IA Generativa y Grafos de Neo4j: RAG time
0 likes126 views
The document discusses the value of graph data for enhancing data relationships and insights, emphasizing the benefits of Neo4j's graph technology in improving model accuracy, simplifying processes, and supporting various applications such as risk assessment and knowledge graph construction. It also highlights the integration of GenAI with Neo4j for better language generation and retrieval-augmented experiences. The presentation concludes with an invitation to an upcoming Graph Summit in Madrid.
IA Generativa y Grafos de Neo4j: RAG time
- 1. Neo4j Inc. All rights reserved 2023 Neo4j and GenAI Luis Salvador PreSales Engineer-Spain Pierre Halftermeyer PreSales Engineer-France
- 4. Neo4j Inc. All rights reserved 2023 TODAY’S REALITY Connections in data are as valuable as the data itself 4
- 5. Graph creates a more intuitive and connected view of data relationships, unlocking deeper insights and context 5
- 6. THE PROPERTY GRAPH: SIMPLY POWERFUL Employee City Company Nodes represent objects (nouns) Relationships are directional Relationships connect nodes are represent actions (verbs) Relationships can have properties (name/value pairs) Nodes can have properties (name/value pairs) name: Emil Eifrem date_of_birth: 1979-03-01 employee_ID: 1 :HAS_CEO start_date: 2008-01-20 :LOCATED_IN 6
- 7. Hybrid Workload Duality Intelligent Applications Transactions - Security - Performance & Scalability - ACID Consistency - Intelligent Modeling - Extensive & Supported Algo Library - Scalable - Graph Visualization - Graph Transformations Graph Transactions Graph Analytics & Data Science 7
- 8. What’s in it for you: ● Improve model accuracy by 30% ● Simplify processes and remove headaches ● More projects into production without additional hiring Neo4j Graph Data Science Analytics Feature Engineering Data Exploration Graph Data Science Queries & Search Machine Learning Visualization 8
- 9. What’s important? Prioritization Who has the most connections? Who has the highest page rank? Who is an influencer? What’s unusual? Anomaly & Fraud Detection Where is a community forming? What are the group dynamics? What’s unusual about this data? What’s next? Predictions What’s the most common path? Who is in the same community? What relationship will form? Pl ay s Lives_in In_sport Likes F a n _ o f Plays_for K n o w s Knows Knows K n o w s Answer critical business questions 9
- 10. 10
- 11. Graphs Types for Common Data Shapes 11 ● Creates context for decisions ● Single entity focus ● Historical & real-time data ● API with singleton queries ● Reporting integration ● Foundation for graph recos X360° Graphs ● Creates holistic view of business ● Pulls data from multiple sources ● Unifies data across silos ● Consistent naming conventions ● Mobilizes data in data lakes ● Supports apps, reports, APIs Knowledge Graphs ● Enables E2E process optimization ● Focus on flows, movement ● Hierarchies and cascades ● Easily handles recursion ● Identifies dependencies ● Traces journey Process Graphs ● Reveals risks hidden in data ● Leverages graph inference ● Depicts complex relationships ● Reveals anomalous patterns ● Automated alerts in real-time ● Ad-hoc forensics Risk Graphs A B C D E
- 12. This is a Graph
- 13. © 2023 Neo4j, Inc. All rights reserved. Vector Index Search 13
- 14. What is a vector ● Length ● Direction ● Components have meaning horizontal vertical 1 a b 2 a b 3 a + b Neo4j Inc. All rights reserved 2024 14
- 15. Vector embeddings Neo4j Inc. All rights reserved 2024 15 ● Same concepts, just “an arrow” ● 100s or 1000s dimensions ● Each dimension corresponds to an interesting feature or characteristic king − man + woman ≈ queen k i n g man wom an 1 k i n g man wom an 2 q u e e n ? 3
- 16. Neighborhoods ● cosine ● direction / angle based vector point query nearest 4 ● Euclidean ● distance based 16
- 17. KGs enable searches with explicit and implicit (vectors) relationships 17
- 18. Neo4j and Vector Search Find relevant documents and content for user queries Find entities associated to content and patterns in connected data. Improve search relevance & insights by enhancing a Knowledge Graph. Use graph algorithms and ML to discover new relationships, entities, and groups. Vector Similarity Search Graph Traversals & Pattern Matching Knowledge Graph Inference & ML Vector Search Graph Database 18
- 20. © 2023 Neo4j, Inc. All rights reserved. LLMs and GenAI 20
- 21. 21
- 22. 22
- 23. Gen AI is everywhere We’re at mile one of the marathon 23 The next big thing
- 24. 24
- 25. 25
- 26. Learns random sentences from random people Talks like a person but doesn’t really understand what it’s saying Occasionally speaks absolute nonsense Is a cute little bird Yes Yes Yes Yes Yes Yes Yes No The limitations of GenAI 26
- 27. The limitations of GenAI Hallucinates Limited input sizes for fine tuning Lack of enterprise domain knowledge Inability to verify answers Sensitive to prompt (input) phrasing Ethical and data bias concerns 27 Definition: Language models generate text that is incorrect, nonsensical, or unreal. • Appear to answer questions confidently even if they don’t have facts • May provide contradicting or inconsistent responses to similar prompts
- 28. How to Help LLMs Do Better? Fine-Tuning Grounding Provide completed examples “shots” to the AI as context in prompts. a.k.a In-Context Learning Provide additional training data to better tune GenAI to your use case Provide AI with the information to use for generating responses All of these are useful, but grounding is where Neo4j adds value Neo4j as the data source for Grounding 28 Few-Shot Learning
- 29. Ground LLMs in Neo4j’s Knowledge Graph 29 29
- 30. 30
- 31. 31 1 2 LLMs for Language Generation Gen AI use cases
- 32. Generate personalized Natural Language experiences Neo4j Inc. All rights reserved 2024 32
- 33. 33 1 2 LLMs for Language Generation RAG-based Applications Gen AI use cases
- 34. Grounding with Retrieval Augmented Generation (RAG) Neo4j Inc. All rights reserved 2024 34
- 35. Natural Language (NL) Search on explicit relationships Neo4j Inc. All rights reserved 2024 35
- 36. Neo4j Inc. All rights reserved 2023 36 Natural Language Search combining explicit and implicit relationships
- 37. 37 1 2 3 LLMs for Language Generation RAG-based Applications Gen AI use cases Knowledge Graph Construction
- 38. Creating a Knowledge Graph From Unstructured Text was Difficult Neo4j Inc. All rights reserved 2024 38
- 39. Knowledge Graph Creation with Cypher Templates 39 Neo4j Inc. All rights reserved 2024 39
- 40. © 2023 Neo4j, Inc. All rights reserved. How will you transform your organization?
- 42. © 2023 Neo4j, Inc. All rights reserved. 42
- 43. © 2023 Neo4j, Inc. All rights reserved. 43
- 44. © 2023 Neo4j, Inc. All rights reserved. 44
- 45. © 2023 Neo4j, Inc. All rights reserved. Thank You! See you 9th April 2024 at our next GraphSummit Madrid! 45