JDJon Dixoninblog.cloudnueva.com·2h ago · 2 min readVector Search is HardIn spite of the demos you have seen, implementing vector search for a real-world application is hard. Google Search has set user expectations for search. Those expectations carry over into APEX apps. 00
SSSameer Selokarinblogbysameer.hashnode.dev·Sep 4 · 15 min readAI Memory: How Can an AI Agent Remember You?Have you ever told an AI assistant something important, only to discover that it has forgotten it in your next conversation? For example: You: My name is Sameer. I’m building an AI memory system call11A
AAbhijatinexpensivetobewrong.hashnode.dev·Aug 31 · 12 min readThe Query Expansion That Made Retrieval WorseHere is a technique that will make your retrieval worse while looking, to everyone on the team, like it should have made it better. Take the user's query. Before you embed it, append a handful of syno00
SSsatyam sahuinthebuildersnotebook.hashnode.dev·Aug 27 · 44 min readBuilding Hybrid Search for Financial Intelligence Originally published on Medium. Reposted here for the Hashnode community. Consider this. You are an equity analyst or an engineer building an AI-powered financial research tool, and you are trying to00
SNSachin Nandanwarinazureguru.net·Aug 26 · 12 min readRAG for Microsoft AI Agent through TextSearchProvider and RedisEarlier this year I had published an article on implemention of InMemory Vector Embeddings in Semantic kernel. At that time my focus was to understand how vector embeddings can be used in Semantic Ker61J
MMma michaelincloudsway.hashnode.dev·Aug 27 · 9 min readAgentic RAG vs. Traditional RAG: How AI Agents Improve RetrievalTL;DR Traditional RAG follows a fixed retrieval-and-generation pipeline, making it fast and predictable for stable knowledge-base questions. Agentic RAG lets an AI agent select retrieval tools, eval00
ASAjitabh Singhinajitabh.net·Aug 11 · 7 min readWhy Chunking Strategy Can Make or Break Your RAG PipelineMost of the attention in a RAG (Retrieval-Augmented Generation) build goes to the embedding model, the vector database, the reranker, or the LLM. One decision gets far less attention but can quietly a77ERK
DADaniel Anthony Romitelli Jrincraftedbydaniel.hashnode.dev·Aug 3 · 9 min readVector Split by Chunk: Why My Retrieval Stops at the Boundary I DrewA draft of mine missed the exact file span it needed. The vector was "close." But the chunk I wanted was buried inside a larger blob, and the miss was clean enough to be embarrassing: the sort of thin00
Mminhleducinminhleduc.hashnode.dev·Aug 1 · 9 min readWhy Your RAG Can't Answer "Why"Part 1 of 3 — Knowledge Graphs for AI Engineers. This one is about what vector search actually can't do, and being honest about when that matters. Here's a question I got asked at work that I couldn't11R
MMaverickinjyanshu.hashnode.dev·Jul 13 · 13 min readVector EmbeddingsHow AI Learned to Understand the Meaning Behind Words Who is this for? You don't need to know any math, code, or machine learning. If you've ever used Google Search, gotten a Netflix recommendation,00
