#vector-embeddings articles

ABAditya Biranjeadityabiranje210.hashnode.devJul 23 · 27 min read

Designing the Ingestion Layer of a Production RAG System

Most RAG postmortems point at retrieval. Wrong chunks come back, the reranker doesn't help, the LLM hallucinates around a gap in context. Almost none of it is a retrieval bug. By the time a query hits

2

A

AGAvanish Gargavanish-garg.hashnode.devJul 22 · 6 min read

AI is an Illusion: Decoding the Greatest Magic Trick in Tech

The 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 phenome

0

APAnkita Patilblog.ankitapatil.devJul 16 · 5 min read

Building a Production-Style AI System: Designing VibeFit from Image Upload to Intelligent Recommendations

Live Demo → Experience the application. Architecture Walkthrough → Understand how the system works. Source Code → Explore the implementation. Project Deep Dive → Read the complete architecture and

0

MMaverickjyanshu.hashnode.devJul 13 · 13 min read

Vector Embeddings

How 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,

0

SSSameer Selokarblogbysameer.hashnode.devJul 12 · 10 min read

Retrieval-Augmented Generation (RAG): What It Is, How It Works, and Why It Sometimes Fails?

Most people think connecting an AI model to your documents magically makes it accurate. The reality is more nuanced. Retrieval-Augmented Generation (RAG) significantly improves an LLM's ability to ans

1

K

JCJim Chundevalelaccidentalcomplexity.hashnode.devJul 5 · 19 min read

Part 3: Open WebUI, a One-Sided Load Balancer, and a Bug Hiding One Field Deep

Two Birds, One Qdrant With the core database built and my own homelab knowledge ingested, I had a second idea. Open WebUI, the chat front end I already run for my Hailo and Gemma models, has its own b

0

AAanchalaanchalfatwani.hashnode.devJun 30 · 7 min read

Beginner’s Guide to Embeddings: How AI Learns to Understand the World

Have you ever wondered how Netflix recommends a movie you actually want to watch? Or how an AI chatbot understands the emotional weight behind a sentence like "I'm drowning here" without checking the

0

SSsatyam sahuthebuildersnotebook.hashnode.devJun 23 · 30 min read

Building an Offline “Life Memorizer” with Gemini 2.0 & Qdrant Edge

Originally 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 s

0

LSLakhan Samaniblog.authorizer.devJun 16 · 11 min read

Your AI assistant can leak files people aren't allowed to see — here's how to fix it

TL;DR Vector search ignores your permission model: an engineer can ask your RAG assistant about board-level financials and get them, because semantically close = retrieved, and a restricted chunk in

6

JZSRI

RTRaghavan T Mchangeofbasis.hashnode.devJun 15 · 4 min read

LLMs Don't Read Words. Here's What They Actually See.

Your phone keyboard has been doing this for years. You type "Happy" and it suggests "birthday." You type "I'll be" and it suggests "there." You ignore it half the time, but it's always right enough to

0

#vector-embeddings

Search Hashnode