SlideShare a Scribd company logo
© 2024 Neo4j, Inc. All rights reserved.
Generative AI
workshop
Marco Bessi-Milano 2024/05/14
1
© 2024 Neo4j, Inc. All rights reserved.
EMEA
PreSale
Team
Computer
Science
PhD
Marco Bessi (he/him/his)
(Marco) -[:LIVES_IN]-> (Prato,Italy)
(Marco) -[:HAS_PHD]-> (ComputerScience PhD)
(ComputerScience PhD) -[:AT]-> (PoliMI)
(Marco) -[:IS_PART_OF]-> (EMEA PreSaleTeam)
(EMEA PreSaleTeam) -[:AT]-> (Neo4j)
Prato,
Italy
PoliMI
2
Your friendly instructor
© 2024 Neo4j, Inc. All rights reserved.
Code of Conduct
● Speak up or be quiet forever. Seriously, this is supposed to
be an interactive session (you could have stayed home and
watched the video afterwards otherwise ;-).
● If you are stuck, ask for help. Don't worry too much about it
though, you will get all the materials and can go through
them at your own pace afterwards.
● Bear with us when (not if ;-) technology fails.
● Have fun!
3
© 2023 Neo4j, Inc. All rights reserved. © 2024 Neo4j, Inc. All rights reserved.
WIFI Access: WIFI-Name: neo4j | Password: graphsummit24
Restrooms: Out of the room and to
In the foyer area
Chargers:
the left the right straight ahead
under on top under the table in first three rows
x
4
x
Logistics
© 2024 Neo4j, Inc. All rights reserved.
Practical
1. Jupyter Notebook
Browse to https://bit.ly/neo4j-gs-milano
Log on with your attendeeXX, password
attendeeXX (with the XX provided to you)
2. Neo4j Browser
We'll get to that from the Notebook, username
and password will be the same.
5
© 2024 Neo4j, Inc. All rights reserved.
Why are you in
THIS workshop?
6
© 2024 Neo4j, Inc. All rights reserved.
Quick poll (by show of hands)
7
© 2024 Neo4j, Inc. All rights reserved.
AI is critical to the success of my
company over the next 5 years
8
© 2024 Neo4j, Inc. All rights reserved.
Results
94% of business leaders agreed with that statement in
october 2022 (Deloitte study)!
9
That actually wasn't the thing about that report that I found
interesting.
© 2024 Neo4j, Inc. All rights reserved.
This is
10
© 2024 Neo4j, Inc. All rights reserved. 11
Managing AI risk
is the biggest
barrier to scaling
AI initiatives1
Widespread Hesitancy: Over half of business leaders
currently discourage adoption of genAI.2
Lack of Explainability: Over 80% of executives worry
the non-transparent nature of genAI could result in poor
or unlawful decisions.2
Risk of Inaccuracy : Inaccuracy and hallucination are two
of the most-cited risks of adopting genAI technology at all
levels of an organization.3
1. Deloitte’s State of AI in the Enterprise 2. BCG’s Digital Acceleration Index Study 2023 3. McKinsey: The state of AI in 2023
© 2024 Neo4j, Inc. All rights reserved. 12
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
Retrieval Augmented Generation
Database of Truth
© 2024 Neo4j, Inc. All rights reserved. 13
Why RAG with vector databases
fall short
Database of Truth
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
© 2024 Neo4j, Inc. All rights reserved.
RAG with
14
Find similar documents
and content
Identify entities
associated to content and
patterns
in connected data
Improve GenAI inferences
and 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. 15
Today
© 2024 Neo4j, Inc. All rights reserved.
Today
we are choosing
clothes
16
© 2024 Neo4j, Inc. All rights reserved.
For cousin Nina
Nina likes t-shirts
17
© 2024 Neo4j, Inc. All rights reserved.
Traditional approach
● Line up options
● Let Nina pick
● Add some
accessories
18
That works, but what if
Nina isn't there, what if
you want to buy Nina a
present?
© 2024 Neo4j, Inc. All rights reserved.
The mission - a graph based AI
shopping/fashion assistant
because Nina is worth it
19
Steps
Knowledge graph building
Semantic search
Personalised search
Recommendation engine
Fashion assistant
© 2024 Neo4j, Inc. All rights reserved.
Tools
20
© 2024 Neo4j, Inc. All rights reserved.
Knowledge
graph building
21
© 2024 Neo4j, Inc. All rights reserved.
Dataset
H&M personalized fashion recommendations
https://www.kaggle.com/competitions/h-and-m-personalized-
fashion-recommendations/data
Changes
● Normalized into a graph model (coming right up)
● Added random (!) names
22
© 2024 Neo4j, Inc. All rights reserved.
Model (labels and types)
23
© 2024 Neo4j, Inc. All rights reserved.
Model (properties)
24
© 2024 Neo4j, Inc. All rights reserved.
Hammer Time
● Go to the Jupyter Lab environment and open the
genai_workshop.ipynb file.
We'll run it together, step by step
● For those not familiar with notebooks, when you run a step,
please wait for the [*] to turn into a [<number>], most steps
will also have output to look at.
● If you want to run ahead, please wait at the point where we
will switch to the Neo4j Browser (that's just before Vector
Search).
25
© 2024 Neo4j, Inc. All rights reserved.
Exploring the graph
In the notebook, click the link to open the Neo4j Browser at
https://browser.neo4j.io
Connect url: neo4j+s://milano-gs-db.graphdatabase.ninja:443
Username: attendeeXX
Password: attendeeXX
26
© 2024 Neo4j, Inc. All rights reserved.
Executing a browser guide
● Cut and paste the browser guide link (:play included) from
the notebook.
● Execute with the blue arrow.
27
© 2024 Neo4j, Inc. All rights reserved.
Executing a browser guide
● Cut and paste the browser guide link (:play included) from
the notebook.
● Execute with the blue arrow.
28
© 2024 Neo4j, Inc. All rights reserved.
One is one and all alone
Find a single person by id
29
MATCH (c:Customer WHERE c.id =
"daae10780ecd14990ea190a1e9917da33fe96cd8cfa5e80b67b4600171aa77e0")
RETURN c;
001
Find a single person by name
MATCH (c:Customer WHERE c.name = "Nina Massey")
RETURN c;
002
© 2024 Neo4j, Inc. All rights reserved.
And it's a customer
30
Find a single customer by name
MATCH sg=(c:Customer)-[:PURCHASED]->(:Article)
WHERE c.name = "Nina Massey"
RETURN sg;
003
© 2024 Neo4j, Inc. All rights reserved.
And that's not without value
It may so far not look interesting, but just with this data we
could determine
● How loyal a customer Nina is
● How big a spender Nina is
● What Nina's favourite colours are
● …
Let's try the colours.
31
© 2024 Neo4j, Inc. All rights reserved.
Showing your true colours
32
Find Nina's favourite colours
MATCH (c:Customer)-[:PURCHASED]->(a:Article)
WHERE c.name = "Nina Massey"
RETURN a.colour AS colour, count(*) AS occurences
ORDER BY occurences DESC;
004
© 2024 Neo4j, Inc. All rights reserved.
From article to product
33
Buying products
MATCH
sg=(c:Customer)-[:PURCHASED]->(:Article)-[:VARIANT_OF]->(:Product)
WHERE c.name = "Nina Massey"
RETURN sg;
005
© 2024 Neo4j, Inc. All rights reserved.
More value
It may still not look very exciting but now we can determine
● Which products Nina has bought multiple times
→ and maybe if that coincided with a promotion
● In which order products are bought
→ and maybe if there is a pattern there that we can also
find with other customers
● …
34
© 2024 Neo4j, Inc. All rights reserved.
Compulsive buying
35
Find Nina's favourite products
MATCH
(c:Customer)-[:PURCHASED]->(:Article)-[:VARIANT_OF]->(p:Product)
WHERE c.name = "Nina Massey"
RETURN p.name AS productname, count(*) AS occurences
ORDER BY occurences DESC;
006
© 2024 Neo4j, Inc. All rights reserved.
Location, location, location
36
Where to find Nina
MATCH
sg=(c:Customer)-[:PURCHASED]->(:Article)-[:LOCATED_IN]->(:Department)
WHERE c.name = "Nina Massey"
RETURN sg;
007
© 2024 Neo4j, Inc. All rights reserved.
Semantic
search
37
© 2024 Neo4j, Inc. All rights reserved.
Vector
● an arrow
● direction and magnitude (strength)
38
© 2024 Neo4j, Inc. All rights reserved.
Vector - array of numbers
● is a way to quantify the direction and magnitude in numbers
● for example in a 2D space, x may indicate the horizontal
direction, y the vertical direction and the magnitude is
calculated by the formula
39
© 2024 Neo4j, Inc. All rights reserved.
Vector - embedding
● represent complex data in a dense numerical form
● embed the data in a high-dimensional space where similar
data is close together
