsfaq Leeon·Oct 9Embeddings, Vector Search & RAG from Scratch with Node.js and PostgreSQL (pgvector)Learn the building blocks before you touch LangChain13 min read·leeonscoding.hashnode.dev3A
PPriya Singh·Sep 27First Time Implementing RAG How I built Repo Recall, a full-stack app that lets you chat with your GitHub repos. Lessons on RAG, embeddings, pgvector, and adm-zip.4 min read·priyasinghdev.hashnode.dev1
MMihir Inamdar·Sep 24I embedded all of Qdrant's docs with FastEmbed. The API would have cost 2 cents.5,084 chunks, 1.2 million tokens, 24 minutes on a 2 vCPU box. What running embeddings locally next to Qdrant actually costs, with every number labeled.9 min read·aihive.hashnode.dev
NNiran Pravithana·Sep 19Cutting MCP Round-Trips with Jev (Part 3)MCP's resolvers ping-pong top-k lists to the LLM every query — slow and costly. We tried Jev to pick server-side, cutting round-trips and cost ~4×.11 min read·marketiv.hashnode.dev12M
SSachin Nandanwar·Aug 26RAG for Microsoft AI Agent through TextSearchProvider and RedisImplement RAG in Microsoft Agent Framework using Redis and TextSearchProvider for vector search, embeddings and semantic retrieval12 min read·azureguru.net61J
NNahid Mahmud·Aug 12Deep Dive into Vector Search: ANN, HNSW, and Production OptimizationLearn core vector search concepts, ANN, IVF, HNSW indexing, and optimization strategies for high-performance AI systems3 min read·nahid-mahmud555.hashnode.dev1
NNahid Mahmud·Aug 10How Computers "Read" and Match Text: A Quick Vector Search ExperimentLearn how Vector Search works under the hood by building a simple semantic search engine in Python using embeddings and cosine distance.3 min read·nahid-mahmud555.hashnode.dev1
GGaurav Kumar·Aug 3How to Evaluate RAG Retrieval: A Practical Guide to Precision, Recall, MRR, MAP, and NDCGYou implemented a search algorithm in your RAG system and it's returning data without any error, and you think that's it, you're done. You're wrong. That mindset works fine for a normal system — an AP14 min read·gauravbytes.dev53APK
AAditya Biranje·Jul 23Designing the Ingestion Layer of a Production RAG SystemHow a modular parsing, chunking, and embedding pipeline turns PDFs, HTML, DOCX, PPTX, and TXT files into queryable vectors in Qdrant — and where it still breaks.27 min read·adityabiranje210.hashnode.dev13A
AAvanish Garg·Jul 22AI is an Illusion: Decoding the Greatest Magic Trick in TechThe most beautiful high-dimensional calculus ever mistaken for a mind, which apparently now runs the world! WELCOME TO THE CURIOSITY CRUNCH — EPISODE 04: A series where we take the technical phenome6 min read·avanish-garg.hashnode.dev
