Graph Databases - Solving Business Problems with Connected Data

In this connected world, traditional data stores often make it difficult to find valuable relationships. By making them a key component of the model, contextualizing a set of data becomes incredibly simple.
In this session, we will walk through what a graph database is and how it can transform your applications and data. We will explore creating, querying, and displaying data and learn how to use simple tools to interact with the database. We will cover the whiteboard-friendly model and the basics of the Cypher query language. Live demos will show developers how to interface with the database and the data in it.
Code: https://github.com/JMHReif/agents-mcp-ohmy

Transcript

1. Graph Databases: Data Storage with Context Jennifer Reif jennifer.reif@neo4j.com @JMHReif github.com/JMHReif jmhreif.com linkedin.com/in/jmhreif Photo by Tomasz Frankowski on Unsplash
2. Who is Jennifer Reif? Developer Advocate, Neo4j • Continuous learner • Technical speaker • Tech blogger, podcaster • Coming soon! ai rstprogramming.com • Other: geek, reader, musician, mom (cat+human) Jennifer Reif fi jennifer.reif@neo4j.com @JMHReif github.com/JMHReif jmhreif.com linkedin.com/in/jmhreif
3. What is a graph? Jennifer ?? Jacob
4. What is a graph? Jennifer WORKED_FOR Company WORKED_FOR Jacob
5. What is a graph? Company WO OR F _ D E K OR RK ED _F W Jennifer ATTENDED School ATTENDED OR Jacob
6. What is a graph? Company WO OR F _ D E K OR RK ED _F OR W ATTENDED Jennifer School ATTENDED _IN EN ED RO EN RO ED LL LL _I N Degree Degree Jacob
7. What is a graph? Company WO OR F _ D E K OR RK ED _F OR W ATTENDED _IN ED RO M EN RO ED LL LL CO Degree _I N Degree C O M PL IN _ D ET E L L ED Adrian School EN PL E TE D Jennifer ATTENDED E O R N Degree Jacob
8. What is a graph? Company Edward Jones OR WO F _ D E K OR RK ED _F OR W ATTENDED Person SIUE _IN ED RO _I N Music C O M PL EN RO M CO Degree LL LL ED Degree Degree CMIS CS IN _ D ET E L L ED Person Adrian E O R N Person Jacob EN PL E TE D Jennifer School ATTENDED
9. What is a graph? Answers through relationships Company OR OR ATTENDED Person Jennifer ED _F OR _IN ED RO _I N Music C O M PL EN RO M LL LL ED Degree Degree CMIS CS IN _ D ET E L L ED Person Adrian E O R N Person Jacob EN CO Degree School ATTENDED SIUE PL E TE D • How many alumni re- school and works for company? RK W • What are common degree journeys? • Who else went to a WO F _ D E K • How many coworkers shared classes/degrees? enroll for higher degrees? Edward Jones
10. Nodes (vertices) Objects or entities Company Edward Jones • Can have labels • May have properties Person School Jennifer Person SIUE Jacob Degree Music Person Adrian Degree Degree CMIS CS
11. Relationships (edges) Connect entities Company Edward Jones OR WO F _ D E K • Must have type (label) OR RK ED _F OR W • Must have direction ATTENDED Person • May have properties SIUE _IN ED RO _I N Music C O M PL EN RO M CO Degree LL LL ED Degree Degree CMIS CS IN _ D ET E L L ED Person Adrian E O R N Person Jacob EN PL E TE D Jennifer School ATTENDED
12. Example: Logistics Home
13. Logistics Home • Where rst? School • Depends on when ready to Opens: 08:00 leave house Grocery Opens: 07:00 Shipping fi Opens: 10:00 Donation Opens: 09:00
14. Logistics Criteria Home WE WEN T_4 NT_ • Where is time critical? 1 WE School _3 NT • Personal preferences for refrigerated food? Opens: 08:00 2 _ T N E W T_6 WEN • How long at each store? Grocery 5 _ T Opens: 07:00 W EN Music Shipping Opens: 10:00 Donation Opens: 09:00
15. Answer questions Habits/preferences Home WE WEN T_4 NT_ • E ciency improvements? WE School _3 NT • Adding stop? Where/time? 1 Opens: 08:00 2 _ T N E • Share load across more people? W WEN T_6 • Distance and location calculations? Grocery EN W Music Shipping Opens: 10:00 ffi 5 _ T Opens: 07:00 Donation Opens: 09:00
16. Other use cases • Fraud detection • Identity and access management • Recommendations • Supply chain
17. Graphs add context and meaning Not just point-to-point, but HOW they connect
18. Data model
19. One model to rule them all… Conceptual = Logical = Physical data model
20. One model to rule them all… Conceptual = Logical = Physical data model
21. Query language
22. Cypher GQL-compliant • Functional and visual • Based on ASCII art • Declarative • Focus on patterns A LIKES B MATCH (A )-[:LI KE S] -> (B )
23. Cypher: write All about patterns Jennifer Neo4j WORKS_FOR NODE NODE CREATE (:Person { name: ‘Jennifer’}) -[:WORKS_FOR]-> (:Company { name: ‘Neo4j’}) LABEL PROPERTY LABEL PROPERTY
24. Cypher: read All about patterns Jennifer WORKS_FOR Neo4j MATCH (:Person { name: ‘Jennifer’} ) -[:WORKS_FOR]-> ( whom ) RETURN whom
25. Let’s explore!
26. Visualization, Data Science, and more!
27. Integrations Lots of options! • Cloud • Visualization • Data transportation • Data science • Applications • Administration, ops, monitoring
28. Purchasing system Orders, products, suppliers, etc • Easily nd unusual patterns • Optimize routes network • Pass bits on to other systems • Pinpoint… • Improvements for inventory • Weak points in supply chain fi fl • In uential products/customers
29. Financial Investments, ownership, etc • Easily track nancial holdings • Understand money movements • Monitor transactions • Pinpoint… • Suspicious activity • True ownership (transactions) fi fl • In uential, valuable holdings
30. Other Social, interactions, etc • Easily navigate human interaction • Understand collaboration • Track behavior, journeys • Pinpoint… • User journeys, collabs • Communities fl • In uential people, events
31. What about AI?
32. Throw an LLM at it Doesn’t often work • LLM strengths: • human-consumable data • general/public info • LLM weaknesses: • context/big picture • private knowledge • Solo LLM = great -> integrated LLM = more great?
33. RAG architecture User 1 • Retrieval Prompt • Data retrieved from external source • Augmented Response 3 LLM LLM API • Augments response with facts Chat API 2 Database Search Prompt + Relevant Information • Generation • Response in natural language Database Relevant Results / Documents
34. Embeddings / Vectors Convert data to a point in space • Series of numbers • 100s or 1000s of dimensions • Dimension = interesting feature / characteristic
35. Vectors in the physical realm https://www.mathsisfun.com/algebra/vectors.html
36. Vectors in the technical realm Kings and Queens king − man + woman ≈ queen m o w an g kin kin queen? man g man an m o w 1 3 2
37. How do we search the vectors? Similarity search • Expensive queries (compare to every vector) • Approximate nearest neighbor (k-ANN) • Example: Library • Book classi cation - genre vs location of plot • Smaller search set = smaller retrieval time! fi Photo by Martin Adams on Unsplash
38. GraphRAG Graph DB as a data source • Higher accuracy (more relevance in result) • Using existing, quality data fi • Explainability, veri ability
39. Explainable AI Why graph with GenAI? • How did the LLM get this answer? • Graphs: • Incorporating siloed data into result • Add extra context/related info to graph • Better veri cation through understandable format fi Photo by No Revisions on Unsplash
40. Let’s code!
42. Resources • Github repository (today’s code): github.com/JMHReif/agents-mcp-ohmy • GraphAcademy LLM courses: graphacademy.neo4j.com/categories/llms/ • Docs for Spring AI: docs.spring.io/spring-ai/reference/api/vectordbs/neo4j.html • Knowledge graph ebook: https://neo4j.com/whitepapers/developers-guide-howto-build-knowledge-graph/ Jennifer Reif jennifer.reif@neo4j.com @JMHReif github.com/JMHReif jmhreif.com linkedin.com/in/jmhreif