Whilst these vectors can be huge (OpenAI now has a 3072
dimension embedding model), this is nothing compared to the
complexity of what they embed.
An embedding is a-massive-dimension reduction.
40
© 2024 Neo4j, Inc. All rights reserved.
Vector - similarity
Euclidean-distance based
41
vector point
query
nearest 4
Cosine-direction based
© 2024 Neo4j, Inc. All rights reserved.
Vector - index
Neo4j implements the Hierarchical Navigable Small World
algorithm to do efficient k-ANN (approximate nearest
neighbours) searches.
42
Backless
blouse
Tie-back
shirt
Sleeve-
less crop
CREATE VECTOR INDEX …
© 2024 Neo4j, Inc. All rights reserved.
Vector - search
43
“Halter neck top”
CALL db.index.vector.queryNodes …
© 2024 Neo4j, Inc. All rights reserved.
Just so it's clear
A full text index search can not find King unless King is in the
text. Context is largely ignored.
A vector index search will find Queen, Prince, Baron, Warlord,
<and so on> to be to some degree similar to what you asked
but might also weave in some unexpected results. Context is-
well-King.
44
© 2024 Neo4j, Inc. All rights reserved.
Hammer Time
● Go back to the Jupyter Lab environment.
We'll continue to run it together, step by step
● If you want to run ahead, please wait at the point where we
will switch to the Neo4j Browser again (that's just after the
Semantic Search with Context heading).
45
© 2024 Neo4j, Inc. All rights reserved.
Personalised
search
46
© 2024 Neo4j, Inc. All rights reserved.
Executing a browser guide
● Cut and paste the browser guide link (:play included) from
the notebook.
● Execute with the blue arrow.
47
© 2024 Neo4j, Inc. All rights reserved.
Executing a browser guide
● Cut and paste the browser guide link (:play included) from
the notebook.
● Execute with the blue arrow.
48
© 2024 Neo4j, Inc. All rights reserved.
HisHer story
Purchase history of a single customer
49
MATCH
(c:Customer)-[pc:PURCHASED]->(:Article)-[:VARIANT_OF]->(p:Product)
WHERE c.name = "Nina Massey"
RETURN c.name AS name,
pc.transactiondate AS transactiondate,
p.name AS product,
p.description AS description
ORDER BY transactiondate DESC;
001
© 2024 Neo4j, Inc. All rights reserved.
Nina won the lottery
Shopping spree
50
MATCH
(c:Customer)-[pc:PURCHASED]->(:Article)-[:VARIANT_OF]->(p:Product)
WHERE c.name = "Nina Massey"
RETURN c.name AS name,
pc.transactiondate AS transactiondate,
collect(p.name) AS spree
ORDER BY size(spree) DESC;
002
© 2024 Neo4j, Inc. All rights reserved.
Double trouble
Eliminate doubles
51
MATCH
(c:Customer)-[pc:PURCHASED]->(:Article)-[:VARIANT_OF]->(p:Product)
WHERE c.name = "Nina Massey"
RETURN c.name AS name,
pc.transactiondate AS transactiondate,
collect(DISTINCT p.name) AS spree
ORDER BY size(spree) DESC;
003
© 2024 Neo4j, Inc. All rights reserved.
WITH or without you
Pipeline building
52
MATCH
(c:Customer)-[pc:PURCHASED]->(:Article)-[:VARIANT_OF]->(p:Product)
WHERE c.name = "Nina Massey"
WITH c.name AS name,
pc.transactiondate AS transactiondate,
collect(DISTINCT p.name) AS spree
ORDER BY size(spree) DESC LIMIT 1
RETURN transactiondate AS dateofinterest;
004
© 2024 Neo4j, Inc. All rights reserved.
Similar customers also buy X (part one)
53
// determine the date of interest
MATCH
(c:Customer)-[pc:PURCHASED]->(:Article)-[:VARIANT_OF]->(p:Product)
WHERE c.name = "Nina Massey"
WITH c.name AS name,
pc.transactiondate AS dateofinterest,
collect(DISTINCT p.name) AS spree
ORDER BY size(spree) DESC LIMIT 1;
...
005
© 2024 Neo4j, Inc. All rights reserved.
Similar customers also buy X (part two)
54
...
// what other products do customers buy
MATCH
(c)-[pc:PURCHASED]->(:Article)<-[:PURCHASED]-(:Customer)-[:PURCHASED]
->(:Article)-[:VARIANT_OF]->(p:Product)
WHERE pc.transactiondate = dateofinterest
RETURN p.name AS product,
count(*) AS commonPurchaseScore,
p.description AS description
ORDER BY commonPurchaseScore DESC;
005
© 2024 Neo4j, Inc. All rights reserved.
I know, I know
that a lot of time today is spend on working with the
knowledge graph, with the data.
55
But then there are also lot of questions along the lines of
● Why should I integrate a knowledge graph with the LLM,
have you seen the results of what <latest model> can do?
→ yes indeed and they are often crap if you dig just below the
surface
© 2024 Neo4j, Inc. All rights reserved.
I know, I know
that a lot of time today is spend on working with the
knowledge graph, with the data.
56
Or rants along the lines of
● You should provide proof and benchmarks that integrating
a knowledge graph with the LLM provides better results!
→ yes indeed and we do but what's the point if you do not
understand the value of a knowledge graph to start with
© 2024 Neo4j, Inc. All rights reserved.
Hammer Time
● Go back to the Jupyter Lab environment.
We'll continue to run it together, step by step
● If you want to run ahead, please wait at Augmenting
Semantic Search with Knowledge Graph Inference & ML.
57
© 2024 Neo4j, Inc. All rights reserved.
Recommendation
engine
58
© 2024 Neo4j, Inc. All rights reserved.
Graph Transactional
So far we always queried the graph database in the following
fashion
● Find starting point (Nina)
● Walk the graph from the starting point
● Stay local to the starting point
→ This is what is called graph transactional querying, used in
hundreds of real time use cases.
59
© 2024 Neo4j, Inc. All rights reserved.
Graph Data Science
You can also consider the graph as a whole and there are many
algorithms that do that
● (Lary) Pagerank
● (Edsger) Dijkstra's pathfinding
● (Vincent) Blondel's Louvain community detection
● <many others>
→ This is what is called graph data science, used in hundreds
of analytical use cases and to enhance the graph for the real
time use cases.
60
© 2024 Neo4j, Inc. All rights reserved.
Our overview
61
© 2024 Neo4j, Inc. All rights reserved.
Remember this?
62
© 2024 Neo4j, Inc. All rights reserved.
It actually looks like this now
63
© 2024 Neo4j, Inc. All rights reserved.
And we want it to look like this
64
© 2024 Neo4j, Inc. All rights reserved.
And we want it to look like this
65
© 2024 Neo4j, Inc. All rights reserved.
Hammer Time
● Go back to the Jupyter Lab environment.
We'll continue to run it together, step by step
● If you want to run ahead, please wait at LLM For Generating
Grounded Content.
66
© 2024 Neo4j, Inc. All rights reserved.
Just so it's clear
There are several possible approaches to create the
CUSTOMERS_ALSO_LIKE relationship. The embedding is
definitely not the easiest ;-), but
● fits the context (earlier on we saw text embeddings, now we
used node embeddings)
● allows the inclusion of properties (even though we didn't do
that)
Important to understand is that the similarity here is based on
what was bought together, not on what the article is!
67
© 2024 Neo4j, Inc. All rights reserved.
Fashion
Assistant
68
© 2024 Neo4j, Inc. All rights reserved.
Pulling it all together
So far you have done
a vector search
and enhanced that
with a personalized search
and you also know what you could recommend.
69
Allow me to introduce you to our AI Fashion Assistant Sam,
who will combine all your hard work. Sam is pretty new to this
though and needs a bit of prompting.
© 2024 Neo4j, Inc. All rights reserved.
Prompting Sam
You are a personal assistant named Sam 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}
---
70
© 2024 Neo4j, Inc. All rights reserved.
Sam's insides
71
© 2024 Neo4j, Inc. All rights reserved.
Sam's insides
72
Personalized Search
Recommendations
Personal information
search prompt
customer id
time of year
© 2024 Neo4j, Inc. All rights reserved.
Hammer Time
● Go back to the Jupyter Lab environment.
We'll continue to run it together to the end, step by step
73
© 2024 Neo4j, Inc. All rights reserved.
Resources
Original session:
https://github.com/neo4j-product-examples/genai-workshop
Today's session:
https://github.com/tomgeudens/jupyter-notebooks/tree/main/genaihm
Today's data:
https://github.com/tomgeudens/trainingdata/tree/main/genaihm
74
© 2024 Neo4j, Inc. All rights reserved.
Thank You!
marco.bessi@neo4j.com
75

