Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris

Jesús Barrasa
Nouveautés Produits
& Graphes de
Connaissances
Head of Solutions Architecture for EMEA
Neo4j

Neo4j Inc. All rights reserved 2024
Recent features in Neo4j
Knowledge Graphs
2
Agenda

● Ubiquitous availability of Aura in all major
clouds: GCP, AWS, Azure
● Enterprise-ready Aura
﹣ SOC II Type 2 compliance
﹣ Better DevOps with AuraDB APIs
﹣ Easier RBAC configuration via Aura
console
﹣ Better observability with security log
forwarding (EAP) and Performance
metrics forwarding (EAP)
﹣ Private Link
3
NEO4J AURA
2023 Key Capabilities

Customer Managed Keys (Encryption)
4 Neo4j Inc. All rights reserved 2024
What is it
Aura encrypts all data at transit &
rest by default.
Customer Managed Keys (CMK)
is an alternative way to protect
cloud data for security conscious
Enterprises, enabling customers
to manage their own keys for
encryption / decryption at disk on
Aura using Key Management
Services (KMS) from their Cloud
Service Provider.
Why it is important
Customers can protect their own
data, control access and have
the ability to revoke access, even
from Neo4j.
Customers can adhere to their
own stringent security policy
around access and key rotation,
on top of Aura’s Enterprise grade
default security and compliance
posture.

Customer Managed Keys (Encryption)
5

6
Graph Schema

Graph Schema: New constraints on
nodes, relationships and properties:
● Unique relationship property
● Relationship key
● Property data types
NEO4J 5.0 NEW CAPABILITIES
Database Enhancements
7

Graph Schema / Graph Type
8
The definition of the informational content of a schema
(or rather a graph type), comprising:
● A set of node type descriptors
(also known as a node type set).
● A set of edge type descriptors
(also known as an edge type set).
● A node type name dictionary that maps node type
names,
which are identifiers, to node types contained in the node
type set of this graph type descriptor such that each
node type name is mapped to a single node type.
● An edge type name dictionary that maps edge
type names,
which are identifiers, to edge types contained in the
edge type set of this graph type descriptor such that
each edge type name is mapped to a single edge type.
CREATE OR REPLACE GRAPH TYPE FraudDet
(a:AccountHolder { FirstName :: STRING!,
LastName :: STRING!,
UniqueId :: STRING! }
...) REQUIRE UniqueId IS KEY,
(c:CreditCard {AccountNumber :: STRING!,
Balance :: FLOAT!,
...} ...) REQUIRE AccountNumber IS KEY, ...
(a)-[:HAS_CARD ...]->(c),
(a)-[:HAS_ACCOUNT ...]->(b),...
CREATE OR REPLACE DATABASE foo
...
[WITH GRAPH TYPE FrautDet]
...

9
QPP

Graph Pattern Matching: Improved
expressivity of graph navigation with
quantified path patterns,
a more powerful and performant syntax
to navigate and traverse your graph.
10

Graph Pattern Matching Example → Fraud Rings
11
QPP
MATCH path=(a:Account)-[:PERFORMS]->(first_tx)
((tx_i)-[:BENEFITS_TO]->(a_i)-[:PERFORMS]->(tx_j)
WHERE tx_i.date < tx_j.date
AND 0.80 <= tx_i.amount / tx_j.amount <= 1.00
){3,6}
(last_tx)-[:BENEFITS_TO]->(a)
WHERE size(apoc.coll.toSet([a]+a_i)) = size([a]+a_i)
RETURN path
👉 read more: https://bit.ly/pierre-qpp

12
Parallel Runtime

Parallel Runtime: Speed up analytical query up to 100x
13

Parallel Runtime Speedup
Up to 100x faster analytical queries by adding CPU
cores
14
More cores
Faster
Queries

20
New in Neo4j 5 -
recap

Neo4j
Product capabilities launched in 2023/2024
21
● Parallel Runtime - faster analytical Queries
● Change Data Capture - better data integration
● Autonomous clustering & Fabric - limitless
scalability
● Graph Schema & constraints
● Backup with point-in-time recovery
● Incremental import
● Neo4j/AuraDB Ops Manager for managing
databases
● Aura Enterprise Database on all clouds
(AWS, GCP, Azure)
● SOC II Type 2 compliance, AuraDB APIs, RBAC
configuration
● Private Link & CMEK
● Log forwarding & performance metrics - better
observability
● Workspace - unified developer experience
● GraphQL Support & Simplified Drivers API
● Bloom support for GDS algorithms
● GDS Python API
● Knowledge Graph Embeddings
● Longest Path & Topological Sort Algorithm
● Vector Search & index
● Embedding APIs & LLM Models - Real Time
integration
● OpenAI + MS Azure OpenAI, VertexAI, AWS
Bedrock, Langchain, LlamaIndex etc. - Real Time
GenAI integration

Graphes de
Connaissances
Le partenaire idéal des LLMs pour une IA fiable
22

1. The Graph
2.The Knowledge
3.LLMS & GraphRAG
4.mini-Demo and
takeaways
23

The Graph
The Shape of data
24

Explore the connections in your data to
unlock deeper insights

26
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: Amy Peters
date_of_birth: 1984-03-01
employee_ID: 1
:HAS_CEO
start_date: 2008-01-20
:LOCATED_IN

27
Cypher (GQL): Pattern Based
MATCH (p:Employee {employee_ID: 1})-[r:WORKS_AT*..3]-(c:Company)
RETURN c.name as company, count(*) as strength
ORDER BY strength DESC
Node
Pattern
Relationship
Pattern

The Knowledge
The Semantic layer
29

Two “types” of semantics
30

31

32

A Knowledge Graph captures
key enterprise knowledge in
the form of entities and
relationships between them.
Some nodes in the graph have
properties with NL text
35
3

These property values get
embedded (transformed into a
numeric representation) and
added to a vector index to
enable vector-based semantic
search.
36
3

A semantic search on the
vector index returns the k
approximate nearest
neighbours to the search
concept (word, question, image,
etc)
37
3

Each result from the vector
search is “dereferenced“ to get
the corresponding node in the
graph and a subsequent graph
exploration finds semantically
related elements that enrich
and augment the final search
result.
38
3

LLMs & GraphRAG
Reliable AI
39

41
Grounding LLMs with KG: GraphRAG

43
Demo: Q&A on document with rich internal structure
https://www.irishstatutebook.ie/eli/2015/si/516/made/en/p
df

44
The document as a graph

45
Merci
jesus.barrasa@neo4j.com

Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris

More Related Content

Similar to Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris

More from Neo4j

Recently uploaded

Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris