SlideShare a Scribd company logo
Graph Summit Paris, 5 juin 2024
Generative AI
Workshop
Nicolas Rouyer, Jean-Marc Guerin
© 2024 Neo4j, Inc. All rights reserved. 2
Neo4j Gen AI Hands-on
Lab with AWS
AWS Office-Tour Carpe Diem, 31 place des Corolles,
92400 Courbevoie, France
Thursday, June 6 13:30 CEST
Registration:
© 2024 Neo4j, Inc. All rights reserved.
Workshop Rules
Ask questions straight away, this is an interactive session
Raise your hand if you are stuck
Have fun
3
© 2024 Neo4j, Inc. All rights reserved.
Before We Start
1/ Create a blank Neo4j Sandbox at https://sandbox.neo4j.com
2/ Open the notebook in Colab (needs a google account!)
4
https://github.com/guerinjeanmarc/genai-workshop
open genai-workshop.ipynb
Neo4j Inc. All rights reserved 2024
5
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
© 2024 Neo4j, Inc. All rights reserved.
Retrieval-Augmented Generation Is Becoming
an Industry Standard
RAG augments LLMs by retrieving
up-to-date, contextual external data to
inform responses:
Reduce hallucinations with
verified data
Provide domain-specific, relevant
responses
Enable traceability back
to sources
6
Retrieval Augmented Generation
Database of Truth
© 2024 Neo4j, Inc. All rights reserved. 7
RAG with Neo4j
Find similar documents
and content
Identify entities
associated to content and
patterns
in connected data
Improve & enrich GenAI
insights. Discover new
relationships and entities
Unify vector search, knowledge graph and data science
capabilities to improve RAG quality and effectiveness
Vector Search
Graph Data
Science
Knowledge
Graph
© 2024 Neo4j, Inc. All rights reserved.
Today
8
© 2024 Neo4j, Inc. All rights reserved.
Today
no chatbot
9
© 2024 Neo4j, Inc. All rights reserved.
Today
10
© 2024 Neo4j, Inc. All rights reserved.
Today
11
We are Choosing
Clothes
© 2024 Neo4j, Inc. All rights reserved.
This is Eva
For her birthday, Eva wants
a Halter Neck Top
How do you choose what to buy?
12
© 2024 Neo4j, Inc. All rights reserved.
This is Eva
For her birthday, Eva wants
a Halter Neck Top
How do you choose what to buy?
1/ Get a list of Halter Neck Top
2/ Match the Halter Neck Top for Eva
3/ Accessorize or add another item
13
© 2024 Neo4j, Inc. All rights reserved.
At Scale: Let’s Build an AI Fashion
Assistant
This Requires:
1. Data: Kaggle H&M
2. Search & Retrieval
3. Context for Personalization
4. Recommendation Engine
5. LLM Powered Content Generator
14
© 2024 Neo4j, Inc. All rights reserved. 15
Solution: LLMs and Knowledge
Graphs
Knowledge
Context
Enrichment
Language
Reasoning
Creativity
KGs LLMs
+
BETTER TOGETHER
© 2024 Neo4j, Inc. All rights reserved.
We'll Build a Targeted, Personalized
Content Generator
16
© 2024 Neo4j, Inc. All rights reserved. 17
Tools
© 2024 Neo4j, Inc. All rights reserved.
Journey
18
1
Graph Building
(Kaggle H&M Dataset)
2
Vector Search
(Initial Retrieval)
3
Semantic Search with
Graph Patterns
(Personalization)
4
Graph DS & ML
(Recommendations)
LLM Powered
Content Generator &
Fashion Assistant
5
© 2024 Neo4j, Inc. All rights reserved. 19
1
Graph Building
(Kaggle H&M Dataset)
2
Vector Search
(Initial Retrieval)
3
Semantic Search with
Graph Patterns
(Personalization)
4
Graph DS & ML
(Recommendations)
LLM Powered
Content Generator &
Fashion Assistant
5
© 2024 Neo4j, Inc. All rights reserved.
Data Model
20
© 2024 Neo4j, Inc. All rights reserved.
Data Model
21
customerId
tDat
Colour
name
type
group
description
© 2024 Neo4j, Inc. All rights reserved.
Now We Can Start
1/ Create a Neo4j Sandbox at https://sandbox.neo4j.com
2/ Open the notebook in Colab (needs a google account!)
22
https://github.com/neo4j-product-examples/genai-workshop
open genai-workshop.ipynb
© 2024 Neo4j, Inc. All rights reserved.
1/ Graph Building
23
Stop before Vector Search
© 2024 Neo4j, Inc. All rights reserved. 24
1
Graph Building
(Kaggle H&M Dataset)
2
Vector Search
(Initial Retrieval)
3
Semantic Search with
Graph Patterns
(Personalization)
4
Graph DS & ML
(Recommendations)
LLM Powered
Content Generator &
Fashion Assistant
5
© 2024 Neo4j, Inc. All rights reserved.
What are Embeddings?
● A type of data compression
● Transform messy data (text, images, audio,
etc.) into a compact format for ML
algorithms
● Most often numeric vectors (a.k.a arrays)
with 100s or 1000s of elements
● Preserve information such that “similar”
items have proportionally “similar”
embedding vectors
● Similarity is measured with vector
algorithms (cosine, euclidean, etc.)
25
Graph Graph Model
Graph Vector
Embeddings
© 2024 Neo4j, Inc. All rights reserved.
What Does “Similarity” Mean?
It Depends:
• Text Embeddings => Semantic Similarity, the meaning
behind a text sequence
• Graph Embeddings => similarity in position or structure in a
graph-can have semantic meaning too
26
© 2024 Neo4j, Inc. All rights reserved.
What will we use embedding for?
1. (now) Vector search using text embeddings
2. (later) Recommendations using graph node embeddings
27
© 2024 Neo4j, Inc. All rights reserved.
Search & Vectors in Neo4j
Neo4j makes search efficient through a variety of indexes including
• Range: General index for predicates based on equality and range.
Numeric, dates, etc.
• Point: Predicts on geospatial points like distance bounding boxes,
etc.
• Text: Predicates on strings like contains, ends with, etc.
• FullText: Text search based on tokenization and analyzers
• Vector: ANN (Approximate Nearest Neighbor) search on vectors
28
© 2024 Neo4j, Inc. All rights reserved.
Vector search
29
“Halter neck top”
Backless
blouse
Tie-back
shirt
Neck
© 2024 Neo4j, Inc. All rights reserved.
Vector search
30
“Halter neck top”
Backless
blouse
Tie-back
shirt
Neck
© 2024 Neo4j, Inc. All rights reserved.
How is similarity measured
31
cosine
direction / angle based
vector point
query
nearest 4
Euclidean
distance based
The vector Index allow to query vectors on large dataset.
It uses HNSW to perform k-ANN queries
© 2024 Neo4j, Inc. All rights reserved.
Vector search
32
“Halter neck top”
Backless
blouse
Tie-back
shirt
Neck
CREATE VECTOR INDEX
db.index.vector.queryNodes
© 2024 Neo4j, Inc. All rights reserved.
Vector search
33
“Halter neck top”
Backless
blouse
Tie-back
shirt
Neck
CREATE VECTOR INDEX
db.index.vector.queryNodes
© 2024 Neo4j, Inc. All rights reserved.
2/ Vector Search
34
Stop before Semantic Search with Graph Patterns
(Personalization)
© 2024 Neo4j, Inc. All rights reserved. 35
1
Graph Building
(Kaggle H&M Dataset)
2
Vector Search
(Initial Retrieval)
3
Semantic Search with
Graph Patterns
(Personalization)
4
Graph DS & ML
(Recommendations)
LLM Powered
Content Generator &
Fashion Assistant
5
© 2024 Neo4j, Inc. All rights reserved.
Neo4j & Semantic Search
36
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 Pattern
Matching
Knowledge Graph
DS/ML
Vector Search
Graph Database
© 2024 Neo4j, Inc. All rights reserved.
Semantic search with graph pattern
37
© 2024 Neo4j, Inc. All rights reserved.
Semantic search with graph pattern
38
© 2024 Neo4j, Inc. All rights reserved.
3/ Semantic Search with
Graph Patterns
Personalization & Context
39
Stop before Graph Data Science & ML (Recommendations)
© 2024 Neo4j, Inc. All rights reserved. 40
1
Graph Building
(Kaggle H&M Dataset)
2
Vector Search
(Initial Retrieval)
3
Semantic Search with
Graph Patterns
(Personalization)
4
Graph DS & ML
(Recommendations)
LLM Powered
Content Generator &
Fashion Assistant
5
© 2024 Neo4j, Inc. All rights reserved.
Pathfinding
& Search
Centrality Community
Detection
Machine
Learning
Link
Prediction
Similarity Embeddings And more …
Over 65 pretuned, parallelized algorithms. Iterate fast with different data sets, models,
and version trained models.
Bring the context of your connected data
into a format that other pipelines can
ingest.
41
Improve Models And Answer Big Questions
The Largest Catalog of
Graph Algorithms
Native Graph Catalog and
Analytics Workspace
Graph Embeddings for
Machine Learning
© 2024 Neo4j, Inc. All rights reserved. 42
© 2024 Neo4j, Inc. All rights reserved.
Node Embeddings
The representation of nodes as
low-dimensional vectors that
summarize their graph position,
the structure of their local graph
neighborhood as well as any
possible node features
43
© 2024 Neo4j, Inc. All rights reserved.
K-Nearest Neighbor (KNN)
w/ Node Embeddings
Draw connections between
highly interconnected nodes
and/or those that have similar
roles in the graph
44
0.2
0.3
0.6
-0.6
0.1
0.4
0.5
-0.4
-0.1
0.5
0.4
-0.4
© 2024 Neo4j, Inc. All rights reserved.
4/ Graph Data Science &
ML
Recommendations
45
Stop before LLM Powered Content Generator
© 2024 Neo4j, Inc. All rights reserved. 46
1
Graph Building
(Kaggle H&M Dataset)
2
Vector Search
(Initial Retrieval)
3
Semantic Search with
Graph Patterns
(Personalization)
4
Graph DS & ML
(Recommendations)
LLM Powered
Content Generator &
Fashion Assistant
5
© 2024 Neo4j, Inc. All rights reserved. 47
Online Retailers uses LLM and Knowledge Graph
for Hyper-Personalized Customer Experiences
Challenge: Scale generation of
hyper-personalized customer experiences
Solution: LLM application, backed by customer
knowledge graph with their preferences,
purchase history and other contextual data, to
generate hyper-personalized email templates.
LLM generates customizes email body based
on customer’s unique context from
Knowledge Graph
Impact: Transform customer experiences
through natural language personalization
© 2024 Neo4j, Inc. All rights reserved.
Prompting the LLM
You are a personal assistant named Sally for a fashion, home, and
beauty company called HRM.
write an email to {customerName}, one of your customers, to
promote and summarize products relevant for them given the
current season / time of year: {timeOfYear} .
Please only mention the products listed below. Do not come up
with or add any new products to the list.
Each product comes with an https `url` field. Make sure to
provide that https url with descriptive name text in markdown for
each product.
---
# Relevant Products:
{searchProds}
# Customer May Also Be Interested In the following
(pick items from here that pair with the above products well for
the current season / time of year: {timeOfYear}.
prioritize those higher in the list if possible):
{recProds}
---
48
© 2024 Neo4j, Inc. All rights reserved.
Langchain Chain
49
customer_id
searchPrompt Personalized
search
Reco
timeOfYear
customerName
prompt llm personalized
email
{searchProds: searchPrompt | personalizedSearch (customer_id)
recProds: customer_id | recommendations
customerName
timeOfYear}
prompt | llm | OutputParser
searchProds
recProds
© 2024 Neo4j, Inc. All rights reserved.
4/ LLM Powered Fashion
Assistant
LLM For Generating Grounded Content
50
© 2024 Neo4j, Inc. All rights reserved.
Real-World GenAI Breakthroughs
Powered by Neo4j
51
Integrating AI with
knowledge graphs for
smarter supply chain
management
Merging structured
and unstructured data
for efficient operations
Converting vast amounts
of unstructured data into
actionable knowledge
Leveraging AI
for customized
content at scale
© 2024 Neo4j, Inc. All rights reserved.
1,700+ Organizations Use Neo4j
52
Banking &
Financial Services
Technology Telecommunications Energy
E-Commerce
Health & Life
Sciences
© 2024 Neo4j, Inc. All rights reserved.
Thank you!
53
© 2024 Neo4j, Inc. All rights reserved.
Neo4j Gen AI Hands-on
Lab with AWS
AWS Office-Tour Carpe Diem, 31 place des Corolles,
92400 Courbevoie, France
Thursday, June 6 13:30 CEST
Registration:

More Related Content

Similar to Atelier - Innover avec l’IA Générative et les graphes de connaissances

Neo4j_Anurag Tandon_Product Vision and Roadmap.Benelux.pptx.pdf
Neo4j_Anurag Tandon_Product Vision and Roadmap.Benelux.pptx.pdfNeo4j_Anurag Tandon_Product Vision and Roadmap.Benelux.pptx.pdf
Neo4j_Anurag Tandon_Product Vision and Roadmap.Benelux.pptx.pdf
Neo4j
 
Webinar - IA generativa e grafi Neo4j: RAG time!
Webinar - IA generativa e grafi Neo4j: RAG time!Webinar - IA generativa e grafi Neo4j: RAG time!
Webinar - IA generativa e grafi Neo4j: RAG time!
Neo4j
 
GraphSummit Milan - Visione e roadmap del prodotto Neo4j
GraphSummit Milan - Visione e roadmap del prodotto Neo4jGraphSummit Milan - Visione e roadmap del prodotto Neo4j
GraphSummit Milan - Visione e roadmap del prodotto Neo4j
Neo4j
 
GraphSummit Stockholm - Neo4j - Knowledge Graphs and Product Updates
GraphSummit Stockholm - Neo4j - Knowledge Graphs and Product UpdatesGraphSummit Stockholm - Neo4j - Knowledge Graphs and Product Updates
GraphSummit Stockholm - Neo4j - Knowledge Graphs and Product Updates
Neo4j
 
Neo4j: Data Engineering for RAG (retrieval augmented generation)
Neo4j: Data Engineering for RAG (retrieval augmented generation)Neo4j: Data Engineering for RAG (retrieval augmented generation)
Neo4j: Data Engineering for RAG (retrieval augmented generation)
Neo4j
 
Connecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfConnecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdf
Neo4j
 
GraphSummit Milan & Stockholm - Neo4j: The Art of the Possible with Graph
GraphSummit Milan & Stockholm - Neo4j: The Art of the Possible with GraphGraphSummit Milan & Stockholm - Neo4j: The Art of the Possible with Graph
GraphSummit Milan & Stockholm - Neo4j: The Art of the Possible with Graph
Neo4j
 
La strada verso il successo con i database a grafo, la Graph Data Science e l...
La strada verso il successo con i database a grafo, la Graph Data Science e l...La strada verso il successo con i database a grafo, la Graph Data Science e l...
La strada verso il successo con i database a grafo, la Graph Data Science e l...
Neo4j
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Neo4j
 
Deeper Insights with Graph Data Science
Deeper Insights with Graph Data ScienceDeeper Insights with Graph Data Science
Deeper Insights with Graph Data Science
Neo4j
 
Knowledge Graphs and Generative AI
Knowledge Graphs and Generative AIKnowledge Graphs and Generative AI
Knowledge Graphs and Generative AI
Neo4j
 
Neo4j Product Updates & Knowledge Graphs at GraphSummit London 14 Nov 2023.pptx
Neo4j Product Updates & Knowledge Graphs at GraphSummit London 14 Nov 2023.pptxNeo4j Product Updates & Knowledge Graphs at GraphSummit London 14 Nov 2023.pptx
Neo4j Product Updates & Knowledge Graphs at GraphSummit London 14 Nov 2023.pptx
Neo4j
 
Neo4j: The path to success with Graph Database and Graph Data Science
Neo4j: The path to success with Graph Database and Graph Data ScienceNeo4j: The path to success with Graph Database and Graph Data Science
Neo4j: The path to success with Graph Database and Graph Data Science
Neo4j
 
The Data Platform for Today's Intelligent Applications.pdf
The Data Platform for Today's Intelligent Applications.pdfThe Data Platform for Today's Intelligent Applications.pdf
The Data Platform for Today's Intelligent Applications.pdf
Neo4j
 
Get Started with the Most Advanced Edition Yet of Neo4j Graph Data Science
Get Started with the Most Advanced Edition Yet of Neo4j Graph Data ScienceGet Started with the Most Advanced Edition Yet of Neo4j Graph Data Science
Get Started with the Most Advanced Edition Yet of Neo4j Graph Data Science
Neo4j
 
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4jGraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
Neo4j
 
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4jGraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
Neo4j
 
Leveraging Graphs for Artificial Intelligence and Machine Learning - Phani Da...
Leveraging Graphs for Artificial Intelligence and Machine Learning - Phani Da...Leveraging Graphs for Artificial Intelligence and Machine Learning - Phani Da...
Leveraging Graphs for Artificial Intelligence and Machine Learning - Phani Da...
Neo4j
 
Neo4j Jesus Barrasa The Art of the Possible with Graph
Neo4j Jesus Barrasa The Art of the Possible with GraphNeo4j Jesus Barrasa The Art of the Possible with Graph
Neo4j Jesus Barrasa The Art of the Possible with Graph
Neo4j
 
Neo4j GraphSummit Copenhagen - The Art Of The Possible With Graph Technology ...
Neo4j GraphSummit Copenhagen - The Art Of The Possible With Graph Technology ...Neo4j GraphSummit Copenhagen - The Art Of The Possible With Graph Technology ...
Neo4j GraphSummit Copenhagen - The Art Of The Possible With Graph Technology ...
Neo4j
 

Similar to Atelier - Innover avec l’IA Générative et les graphes de connaissances (20)

Neo4j_Anurag Tandon_Product Vision and Roadmap.Benelux.pptx.pdf
Neo4j_Anurag Tandon_Product Vision and Roadmap.Benelux.pptx.pdfNeo4j_Anurag Tandon_Product Vision and Roadmap.Benelux.pptx.pdf
Neo4j_Anurag Tandon_Product Vision and Roadmap.Benelux.pptx.pdf
 
Webinar - IA generativa e grafi Neo4j: RAG time!
Webinar - IA generativa e grafi Neo4j: RAG time!Webinar - IA generativa e grafi Neo4j: RAG time!
Webinar - IA generativa e grafi Neo4j: RAG time!
 
GraphSummit Milan - Visione e roadmap del prodotto Neo4j
GraphSummit Milan - Visione e roadmap del prodotto Neo4jGraphSummit Milan - Visione e roadmap del prodotto Neo4j
GraphSummit Milan - Visione e roadmap del prodotto Neo4j
 
GraphSummit Stockholm - Neo4j - Knowledge Graphs and Product Updates
GraphSummit Stockholm - Neo4j - Knowledge Graphs and Product UpdatesGraphSummit Stockholm - Neo4j - Knowledge Graphs and Product Updates
GraphSummit Stockholm - Neo4j - Knowledge Graphs and Product Updates
 
Neo4j: Data Engineering for RAG (retrieval augmented generation)
Neo4j: Data Engineering for RAG (retrieval augmented generation)Neo4j: Data Engineering for RAG (retrieval augmented generation)
Neo4j: Data Engineering for RAG (retrieval augmented generation)
 
Connecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfConnecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdf
 
GraphSummit Milan & Stockholm - Neo4j: The Art of the Possible with Graph
GraphSummit Milan & Stockholm - Neo4j: The Art of the Possible with GraphGraphSummit Milan & Stockholm - Neo4j: The Art of the Possible with Graph
GraphSummit Milan & Stockholm - Neo4j: The Art of the Possible with Graph
 
La strada verso il successo con i database a grafo, la Graph Data Science e l...
La strada verso il successo con i database a grafo, la Graph Data Science e l...La strada verso il successo con i database a grafo, la Graph Data Science e l...
La strada verso il successo con i database a grafo, la Graph Data Science e l...
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Deeper Insights with Graph Data Science
Deeper Insights with Graph Data ScienceDeeper Insights with Graph Data Science
Deeper Insights with Graph Data Science
 
Knowledge Graphs and Generative AI
Knowledge Graphs and Generative AIKnowledge Graphs and Generative AI
Knowledge Graphs and Generative AI
 
Neo4j Product Updates & Knowledge Graphs at GraphSummit London 14 Nov 2023.pptx
Neo4j Product Updates & Knowledge Graphs at GraphSummit London 14 Nov 2023.pptxNeo4j Product Updates & Knowledge Graphs at GraphSummit London 14 Nov 2023.pptx
Neo4j Product Updates & Knowledge Graphs at GraphSummit London 14 Nov 2023.pptx
 
Neo4j: The path to success with Graph Database and Graph Data Science
Neo4j: The path to success with Graph Database and Graph Data ScienceNeo4j: The path to success with Graph Database and Graph Data Science
Neo4j: The path to success with Graph Database and Graph Data Science
 
The Data Platform for Today's Intelligent Applications.pdf
The Data Platform for Today's Intelligent Applications.pdfThe Data Platform for Today's Intelligent Applications.pdf
The Data Platform for Today's Intelligent Applications.pdf
 
Get Started with the Most Advanced Edition Yet of Neo4j Graph Data Science
Get Started with the Most Advanced Edition Yet of Neo4j Graph Data ScienceGet Started with the Most Advanced Edition Yet of Neo4j Graph Data Science
Get Started with the Most Advanced Edition Yet of Neo4j Graph Data Science
 
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4jGraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
 
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4jGraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
 
Leveraging Graphs for Artificial Intelligence and Machine Learning - Phani Da...
Leveraging Graphs for Artificial Intelligence and Machine Learning - Phani Da...Leveraging Graphs for Artificial Intelligence and Machine Learning - Phani Da...
Leveraging Graphs for Artificial Intelligence and Machine Learning - Phani Da...
 
Neo4j Jesus Barrasa The Art of the Possible with Graph
Neo4j Jesus Barrasa The Art of the Possible with GraphNeo4j Jesus Barrasa The Art of the Possible with Graph
Neo4j Jesus Barrasa The Art of the Possible with Graph
 
Neo4j GraphSummit Copenhagen - The Art Of The Possible With Graph Technology ...
Neo4j GraphSummit Copenhagen - The Art Of The Possible With Graph Technology ...Neo4j GraphSummit Copenhagen - The Art Of The Possible With Graph Technology ...
Neo4j GraphSummit Copenhagen - The Art Of The Possible With Graph Technology ...
 

More from Neo4j

BT & Neo4j: Knowledge Graphs for Critical Enterprise Systems.pptx.pdf
BT & Neo4j: Knowledge Graphs for Critical Enterprise Systems.pptx.pdfBT & Neo4j: Knowledge Graphs for Critical Enterprise Systems.pptx.pdf
BT & Neo4j: Knowledge Graphs for Critical Enterprise Systems.pptx.pdf
Neo4j
 
Harnessing the Power of NLP and Knowledge Graphs for Opioid Research
Harnessing the Power of NLP and Knowledge Graphs for Opioid ResearchHarnessing the Power of NLP and Knowledge Graphs for Opioid Research
Harnessing the Power of NLP and Knowledge Graphs for Opioid Research
Neo4j
 
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge GraphGraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
Neo4j
 
Leveraging the Graph for Clinical Trials and Standards
Leveraging the Graph for Clinical Trials and StandardsLeveraging the Graph for Clinical Trials and Standards
Leveraging the Graph for Clinical Trials and Standards
Neo4j
 
Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Biomedical Knowledge Graphs for Data Scientists and BioinformaticiansBiomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Neo4j
 
Atelier - Architecture d’applications de Graphes - GraphSummit Paris
Atelier - Architecture d’applications de Graphes - GraphSummit ParisAtelier - Architecture d’applications de Graphes - GraphSummit Paris
Atelier - Architecture d’applications de Graphes - GraphSummit Paris
Neo4j
 
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit ParisNeo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j
 
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit ParisNeo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j
 
FLOA - Détection de Fraude - GraphSummit Paris
FLOA -  Détection de Fraude - GraphSummit ParisFLOA -  Détection de Fraude - GraphSummit Paris
FLOA - Détection de Fraude - GraphSummit Paris
Neo4j
 
SOPRA STERIA - GraphRAG : repousser les limitations du RAG via l’utilisation ...
SOPRA STERIA - GraphRAG : repousser les limitations du RAG via l’utilisation ...SOPRA STERIA - GraphRAG : repousser les limitations du RAG via l’utilisation ...
SOPRA STERIA - GraphRAG : repousser les limitations du RAG via l’utilisation ...
Neo4j
 
ADEO - Knowledge Graph pour le e-commerce, entre challenges et opportunités ...
ADEO -  Knowledge Graph pour le e-commerce, entre challenges et opportunités ...ADEO -  Knowledge Graph pour le e-commerce, entre challenges et opportunités ...
ADEO - Knowledge Graph pour le e-commerce, entre challenges et opportunités ...
Neo4j
 
GraphSummit Paris - The art of the possible with Graph Technology
GraphSummit Paris - The art of the possible with Graph TechnologyGraphSummit Paris - The art of the possible with Graph Technology
GraphSummit Paris - The art of the possible with Graph Technology
Neo4j
 
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
Neo4j
 
GraphSummit Singapore | The Future of Agility: Supercharging Digital Transfor...
GraphSummit Singapore | The Future of Agility: Supercharging Digital Transfor...GraphSummit Singapore | The Future of Agility: Supercharging Digital Transfor...
GraphSummit Singapore | The Future of Agility: Supercharging Digital Transfor...
Neo4j
 
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
Neo4j
 
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
Neo4j
 
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
Neo4j
 
GraphAware - Transforming policing with graph-based intelligence analysis
GraphAware - Transforming policing with graph-based intelligence analysisGraphAware - Transforming policing with graph-based intelligence analysis
GraphAware - Transforming policing with graph-based intelligence analysis
Neo4j
 
KLARNA - Language Models and Knowledge Graphs: A Systems Approach
KLARNA -  Language Models and Knowledge Graphs: A Systems ApproachKLARNA -  Language Models and Knowledge Graphs: A Systems Approach
KLARNA - Language Models and Knowledge Graphs: A Systems Approach
Neo4j
 
INGKA DIGITAL: Linked Metadata by Design
INGKA DIGITAL: Linked Metadata by DesignINGKA DIGITAL: Linked Metadata by Design
INGKA DIGITAL: Linked Metadata by Design
Neo4j
 

More from Neo4j (20)

BT & Neo4j: Knowledge Graphs for Critical Enterprise Systems.pptx.pdf
BT & Neo4j: Knowledge Graphs for Critical Enterprise Systems.pptx.pdfBT & Neo4j: Knowledge Graphs for Critical Enterprise Systems.pptx.pdf
BT & Neo4j: Knowledge Graphs for Critical Enterprise Systems.pptx.pdf
 
Harnessing the Power of NLP and Knowledge Graphs for Opioid Research
Harnessing the Power of NLP and Knowledge Graphs for Opioid ResearchHarnessing the Power of NLP and Knowledge Graphs for Opioid Research
Harnessing the Power of NLP and Knowledge Graphs for Opioid Research
 
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge GraphGraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
 
Leveraging the Graph for Clinical Trials and Standards
Leveraging the Graph for Clinical Trials and StandardsLeveraging the Graph for Clinical Trials and Standards
Leveraging the Graph for Clinical Trials and Standards
 
Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Biomedical Knowledge Graphs for Data Scientists and BioinformaticiansBiomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
 
Atelier - Architecture d’applications de Graphes - GraphSummit Paris
Atelier - Architecture d’applications de Graphes - GraphSummit ParisAtelier - Architecture d’applications de Graphes - GraphSummit Paris
Atelier - Architecture d’applications de Graphes - GraphSummit Paris
 
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit ParisNeo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
 
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit ParisNeo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
 
FLOA - Détection de Fraude - GraphSummit Paris
FLOA -  Détection de Fraude - GraphSummit ParisFLOA -  Détection de Fraude - GraphSummit Paris
FLOA - Détection de Fraude - GraphSummit Paris
 
SOPRA STERIA - GraphRAG : repousser les limitations du RAG via l’utilisation ...
SOPRA STERIA - GraphRAG : repousser les limitations du RAG via l’utilisation ...SOPRA STERIA - GraphRAG : repousser les limitations du RAG via l’utilisation ...
SOPRA STERIA - GraphRAG : repousser les limitations du RAG via l’utilisation ...
 
ADEO - Knowledge Graph pour le e-commerce, entre challenges et opportunités ...
ADEO -  Knowledge Graph pour le e-commerce, entre challenges et opportunités ...ADEO -  Knowledge Graph pour le e-commerce, entre challenges et opportunités ...
ADEO - Knowledge Graph pour le e-commerce, entre challenges et opportunités ...
 
GraphSummit Paris - The art of the possible with Graph Technology
GraphSummit Paris - The art of the possible with Graph TechnologyGraphSummit Paris - The art of the possible with Graph Technology
GraphSummit Paris - The art of the possible with Graph Technology
 
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
 
GraphSummit Singapore | The Future of Agility: Supercharging Digital Transfor...
GraphSummit Singapore | The Future of Agility: Supercharging Digital Transfor...GraphSummit Singapore | The Future of Agility: Supercharging Digital Transfor...
GraphSummit Singapore | The Future of Agility: Supercharging Digital Transfor...
 
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
 
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
 
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
 
GraphAware - Transforming policing with graph-based intelligence analysis
GraphAware - Transforming policing with graph-based intelligence analysisGraphAware - Transforming policing with graph-based intelligence analysis
GraphAware - Transforming policing with graph-based intelligence analysis
 
KLARNA - Language Models and Knowledge Graphs: A Systems Approach
KLARNA -  Language Models and Knowledge Graphs: A Systems ApproachKLARNA -  Language Models and Knowledge Graphs: A Systems Approach
KLARNA - Language Models and Knowledge Graphs: A Systems Approach
 
INGKA DIGITAL: Linked Metadata by Design
INGKA DIGITAL: Linked Metadata by DesignINGKA DIGITAL: Linked Metadata by Design
INGKA DIGITAL: Linked Metadata by Design
 

Recently uploaded

ENISA Threat Landscape 2023 documentation
ENISA Threat Landscape 2023 documentationENISA Threat Landscape 2023 documentation
ENISA Threat Landscape 2023 documentation
sofiafernandezon
 
welcome to presentation on Google Apps
welcome to   presentation on Google Appswelcome to   presentation on Google Apps
welcome to presentation on Google Apps
AsifKarimJim
 
COMPSAC 2024 D&I Panel: Charting a Course for Equity: Strategies for Overcomi...
COMPSAC 2024 D&I Panel: Charting a Course for Equity: Strategies for Overcomi...COMPSAC 2024 D&I Panel: Charting a Course for Equity: Strategies for Overcomi...
COMPSAC 2024 D&I Panel: Charting a Course for Equity: Strategies for Overcomi...
Hironori Washizaki
 
Seamless PostgreSQL to Snowflake Data Transfer in 8 Simple Steps
Seamless PostgreSQL to Snowflake Data Transfer in 8 Simple StepsSeamless PostgreSQL to Snowflake Data Transfer in 8 Simple Steps
Seamless PostgreSQL to Snowflake Data Transfer in 8 Simple Steps
Estuary Flow
 
NBFC Software: Optimize Your Non-Banking Financial Company
NBFC Software: Optimize Your Non-Banking Financial CompanyNBFC Software: Optimize Your Non-Banking Financial Company
NBFC Software: Optimize Your Non-Banking Financial Company
NBFC Softwares
 
MVP Mobile Application - Codearrest.pptx
MVP Mobile Application - Codearrest.pptxMVP Mobile Application - Codearrest.pptx
MVP Mobile Application - Codearrest.pptx
Mitchell Marsh
 
Abortion pills in Fujairah *((+971588192166*)☎️)¥) **Effective Abortion Pills...
Abortion pills in Fujairah *((+971588192166*)☎️)¥) **Effective Abortion Pills...Abortion pills in Fujairah *((+971588192166*)☎️)¥) **Effective Abortion Pills...
Abortion pills in Fujairah *((+971588192166*)☎️)¥) **Effective Abortion Pills...
Medical / Health Care (+971588192166) Mifepristone and Misoprostol tablets 200mg
 
AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Course Introducti...
AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Course Introducti...AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Course Introducti...
AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Course Introducti...
karim wahed
 
Attendance Tracking From Paper To Digital
Attendance Tracking From Paper To DigitalAttendance Tracking From Paper To Digital
Attendance Tracking From Paper To Digital
Task Tracker
 
Google ML-Kit - Understanding on-device machine learning
Google ML-Kit - Understanding on-device machine learningGoogle ML-Kit - Understanding on-device machine learning
Google ML-Kit - Understanding on-device machine learning
VishrutGoyani1
 
Discover the Power of ONEMONITAR: The Ultimate Mobile Spy App for Android Dev...
Discover the Power of ONEMONITAR: The Ultimate Mobile Spy App for Android Dev...Discover the Power of ONEMONITAR: The Ultimate Mobile Spy App for Android Dev...
Discover the Power of ONEMONITAR: The Ultimate Mobile Spy App for Android Dev...
onemonitarsoftware
 
introduction of Ansys software and basic and advance knowledge of modelling s...
introduction of Ansys software and basic and advance knowledge of modelling s...introduction of Ansys software and basic and advance knowledge of modelling s...
introduction of Ansys software and basic and advance knowledge of modelling s...
sachin chaurasia
 
dachnug51 - All you ever wanted to know about domino licensing.pdf
dachnug51 - All you ever wanted to know about domino licensing.pdfdachnug51 - All you ever wanted to know about domino licensing.pdf
dachnug51 - All you ever wanted to know about domino licensing.pdf
DNUG e.V.
 
