Neo4j: The Art of Possible with Graph Technology
0 likes104 views
The document discusses the significance of graph technology in understanding relationships across various sectors, emphasizing its transformative power in applications like anti-money laundering and risk analysis. It highlights Neo4j's role in driving enterprise transformation through interconnected data graphs and discusses the potential of generative AI, which is projected to reach $1.3 trillion in revenue by 2032, despite challenges in implementation. The document also introduces 'graphrag', a methodology combining vector search and knowledge graphs to improve the accuracy of AI responses and facilitate easier development.
Neo4j: The Art of Possible with Graph Technology
- 2. The Art of the Possible With Graph Technology Ivan Rodríguez Neo4j Iberia
- 3. Relationships are all around us. 3
- 4. Relationships help us understand the world. 4
- 6. 6 This is our Big Idea, and we encode that idea in software.
- 7. 7 With that software, our customers change the world.
- 8. Mission to Mars Curing Cancer Protecting Democracy
- 9. The power of the graph model
- 10. The power of the graph model
- 11. The power of the graph model
- 12. The power of the graph model
- 13. The power of the graph model
- 14. The power of the graph model
- 15. The power of the graph model
- 18. Employees Network & Security Product Customers Transactions Process Suppliers Graph is insightful Employees Network & Security What’s important? Process Suppliers What’s unusual? Product Transactions Customers What’s next?
- 19. 19 Trusted by 75 of the 8 / 10 Top Retailers 10 /10 Top Automakers 20 / 20 Top US banks 3 / 5 Top Aircraft Manufacturers 7 / 10 Top Telcos 3 / 5 Top Hotel Groups 8 / 10 Top Insurance Companies 5 / 5 Top Pharmaceuticals
- 20. Employees Network & Security Suppliers & Partners Product Customer Finance Process The Seven Graphs of the Enterprise
- 21. Supplier Inventory Product Suppliers Route Planning & Optimization Real-time Shipment Tracking Inventory Planning Risk Analysis Uncover patterns in your supplier data
- 22. Supplier Inventory Product Suppliers Uncover patterns in your supplier data
- 23. Supplier Inventory Product Suppliers Uncover patterns in your supplier data Estimated annual Economic savings Estimated traffic congestion reduction 10% £570M
- 24. Uncover patterns in your Transactions Product Transactions Anti-money Laundering Circular Payments Fraud Detection Customer transactions data
- 25. Uncover patterns in your Transactions Product Transactions Customer transactions data
- 26. Uncover patterns in your Transactions Product Transactions Customer transactions data Approves or rejects applications in less than two seconds 20% reduction in credit application fraud
- 27. Talent Learning & Development Career Management Skills Management Orgs (who is who) Job Search Account/Identity Control Reputation Scoring Threat Detection Access Control Zero Trust Route Planning & Optimization Real-time Shipment Tracking Inventory Planning Risk Analysis Product Recommendations New Product Introductions Product Customizations Product Inventory Product Pricing Bottleneck Identification Process Improvement Process Automation Process Monitoring Recommendations Loyalty Programs Churn Prevention Customer Offers Dynamic Pricing Intelligent Ads Anti-money Laundering Circular Payments Fraud Detection Employees Network & Security Suppliers Product Customers Finance Process Connect Your Seven Graphs to Drive Transformation
- 28. 28
- 29. Neo4j Inc. All rights reserved 2024 $11 $18 $37 $64 $128 $219 $340 $457 $611 $790 $981 $1,166 $1,361 2% 2% 4% 6% 7% 8% 10% 11% 12% 12% 0% 5% 10% 15% 20% 25% 30% $- $200 $400 $600 $800 $1,000 $1,200 $1,400 $1,600 2020 2022 2024 2026 2028 2030 2032 Generative AI Races Toward $1.3 Trillion in Revenue by 2032 Generative AI Revenue Generative AI as a % of Total Technology Spend However, 71% of organizations are stuck piloting GenAI projects 2024 IBM CEO Survey Bloomberg Intelligence
- 30. Why are LLMs hitting a barrier? 30
- 35. GraphRAG is RAG where the R path includes a Knowledge Graph. What is GraphRAG?
- 37. The core GraphRAG pattern is very simple, yet powerful. 1. Do a vector search to find an initial set of nodes 2. Traverse the graph around those nodes to add context Optional: Rank the results using the graph and pass the top-k documents to the LLM GraphRAG Retrieval Patterns
- 38. The Benefits of GraphRAG
- 39. Neo4j Inc. All rights reserved 2024 Design in prg 3X A Knowledge Graph improves the accuracy of LLM responses by 54.2%, an average of 3x Higher Accuracy 1.
- 40. Feedback from an AI Engineer Easier Development 2. Redacted
- 41. Human View of an Apple LLM + Vector View of an Apple Easier Development: Why 2.
- 42. Knowledge Graph View of an Apple LLM + Vector View of an Apple 2. Easier Development: Why
- 43. Easier Development: Why Transparent & Explainable Opaque & Implicit AI Engineer: "I actually already fixed a couple of bugs thanks to this!” 2.
- 44. Detour! Knowledge Graph Creation Unstructured data Typically PDFs or other text documents Mix of structured & unstructured data Structured data with long- form text Structured data Structured data with short text values Watch This Space!
- 46. The Benefits of GraphRAG 1. Higher Accuracy 2. Easier Development 3. Explainability & Governance
- 47. Relationships are everywhere And enable accurate & explainable AI They power transformative use cases
- 48. Connect