NODES 2025
as the organisers put it
NODES 2025 on November 6 is the biggest graph community gathering dedicated to applications, data intelligence, knowledge graphs, and AI.
| title | author | length |
|---|---|---|
| Agentic GraphRAG: Multi-Agent Knowledge Graph | Akhil Hemanth | 28m |
A reproducible multi-step system ingests PDFs and tables, runs a four-agent pipeline (analyzer, extractor, merger, optimizer) with OpenAI Chat Kit and… | ||
| GraphRAG for Law: Building Legal Reasoning Agents | Aleksandr Khazov | 36m |
GraphRAG uses Neo4j + APOC + native vector search to model statutes, sections and precedents as granular nodes with embeddings, combining semantic vectors, a… | ||
| Ontology Creation | Alex Gilmore, Jesús Barrasa | 28m |
Builds a graph schema from messy HTML and structured CSVs using the Data Modeling MCP server and Claude Desktop, producing a JSON model that the server… | ||
| Keynote: Fireside Chat | Andrew Ng, Emil Eifrem | 30m |
Defines agentic AI as iterative, multi-step workflows and lays out four design patterns: tool calling, planning, reflection, multi-agent collaboration, argues… | ||
| Agentic AI for Enterprise Knowledge Graph Management | Dattaraj Rao, Sadashiv Borkar | 30m |
An ontology-driven loan underwriting demo uses Neo4j as the single source of truth, ingesting documents via a visual document-intelligence agent that maps… | ||
| GDS Agent for Graph Algorithmic Reasoning | Brian Shi | 24m |
An agent that exposes Neo4j Graph Data Science algorithms over an MCP server runs locally and projects subgraphs, inspects schema, chooses algorithms and… | ||
| From Documents to Dynamic Graphs: Ontology-Driven Clinical Graph Construction | Jarrod Marks | 34m |
An extended pipeline built on neo4j-graphrag converts clinical notes into a live knowledge graph by extracting LLM-identified entities, validating them against… | ||
| Graph Neural Networks + LLM on | Brian Shi, Rishi Puri | 29m |
Demonstration of GNN+LLM pipelines shows PyTorch Geometric 2.7 integrated with Neo4j for GraphRAG workflows, including a text-to-KG class that extracts triples… | ||
| The Fastest Path To Building An Agent For Your Knowledge Graph Is By Using MCP | William Lyon | 30m |
Claim: the fastest practical route to a knowledge-graph agent is to expose Neo4j as MCP tools and use an Aura/agent front end to call them. The demo wires up… | ||
| Leveraging Knowledge Graphs and LLMs to Document Large Scale Codebases | Thomas Orth | 15m |
Lockheed Martin builds a pipeline that parses multi-language repos with Tree-sitter, extracts import and class-interaction edges into a knowledge graph, ranks… | ||
| From Unstructured to Connected: Building Knowledge Graphs for GenAI | Estelle Scifo, Nathalie Charbel | 29m |
Shows how the open‑source neo4j-graphrag Python package ingests a 9‑page Wikipedia PDF about climate change, splits text (default 7 chunks, custom section… | ||
| Building Contextual Knowledge Graphs to Adapt, Evaluate, and Leverage LLMs | Samira Korani | 22m |
Combines Geonames, OpenStreetMap, Yelp, Wikidata and event/weather APIs into a Neo4j graph that adds temporal, situational and demographic attributes to… | ||
| Building Modular AI Agents with LangGraph, MCP, and | Shubham Shardul | 29m |
Claim: MCP turns connectors into discoverable, schema-driven services so agents can validate inputs and swap tools without code changes. Demo builds a… | ||
| Adaptive Knowledge Graphs for Dynamic RAG Systems | Vaibhava Lakshmi Ravideshik | 27m |
Shows a working GraphRAG pipeline that combines embeddings for semantic search with Neo4j graph traversal to answer multihop queries (e.g., "which ex‑Google… | ||
| Agentic Memory | Tomaz Bratanic | 28m |
Argues that adding a persistent memory layer fixes stateless LLMs by storing short-term sessions (retrieve by session ID) and long-term episodic, semantic and… | ||
| Graph Analytics in Snowflake: Beyond Traditional SQL | Olga Razvenskaia | 26m |
Neo4j Graph Analytics on the Snowflake Marketplace runs graph algorithms directly against Snowflake tables with a zero-ETL approach, doing graph projection… | ||
| Keynote: Neo4j Product Vision and Roadmap | Sudhir Hasbe | 29m |
Neo4j presents concrete product moves: Aura Agents is in beta and claims an agent from enterprise data in under five minutes, serverless GDS runs 65+ graph… | ||
| Agentic GraphRAG: Multi-Agent Knowledge Graph Construction for Research Teams | Akhil Hemanth | 29m |
