GraphRAG: Data with Context

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. Then, we will look at how graphs are lending their strengths to the AI industry through vectors and GraphRAG. Live demos will show developers how to interact with graph data and use it in technical systems.
Join us to learn how graph databases are used to improve the data world and help developers easily extract/import connected data!
Code: https://github.com/JMHReif/ai-pet-travel

Transcript

1. GraphRAG: Data 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 • Other: geek Jennifer Reif 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? Company Jennifer Jacob WORKED_FOR WORKED_FOR
5. What is a graph? Company Jennifer Jacob School W ORKED_FOR WORKED_FOR ATTENDED ATTENDED
6. What is a graph? Degree Degree Company Jennifer Jacob School ATTENDED ATTENDED W ORKED_FOR WORKED_FOR EN RO LLED_IN ENROLLED_IN
7. What is a graph? Adrian Degree Degree Company Jennifer Jacob School ATTENDED ATTENDED W ORKED_FOR WORKED_FOR EN RO LLED_IN ENROLLED_IN ENROLLED_IN Degree C O M PLETED COM PLETED
8. What is a graph? Person Degree Degree Company Person Person School ATTENDED ATTENDED W ORKED_FOR WORKED_FOR EN RO LLED_IN ENROLLED_IN ENROLLED_IN Degree C O M PLETED COM PLETED Edward Jones Jacob Jennifer SIUE Music CMIS CS Adrian
9. What is a graph? Answers through relationships • How many coworkers shared classes/degrees? • What are common degree journeys? • How many alumni re- enroll for higher degrees? • Who else went to a school and works for company? Person Degree Degree Company Person Person School ATTENDED ATTENDED W ORKED_FOR WORKED_FOR EN RO LLED_IN ENROLLED_IN ENROLLED_IN Degree C O M PLETED COM PLETED Edward Jones Jacob Jennifer SIUE Music CMIS CS Adrian
10. Nodes (vertices) Objects or entities • Can have labels • May have properties Person Degree Degree Company Person Person School Degree Edward Jones Jacob Jennifer SIUE Music CMIS CS Adrian
11. Relationships (edges) Connect entities • Must have type (label) • Must have direction • May have properties Person Degree Degree Company Person Person School ATTENDED ATTENDED W ORKED_FOR WORKED_FOR EN RO LLED_IN ENROLLED_IN ENROLLED_IN Degree C O M PLETED COM PLETED Edward Jones Jacob Jennifer SIUE Music CMIS CS Adrian
12. Other use cases • Fraud detection • Identity and access management • Recommendations • Supply chain • Logistics
13. Graphs add context and meaning Not just point-to-point, but HOW they connect
14. One model to rule them all… Conceptual = Logical = Physical data model
15. One model to rule them all… Conceptual = Logical = Physical data model
16. Cypher GQL-compliant • Functional and visual • Based on ASCII art • Declarative • Focus on patterns A B LIKES MATCH (A)-[:LIKES]->(B)
17. Cypher: write All about patterns Jennifer Neo4j WORKS_FOR CREATE (:Person { name: ‘Jennifer’}) -[:WORKS_FOR]-> (:Company { name: ‘Neo4j’}) NODE PROPERTY NODE PROPERTY LABEL LABEL
18. Cypher: read All about patterns Jennifer Neo4j WORKS_FOR MATCH (:Person { name: ‘Jennifer’} ) -[:WORKS_FOR]-> ( whom ) RETURN whom
19. A knowledge graph is a specific implementation of a graph database, where information is integrated from many different sources, representing the inherent knowledge of a particular domain.
20. Knowledge graphs
21. Knowledge graphs are • Optimized for relationships • Well suited for complex, interconnected data • Schema-optional • Can readily adapt/evolve as they grow
22. Demo!
23. AI
24. Throw an LLM at it Doesn’t often work • LLM strengths: • human-consumable data • probabilistic answers • LLM weaknesses: • complex logic • recognizing nuances • Solo LLM = great -> integrated LLM = more great?
25. RAG architecture • Retrieval • Data retrieved from external source • Augmented • Augments response with facts • Generation • Response in natural language Prompt + Relevant Information LLM API LLM
 Chat API User Database Search Prompt Response Relevant Results / Documents 2 3 1 Database
26. LLMs take text, not databases And context window limit
27. Lexical to Semantic search • Keyword searches aren’t enough • Data dictionaries are complex and limited • How do we search relevant/contextual info?
28. Embeddings / Vectors Convert data to a point in space • Series of numbers • 100s or 1000s of dimensions • Dimension = interesting feature / characteristic
29. Vectors in the physical realm https://www.mathsisfun.com/algebra/vectors.html
30. Vectors in the technical realm Kings and Queens king − man + woman ≈ queen king man wom an 1 king man wom an 2 queen? 3
31. LLMs take text, not databases Vectors
32. How do we search the vectors? Similarity search • Expensive queries (compare to every vector) • Approximate nearest neighbor (k-ANN) • Example: Library • Book classi fi cation - genre vs location of plot • Smaller search set = smaller retrieval time! Photo by Martin Adams on Unsplash
33. Provide prompt + context to LLM Vectors Text
34. Vector-only RAG Similarity is insu ff i cient for rich reasoning/explainability • Missing context, relationships • Vector similarity != relevance • Lack explainability
35. GraphRAG Graph DB as a data source • More relevant data to provide as context • Quality connected data, higher accuracy • Explainability, veri fi ability
36. GraphRAG
37. 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 fi cation through understandable format Photo by No Revisions on Unsplash
38. Knowledge graph as knowledge base Document in KG -> Knowledge Graph
39. Explainability
40. Nothing is a silver bullet LLM is (of sorts) mind of its own • Can’t guarantee a consistent answer • Prompt engineering • Context window limits
41. Let’s code!
43. Resources • Github repository (today’s code): github.com/JMHReif/ai-pet-travel • 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-how- to-build-knowledge-graph/ Jennifer Reif jennifer.reif@neo4j.com @JMHReif github.com/JMHReif jmhreif.com linkedin.com/in/jmhreif