Splunk_Remote_Work_Insights_Overview.pptx
Splunk_Remote_Work_Insights_Overview.pptxSplunk_Remote_Work_Insights_Overview.pptx
Splunk_Remote_Work_Insights_Overview.pptx
sudsdeep
 
AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Final Course Know...
AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Final Course Know...AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Final Course Know...
AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Final Course Know...
karim wahed
 
WEBINAR SLIDES: CCX for Cloud Service Providers
WEBINAR SLIDES: CCX for Cloud Service ProvidersWEBINAR SLIDES: CCX for Cloud Service Providers
WEBINAR SLIDES: CCX for Cloud Service Providers
Severalnines
 
Cisco Live Announcements: New ThousandEyes Release Highlights - July 2024
Cisco Live Announcements: New ThousandEyes Release Highlights - July 2024Cisco Live Announcements: New ThousandEyes Release Highlights - July 2024
Cisco Live Announcements: New ThousandEyes Release Highlights - July 2024
ThousandEyes
 
ThaiPy meetup - Indexes and Django
ThaiPy meetup - Indexes and DjangoThaiPy meetup - Indexes and Django
ThaiPy meetup - Indexes and Django
akshesh doshi
 
Break data silos with real-time connectivity using Confluent Cloud Connectors
Break data silos with real-time connectivity using Confluent Cloud ConnectorsBreak data silos with real-time connectivity using Confluent Cloud Connectors
Break data silos with real-time connectivity using Confluent Cloud Connectors
confluent
 
Leading Project Management Tool Taskruop.pptx
Leading Project Management Tool Taskruop.pptxLeading Project Management Tool Taskruop.pptx
Leading Project Management Tool Taskruop.pptx
taskroupseo
 

Recently uploaded (20)

ENISA Threat Landscape 2023 documentation
ENISA Threat Landscape 2023 documentationENISA Threat Landscape 2023 documentation
ENISA Threat Landscape 2023 documentation
 
welcome to presentation on Google Apps
welcome to   presentation on Google Appswelcome to   presentation on Google Apps
welcome to presentation on Google Apps
 
COMPSAC 2024 D&I Panel: Charting a Course for Equity: Strategies for Overcomi...
COMPSAC 2024 D&I Panel: Charting a Course for Equity: Strategies for Overcomi...COMPSAC 2024 D&I Panel: Charting a Course for Equity: Strategies for Overcomi...
COMPSAC 2024 D&I Panel: Charting a Course for Equity: Strategies for Overcomi...
 
Seamless PostgreSQL to Snowflake Data Transfer in 8 Simple Steps
Seamless PostgreSQL to Snowflake Data Transfer in 8 Simple StepsSeamless PostgreSQL to Snowflake Data Transfer in 8 Simple Steps
Seamless PostgreSQL to Snowflake Data Transfer in 8 Simple Steps
 
NBFC Software: Optimize Your Non-Banking Financial Company
NBFC Software: Optimize Your Non-Banking Financial CompanyNBFC Software: Optimize Your Non-Banking Financial Company
NBFC Software: Optimize Your Non-Banking Financial Company
 
MVP Mobile Application - Codearrest.pptx
MVP Mobile Application - Codearrest.pptxMVP Mobile Application - Codearrest.pptx
MVP Mobile Application - Codearrest.pptx
 
Abortion pills in Fujairah *((+971588192166*)☎️)¥) **Effective Abortion Pills...
Abortion pills in Fujairah *((+971588192166*)☎️)¥) **Effective Abortion Pills...Abortion pills in Fujairah *((+971588192166*)☎️)¥) **Effective Abortion Pills...
Abortion pills in Fujairah *((+971588192166*)☎️)¥) **Effective Abortion Pills...
 
AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Course Introducti...
AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Course Introducti...AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Course Introducti...
AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Course Introducti...
 
Attendance Tracking From Paper To Digital
Attendance Tracking From Paper To DigitalAttendance Tracking From Paper To Digital
Attendance Tracking From Paper To Digital
 
Google ML-Kit - Understanding on-device machine learning
Google ML-Kit - Understanding on-device machine learningGoogle ML-Kit - Understanding on-device machine learning
Google ML-Kit - Understanding on-device machine learning
 
Discover the Power of ONEMONITAR: The Ultimate Mobile Spy App for Android Dev...
Discover the Power of ONEMONITAR: The Ultimate Mobile Spy App for Android Dev...Discover the Power of ONEMONITAR: The Ultimate Mobile Spy App for Android Dev...
Discover the Power of ONEMONITAR: The Ultimate Mobile Spy App for Android Dev...
 
introduction of Ansys software and basic and advance knowledge of modelling s...
introduction of Ansys software and basic and advance knowledge of modelling s...introduction of Ansys software and basic and advance knowledge of modelling s...
introduction of Ansys software and basic and advance knowledge of modelling s...
 
dachnug51 - All you ever wanted to know about domino licensing.pdf
dachnug51 - All you ever wanted to know about domino licensing.pdfdachnug51 - All you ever wanted to know about domino licensing.pdf
dachnug51 - All you ever wanted to know about domino licensing.pdf
 
Splunk_Remote_Work_Insights_Overview.pptx
Splunk_Remote_Work_Insights_Overview.pptxSplunk_Remote_Work_Insights_Overview.pptx
Splunk_Remote_Work_Insights_Overview.pptx
 
AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Final Course Know...
AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Final Course Know...AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Final Course Know...
AWS Cloud Practitioner Essentials (Second Edition) (Arabic) Final Course Know...
 
WEBINAR SLIDES: CCX for Cloud Service Providers
WEBINAR SLIDES: CCX for Cloud Service ProvidersWEBINAR SLIDES: CCX for Cloud Service Providers
WEBINAR SLIDES: CCX for Cloud Service Providers
 
Cisco Live Announcements: New ThousandEyes Release Highlights - July 2024
Cisco Live Announcements: New ThousandEyes Release Highlights - July 2024Cisco Live Announcements: New ThousandEyes Release Highlights - July 2024
Cisco Live Announcements: New ThousandEyes Release Highlights - July 2024
 
ThaiPy meetup - Indexes and Django
ThaiPy meetup - Indexes and DjangoThaiPy meetup - Indexes and Django
ThaiPy meetup - Indexes and Django
 
Break data silos with real-time connectivity using Confluent Cloud Connectors
Break data silos with real-time connectivity using Confluent Cloud ConnectorsBreak data silos with real-time connectivity using Confluent Cloud Connectors
Break data silos with real-time connectivity using Confluent Cloud Connectors
 
Leading Project Management Tool Taskruop.pptx
Leading Project Management Tool Taskruop.pptxLeading Project Management Tool Taskruop.pptx
Leading Project Management Tool Taskruop.pptx
 

Atelier - Innover avec l’IA Générative et les graphes de connaissances

  • 1. Graph Summit Paris, 5 juin 2024 Generative AI Workshop Nicolas Rouyer, Jean-Marc Guerin
  • 2. © 2024 Neo4j, Inc. All rights reserved. 2 Neo4j Gen AI Hands-on Lab with AWS AWS Office-Tour Carpe Diem, 31 place des Corolles, 92400 Courbevoie, France Thursday, June 6 13:30 CEST Registration:
  • 3. © 2024 Neo4j, Inc. All rights reserved. Workshop Rules Ask questions straight away, this is an interactive session Raise your hand if you are stuck Have fun 3
  • 4. © 2024 Neo4j, Inc. All rights reserved. Before We Start 1/ Create a blank Neo4j Sandbox at https://sandbox.neo4j.com 2/ Open the notebook in Colab (needs a google account!) 4 https://github.com/guerinjeanmarc/genai-workshop open genai-workshop.ipynb
  • 5. Neo4j Inc. All rights reserved 2024 5 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
  • 6. © 2024 Neo4j, Inc. All rights reserved. Retrieval-Augmented Generation Is Becoming an Industry Standard RAG augments LLMs by retrieving up-to-date, contextual external data to inform responses: Reduce hallucinations with verified data Provide domain-specific, relevant responses Enable traceability back to sources 6 Retrieval Augmented Generation Database of Truth
  • 7. © 2024 Neo4j, Inc. All rights reserved. 7 RAG with Neo4j Find similar documents and content Identify entities associated to content and patterns in connected data Improve & enrich GenAI insights. Discover new relationships and entities Unify vector search, knowledge graph and data science capabilities to improve RAG quality and effectiveness Vector Search Graph Data Science Knowledge Graph
  • 8. © 2024 Neo4j, Inc. All rights reserved. Today 8
  • 9. © 2024 Neo4j, Inc. All rights reserved. Today no chatbot 9
  • 10. © 2024 Neo4j, Inc. All rights reserved. Today 10
  • 11. © 2024 Neo4j, Inc. All rights reserved. Today 11 We are Choosing Clothes
  • 12. © 2024 Neo4j, Inc. All rights reserved. This is Eva For her birthday, Eva wants a Halter Neck Top How do you choose what to buy? 12
  • 13. © 2024 Neo4j, Inc. All rights reserved. This is Eva For her birthday, Eva wants a Halter Neck Top How do you choose what to buy? 1/ Get a list of Halter Neck Top 2/ Match the Halter Neck Top for Eva 3/ Accessorize or add another item 13
  • 14. © 2024 Neo4j, Inc. All rights reserved. At Scale: Let’s Build an AI Fashion Assistant This Requires: 1. Data: Kaggle H&M 2. Search & Retrieval 3. Context for Personalization 4. Recommendation Engine 5. LLM Powered Content Generator 14
  • 15. © 2024 Neo4j, Inc. All rights reserved. 15 Solution: LLMs and Knowledge Graphs Knowledge Context Enrichment Language Reasoning Creativity KGs LLMs + BETTER TOGETHER
  • 16. © 2024 Neo4j, Inc. All rights reserved. We'll Build a Targeted, Personalized Content Generator 16
  • 17. © 2024 Neo4j, Inc. All rights reserved. 17 Tools
  • 18. © 2024 Neo4j, Inc. All rights reserved. Journey 18 1 Graph Building (Kaggle H&M Dataset) 2 Vector Search (Initial Retrieval) 3 Semantic Search with Graph Patterns (Personalization) 4 Graph DS & ML (Recommendations) LLM Powered Content Generator & Fashion Assistant 5
  • 19. © 2024 Neo4j, Inc. All rights reserved. 19 1 Graph Building (Kaggle H&M Dataset) 2 Vector Search (Initial Retrieval) 3 Semantic Search with Graph Patterns (Personalization) 4 Graph DS & ML (Recommendations) LLM Powered Content Generator & Fashion Assistant 5
  • 20. © 2024 Neo4j, Inc. All rights reserved. Data Model 20
  • 21. © 2024 Neo4j, Inc. All rights reserved. Data Model 21 customerId tDat Colour name type group description
  • 22. © 2024 Neo4j, Inc. All rights reserved. Now We Can Start 1/ Create a Neo4j Sandbox at https://sandbox.neo4j.com 2/ Open the notebook in Colab (needs a google account!) 22 https://github.com/neo4j-product-examples/genai-workshop open genai-workshop.ipynb
  • 23. © 2024 Neo4j, Inc. All rights reserved. 1/ Graph Building 23 Stop before Vector Search
  • 24. © 2024 Neo4j, Inc. All rights reserved. 24 1 Graph Building (Kaggle H&M Dataset) 2 Vector Search (Initial Retrieval) 3 Semantic Search with Graph Patterns (Personalization) 4 Graph DS & ML (Recommendations) LLM Powered Content Generator & Fashion Assistant 5
  • 25. © 2024 Neo4j, Inc. All rights reserved. What are Embeddings? ● A type of data compression ● Transform messy data (text, images, audio, etc.) into a compact format for ML algorithms ● Most often numeric vectors (a.k.a arrays) with 100s or 1000s of elements ● Preserve information such that “similar” items have proportionally “similar” embedding vectors ● Similarity is measured with vector algorithms (cosine, euclidean, etc.) 25 Graph Graph Model Graph Vector Embeddings
  • 26. © 2024 Neo4j, Inc. All rights reserved. What Does “Similarity” Mean? It Depends: • Text Embeddings => Semantic Similarity, the meaning behind a text sequence • Graph Embeddings => similarity in position or structure in a graph-can have semantic meaning too 26
  • 27. © 2024 Neo4j, Inc. All rights reserved. What will we use embedding for? 1. (now) Vector search using text embeddings 2. (later) Recommendations using graph node embeddings 27
  • 28. © 2024 Neo4j, Inc. All rights reserved. Search & Vectors in Neo4j Neo4j makes search efficient through a variety of indexes including • Range: General index for predicates based on equality and range. Numeric, dates, etc. • Point: Predicts on geospatial points like distance bounding boxes, etc. • Text: Predicates on strings like contains, ends with, etc. • FullText: Text search based on tokenization and analyzers • Vector: ANN (Approximate Nearest Neighbor) search on vectors 28
  • 29. © 2024 Neo4j, Inc. All rights reserved. Vector search 29 “Halter neck top” Backless blouse Tie-back shirt Neck
  • 30. © 2024 Neo4j, Inc. All rights reserved. Vector search 30 “Halter neck top” Backless blouse Tie-back shirt Neck
  • 31. © 2024 Neo4j, Inc. All rights reserved. How is similarity measured 31 cosine direction / angle based vector point query nearest 4 Euclidean distance based The vector Index allow to query vectors on large dataset. It uses HNSW to perform k-ANN queries
  • 32. © 2024 Neo4j, Inc. All rights reserved. Vector search 32 “Halter neck top” Backless blouse Tie-back shirt Neck CREATE VECTOR INDEX db.index.vector.queryNodes
  • 33. © 2024 Neo4j, Inc. All rights reserved. Vector search 33 “Halter neck top” Backless blouse Tie-back shirt Neck CREATE VECTOR INDEX db.index.vector.queryNodes
  • 34. © 2024 Neo4j, Inc. All rights reserved. 2/ Vector Search 34 Stop before Semantic Search with Graph Patterns (Personalization)
  • 35. © 2024 Neo4j, Inc. All rights reserved. 35 1 Graph Building (Kaggle H&M Dataset) 2 Vector Search (Initial Retrieval) 3 Semantic Search with Graph Patterns (Personalization) 4 Graph DS & ML (Recommendations) LLM Powered Content Generator & Fashion Assistant 5
  • 36. © 2024 Neo4j, Inc. All rights reserved. Neo4j & Semantic Search 36 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 Pattern Matching Knowledge Graph DS/ML Vector Search Graph Database
  • 37. © 2024 Neo4j, Inc. All rights reserved. Semantic search with graph pattern 37
  • 38. © 2024 Neo4j, Inc. All rights reserved. Semantic search with graph pattern 38
  • 39. © 2024 Neo4j, Inc. All rights reserved. 3/ Semantic Search with Graph Patterns Personalization & Context 39 Stop before Graph Data Science & ML (Recommendations)
  • 40. © 2024 Neo4j, Inc. All rights reserved. 40 1 Graph Building (Kaggle H&M Dataset) 2 Vector Search (Initial Retrieval) 3 Semantic Search with Graph Patterns (Personalization) 4 Graph DS & ML (Recommendations) LLM Powered Content Generator & Fashion Assistant 5
  • 41. © 2024 Neo4j, Inc. All rights reserved. Pathfinding & Search Centrality Community Detection Machine Learning Link Prediction Similarity Embeddings And more … Over 65 pretuned, parallelized algorithms. Iterate fast with different data sets, models, and version trained models. Bring the context of your connected data into a format that other pipelines can ingest. 41 Improve Models And Answer Big Questions The Largest Catalog of Graph Algorithms Native Graph Catalog and Analytics Workspace Graph Embeddings for Machine Learning
  • 42. © 2024 Neo4j, Inc. All rights reserved. 42
  • 43. © 2024 Neo4j, Inc. All rights reserved. Node Embeddings The representation of nodes as low-dimensional vectors that summarize their graph position, the structure of their local graph neighborhood as well as any possible node features 43
  • 44. © 2024 Neo4j, Inc. All rights reserved. K-Nearest Neighbor (KNN) w/ Node Embeddings Draw connections between highly interconnected nodes and/or those that have similar roles in the graph 44 0.2 0.3 0.6 -0.6 0.1 0.4 0.5 -0.4 -0.1 0.5 0.4 -0.4
  • 45. © 2024 Neo4j, Inc. All rights reserved. 4/ Graph Data Science & ML Recommendations 45 Stop before LLM Powered Content Generator
  • 46. © 2024 Neo4j, Inc. All rights reserved. 46 1 Graph Building (Kaggle H&M Dataset) 2 Vector Search (Initial Retrieval) 3 Semantic Search with Graph Patterns (Personalization) 4 Graph DS & ML (Recommendations) LLM Powered Content Generator & Fashion Assistant 5
  • 47. © 2024 Neo4j, Inc. All rights reserved. 47 Online Retailers uses LLM and Knowledge Graph for Hyper-Personalized Customer Experiences Challenge: Scale generation of hyper-personalized customer experiences Solution: LLM application, backed by customer knowledge graph with their preferences, purchase history and other contextual data, to generate hyper-personalized email templates. LLM generates customizes email body based on customer’s unique context from Knowledge Graph Impact: Transform customer experiences through natural language personalization
  • 48. © 2024 Neo4j, Inc. All rights reserved. Prompting the LLM You are a personal assistant named Sally for a fashion, home, and beauty company called HRM. write an email to {customerName}, one of your customers, to promote and summarize products relevant for them given the current season / time of year: {timeOfYear} . Please only mention the products listed below. Do not come up with or add any new products to the list. Each product comes with an https `url` field. Make sure to provide that https url with descriptive name text in markdown for each product. --- # Relevant Products: {searchProds} # Customer May Also Be Interested In the following (pick items from here that pair with the above products well for the current season / time of year: {timeOfYear}. prioritize those higher in the list if possible): {recProds} --- 48
  • 49. © 2024 Neo4j, Inc. All rights reserved. Langchain Chain 49 customer_id searchPrompt Personalized search Reco timeOfYear customerName prompt llm personalized email {searchProds: searchPrompt | personalizedSearch (customer_id) recProds: customer_id | recommendations customerName timeOfYear} prompt | llm | OutputParser searchProds recProds
  • 50. © 2024 Neo4j, Inc. All rights reserved. 4/ LLM Powered Fashion Assistant LLM For Generating Grounded Content 50
  • 51. © 2024 Neo4j, Inc. All rights reserved. Real-World GenAI Breakthroughs Powered by Neo4j 51 Integrating AI with knowledge graphs for smarter supply chain management Merging structured and unstructured data for efficient operations Converting vast amounts of unstructured data into actionable knowledge Leveraging AI for customized content at scale
  • 52. © 2024 Neo4j, Inc. All rights reserved. 1,700+ Organizations Use Neo4j 52 Banking & Financial Services Technology Telecommunications Energy E-Commerce Health & Life Sciences
  • 53. © 2024 Neo4j, Inc. All rights reserved. Thank you! 53
  • 54. © 2024 Neo4j, Inc. All rights reserved. Neo4j Gen AI Hands-on Lab with AWS AWS Office-Tour Carpe Diem, 31 place des Corolles, 92400 Courbevoie, France Thursday, June 6 13:30 CEST Registration: