Neo4j-Building_a_Knowledge_Graph_to_get_your_Enterprise_Data_AI-ready.pdf

Transcript

1. Building a Knowledge Graph to get your Data AI-ready Niels de Jong - Product Manager @ Neo4j
3. Only three topics 3 1. What is a graph? ✅ 2. Why use graph for ✨AI✨? 3. How to get started with graph?
4. Why use graph? 4
5. 85% of IT leaders cite data quality as their top AI challenge KPMG AI Quarterly Pulse Survey 2025 100 senior executives from $1B+ revenue companies Lack of Standardization Scale of Query Diversity Data Organization AI needs data organized in ways it can effectively access AI requires high-quality harmonized data to be reliable AI demands rapidly accelerated question-to-query execution AI: it is (and always was) a data challenge 5
6. Knowledge graphs = design pattern to organize & access interrelated data 6
7. Retrieval Augmented Generation RAG augments the LLM by intercepting a user's prompt… …then making a query to external data… then passing relevant results from the query for a complete, curated response. 777 Own Data GenAI Application Complete Response User Prompt LLM Question + Relevant Info
8. Neo4j Inc. All rights reserved 2023 A Neo4j Knowledge Graph combined with LLM’s obtains some unique improvements: Accuracy - Obtain better answers compared to plain vector searches Specificity: domain specific, factual knowledge on your subject Explainability: Provide the user with more reasoning on how the results were obtained. Retrieval Augmented Generation Evolving From RAG to GraphRAG
9. GenAI Language Statistics Creativity KGs Knowledge Facts Context Accurate Contextual Explainable Knowledge graphs unlock GenAI
10. How to graph? 10
11. • Storage • Graph Transactions • Querying Graph Database Graph Analytics • Graph Analytics • Machine Learning • Graph Data Science Neo4j Inc. All rights reserved 2025 11 Both queries and algorithms are available as agentic tools
12. 12 Neo4j Inc. All rights reserved 2025 Analytics Tooling Graph Transactions Data Integration Dev. & Admin Drivers & APIs Discovery & Visualization Graph Analytics & Data Science Developers Admins Business Users Data Analysts Data Scientists Neo4j = GraphDB + Platform
13. 13 Bringing in your data Unstructured Structured Mixed User Manuals Legal Contracts Security & Project Management Tools Financial Transactions CRM/ Historic Customer Data Text blobs, Images, Audio, etc. Linked Structured & Unstructured Table with unstructured fields | Documents linked to tables | Interconnected metadata Tables & flat files (CSV, JSON) Documents with Lexical Structure Product Catalogs Research Papers Internal Documentation Data Lakes Operational Stores Supply Chain & Inventory Data → Neo4j KG builder → Neo4j Data Importer → Ecosystem tools
14. 14 table1 document1 document4
15. Demo From zero to GraphRAG-powered agent in 10 minutes 15 Data: Top 2000
16. Thank you Please rate the session in the Data Expo app. Come find us at booth 59!