A production-ready platform ingests PDFs and datasets and runs a four-agent pipeline — analyzer, extractor, merger and optimizer — built with Neo4j, LangChain… | ||
| Easy Jupyter Notebook Graph Visualization in 10 minutes | Florentin Dörre, Adam Schill Collberg | 14m |
A new Python package called neo4j-viz Python library renders interactive, Bloom-like graphs inside Jupyter by wrapping the NVL JavaScript renderer and using… | ||
| Keynote: Think Faster: Graphs and AI for Real-Time Crisis Resolution | Conor O'Shea | 25m |
A production ETL pipeline samples network traffic 2400 flow records every 5 seconds and builds live Neo4j graphs that correlate ExtraHop flow data, Splunk… | ||
| Agentic RAG Meets Neo4j: Multi-Hop Reasoning Over Scientific Knowledge Graphs | Annabelle Blangero, Jean Lelong | 30m |
INRAExplorer combines a Neo4j knowledge graph (about 400,000 nodes and >1M edges) with a multitool LLM agent that writes Cypher to run iterative, multi‑hop… | ||
| Crafting a Neo4j Knowledge Graph Semantic Reasoner for LPG-Based Ontologies with Python and CDC | Pierre Halftermeyer | 31m |
A Neo4j-based semantic reasoner is constructed with Python that maps LPG structures to RDF/OWL, generates Cypher rules from an RDF ontology, and applies them… | ||
| GraphRAG for Supply Chain Resilience: Building an AI Supplier Discovery Engine | Pedro Parraguez Ruiz, Nelson Guamán Leiva | 16m |
Architecture converts fragmented multilingual EU procurement CSVs into a Neo4j cross-border knowledge graph that powers a GraphRAG stack combining vector… | ||
| Supply Chain Risk Predictions with Neo4j Graph Data Technology | Kateryna Nesvit Ph.D. | 14m |
Graph model encodes ports as nodes with congestion, berth efficiency and capacity attributes and shipping lanes as weighted edges with disruption… | ||
| Beyond Retrieval: Adding a Reasoning Layer to RAG | Ashok Vishwakarma | 19m |
A RAG stack augments vector retrieval with Neo4j so the system does entity extraction and Entity Linking into nodes then uses Cypher for Multi-Hop Traversal to… | ||
| Rethinking Line of Business Applications: Graphs & Cypher as an Alternative to RDBMS & SQL | Marcos Pinedo | 39m |
Argues that graphs plus Cypher can replace RDBMS for transactional LOB systems and shows a working prototype ride‑hailing app called Elder built in TypeScript… | ||
| Improving Text2Cypher: Lessons from Schema Filtering and Hard Example Selection | Makbule Gulcin Ozsoy | 23m |
Neo4j builds a Text2Cypher pipeline that converts a graph schema to text and selects only relevant elements before calling an LLM, using dynamic schema… | ||
| Building Smarter Knowledge Graph Pipeline for Secure Semiconductor Chips | Seema Naswa, Peter Levin | 28m |
Parses RTL into a knowledge graph that models signals, registers and hierarchies as nodes and data/control/synchronization as edges, scaling from millions of… | ||
| Building Evolving AI Agents Via Dynamic Memory Representations Using Temporal Knowledge Graphs | Michael Banf | 15m |
Claims a practical memory architecture that layers Neo4j + LangGraph + Graphiti to store evolving agent memory, extracts entities with Pydantic entity schemas… | ||
| #NODES2025 countdown | Andrew Ng, Emil Eifrem | 01m |
A fireside chat lays out concrete pipelines for combining large models with graph databases, showing a GraphRAG pattern that attaches node-level provenance to… | ||
| Harmonizing AI and Graphs: Building Intelligent Music Apps with Neo4j and AI | Luanne Misquita | 32m |
Graph of ~200 nodes uses Neo4j for artists, albums, producers and text summaries with embeddings and a Spring Boot app uses Spring AI to inject a chat client… | ||
| Turning Raw Data into Life-Saving Decisions Using Neo4j and n8n | Claire Champourlier | 14m |
Labus the Compass turns mixed public crash records and citizen reports into actionable maps by linking a Neo4j graph + n8n workflows to a separate Supabase… | ||
| From Spaghetti to Structure: Decoding Complex Codebases with Graphs and GenAI | Arun Pillai | 21m |
Claim: lack of documentation blocks modernization for 96% of customers and 41% report productivity loss. Built Decipher, a pipeline that replaces regex with… | ||
| GraphRag in Action: Revolutionizing Fraud Detection Techniques | Alessio De Angelis | 35m |
Demonstrates a working GraphRAG pipeline that generates Cypher from natural language, runs it against a synthetic financial dataset provided by Neo4j, and… | ||
| Real-Time Data Transformation for Knowledge Graph with LLMs | Linghua Jin | 12m |
Shows a concrete pipeline that continuously turns markdown into a live graph: CocoIndex ingests files, calls GPT-4o to extract titles, summaries, and… | ||
| Mapping the Invisible Graph Powered Archaeology with Neo4j, LiDAR, and LLMs | Divakar Kumar | 30m |
A working system called Archaios combines LiDAR-derived layer extraction, Azure Document Intelligence layout OCR, semantic chunking and embedding, and a Neo4j… | ||
| Building GenAI Apps with the LangChain Neo4j Package | Alex Thomas | 30m |
Hands‑on demo of the LangChain Neo4j Python integration showing concrete code: connect with Neo4jGraph to run Cypher, add a new actor+movie node and visualize… | ||
| MedQGraph: TMKGs for AI-Driven Healthcare Insights | Isaac Rittherson, Ishan Chaudhary | 16m |
Prototype converts MIMIC‑IV (~300k ICU encounters) into a temporal medical knowledge graph on Neo4j Aura, using Neo4j GDS for embeddings and GPT-4 entity… | ||
| A Sommelier's Guide to Recommendation Algorithms: Classical and Graph-Based Recommender Systems | Moritz Wegener | 33m |
Compares classical embeddings (feature-scaling, one‑hot, target encoding, sentence‑transformers) and matrix‑factorization with SGD against a graph pipeline… | ||
| Airport Layouts as Graphs: How I Built a Real-World Accurate, AI Air Traffic Control Agent | Keanan Koppenhaver | 15m |
Built an AI ATC agent that combines live METAR calls (via aviation.weather.gov), an open‑source runway selection algorithm from GitHub, and a Neo4j airport… | ||
| GraphRAG-Powered AI Agents: Transforming Corporate Metadata into Intelligent Knowledge | Loys Belleguie | 15m |
A system combines Neo4j knowledge graph with LLM-based agents and pipeline tooling to turn catalog metadata and ingested PDFs into a searchable knowledge base… | ||
| Combine GDS and Agentic AI for Automatic Report Generation | Alessandro Negro | 29m |
Combines Neo4j GDS and LangGraph to turn Chicago Police datasets into automated investigative briefs: builds a co‑offending network, runs Louvain, PageRank and… | ||
| From Unstructured Docs to Graph Intelligence: A Framework for Building Graph+Embedding Pipelines | Satej Sahu | 30m |
A practical pipeline called D2GEP converts PDFs and transcripts into subject‑predicate‑object triples plus passage and node embeddings, using LangChain and… | ||
| Knowledge Combined Common Data Model: A Graph-Based Integration of Reactome and OMOP CDM | Sungjae Jung | 26m |
Unified graph loads Reactome and an OMOP CDM-converted MIMIC‑IV into Neo4j and adds ontology links from BioOntology so queries traverse from patient records to… | ||
| Integrating Neo4j with Google Gemini: Architectural Patterns for AI Agents | Jitendra Gupta | 31m |
Shows concrete integration patterns: natural language → Cypher where Gemini generates validated Cypher for Neo4j (AuraDB or self‑hosted) via Vertex AI/Cloud… | ||
| Aura Import: Anywhere, Anytime | Dhru Devalia, Jun Chen | 15m |
A no‑code import service moves CSV/Parquet from Google Cloud Storage (also AWS S3 and Azure) into Aura using HMAC keys, auto‑extracts headers and builds a… | ||
| Beyond Vibe Coding: AI Agents for Technical Debt Detection | Kambui Nurse | 28m |
An extensible framework uses Dagger to spin up ephemeral containers and Neo4j to store a code graph built from Python, JavaScript and TypeScript parsers; the… | ||
| Agentic Approach to Using Neo4j Knowledge Graphs in Salesforce | Belavadi N. Ramesh | 13m |
Shows a working integration that wires Salesforce LWC + Apex to a Python MCP server acting as a graph RAG pipeline that queries Neo4j and an LLM (Claude) so… | ||
| KG Construction Using LLMs | Yassir Lairgi | 30m |
An open‑source pipeline called iText2KG incrementally turns documents into knowledge graphs by distilling text into semantic blocks, extracting entities and… | ||
| CyRAG: Retrieval Augmented Generation for Robust Cyber Defense | Mahantesh Halappanavar, Siddhartha Shankar Das, Moqaddur Rahman, Joseph Aguayo | 26m |
CyRAG integrates CVE, CWE, CAPEC and ATT&CK into a retrieval-augmented LLM pipeline and stores interconnected threat intelligence in a Neo4j knowledge graph… | ||
| Making Your Knowledge Graph LLM-Ready: Quality Assessment and Design Strategies for GraphRAG | Panos Alexopoulos | 30m |
GraphRAG uses either text-to-query → schema-derived Cypher/SPARQL/SQL or fact-embeddings → vector DB retrieval and succeeds only if retrieval, generation and… | ||
| From Aviation Data to AI Copilot: Building a Conversational Graph for Flight Intelligence | Vishakha Verma | 15m |
Claims a working pipeline that turns live METAR/TAF into radio-formatted weather, picks the active runway and computes taxi routing, all tied into a… | ||
| From Side Project to Startup: Graph Lessons From the Cartography Journey | Alex Chantavy | 28m |
Cartography starts as a Python service that pipes cloud provider data into Neo4j + Python and evolves into an OSS project and YC-backed startup; the team… | ||
| The GraphRAG System That Asks Back: Intelligent Probing with Better Contextual Answers | Rajarshee Dhar, Vivek Singh | 30m |
Graph-powered RAG that builds explicit entity relationships with Neo4j knowledge graph and a retrieval pipeline reduces token waste by avoiding blind top-K… | ||
| FHIR in the W.H.O.L.E.: Graphing Clinical Data for Smarter AI Systems | Julia Hitzbleck | 30m |
Graph-based pipeline called FHIR in the W.H.O.L.E. converts FHIR JSON into semantically linked nodes and runs on Neo4j community edition to support Clinical AI… | ||
| Live-Coding Graph-Native Agents: Neo4j AuraDB + Microsoft Agent Framework in Action | Christian Glessner | 30m |
Connects Microsoft Agent Framework with Neo4j AuraDB and Azure AI Foundry to give agents a true GraphRAG-style graph memory, ingesting three real contracts via… | ||
| Multiple Knowledge Graphs for Sophisticated RAG | Kaj van de Loo | 15m |
An AI-first SaaS models two Neo4j graphs: a tenant-specific context graph (live updates from Slack, Drive, docs, embeddings in a vector DB) and an external… | ||
| Stay or Go? Predicting Customer Churn through Graph Relationships | Aayushi Sinha, Rangesh Sripathi, Chandrasekhar Rangu, Sridharan Sundaram | 29m |
A production pipeline models customers, products, tickets and events in Neo4j + GDS and extracts graph embeddings plus features from community detection… | ||
| Transparent Multi-Agent AI | Morgan Senechal | 29m |
Live demo of a working multi‑agent stack that uses Neo4j to record every orchestration step so retrievals, planner outputs, task assignments and tool calls are… | ||
| Anonymization in the LLM Era: No Room for Compromise | Christophe Willemsen | 28m |
LLMs amplify data leaks: an employee once uploads 3,000 records uploaded and an LLM-powered pipeline multiplies exposure across microservices, RAG, agents and… | ||
| The Personal Knowledge Vault: Art Collection Use Case | MIKE MORLEY | 31m |
A deployed prototype turns 19th century ledgers and modern emails into linked graph documents, indexes them with a Neo4j-powered GraphRAG, and serves images… | ||
| Breaking Silos: Using Neo4j to Unify Tax and Finance Data | Coskun Cavusoglu, Michael Tran | 29m |
Shows a working pipeline that extracts entities and ownership links from Snowflake into a Neo4j graph, runs entity resolution by comparing relationship… | ||
| GraphReader Agentic RAG: Rethinking Long-Context Retrieval Systems | Jayita Bhattacharyya, Soumya Ranjan Das | 27m |
Reproduces the GraphReader paper with open-source tools, building a Neo4j knowledge graph from section-wise chunks, extracting atomic facts and key elements… | ||
| Graph-Powered Job Matcher: From SQL Tables to Neo4j RAG in Production | Otávio Calaça Xavier | 24m |
Shows a production pipeline that moves SQL HR tables into Neo4j, combines Cypher path reasoning with Neo4j’s native vector index and LangChain to build a… | ||
| Enhancing Retrieval-Augmented Generation with GraphRAG Patterns in Neo4j | Amit R | 16m |
GraphRAG implemented with Neo4j combines multi-hop reasoning and hybrid vector-graph retrieval to return connected subgraphs instead of isolated text chunks… | ||
| From Journeys to Systems: Rethinking Customer Experience with Knowledge Graphs | Ricardo Martins | 17m |
Claims that customer journeys become live, queryable graphs rather than static maps, implemented with Neo4j/Aura and Cypher and modeled as five node types… | ||
| Rendering Graphs Your Way: The Case for Going Custom | Tony Smid | 29m |
A custom graph renderer is engineered from scratch using WebGL rendering (optionally WebAssembly), an event-driven core, web workers and Graphology for the… | ||
| Topology Over Predictions: Using Graph Context to Drive Real-Time Lending Decisions | Matthew Watts | 12m |
Argues for replacing periodic retraining with continuous graph memory that keeps institutional context by preserving topology rather than flattening it to… | ||
| Using Microsoft Fabric Workload for AuraDB to Make Product Recommendations from OneLake Data | Stu Moore, Emre Hizal | 14m |
Demonstration shows Neo4j Graph Intelligence as a Fabric workload that transforms OneLake tables (Northwind dataset) into a graph, runs a Spark import that… | ||
| Location Insights for Your Graphs with Neo4j, PostGIS, and Brickgraph | David Bender | 23m |
Demonstrates a production flow that pairs Neo4j for graph objects with PostGIS (and PGVector) for geometry and embeddings so the system supports semantic plus… | ||
| Traversing from Zero to Production with Graphs | Abhishek Das | 29m |
Two years of production experience with Neo4j drives a practical playbook: model relationships not documents, use Neo4j Aura or local Docker for deployment… | ||
| Unlocking Real-Time News Recommendations: The Power of Graph Relationships in Neo4j | Himanshu Aggarwal | 21m |
Glance builds a content knowledge graph in Neo4j that ingests over 50,000 articles daily and stores a network of 50 million nodes and 150 million… | ||
| Building an Entire Graph Application with Nodestream | Zach Probst | 25m |
A working task-dependency analytics pipeline is built end-to-end: Postgres-backed API emits Kafka events, Nodestream consumes them and maps data via YAML… | ||
| Introducing the Open Source Semantic Graph Editor of Deutsche Bahn | Jörg Baach, Mihajlo Lazar, Klaus Bermuth | 30m |
Deutsche Bahn open-sources a semantic graph editor that runs on Neo4j label property graphs, with a Python/Flask backend and React + SigmaJS frontend, released… | ||
| Find the Fraud: Assessing Tax Non-Compliance in the IRS | Adam Conovaloff | 15m |
Applies graph neural networks to simulated IRS filing networks using a Python simulator, Neo4j-style graphs and PyTorch style GNNs, featurizing nodes with 16… | ||
| Chagu: Graph-Powered LLM Shielding and Anomaly Detection for Secure AI Pipelines | Talex Maxim | 27m |
Chagu claims a graph-native defense that traces prompt→response execution paths, detects prompt injections and semantic drift, and raises alerts in real time… | ||
| A Data Management Layer for Neo4j | Pavan Kumar Narendra | 16m |
Company moves from one Neo4j project to many by building a data management layer called Anansi that enforces type-safe entities and identifiers, records schema… | ||
| All Aboard: Reasoning with LLMs and Neo4j via MCP | Jonathan Giffard, Michael Webb | 16m |
Official MCP server connects Neo4j to LLMs so an agent runs queries, returns Cypher, and executes graph algorithms live. Demo uses a London Underground graph… | ||
| Syntes AI Digital Twin Agentic Platform with Graph Data Model | Anatoliy Tishin | 15m |
Syntes AI runs a multi-tenant SaaS with Neo4j per-tenant partitions and two-way ELT connectors to source systems like Shopify and Snowflake, using… | ||
| Revolutionizing Platform Engineering with AI Agents and GraphRAG | Shubham Bakshi | 12m |
Outshift builds an internal AI platform engineer called CAPE that ingests docs, JSON/YAML resources and live data into Neo4j and moves from vector-embedding… | ||
| Multiagent GenAI-Powered Oncology Research with GraphMedAI and Neo4j | Hanafi Yakouben, Zouhair Allaoui | 15m |
GraphMedAI builds a Neo4j knowledge graph enriched by RAG from PubMed and ClinicalTrials.gov, adds embeddings for vector similarity, and runs a multiagent… | ||
| Reconstructing the Past with Knowledge Graphs: Empowering Historians through Neo4j and GenAI | Ilya Verbitskiy | 28m |
Builds a Neo4j knowledge graph of Roman coins (ingesting OC Online Coins of the Roman Empire, tens of thousands of types), creates vector embeddings with… | ||
| Narrative Extraction with GenAI: Human-centric Knowledge Graph Creation from Text | Federica Ventrutto | 16m |
Proposes a narrative-first extraction pipeline that runs a GenAI step to summarize a document into main actors, events, and dynamics, then performs entity and… | ||
| Disrupting Customer Data Platforms: Neo4j vs. the Status Quo | Shaurya Agrawal | 23m |
Claims Neo4j replaces RDBMS for CDPs by storing relationships natively and avoiding costly joins, demonstrated with a runnable demo of seven Cypher files on… | ||
| See What the Graph Sees: Demystifying PageRank Through Visual Storytelling | Nicolas Rouyer | 15m |
Interactive demo shows PageRank implemented step by step on a bike trip graph using NeoDash, Neo4j Bloom, and graph state machines. The graph initializes every… | ||
| Graphs on the High Seas: UI/UX Considerations for Great Geospatial Graph Visualization | Dan Williams | 15m |
Shows a working pipeline that fuses millions of AIS observations with a knowledge graph to detect and persist ship-to-ship transfer detection events, using… | ||
| Interconnected Capital: Visualizing WAM, PE, RE, and HF Data with Neo4j | Han Wang, Michael Tran | 30m |
Neo4j plus a Snowflake-backed tax data warehouse models legal and investor relationships so queries that took minutes or timed out become fast and actionable… | ||
| How to Find a Killer Using Graphs: What Sherlock Holmes Was Really Doing with That Red String | Pawel Goląb | 29m |
A digital murder-board called Networks Notebook converts PDFs, images and OCR into a property knowledge graph, extracts entities and relations with LLMs or… | ||
| Talk to Your Graph: A Practical Guide to Building a Dual-LLM Q&A System for a Fashion Graph | Vaskya Nabila, Celine Auriel | 10m |
End-to-end Python system builds a fashion knowledge graph from CSV by prompting Google Gemini to act as an AI Architect, producing a JSON schema map that Neo4j… | ||
| The Green Potential of Knowledge Graphs | Joakim Nilsson | 12m |
Claims that a Neo4j knowledge graph maps supply‑chain emissions end to end and surfaces actionable hotspots, with supply chains causing over 60% of global GHG… | ||
| Knowledge Graph of Drugs Data for Swiss Healthcare System | Christian Franke | 15m |
A bachelor thesis builds a Neo4j knowledge graph of Swiss and European public drug datasets using R to produce CSVs and loads them into Neo4j, staying well… | ||
| Connecting the Dots: The Path from Document Database to Graph Database | Murthy Chandrapaty, William Liang | 13m |
Compares Cosmos DB and Neo4j migration with concrete results and methods: an T0–T3 live migration that snapshots, bulk migrates, replays change events and… | ||
| RAG and Voice Agent Applications | Tony Xavier | 15m |
Argues that production voice agents require a three‑layer memory: short LLM context, working memory via graph traversal, and long‑term graph storage… | ||
| RushDB in Action: Building AI-Native Apps with Self-Aware Graphs | Artemiy Vereshchinskiy | 30m |
Claims a graph-native DB called RushDB built on Neo4j that auto-ingests JSON, auto-discovers schema and creates labeled meta property graphs with reusable… | ||
| Smarter Industrial Fault Diagnosis with Knowledge Graphs and Large Language Models | Wan Razaq | 33m |
Prototype called GraphRAG converts 15 years of Dutch maintenance Excel logs and English OEM PDFs into a Neo4j graph using GPT-4/GPT-4o multimodal extraction… | ||
| Context and Correlation in Observability Through Graph-Powered Insights | Bhanu Kovuri | 20m |
Splunk Observability derives an entity graph from OpenTelemetry signals (metrics from Kubernetes, traces for APM), persists relationships in Neo4j, and uses… | ||
| From Warehouse to Wisdom: Activating Business Data with Neo4j | Michael Tran | 29m |
A tax data warehouse in Snowflake feeds a Neo4j graph to answer concrete questions like indirect ownership pushing investors over filing thresholds and… | ||
| Powering Legal Research with Knowledge Graphs and Large Language Models | Basant Mounir, Ahmad Abdelaal | 29m |
Ingests EU Commission cases across five domains (mergers, state aid, antitrust/cartels, DMA, foreign subsidies), filters to nine fields and legal bases… | ||
| Early Path Traversal Pruning | Jan Zak | 08m |
Variable-length traversals from a bound source to unbound targets now prune dead branches during traversal when a running accumulator fails a condition… | ||
| Is My Brain a Knowledge Graph? A Human Take on Connecting the Dots | Ramona Truta | 31m |
Connects personal anecdotes (46 completed courses, Waterloo–Paris–Napoleon–ABBA chain) to three concrete claims about memory: prioritize context over content… | ||
| How Lettria Unlocked 20% Accuracy Gains with Qdrant and Neo4j | Romain Albrand | 17m |
Lettria builds a GraphRAG pipeline combining a document parser, an ontology-driven knowledge graph and vector storage in Qdrant and Neo4j and reports a 20%… | ||
| From Sushi to Semantics: A GraphRAG-Powered Japanese Food Explorer with Neo4j and MCP | Koji Annoura | 19m |
A Neo4j knowledge graph links dishes, ingredients, regions and historical notes and a working prototype answers cultural queries more accurately than ChatGPT… | ||
| GraphQL Data APIs in Aura | Liam Doodson | 15m |
Shows how simple GraphQL type definitions become a running API in minutes using the GraphQL library and the GraphQL toolbox against an Aura Neo4j instance… | ||
| Connecting Java Applications over HTTP to Query API | Dmitriy Tverdiakov, Greg Woods | 30m |
A preview Java driver module translates run and pull Bolt messages into POSTs to /db/{db}/query/v2, buffers returned records in memory, and honors Neo4j… | ||
| Immerse Yourself in Your Data With VR Visualization of Neo4j Graphs | James Mireles | 10m |
A VR pipeline pulls Neo4j graphs into Unity using the Bolt protocol and a force-directed 3D layout so nodes repel or attract with physics, relationships draw… | ||
| Turning Reviews into Real Insights: Emotion-Aware Sentiment Analysis with GraphRAG and Neo4j | Lijimol George | 12m |
GraphRAG builds a Neo4j knowledge graph from 41,000 Skytrax reviews using Sentence-BERT embeddings, Cypher queries and a RAG layer with LLMs (tested with… | ||
| Taming the Evolution of Cypher: What Cypher Versions Mean for You | Gem Lamont | 11m |
Neo4j 2025.06 decouples language from server so a single DBMS can host multiple Cypher versions—Cypher 5 frozen LTS and Cypher 25 monthly releases. Cypher 5… | ||
| Empowering Voice AI Agents with Real-Time Knowledge from Neo4j | Rob Wylie | 14m |
Demonstrates a production system that grounds voice agents in Neo4j for real‑time retrieval using Neo4j as real-time knowledge store and graph RAG; documents… | ||
| Labor Market Landscape Modeling with Knowledge Graphs | Yee Sen TAN, Lois JI | 15m |
A production Job‑Skills Knowledge Graph (JSKG) built on Neo4j ingests the national Skills Framework, near‑real‑time job postings and curated training courses… | ||
| Structr 6.0 – AI-enabled Low-Code Based on Neo4j | Axel Morgner | 29m |
Structr 6.0 ships an MCP server that lets LLMs and agents call the Structr APIs to modify schema and data, plus Traits and multiple inheritance for resolving… | ||
| Text2Cypher Beyond English: Initial Evaluation with Foundational LLMs | Makbule Gulcin Ozsoy, Will Tai | 14m |
Paper-style evaluation of Text2Cypher using foundational LLMs compares English, Spanish and Turkish by feeding the same Cypher queries but translated questions… | ||
| Automating Disaster Recovery with Aura API | Philip Mortiboy | 15m |
Altrata automates Neo4j disaster recovery on Aura by wrapping the Aura API into one-click workflows: a GitHub Actions flow lists hourly snapshots, runs an… | ||
| Tracing the LLM Behaviour: Debugging and Evolving Agent Workflows with Neo4j | Rangesh Sripathi, Aayushi Sinha, Sridharan Sundaram | 30m |
A practical pipeline captures every agent event into a Neo4j graph of steps, tools, memories and outputs via a lightweight observer that emits Cypher inserts… | ||
| Beyond RAG: Building the AI Corporate Brain with Knowledge Graphs and Virtue Ethics | Anderson Prewitt | 20m |
Argues that combining knowledge graph + Graph ML with vector search/LLM RAG builds an "AI Corporate Brain" that maps customers, products, processes and… | ||
| Structuring the Video Internet: How Vpin Uses Neo4j to Turn Watching into Learning | Chris Wei | 31m |
Vpin converts passive video watching into structured, searchable learning with a four-step pipeline: curate intuitively (capture URLs or share links), AI… | ||
| Rethinking Data: A Data Scientist’s First Dive into GQLs | Suha Mokalla | 18m |
Converted ad impression CSVs and census counts into a graph with nodes for location, time, impressions, period and ingested via Neo4j Aura/Desktop using… | ||
| Leveraging Knowledge Graph and Imaging to Predict Gene–Disease Links in Cardiovascular Diseases | Khaled Rjoob | 17m |
Built a multimodal knowledge graph from UK Biobank plus 18 external databases that integrates cardiac MRI features as nodes with feature values stored on… | ||
| Property Sharding: I Want to Shard My Database, Now What? | Nadja Müller, Max Bautzer, Conor Watson | 22m |
Explains a working Neo4j Property Sharding system called Infinraph that splits a single topology onto one graph shard and moves all node and relationship… | ||
| Introducing Fleet Manager | Chris Shelmerdine, Pramod Borkar | 27m |
Fleet Manager provides a cloud control plane inside the Aura console to register and manage Neo4j deployments (Aura, self‑managed, desktop, community… | ||
| Enhancing Benefit Adjudication Through Graph Node Embedding, Clustering, and Outlier Detection | Yao Ma, Manish Mithaiwala | 17m |
Synthetic hospitalization adjudication data with three cohorts of ~75 patients each plus a fourth noisy group (44 extra medications, 34 ICD codes) is loaded… | ||
| Live Q&A | Emil Eifrem, Andreas Kollegger | 31m |
Claims that AI is already delivering value while also creating hype and some failed bets. Companies report more than 10 production projects on graphs, driving… | ||
| From Air Quality to Aircraft and Automobiles, Data Is Everywhere | Timothy J Spann | 15m |
Shows a runnable pattern that wires Apache NiFi, Snowflake, Neo4j, Cortex AI and local LLMs like LLAMA into a RAG pipeline for an open lakehouse using Iceberg… | ||
| One Configuration, Many Imports | Florent Biville, Emre Hizal, Erik Nord | 30m |
A uniform configuration called import-spec maps Parquet sources to Neo4j nodes and relationships and generates Neo4j Admin headers and schema files… | ||
| The Company You Keep: Mapping Scientific Collaboration with Graphs | Pedro Sader Azevedo | 13m |
Built a co-authorship graph from Scopus data (2000–2025) for authors with at least one UNICAMP affiliation, modeling author, document, institution nodes plus a… | ||
| Knowledge Graph–Driven Feedback Loops to Optimize TikTok Shop Video Marketing | Taeyang Kim, David Fagerburg | 29m |
Claims a closed-loop system that links creative video features to real sales using Neo4j knowledge graph built from TikTok Shop seller analytics, with… | ||
| Live Q&A | ABK, Michael Hunger | 32m |
Live Q&A covers concrete Neo4j updates and production patterns: Aura Agents preview (launched Oct 2) already shows about 800 agents created, Neo4j adds… | ||
| Beyond Tags: Content Discovery with Tripadvisor's Hybrid Graph Search | Varuni Gang, Konstantin Buzdin, Amir Afrasiabi Rad, Meng Pan | 25m |
Tripadvisor builds a hybrid retriever inside Neo4j combining structural tag lookups with destination-scoped vector search, using per-destination vector… | ||
| Knowledge Graphs for Locations in the Humanitarian and Development Sector | Himanshu Ardawatia | 14m |
NRC restructures fragmented location master data into a knowledge graph using Neo4j + RDF mapping and API ingestion to unify records across 40 country… | ||
| Batch Data to Graphs: Integrating Neo4j and Flink via JDBC | Eugene Rubanov | 12m |
Shows a working pattern to import a bounded dataset from Flink into Neo4j using the Neo4j JDBC/GDBC driver and Flink’s JDBC connector, assembling a DataStream… | ||
| EEG Topologies with Neo4j: Interpolation-Driven Graph Learning for Chronic Pain Detection | Zeyno Dodd | 14m |
Implements a Neo4j mult-tier EEG graph that maps a canonical sensor topology to study sessions, uses Cypher inverse-distance interpolation to create edges… | ||
| Spring in Autumn | Gerrit Meier | 29m |
Shows concrete wiring: include the driver dependency and Spring Boot auto‑config creates a usable Neo4j connection with health and metrics, add Spring Data… | ||
| G-forces Meet Graphs: Analyzing 50+ Years of Formula 1 Sponsorship Using GDS | William Steadman, Joe Cobbs, David Tyler | 14m |
Graph schema encodes brands, annual deal squad nodes and yearly deal instances so 54 seasons, ~10,000 deal-years (≈3,300 unique deals) across ~2,000 brands and… | ||
| Live Q&A | Emil Eifrem, Andreas Kollegger | 31m |
Live Q&A lays out concrete claims and product directions: Neo4j pushes a knowledge graph builder workflow that combines LLM-driven extraction with curated… | ||
| Using the GDS Steiner Algorithm for Disney's 4 Park Challenge | Eric Monk | 15m |
Uses the minimum directed Steiner tree implementation in Neo4j GDS on a hand-crafted graph created from Leaflet/OpenStreetMap waypoints plus themeparks.wiki… | ||
| Human-Centered Contact Tracing Apps | Arik Setyawan, Irwan Kautsar | 14m |
A human-centered contact tracing platform uses Neo4j to store meetings as nodes and edges and runs simple graph traversals to find direct and second‑degree… | ||
| Conquering Neo4j Errors: GQLSTATUS Codes to the Rescue | Louise Berglund | 25m |
Neo4j replaces brittle text parsing with a structured GQL status system that provides a stable 5‑character code plus human descriptions, diagnostics, and… | ||
| Mapping Argentina’s Scientific Ecosystem: Building Collaboration Networks with Neo4j | Octavio Zerdá Sánchez | 17m |
Uses open ministry data from 2011–2019 to build a temporal, tripartite knowledge graph of researchers–projects–subareas, integrating >45,000 researchers… | ||
| Neo4j Meets FinOps & GreenOps: Real-Time Graphs for Cloud Cost Intelligence | Mehdi Jafari | 10m |
Replaces brittle spreadsheets with a real time Neo4j graph that models resources teams products and emissions, integrating cost data from Azure AWS GCP… | ||
| nothing matches | ||