More Related Content

Similar to Workshop: Enabling GenAI Breakthroughs with Knowledge Graphs - GraphSummit Milan

The Knowledge Graph Explosion
The Knowledge Graph ExplosionThe Knowledge Graph Explosion
The Knowledge Graph Explosion
Neo4j
 
Keynote Presentation at GraphTalk Oslo 2023
Keynote Presentation at GraphTalk Oslo 2023Keynote Presentation at GraphTalk Oslo 2023
Keynote Presentation at GraphTalk Oslo 2023
Neo4j
 
Atelier - Innover avec l’IA Générative et les graphes de connaissances
Atelier - Innover avec l’IA Générative et les graphes de connaissancesAtelier - Innover avec l’IA Générative et les graphes de connaissances
Atelier - Innover avec l’IA Générative et les graphes de connaissances
Neo4j
 
Workshop - Architecting Innovative Graph Applications- GraphSummit Milan
Workshop -  Architecting Innovative Graph Applications- GraphSummit MilanWorkshop -  Architecting Innovative Graph Applications- GraphSummit Milan
Workshop - Architecting Innovative Graph Applications- GraphSummit Milan
Neo4j
 
Modeling Cybersecurity with Neo4j, Based on Real-Life Data Insights
Modeling Cybersecurity with Neo4j, Based on Real-Life Data InsightsModeling Cybersecurity with Neo4j, Based on Real-Life Data Insights
Modeling Cybersecurity with Neo4j, Based on Real-Life Data Insights
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
 
OB Term 1_Group 8_Gig Work_v0.01_TT.pptx
OB Term 1_Group 8_Gig Work_v0.01_TT.pptxOB Term 1_Group 8_Gig Work_v0.01_TT.pptx
OB Term 1_Group 8_Gig Work_v0.01_TT.pptx
JayanthSaiSivanandB
 
Training Series - Intro to Neo4j
Training Series - Intro to Neo4jTraining Series - Intro to Neo4j
Training Series - Intro to Neo4j
Neo4j
 
Best Practices for Embedding Analytics by GoodData Product Leader
Best Practices for Embedding Analytics by GoodData Product LeaderBest Practices for Embedding Analytics by GoodData Product Leader
Best Practices for Embedding Analytics by GoodData Product Leader
Product School
 
Design Systems - Siili collective
Design Systems - Siili collectiveDesign Systems - Siili collective
Design Systems - Siili collective
Tomi Sjöblom
 
Agile Chennai 2023 | AI-Powered Agile : Transforming How We Deliver Extraordi...
Agile Chennai 2023 | AI-Powered Agile : Transforming How We Deliver Extraordi...Agile Chennai 2023 | AI-Powered Agile : Transforming How We Deliver Extraordi...
Agile Chennai 2023 | AI-Powered Agile : Transforming How We Deliver Extraordi...
AgileNetwork
 
Rocking the Digital Workplace
Rocking the Digital WorkplaceRocking the Digital Workplace
Rocking the Digital Workplace
Cynthia Clay
 
Rocking the Digital Workplace
Rocking the Digital Workplace Rocking the Digital Workplace
Rocking the Digital Workplace
Cynthia Clay
 
Emil Eifrém - The Data Platform for Today’s Intelligent Applications
Emil Eifrém - The Data Platform for Today’s Intelligent ApplicationsEmil Eifrém - The Data Platform for Today’s Intelligent Applications
Emil Eifrém - The Data Platform for Today’s Intelligent Applications
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
 
2018/2019 Global CAD Trends Survey Report - by Business Advantage v3.0
2018/2019 Global CAD Trends Survey Report - by Business Advantage v3.02018/2019 Global CAD Trends Survey Report - by Business Advantage v3.0
2018/2019 Global CAD Trends Survey Report - by Business Advantage v3.0
Business Advantage
 
TheKnowledgeGraphExplosion_Natarajan.pdf
TheKnowledgeGraphExplosion_Natarajan.pdfTheKnowledgeGraphExplosion_Natarajan.pdf
TheKnowledgeGraphExplosion_Natarajan.pdf
Neo4j
 
By Thoughtworks | Building data as a product: The key to unlocking Data Mesh'...
By Thoughtworks | Building data as a product: The key to unlocking Data Mesh'...By Thoughtworks | Building data as a product: The key to unlocking Data Mesh'...
By Thoughtworks | Building data as a product: The key to unlocking Data Mesh'...
IngridBuenaventura
 
Government GraphSummit: Keynote - Graphs in Government
Government GraphSummit: Keynote - Graphs in GovernmentGovernment GraphSummit: Keynote - Graphs in Government
Government GraphSummit: Keynote - Graphs in Government
Neo4j
 
A Universe of Knowledge Graphs
A Universe of Knowledge GraphsA Universe of Knowledge Graphs
A Universe of Knowledge Graphs
Neo4j
 

Similar to Workshop: Enabling GenAI Breakthroughs with Knowledge Graphs - GraphSummit Milan (20)

The Knowledge Graph Explosion
The Knowledge Graph ExplosionThe Knowledge Graph Explosion
The Knowledge Graph Explosion
 
Keynote Presentation at GraphTalk Oslo 2023
Keynote Presentation at GraphTalk Oslo 2023Keynote Presentation at GraphTalk Oslo 2023
Keynote Presentation at GraphTalk Oslo 2023
 
Atelier - Innover avec l’IA Générative et les graphes de connaissances
Atelier - Innover avec l’IA Générative et les graphes de connaissancesAtelier - Innover avec l’IA Générative et les graphes de connaissances
Atelier - Innover avec l’IA Générative et les graphes de connaissances
 
Workshop - Architecting Innovative Graph Applications- GraphSummit Milan
Workshop -  Architecting Innovative Graph Applications- GraphSummit MilanWorkshop -  Architecting Innovative Graph Applications- GraphSummit Milan
Workshop - Architecting Innovative Graph Applications- GraphSummit Milan
 
Modeling Cybersecurity with Neo4j, Based on Real-Life Data Insights
Modeling Cybersecurity with Neo4j, Based on Real-Life Data InsightsModeling Cybersecurity with Neo4j, Based on Real-Life Data Insights
Modeling Cybersecurity with Neo4j, Based on Real-Life Data Insights
 
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
 
OB Term 1_Group 8_Gig Work_v0.01_TT.pptx
OB Term 1_Group 8_Gig Work_v0.01_TT.pptxOB Term 1_Group 8_Gig Work_v0.01_TT.pptx
OB Term 1_Group 8_Gig Work_v0.01_TT.pptx
 
Training Series - Intro to Neo4j
Training Series - Intro to Neo4jTraining Series - Intro to Neo4j
Training Series - Intro to Neo4j
 
Best Practices for Embedding Analytics by GoodData Product Leader
Best Practices for Embedding Analytics by GoodData Product LeaderBest Practices for Embedding Analytics by GoodData Product Leader
Best Practices for Embedding Analytics by GoodData Product Leader
 
Design Systems - Siili collective
Design Systems - Siili collectiveDesign Systems - Siili collective
Design Systems - Siili collective
 
Agile Chennai 2023 | AI-Powered Agile : Transforming How We Deliver Extraordi...
Agile Chennai 2023 | AI-Powered Agile : Transforming How We Deliver Extraordi...Agile Chennai 2023 | AI-Powered Agile : Transforming How We Deliver Extraordi...
Agile Chennai 2023 | AI-Powered Agile : Transforming How We Deliver Extraordi...
 
Rocking the Digital Workplace
Rocking the Digital WorkplaceRocking the Digital Workplace
Rocking the Digital Workplace
 
Rocking the Digital Workplace
Rocking the Digital Workplace Rocking the Digital Workplace
Rocking the Digital Workplace
 
Emil Eifrém - The Data Platform for Today’s Intelligent Applications
Emil Eifrém - The Data Platform for Today’s Intelligent ApplicationsEmil Eifrém - The Data Platform for Today’s Intelligent Applications
Emil Eifrém - The Data Platform for Today’s Intelligent Applications
 
Deeper Insights with Graph Data Science
Deeper Insights with Graph Data ScienceDeeper Insights with Graph Data Science
Deeper Insights with Graph Data Science
 
2018/2019 Global CAD Trends Survey Report - by Business Advantage v3.0
2018/2019 Global CAD Trends Survey Report - by Business Advantage v3.02018/2019 Global CAD Trends Survey Report - by Business Advantage v3.0
2018/2019 Global CAD Trends Survey Report - by Business Advantage v3.0
 
TheKnowledgeGraphExplosion_Natarajan.pdf
TheKnowledgeGraphExplosion_Natarajan.pdfTheKnowledgeGraphExplosion_Natarajan.pdf
TheKnowledgeGraphExplosion_Natarajan.pdf
 
By Thoughtworks | Building data as a product: The key to unlocking Data Mesh'...
By Thoughtworks | Building data as a product: The key to unlocking Data Mesh'...By Thoughtworks | Building data as a product: The key to unlocking Data Mesh'...
By Thoughtworks | Building data as a product: The key to unlocking Data Mesh'...
 
Government GraphSummit: Keynote - Graphs in Government
Government GraphSummit: Keynote - Graphs in GovernmentGovernment GraphSummit: Keynote - Graphs in Government
Government GraphSummit: Keynote - Graphs in Government
 
A Universe of Knowledge Graphs
A Universe of Knowledge GraphsA Universe of Knowledge Graphs
A Universe of Knowledge Graphs
 

More from 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 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
 
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
 
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
 
Your enemies use GenAI too - staying ahead of fraud with Neo4j
Your enemies use GenAI too - staying ahead of fraud with Neo4jYour enemies use GenAI too - staying ahead of fraud with Neo4j
Your enemies use GenAI too - staying ahead of fraud with Neo4j
Neo4j
 

More from Neo4j (20)

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 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
 
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
 
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
 
Your enemies use GenAI too - staying ahead of fraud with Neo4j
Your enemies use GenAI too - staying ahead of fraud with Neo4jYour enemies use GenAI too - staying ahead of fraud with Neo4j
Your enemies use GenAI too - staying ahead of fraud with Neo4j
 

