Novedades de Productos y Roadmap Neo4j
Luis Salvador, Ingeniero de Preventas, Neo4j
Echa un vistazo a las últimas innovaciones de Neo4j que permiten la inteligencia basada en relaciones a escala. Obtenga más información sobre las últimas integraciones en la nube y mejoras de productos que hacen de Neo4j una opción esencial para los desarrolladores que crean aplicaciones con datos interconectados e IA generativa.
4. • Parallel Runtime for faster analytical Queries
• Change Data Capture better data integration
• Autonomous clustering and Fabric for limitless scalability
• Graph Schema, Improved Backup recovery, incremental
import
• Neo4j Ops Manager for managing databases
• Aura Enterprise Database on all clouds (AWS, GCP, Azure)
• SOC II Type 2 compliance, AuraDB APIs, RBAC
configuration
• Better observability with security log forwarding
Performance metrics forwarding (EAP)
• Private Link & CMEK (Coming soon)
Neo4j product capabilities launched in 2023
Neo4j Inc. All rights reserved 20244
4
• Unified Developer Experience with Workspace
• Self-service Data Import
• GraphQL Support & Simplified Drivers API
• Bloom support for GDS algorithms
• GDS Python API
• Knowledge Graph Embeddings
• Longest Path & Topological Sort Algorithm
• Vector Search
• Real Time integration with Embedding APIs & LLM
Models
• Cloud Integrations (OpenAI + MS Azure OpenAI,
VertexAI, AWS Bedrock, Langchain, LlamaIndex)
5. Graph Schema: New constraints on
nodes, relationships and properties:
• Unique relationship property
• Relationship key
• Property data types
NEO4J 5.x NEW CAPABILITIES
Database Enhancements
Neo4j Inc. All rights reserved 20244
5
6. Graph Pattern Matching: Improved
expressivity of graph navigation with
quantified path patterns,
a more powerful and performant
syntax to navigate and traverse your
graph.
NEO4J 5.x NEW CAPABILITIES
Database Enhancements
Neo4j Inc. All rights reserved 20244
6
7. NEO4J 5.x NEW CAPABILITIES
Database Enhancements
Graph Pattern Matching Example → Fraud Rings
Neo4j Inc. All rights reserved 20244
7
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
8. NEO4J 5.x NEW CAPABILITIES
Parallel Runtime: Speed up analytical query up to 100x
Neo4j Inc. All rights reserved 20244
8
9. Parallel Runtime Speedup
Up to 100x faster analytical queries by adding CPU
cores
Neo4j Inc. All rights reserved 20244
9
More cores
Faster
Queries
10. NEO4J 5.x NEW CAPABILITIES
Change Data Capture: Automated Real-Time
Change Tracking
Neo4j Inc. All rights reserved 20244
10
12. Vector embeddings
12
● Same concepts, just “an arrow”
● 100s or 1000s dimensions
● Each dimension corresponds to an
interesting feature or characteristic
king − man + woman ≈ queen
1 2 3
17. Neo4j Inc. All rights reserved 2024
17
94%of business
leaders agree that AI is
critical to success over
the next five years1
1. Deloitte’s State of AI in the Enterprise
20. Ground LLMs in Neo4j’s Knowledge Graph
20 Neo4j Inc. All rights reserved 2024
20
21. Why RAG With Vector Databases Fall Short
Similarity is insufficient for rich enterprise reasoning
Neo4j Inc. All rights reserved 2024
21
1
3
2
4
Only leverage a fraction of
your data: Beyond simple
“metadata”, vector databases
alone fail to capture
relationships from structured
data
Miss critical context: Struggle
to capture connections across
nuanced facts, making it
challenging to answer multi-
step, domain-specific,
questions
Vector Similarity ≠ Relevance:
Vector search uses an incomplete
measure of similarity. Relying on it
solely can result in irrelevant and
duplicative results
Lack explainability:
The black-box nature of
vectors lacks transparency
and explainability
22. 22
What is a Knowledge Graph?
An information architecture with layered connections.
Neo4j Inc. All rights reserved 20244
DATA INFORMATION KNOWLEDGE INSIGHT MEANING
records sets relationships patterns layers
23. Neo4j Inc. All rights reserved 2024
23
Knowledge Graphs + LLMs
23
Facts
Explicit
Explainable
Words
Implicit
Opaque
KGs LLMs
+
24. RAG with Neo4j
Neo4j Inc. All rights reserved 20244
24
Find similar documents,
content and data
Expanded context for related
information and ranking
results
Improve GenAI inferences and
insights. Discover new
relationships and entities
Unified search, knowledge graph and data science capabilities to
improve RAG quality and effectiveness
Vector Search,
Full-text Search,
Geospatial, Pattern
match
Data Science
Knowledge Graph
26. Neo4j Inc. All rights reserved 2024
26
Knowledge Graph
Construction with
Cypher Templates
27. Human
27
1 Knowledge Graph Construction
Gen AI use cases LLM
Knowledge
Graph
2 RAG-based Chat Applications
28. Neo4j Inc. All rights reserved 2024
28
Natural Language
Search combining
explicit and implicit
relationships
29. Application Human
29
1 Knowledge Graph Construction
Gen AI use cases LLM
Knowledge
Graph
2 RAG-based Chat Applications
3 RAG-enhanced General Applications
30. Neo4j Inc. All rights reserved 2024
30
Natural Language
assistants and co-
pilots,
rooted in business
policy
Prompt +
Relevant
Information
Embedding API LLM API
User
Database
Search
Prompt Response
Relevant Results
Knowledge
Graph
Application
31. • Integrate Neo4j with leading LLM
open-source frameworks such as
LangChain and LlamaIndex
• Call LLM APIs natively via Cypher using
our open-source APOC library
• Agnostic LLM orchestration connecting
graphs to OpenAI, AWS Bedrock, GCP
Vertex AI, Azure, Anthropic, Hugging
Face, and other proprietary and open-
source foundation models
Integrate with the GenAI Ecosystem
Neo4j Inc. All rights reserved 2024
31
GenAI Stack
Application
Generative AI & Embedding Models
Orchestration
Grounding Knowledge Graph
Neo4jGraph
Neo4jVector
GraphCypherQAChain
n
Neo4jGraphStore
Neo4jVectorStore
KnowledgeGraphIndex
Neo4j GenAI Integrations
Text | Chat | Embedding
NL Query | Image Gen
Neo4j Drivers
Java
Python JavaScript
32. • Co-Pilot in Neo4j Browser for
autocomplete & Cypher generation
• Bloom & NeoDash NL integration
• More framework integrations:
• Langchain, LlamaIndex,
SemanticKernel, Spring.AI, Haystack
POWERING GENERATIVE AI APPS
Neo4j’s GenAI Roadmap
Neo4j Inc. All rights reserved 2024
32
Coming 2024+
33. • Parallel Runtime for faster analytical Queries
• Change Data Capture better data integration
• Autonomous clustering and Fabric for limitless scalability
• Graph Schema, Improved Backup recovery, incremental
import
• Neo4j Ops Manager for managing databases
• Aura Enterprise Database on all clouds (AWS, GCP, Azure)
• SOC II Type 2 compliance, AuraDB APIs, RBAC
configuration
• Better observability with security log forwarding
Performance metrics forwarding (EAP)
• Private Link & CMEK (Coming soon)
Neo4j product capabilities launched in 2023
Neo4j Inc. All rights reserved 2024
33
• Unified Developer Experience with Workspace
• Self-service Data Import
• GraphQL Support & Simplified Drivers API
• Bloom support for GDS algorithms
• GDS Python API
• Knowledge Graph Embeddings
• Longest Path & Topological Sort Algorithm
• Vector Search
• Real Time integration with Embedding APIs & LLM
Models
• Cloud Integrations (OpenAI + MS Azure OpenAI,
VertexAI, AWS Bedrock, Langchain, LlamaIndex)