Neo4j

A hidden flaw in #RAG pipelines: semantic drift.
Smarter chunking and a knowledge graph powered by Neo4j transform RAG into an accurate, explainable, and trustworthy reasoning engine.
By Nomthandazo Tshuma

bit.ly/4mqVkRo

#Neo4j #GraphRAG

Unleashing the Power of Schema: What’s New in the neo4j-graphrag Python Package - Graph Database & Analytics By combining powerful schema guidance and granular pruning, you’ll turn your unstructured data into more accurate and queryable graphs.

✅Automatically infer schema from text
✅Apply flexible schema enforcement options
✅Have granular control over the extraction process

Real example included: transforming cybersecurity advisories into actionable intelligence. Take a look!

bit.ly/3UCD6jQ

#Neo4j #Python

Unleashing the Power of Schema: What’s New in the neo4j-graphrag Python Package - Graph Database & Analytics By combining powerful schema guidance and granular pruning, you’ll turn your unstructured data into more accurate and queryable graphs.

🔥 New in the Neo4j's Python package!Automatically infers schemas from your text data!

Does not matter if you are a beginner or an expert, you can now improve your knowledge graph construction process thanks to the new schema capabilities introduced in the package:

How to Evaluate Graph Retrieval in MCP Agentic Systems | Towards Data Science A framework for measuring retrieval quality in Model Context Protocol agents.

Everyone’s building agents and spinning up MCP servers. But almost no one is talking about evaluation. In my latest post, I introduce a framework for evaluating graph retrieval in @neo4j.com MCP-based agentic systems, using @langchain.bsky.social

towardsdatascience.com/evaluating-g...

I Would Walk 500 Miles - Graph Database & Analytics Learn how to use the new Cypher REPEATABLE ELEMENTS match mode to solve queries that we weren’t able to before.

With real use cases, he arrives at interesting conclusions about the benefits and challenges.

bit.ly/3Hd48LE

#neo4j #cypher

I Would Walk 500 Miles - Graph Database & Analytics Learn how to use the new Cypher REPEATABLE ELEMENTS match mode to solve queries that we weren’t able to before.

Christoffer shows how to use the new REPEATABLE ELEMENTS match mode to solve queries that we weren’t able to before, like finding circular patterns where one of the nodes only has one incoming/outgoing relationship.
+

Going Meta S02E11 – a Series on Semantics, Knowledge Graphs and All Things AI YouTube video by Neo4j

Back to regular business in August: Hands-On example on the intersection of #ai and #graph - Tune in:
youtube.com/live/IlI3uNj...

Neo4j Live: From Text to Insights with Dashboards on Aura Are you ready for a new way to build dashboards with your graph data? Are you tired of switching contexts between query writing and visualization? In this session, we’ll explore how Neo4j Aura uses AI...

Today we show you how to create graph-powered dashboards just with natural language: Prompt → Cypher → Visualization in one flow youtube.com/live/NSkg1Yj... #dashboard

My recap highlighting a few of the sessions from the @neo4j.com Life Science & Pharma Day has been published: medium.com/neo4j/grapht... #lifescience #pharma #data #biotech

What Is a Graph Database? - Graph Database & Analytics Graph databases store data as networks of nodes and relationships, making it easier to analyze connections in complex, highly connected datasets.

Grounding AI to prevent hallucinations
Accelerating biotech discoveries
Exposing financial crimes (Panama Papers-style investigations)
Creating true customer 360° views

Learn more about how: bit.ly/4o2kveC

#GenAI #Graphdatabase #Neo4j

What is a Graph database?

Connected data is revolutionizing how forward-thinking companies solve complex challenges:

+

Text2Cypher Across Languages: Evaluating Foundational Models Beyond English - Graph Database & Analytics Explore how question language affects model performance on the Text2Cypher task using a multilingual test set with shared Cypher queries.

Makbule Gulcin Ozsoy and Will Tais analyze this in a blog where they shared a detailed evaluation to understand how the input language affects the quality of the generated Cypher queries- this test was made in English, Spanish, and Turkish, and the results might surprise you...

bit.ly/45mognS

Text2Cypher Across Languages: Evaluating Foundational Models Beyond English - Graph Database & Analytics Explore how question language affects model performance on the Text2Cypher task using a multilingual test set with shared Cypher queries.

Have you ever wondered how well #LLMs handle natural language to #Cypher query conversion across different languages?
+

Ever wondered why #graphdatabases matter?
Curious how to read and write data in #Neo4j?

We've got you covered! Our new series with Nyah Macklin and Martin O'Hanlon answers these and other questions.

Take a look and get introduced to the amazing world of Neo4j 🤩 🚀: bit.ly/3TSNFPH

Neo4j Live: From Text to Insights with Dashboards on Aura Are you ready for a new way to build dashboards with your graph data? Are you tired of switching contexts between query writing and visualization? In this session, we’ll explore how Neo4j Aura uses AI...

“What if I could just say what I want and get a dashboard?” - Now you can on Aura! Tune in for more next week youtube.com/live/NSkg1Yj... #dashboard #genai

Everything a Developer Needs to Know About the Model Context Protocol (MCP) - Graph Database & Analytics The Model Context Protocol gives users a wide range of services they can connect to from the comfort of their AI client.

If you are a developer, you need to go deep on the Model Context Protocol #MCP

@mesirii.de wrote this detailed blog where he explains the ecosystem, the challenges, and the benefits.

If you are looking to implement it on GenAI and Agent systems, start right here:

bit.ly/3IIgHPr

#MCP

Neo4j Live: Essential GraphRAG YouTube video by Neo4j

Are you ready to kick things of with GenAI and GraphRAG? Learn how in our live stream today:
youtube.com/live/X4IFOiY... #neo4j #graphrag #knowledgegraph #genai

GraphRAG in Action: A Simple Agent for Know-Your-Customer Investigations | Towards Data Science This blog post provides a hands-on guide for AI engineers and developers on how to build an initial KYC agent prototype with the OpenAI Agents SDK. We'll explore how to equip our agent with a suite of...

Find out how AI + knowledge graphs detect sophisticated financial crimes in KYC investigations.

Full technical walkthrough with OpenAI's Agents SDK, MCP, #Ollama, and #Neo4j.↓

towardsdatascience.com/graphrag-in-...

#GraphRAG #knowledgegraph #FraudDetection

GraphRAG in Action: A Simple Agent for Know-Your-Customer Investigations | Towards Data Science This blog post provides a hands-on guide for AI engineers and developers on how to build an initial KYC agent prototype with the OpenAI Agents SDK. We'll explore how to equip our agent with a suite of...

Ed Sandoval showcases a powerful use case for AI grounded by a knowledge graph (GraphRAG): Know-Your-Customer (KYC) - a critical defense line against illicit activities.

@towardsdatascience.com

Image

Want to ground your #LLMs with real context?

The Neo4j + LLM Fundamentals course walks you through using langchain.bsky.social , #Python, and Neo4j to build smarter #GenAI apps, with fewer hallucinations.

Free on GraphAcademy: bit.ly
#Neo4j

Cypher Versioning - Graph Database & Analytics Balance the stability and evolution of graph querying with Cypher versions offering extended support for existing Cypher queries.

Cypher 25 is where new features land first, ideal for developers building the next wave of graph-powered apps.

Valerio Malenchino breaks down what #Cypher versioning means, how to choose the right version, and how to start experimenting without rewriting your entire stack: bit.ly/4kGj7eW
#Neo4j

Cypher Versioning - Graph Database & Analytics Balance the stability and evolution of graph querying with Cypher versions offering extended support for existing Cypher queries.

Big news for Cypher users: versioning is here! 🤩

Two tracks, one goal: balance stability and innovation.

Cypher 5 is now frozen and stable, perfect for production environments that value consistency.
+

This is a really good and interesting conversation between my colleagues @jimbobc.bsky.social and @alekusi.bsky.social from @neo4j.com about new ideas and research for a #graph #database #runtime and gratefully focusing on system engineering and little on AI for a change.

Neo4j Live: Essential GraphRAG RAG is powerful, but only when the right context fuels it. Join us in this livestream as we sit down with Tomaz Bratanic, author of the book "Essential GraphRAG", to explore how knowledge graphs can e...

Get ready for "Essential GraphRAG" next week for a hands-on look at building high-performance, graph-powered RAG systems.
youtube.com/live/X4IFOiY... #neo4j #graphrag #knowledgegraph

#Cypher now has versions. Why? So you get stability where you need it, and innovation where you want it.

✅ Cypher 5 = frozen, stable
✅ Cypher 25 = evolving, feature-rich

Here’s how it works (and why it matters): bit.ly/3GmqcDn

#Neo4j #query #graphdatabase

Your business runs on connections: between customers, products, people, processes.
So why is your data still stuck in tables?

These 7 enterprise graphs map your org the way it actually works, and unlock smarter #GenAI, better insights, and faster decisions.
bit.ly/44DoNAg

#Neo4j

YouTube video by Neo4j Episode 1: How Neo4j Changes The Way You Think About Data

Incredibly happy that our new intro video series is now ready for everybody to watch: youtu.be/F-bwn8p3Pes - @neo4j.com #graphdatabase

Image

Building a recommender? Importing from relational? Tracking changes in real time?

#Neo4j tutorials walk you through it all step by step.✅

Get hands-on: bit.ly
#GraphDatabase #KnowledgeGraph #GenAI

Neo4j Live: Aurendil - A Future Graph Database Runtime YouTube video by Neo4j

Join us this week and hear about Neo4j Research’s radical new graph-native runtime that rewrites the rules of query execution youtube.com/live/sZketgH... #neo4j #cypher #database #research

Image

If your data isn’t connected, your AI won’t be either.

This guide walks you through building a #KnowledgeGraph step by step, so you can unlock better search, smarter recommendations, and #GenAI that actually works.

Read it here: bit.ly

#Neo4j