Recently uploaded

TMU毕业证书精仿办理
TMU毕业证书精仿办理TMU毕业证书精仿办理
TMU毕业证书精仿办理
aeeva
 
The Role of DevOps in Digital Transformation.pdf
The Role of DevOps in Digital Transformation.pdfThe Role of DevOps in Digital Transformation.pdf
The Role of DevOps in Digital Transformation.pdf
mohitd6
 
Upturn India Technologies - Web development company in Nashik
Upturn India Technologies - Web development company in NashikUpturn India Technologies - Web development company in Nashik
Upturn India Technologies - Web development company in Nashik
Upturn India Technologies
 
All you need to know about Spring Boot and GraalVM
All you need to know about Spring Boot and GraalVMAll you need to know about Spring Boot and GraalVM
All you need to know about Spring Boot and GraalVM
Alina Yurenko
 
ppt on the brain chip neuralink.pptx
ppt  on   the brain  chip neuralink.pptxppt  on   the brain  chip neuralink.pptx
ppt on the brain chip neuralink.pptx
Reetu63
 
Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...
Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...
Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...
XfilesPro
 
Voxxed Days Trieste 2024 - Unleashing the Power of Vector Search and Semantic...
Voxxed Days Trieste 2024 - Unleashing the Power of Vector Search and Semantic...Voxxed Days Trieste 2024 - Unleashing the Power of Vector Search and Semantic...
Voxxed Days Trieste 2024 - Unleashing the Power of Vector Search and Semantic...
Luigi Fugaro
 
Manyata Tech Park Bangalore_ Infrastructure, Facilities and More
Manyata Tech Park Bangalore_ Infrastructure, Facilities and MoreManyata Tech Park Bangalore_ Infrastructure, Facilities and More
Manyata Tech Park Bangalore_ Infrastructure, Facilities and More
narinav14
 
Boost Your Savings with These Money Management Apps
Boost Your Savings with These Money Management AppsBoost Your Savings with These Money Management Apps
Boost Your Savings with These Money Management Apps
Jhone kinadey
 
Operational ease MuleSoft and Salesforce Service Cloud Solution v1.0.pptx
Operational ease MuleSoft and Salesforce Service Cloud Solution v1.0.pptxOperational ease MuleSoft and Salesforce Service Cloud Solution v1.0.pptx
Operational ease MuleSoft and Salesforce Service Cloud Solution v1.0.pptx
sandeepmenon62
 
The Rising Future of CPaaS in the Middle East 2024
The Rising Future of CPaaS in the Middle East 2024The Rising Future of CPaaS in the Middle East 2024
The Rising Future of CPaaS in the Middle East 2024
Yara Milbes
 
Migration From CH 1.0 to CH 2.0 and Mule 4.6 & Java 17 Upgrade.pptx
Migration From CH 1.0 to CH 2.0 and  Mule 4.6 & Java 17 Upgrade.pptxMigration From CH 1.0 to CH 2.0 and  Mule 4.6 & Java 17 Upgrade.pptx
Migration From CH 1.0 to CH 2.0 and Mule 4.6 & Java 17 Upgrade.pptx
ervikas4
 
Optimizing Your E-commerce with WooCommerce.pptx
Optimizing Your E-commerce with WooCommerce.pptxOptimizing Your E-commerce with WooCommerce.pptx
Optimizing Your E-commerce with WooCommerce.pptx
WebConnect Pvt Ltd
 
Orca: Nocode Graphical Editor for Container Orchestration
Orca: Nocode Graphical Editor for Container OrchestrationOrca: Nocode Graphical Editor for Container Orchestration
Orca: Nocode Graphical Editor for Container Orchestration
Pedro J. Molina
 
How Can Hiring A Mobile App Development Company Help Your Business Grow?
How Can Hiring A Mobile App Development Company Help Your Business Grow?How Can Hiring A Mobile App Development Company Help Your Business Grow?
How Can Hiring A Mobile App Development Company Help Your Business Grow?
ToXSL Technologies
 
Penify - Let AI do the Documentation, you write the Code.
Penify - Let AI do the Documentation, you write the Code.Penify - Let AI do the Documentation, you write the Code.
Penify - Let AI do the Documentation, you write the Code.
KrishnaveniMohan1
 
美洲杯赔率投注网【​网址​🎉3977·EE​🎉】
美洲杯赔率投注网【​网址​🎉3977·EE​🎉】美洲杯赔率投注网【​网址​🎉3977·EE​🎉】
美洲杯赔率投注网【​网址​🎉3977·EE​🎉】
widenerjobeyrl638
 
Superpower Your Apache Kafka Applications Development with Complementary Open...
Superpower Your Apache Kafka Applications Development with Complementary Open...Superpower Your Apache Kafka Applications Development with Complementary Open...
Superpower Your Apache Kafka Applications Development with Complementary Open...
Paul Brebner
 
Baha Majid WCA4Z IBM Z Customer Council Boston June 2024.pdf
Baha Majid WCA4Z IBM Z Customer Council Boston June 2024.pdfBaha Majid WCA4Z IBM Z Customer Council Boston June 2024.pdf
Baha Majid WCA4Z IBM Z Customer Council Boston June 2024.pdf
Baha Majid
 

Recently uploaded (20)

TMU毕业证书精仿办理
TMU毕业证书精仿办理TMU毕业证书精仿办理
TMU毕业证书精仿办理
 
The Role of DevOps in Digital Transformation.pdf
The Role of DevOps in Digital Transformation.pdfThe Role of DevOps in Digital Transformation.pdf
The Role of DevOps in Digital Transformation.pdf
 
Upturn India Technologies - Web development company in Nashik
Upturn India Technologies - Web development company in NashikUpturn India Technologies - Web development company in Nashik
Upturn India Technologies - Web development company in Nashik
 
All you need to know about Spring Boot and GraalVM
All you need to know about Spring Boot and GraalVMAll you need to know about Spring Boot and GraalVM
All you need to know about Spring Boot and GraalVM
 
ppt on the brain chip neuralink.pptx
ppt  on   the brain  chip neuralink.pptxppt  on   the brain  chip neuralink.pptx
ppt on the brain chip neuralink.pptx
 
Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...
Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...
Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...
 
Voxxed Days Trieste 2024 - Unleashing the Power of Vector Search and Semantic...
Voxxed Days Trieste 2024 - Unleashing the Power of Vector Search and Semantic...Voxxed Days Trieste 2024 - Unleashing the Power of Vector Search and Semantic...
Voxxed Days Trieste 2024 - Unleashing the Power of Vector Search and Semantic...
 
