Neo4j

Most RAG systems today score how semantically similar a new query is to stored text chunks and return a list of the best matches. However, information doesn’t need to include similar words to be relevant. Data entities might be related… Read more →

You’ve been accepted into the Neo4j Startup Program, congrats. This guide walks through the handful of steps between “approved” and “credits are live on my account,” since this is where most of the questions we hear come from. What happens after… Read more →

The knowledge layer for enterprise AI: ProcessesThis series is the practical build companion to Jesús Barrasa’s knowledge layer manifesto. This chapter is built on the previous chapter 1: Operating StructureRosa Delgado runs Risk & Compliance at AcmeBank. In the first… Read more →

이 글은 Neo4j 공식 블로그의 “The knowledge layer for enterprise AI”(2026년 7월 20일) 게시물을 한국어로 번역한 것입니다. 풍부한 맥락을 갖춘 엔터프라이즈 AI를 위한 선언문 엔터프라이즈 AI가 실패하는 이유는 모델 때문이 아닙니다. 최첨단 LLM은 몇 달에 한 번씩 더 저렴하고 더… Read more →

Turn accumulated learnings into procedures and user profiles, then feed them back into the agentPart 3 of the self-learning multi-agent series. Part 1 covered the tools and hooks. Part 2 introduced the semantic layer and memoryCoauthored with Firat TekinerAdding memory to an agent… Read more →

Over the years, I’ve seen two broad philosophies emerge for building an intelligence analysis platform. One concentrates knowledge and capability inside the vendor. The other builds them inside the customer’s own team. The distinction matters more as the platform grows.… Read more →

Retailers rarely lack data. Between customer profiles, point-of-sale transactions, inventory levels, and promo schedules, modern enterprises generate terabytes of signals daily. The issue is that legacy relational architectures keep this information locked in siloed systems across POS platforms, inventory systems,… Read more →

A vector-only pipeline can be a great fit for your agentic AI project — right up until an accurate, explainable response depends on how disparate facts connect. Take a support example, where a manager asks which vendor’s outage caused three… Read more →

Optimizing graph import partitioning based on workers and k-1 coloring algorithm.This article is a generalization of the approach designed by Eric MONK in his article “Mix and batch: a technique for fast, parallel relationship loading in Neo4j”. It explains the… Read more →

Somebody asks whether GuardDuty covers every account. The question is about holes in the coverage, not about whether the service is switched on. From a flat resource inventory that is a genuinely annoying question. You export accounts, export detectors, line… Read more →

As an AI application grows, its embeddings can quickly become one of its largest demands on memory. More documents, finer-grained chunks and richer embedding models all increase the amount of vector data your database needs to search. Keeping retrieval fast… Read more →