#vector-search articles

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

MYManoir Yantaim1y-tech.hashnode.devMay 8 · 1 min read

Building an AI Agent with Persistent Memory: A Technical Deep Dive

Building an AI Agent with Persistent Memory Most AI assistants start fresh every conversation. Hermes Agent doesn't. The Memory Stack Hermes uses a three-layer memory system: 1. SQLite FTS5 (Full-Text Search) — Fast keyword search across all past con...

0

TITech Insights Hubtopperblog.hashnode.devMay 6 · 8 min read

Embedding-First Architecture for Real-World LLM Apps

In Postgres: -- CREATE EXTENSION IF NOT EXISTS vector; 2) Database schema (pgvector + metadata) ```sql -- Documents table CREATE TABLE IF NOT EXISTS documents ( doc_id TEXT PRIMARY KEY, source TEXT, title TEXT, created_at TIMESTAMPTZ DEFAULT...

0

UPUV Pantaallthingsgcp.comApr 27 · 3 min read

AlloyDB Just Got Smarter: AI Functions and Seriously Improved Vector Search

Alright, let's talk AlloyDB for a minute. If you're using it, or thinking about it, there's some genuinely exciting stuff dropping. Google just rolled out a bunch of new AI functions and made some big improvements to vector search. And honestly, it m...

0

UPUV Pantaallthingsgcp.comApr 20 · 3 min read

AlloyDB Just Got Smarter with New AI Functions and Vector Search Upgrades

You know how everyone's talking about bringing AI closer to your data? Well, Google Cloud's AlloyDB for PostgreSQL is really leaning into that. They just rolled out some pretty cool updates that let you do more AI-powered stuff directly inside your d...

0

KEkingsley ebube onohkingsleyonoh.hashnode.devApr 18 · 6 min read

I Built a Knowledge Graph Into the Retrieval Pipeline and Then Dropped It in Production

The vector search returned seven chunks about "database indexing strategies" for a query about "machine learning model training." All seven had cosine similarity scores above 0.72. All seven were confidently, precisely wrong. This is the failure mode...

0

MVMohit Vermaaiwithmohit.hashnode.devApr 9 · 7 min read

GraphRAG Beats Vector Search by 86% — But 92% of Teams Are Building It Wrong

GraphRAG Beats Vector Search by 86% — But 92% of Teams Are Building It Wrong Microsoft's GraphRAG paper showed that graph-structured retrieval with community summarization significantly outperforms flat vector search on multi-hop and thematic queries...

0

Aaiagentmemoryaiagentmemory.hashnode.devApr 7 · 9 min read

In-Memory Vector Database for Node.js: Supercharge AI Agent Recall

An in-memory vector database for Node.js is a specialized system that stores vector embeddings in RAM for ultra-fast similarity searches, enabling real-time data retrieval crucial for AI agents. This architecture dramatically speeds up recall for Nod...

0

FSFahad Shahrisingwave.comApr 7 · 14 min read

Semantic Product Recommendations with Vector Search and Streaming SQL

{ "@context": "https://schema.org", "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "What are semantic recommendations?", "acceptedAnswer": { "@type": "Answer", "text": "Semantic recommen...

0

JJahanzaibjahanzaibai.hashnode.devApr 4 · 19 min read

Agentic RAG: The Complete Production Guide Nobody Else Wrote

Three months into a contract with a mid-sized insurance company, I was sitting across from their CTO watching their "AI knowledge base" answer questions about their own products. The system retrieved the right documents 90% of the time. But on anythi...

0

#vector-search

Search Hashnode