Manyata Tech Park Bangalore_ Infrastructure, Facilities and More
Manyata Tech Park Bangalore_ Infrastructure, Facilities and MoreManyata Tech Park Bangalore_ Infrastructure, Facilities and More
Manyata Tech Park Bangalore_ Infrastructure, Facilities and More
 
Boost Your Savings with These Money Management Apps
Boost Your Savings with These Money Management AppsBoost Your Savings with These Money Management Apps
Boost Your Savings with These Money Management Apps
 
Operational ease MuleSoft and Salesforce Service Cloud Solution v1.0.pptx
Operational ease MuleSoft and Salesforce Service Cloud Solution v1.0.pptxOperational ease MuleSoft and Salesforce Service Cloud Solution v1.0.pptx
Operational ease MuleSoft and Salesforce Service Cloud Solution v1.0.pptx
 
The Rising Future of CPaaS in the Middle East 2024
The Rising Future of CPaaS in the Middle East 2024The Rising Future of CPaaS in the Middle East 2024
The Rising Future of CPaaS in the Middle East 2024
 
Migration From CH 1.0 to CH 2.0 and Mule 4.6 & Java 17 Upgrade.pptx
Migration From CH 1.0 to CH 2.0 and  Mule 4.6 & Java 17 Upgrade.pptxMigration From CH 1.0 to CH 2.0 and  Mule 4.6 & Java 17 Upgrade.pptx
Migration From CH 1.0 to CH 2.0 and Mule 4.6 & Java 17 Upgrade.pptx
 
Optimizing Your E-commerce with WooCommerce.pptx
Optimizing Your E-commerce with WooCommerce.pptxOptimizing Your E-commerce with WooCommerce.pptx
Optimizing Your E-commerce with WooCommerce.pptx
 
Orca: Nocode Graphical Editor for Container Orchestration
Orca: Nocode Graphical Editor for Container OrchestrationOrca: Nocode Graphical Editor for Container Orchestration
Orca: Nocode Graphical Editor for Container Orchestration
 
How Can Hiring A Mobile App Development Company Help Your Business Grow?
How Can Hiring A Mobile App Development Company Help Your Business Grow?How Can Hiring A Mobile App Development Company Help Your Business Grow?
How Can Hiring A Mobile App Development Company Help Your Business Grow?
 
bgiolcb
bgiolcbbgiolcb
bgiolcb
 
Penify - Let AI do the Documentation, you write the Code.
Penify - Let AI do the Documentation, you write the Code.Penify - Let AI do the Documentation, you write the Code.
Penify - Let AI do the Documentation, you write the Code.
 
美洲杯赔率投注网【​网址​🎉3977·EE​🎉】
美洲杯赔率投注网【​网址​🎉3977·EE​🎉】美洲杯赔率投注网【​网址​🎉3977·EE​🎉】
美洲杯赔率投注网【​网址​🎉3977·EE​🎉】
 
Superpower Your Apache Kafka Applications Development with Complementary Open...
Superpower Your Apache Kafka Applications Development with Complementary Open...Superpower Your Apache Kafka Applications Development with Complementary Open...
Superpower Your Apache Kafka Applications Development with Complementary Open...
 
Baha Majid WCA4Z IBM Z Customer Council Boston June 2024.pdf
Baha Majid WCA4Z IBM Z Customer Council Boston June 2024.pdfBaha Majid WCA4Z IBM Z Customer Council Boston June 2024.pdf
Baha Majid WCA4Z IBM Z Customer Council Boston June 2024.pdf
 

Workshop: Enabling GenAI Breakthroughs with Knowledge Graphs - GraphSummit Milan

  • 1. © 2024 Neo4j, Inc. All rights reserved. Generative AI workshop Marco Bessi-Milano 2024/05/14 1
  • 2. © 2024 Neo4j, Inc. All rights reserved. EMEA PreSale Team Computer Science PhD Marco Bessi (he/him/his) (Marco) -[:LIVES_IN]-> (Prato,Italy) (Marco) -[:HAS_PHD]-> (ComputerScience PhD) (ComputerScience PhD) -[:AT]-> (PoliMI) (Marco) -[:IS_PART_OF]-> (EMEA PreSaleTeam) (EMEA PreSaleTeam) -[:AT]-> (Neo4j) Prato, Italy PoliMI 2 Your friendly instructor
  • 3. © 2024 Neo4j, Inc. All rights reserved. Code of Conduct ● Speak up or be quiet forever. Seriously, this is supposed to be an interactive session (you could have stayed home and watched the video afterwards otherwise ;-). ● If you are stuck, ask for help. Don't worry too much about it though, you will get all the materials and can go through them at your own pace afterwards. ● Bear with us when (not if ;-) technology fails. ● Have fun! 3
  • 4. © 2023 Neo4j, Inc. All rights reserved. © 2024 Neo4j, Inc. All rights reserved. WIFI Access: WIFI-Name: neo4j | Password: graphsummit24 Restrooms: Out of the room and to In the foyer area Chargers: the left the right straight ahead under on top under the table in first three rows x 4 x Logistics
  • 5. © 2024 Neo4j, Inc. All rights reserved. Practical 1. Jupyter Notebook Browse to https://bit.ly/neo4j-gs-milano Log on with your attendeeXX, password attendeeXX (with the XX provided to you) 2. Neo4j Browser We'll get to that from the Notebook, username and password will be the same. 5
  • 6. © 2024 Neo4j, Inc. All rights reserved. Why are you in THIS workshop? 6
  • 7. © 2024 Neo4j, Inc. All rights reserved. Quick poll (by show of hands) 7
  • 8. © 2024 Neo4j, Inc. All rights reserved. AI is critical to the success of my company over the next 5 years 8
  • 9. © 2024 Neo4j, Inc. All rights reserved. Results 94% of business leaders agreed with that statement in october 2022 (Deloitte study)! 9 That actually wasn't the thing about that report that I found interesting.
  • 10. © 2024 Neo4j, Inc. All rights reserved. This is 10
  • 11. © 2024 Neo4j, Inc. All rights reserved. 11 Managing AI risk is the biggest barrier to scaling AI initiatives1 Widespread Hesitancy: Over half of business leaders currently discourage adoption of genAI.2 Lack of Explainability: Over 80% of executives worry the non-transparent nature of genAI could result in poor or unlawful decisions.2 Risk of Inaccuracy : Inaccuracy and hallucination are two of the most-cited risks of adopting genAI technology at all levels of an organization.3 1. Deloitte’s State of AI in the Enterprise 2. BCG’s Digital Acceleration Index Study 2023 3. McKinsey: The state of AI in 2023
  • 12. © 2024 Neo4j, Inc. All rights reserved. 12 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 Retrieval Augmented Generation Database of Truth
  • 13. © 2024 Neo4j, Inc. All rights reserved. 13 Why RAG with vector databases fall short Database of Truth 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
  • 14. © 2024 Neo4j, Inc. All rights reserved. RAG with 14 Find similar documents and content Identify entities associated to content and patterns in connected data Improve GenAI inferences and 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
  • 15. © 2024 Neo4j, Inc. All rights reserved. 15 Today
  • 16. © 2024 Neo4j, Inc. All rights reserved. Today we are choosing clothes 16
  • 17. © 2024 Neo4j, Inc. All rights reserved. For cousin Nina Nina likes t-shirts 17
  • 18. © 2024 Neo4j, Inc. All rights reserved. Traditional approach ● Line up options ● Let Nina pick ● Add some accessories 18 That works, but what if Nina isn't there, what if you want to buy Nina a present?
  • 19. © 2024 Neo4j, Inc. All rights reserved. The mission - a graph based AI shopping/fashion assistant because Nina is worth it 19 Steps Knowledge graph building Semantic search Personalised search Recommendation engine Fashion assistant
  • 20. © 2024 Neo4j, Inc. All rights reserved. Tools 20
  • 21. © 2024 Neo4j, Inc. All rights reserved. Knowledge graph building 21
  • 22. © 2024 Neo4j, Inc. All rights reserved. Dataset H&M personalized fashion recommendations https://www.kaggle.com/competitions/h-and-m-personalized- fashion-recommendations/data Changes ● Normalized into a graph model (coming right up) ● Added random (!) names 22
  • 23. © 2024 Neo4j, Inc. All rights reserved. Model (labels and types) 23
  • 24. © 2024 Neo4j, Inc. All rights reserved. Model (properties) 24
  • 25. © 2024 Neo4j, Inc. All rights reserved. Hammer Time ● Go to the Jupyter Lab environment and open the genai_workshop.ipynb file. We'll run it together, step by step ● For those not familiar with notebooks, when you run a step, please wait for the [*] to turn into a [<number>], most steps will also have output to look at. ● If you want to run ahead, please wait at the point where we will switch to the Neo4j Browser (that's just before Vector Search). 25
  • 26. © 2024 Neo4j, Inc. All rights reserved. Exploring the graph In the notebook, click the link to open the Neo4j Browser at https://browser.neo4j.io Connect url: neo4j+s://milano-gs-db.graphdatabase.ninja:443 Username: attendeeXX Password: attendeeXX 26
  • 27. © 2024 Neo4j, Inc. All rights reserved. Executing a browser guide ● Cut and paste the browser guide link (:play included) from the notebook. ● Execute with the blue arrow. 27
  • 28. © 2024 Neo4j, Inc. All rights reserved. Executing a browser guide ● Cut and paste the browser guide link (:play included) from the notebook. ● Execute with the blue arrow. 28
  • 29. © 2024 Neo4j, Inc. All rights reserved. One is one and all alone Find a single person by id 29 MATCH (c:Customer WHERE c.id = "daae10780ecd14990ea190a1e9917da33fe96cd8cfa5e80b67b4600171aa77e0") RETURN c; 001 Find a single person by name MATCH (c:Customer WHERE c.name = "Nina Massey") RETURN c; 002
  • 30. © 2024 Neo4j, Inc. All rights reserved. And it's a customer 30 Find a single customer by name MATCH sg=(c:Customer)-[:PURCHASED]->(:Article) WHERE c.name = "Nina Massey" RETURN sg; 003
  • 31. © 2024 Neo4j, Inc. All rights reserved. And that's not without value It may so far not look interesting, but just with this data we could determine ● How loyal a customer Nina is ● How big a spender Nina is ● What Nina's favourite colours are ● … Let's try the colours. 31
  • 32. © 2024 Neo4j, Inc. All rights reserved. Showing your true colours 32 Find Nina's favourite colours MATCH (c:Customer)-[:PURCHASED]->(a:Article) WHERE c.name = "Nina Massey" RETURN a.colour AS colour, count(*) AS occurences ORDER BY occurences DESC; 004
  • 33. © 2024 Neo4j, Inc. All rights reserved. From article to product 33 Buying products MATCH sg=(c:Customer)-[:PURCHASED]->(:Article)-[:VARIANT_OF]->(:Product) WHERE c.name = "Nina Massey" RETURN sg; 005
  • 34. © 2024 Neo4j, Inc. All rights reserved. More value It may still not look very exciting but now we can determine ● Which products Nina has bought multiple times → and maybe if that coincided with a promotion ● In which order products are bought → and maybe if there is a pattern there that we can also find with other customers ● … 34
  • 35. © 2024 Neo4j, Inc. All rights reserved. Compulsive buying 35 Find Nina's favourite products MATCH (c:Customer)-[:PURCHASED]->(:Article)-[:VARIANT_OF]->(p:Product) WHERE c.name = "Nina Massey" RETURN p.name AS productname, count(*) AS occurences ORDER BY occurences DESC; 006
  • 36. © 2024 Neo4j, Inc. All rights reserved. Location, location, location 36 Where to find Nina MATCH sg=(c:Customer)-[:PURCHASED]->(:Article)-[:LOCATED_IN]->(:Department) WHERE c.name = "Nina Massey" RETURN sg; 007
  • 37. © 2024 Neo4j, Inc. All rights reserved. Semantic search 37
  • 38. © 2024 Neo4j, Inc. All rights reserved. Vector ● an arrow ● direction and magnitude (strength) 38
  • 39. © 2024 Neo4j, Inc. All rights reserved. Vector - array of numbers ● is a way to quantify the direction and magnitude in numbers ● for example in a 2D space, x may indicate the horizontal direction, y the vertical direction and the magnitude is calculated by the formula 39
  • 40. © 2024 Neo4j, Inc. All rights reserved. Vector - embedding ● represent complex data in a dense numerical form ● embed the data in a high-dimensional space where similar data is close together Whilst these vectors can be huge (OpenAI now has a 3072 dimension embedding model), this is nothing compared to the complexity of what they embed. An embedding is a-massive-dimension reduction. 40
  • 41. © 2024 Neo4j, Inc. All rights reserved. Vector - similarity Euclidean-distance based 41 vector point query nearest 4 Cosine-direction based
  • 42. © 2024 Neo4j, Inc. All rights reserved. Vector - index Neo4j implements the Hierarchical Navigable Small World algorithm to do efficient k-ANN (approximate nearest neighbours) searches. 42 Backless blouse Tie-back shirt Sleeve- less crop CREATE VECTOR INDEX …
  • 43. © 2024 Neo4j, Inc. All rights reserved. Vector - search 43 “Halter neck top” CALL db.index.vector.queryNodes …
  • 44. © 2024 Neo4j, Inc. All rights reserved. Just so it's clear A full text index search can not find King unless King is in the text. Context is largely ignored. A vector index search will find Queen, Prince, Baron, Warlord, <and so on> to be to some degree similar to what you asked but might also weave in some unexpected results. Context is- well-King. 44
  • 45. © 2024 Neo4j, Inc. All rights reserved. Hammer Time ● Go back to the Jupyter Lab environment. We'll continue to run it together, step by step ● If you want to run ahead, please wait at the point where we will switch to the Neo4j Browser again (that's just after the Semantic Search with Context heading). 45
  • 46. © 2024 Neo4j, Inc. All rights reserved. Personalised search 46
  • 47. © 2024 Neo4j, Inc. All rights reserved. Executing a browser guide ● Cut and paste the browser guide link (:play included) from the notebook. ● Execute with the blue arrow. 47
  • 48. © 2024 Neo4j, Inc. All rights reserved. Executing a browser guide ● Cut and paste the browser guide link (:play included) from the notebook. ● Execute with the blue arrow. 48
  • 49. © 2024 Neo4j, Inc. All rights reserved. HisHer story Purchase history of a single customer 49 MATCH (c:Customer)-[pc:PURCHASED]->(:Article)-[:VARIANT_OF]->(p:Product) WHERE c.name = "Nina Massey" RETURN c.name AS name, pc.transactiondate AS transactiondate, p.name AS product, p.description AS description ORDER BY transactiondate DESC; 001
  • 50. © 2024 Neo4j, Inc. All rights reserved. Nina won the lottery Shopping spree 50 MATCH (c:Customer)-[pc:PURCHASED]->(:Article)-[:VARIANT_OF]->(p:Product) WHERE c.name = "Nina Massey" RETURN c.name AS name, pc.transactiondate AS transactiondate, collect(p.name) AS spree ORDER BY size(spree) DESC; 002
  • 51. © 2024 Neo4j, Inc. All rights reserved. Double trouble Eliminate doubles 51 MATCH (c:Customer)-[pc:PURCHASED]->(:Article)-[:VARIANT_OF]->(p:Product) WHERE c.name = "Nina Massey" RETURN c.name AS name, pc.transactiondate AS transactiondate, collect(DISTINCT p.name) AS spree ORDER BY size(spree) DESC; 003
  • 52. © 2024 Neo4j, Inc. All rights reserved. WITH or without you Pipeline building 52 MATCH (c:Customer)-[pc:PURCHASED]->(:Article)-[:VARIANT_OF]->(p:Product) WHERE c.name = "Nina Massey" WITH c.name AS name, pc.transactiondate AS transactiondate, collect(DISTINCT p.name) AS spree ORDER BY size(spree) DESC LIMIT 1 RETURN transactiondate AS dateofinterest; 004
  • 53. © 2024 Neo4j, Inc. All rights reserved. Similar customers also buy X (part one) 53 // determine the date of interest MATCH (c:Customer)-[pc:PURCHASED]->(:Article)-[:VARIANT_OF]->(p:Product) WHERE c.name = "Nina Massey" WITH c.name AS name, pc.transactiondate AS dateofinterest, collect(DISTINCT p.name) AS spree ORDER BY size(spree) DESC LIMIT 1; ... 005
  • 54. © 2024 Neo4j, Inc. All rights reserved. Similar customers also buy X (part two) 54 ... // what other products do customers buy MATCH (c)-[pc:PURCHASED]->(:Article)<-[:PURCHASED]-(:Customer)-[:PURCHASED] ->(:Article)-[:VARIANT_OF]->(p:Product) WHERE pc.transactiondate = dateofinterest RETURN p.name AS product, count(*) AS commonPurchaseScore, p.description AS description ORDER BY commonPurchaseScore DESC; 005
  • 55. © 2024 Neo4j, Inc. All rights reserved. I know, I know that a lot of time today is spend on working with the knowledge graph, with the data. 55 But then there are also lot of questions along the lines of ● Why should I integrate a knowledge graph with the LLM, have you seen the results of what <latest model> can do? → yes indeed and they are often crap if you dig just below the surface
  • 56. © 2024 Neo4j, Inc. All rights reserved. I know, I know that a lot of time today is spend on working with the knowledge graph, with the data. 56 Or rants along the lines of ● You should provide proof and benchmarks that integrating a knowledge graph with the LLM provides better results! → yes indeed and we do but what's the point if you do not understand the value of a knowledge graph to start with
  • 57. © 2024 Neo4j, Inc. All rights reserved. Hammer Time ● Go back to the Jupyter Lab environment. We'll continue to run it together, step by step ● If you want to run ahead, please wait at Augmenting Semantic Search with Knowledge Graph Inference & ML. 57
  • 58. © 2024 Neo4j, Inc. All rights reserved. Recommendation engine 58
  • 59. © 2024 Neo4j, Inc. All rights reserved. Graph Transactional So far we always queried the graph database in the following fashion ● Find starting point (Nina) ● Walk the graph from the starting point ● Stay local to the starting point → This is what is called graph transactional querying, used in hundreds of real time use cases. 59
  • 60. © 2024 Neo4j, Inc. All rights reserved. Graph Data Science You can also consider the graph as a whole and there are many algorithms that do that ● (Lary) Pagerank ● (Edsger) Dijkstra's pathfinding ● (Vincent) Blondel's Louvain community detection ● <many others> → This is what is called graph data science, used in hundreds of analytical use cases and to enhance the graph for the real time use cases. 60
  • 61. © 2024 Neo4j, Inc. All rights reserved. Our overview 61
  • 62. © 2024 Neo4j, Inc. All rights reserved. Remember this? 62
  • 63. © 2024 Neo4j, Inc. All rights reserved. It actually looks like this now 63
  • 64. © 2024 Neo4j, Inc. All rights reserved. And we want it to look like this 64
  • 65. © 2024 Neo4j, Inc. All rights reserved. And we want it to look like this 65
  • 66. © 2024 Neo4j, Inc. All rights reserved. Hammer Time ● Go back to the Jupyter Lab environment. We'll continue to run it together, step by step ● If you want to run ahead, please wait at LLM For Generating Grounded Content. 66
  • 67. © 2024 Neo4j, Inc. All rights reserved. Just so it's clear There are several possible approaches to create the CUSTOMERS_ALSO_LIKE relationship. The embedding is definitely not the easiest ;-), but ● fits the context (earlier on we saw text embeddings, now we used node embeddings) ● allows the inclusion of properties (even though we didn't do that) Important to understand is that the similarity here is based on what was bought together, not on what the article is! 67
  • 68. © 2024 Neo4j, Inc. All rights reserved. Fashion Assistant 68
  • 69. © 2024 Neo4j, Inc. All rights reserved. Pulling it all together So far you have done a vector search and enhanced that with a personalized search and you also know what you could recommend. 69 Allow me to introduce you to our AI Fashion Assistant Sam, who will combine all your hard work. Sam is pretty new to this though and needs a bit of prompting.
  • 70. © 2024 Neo4j, Inc. All rights reserved. Prompting Sam You are a personal assistant named Sam 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} --- 70
  • 71. © 2024 Neo4j, Inc. All rights reserved. Sam's insides 71
  • 72. © 2024 Neo4j, Inc. All rights reserved. Sam's insides 72 Personalized Search Recommendations Personal information search prompt customer id time of year
  • 73. © 2024 Neo4j, Inc. All rights reserved. Hammer Time ● Go back to the Jupyter Lab environment. We'll continue to run it together to the end, step by step 73
  • 74. © 2024 Neo4j, Inc. All rights reserved. Resources Original session: https://github.com/neo4j-product-examples/genai-workshop Today's session: https://github.com/tomgeudens/jupyter-notebooks/tree/main/genaihm Today's data: https://github.com/tomgeudens/trainingdata/tree/main/genaihm 74
  • 75. © 2024 Neo4j, Inc. All rights reserved. Thank You! marco.bessi@neo4j.com 75