Capture One Enterprise for MacOS Download
- 1. © 2022, Amazon Web Services, Inc. or its Affiliates. Hands on Lab with Neo4j and Amazon Bedrock
- 2. © 2022, Amazon Web Services, Inc. or its Affiliates. Introduction to Neo4j Lee Razo Senior Cloud Partner Architect Neo4j Jean-Marc Guerin Presales Engineer Neo4j
- 3. © 2022, Amazon Web Services, Inc. or its Affiliates. Neo4j and Amazon Bedrock Input Data AWS Gradio Application Graph Data Science Graph Database Bloom Web Interface User Neo4j AuraDS Professional Amazon SageMaker Studio Amazon Bedrock
- 4. © 2022, Amazon Web Services, Inc. or its Affiliates. Introduction to Neo4j Ben.Lackey@Neo4j.com Director - Global Cloud Channel Partner Architecture +1 720 933 9852
- 5. © 2022, Amazon Web Services, Inc. or its Affiliates. Why use a graph database? Kind of Connected Data Questions Description Example How can you tell there are enough hops? Journey Questions -What is the journey or lineage from left to right, or from right to left -Can perform aggregations across traversals Left to right - impact of an upstream change on downstream customers What is the ETA for a job to complete Right to left - all the upstream systems associated with a downstream customer Complex Pattern Match Across Entities ● 360 Questions ● Graph Aided Search ● Variable length pattern matching -Everything we know about an entity -Cohort analysis -Can perform aggregations across traversals -All products, transactions, household members associated with an customer -People who share an address and own a policy and ... Graph Algorithms ● Similarity, Community Detection, Centrality, Pathfinding, Link Prediction, etc Unlike the above above, which project small subgraphs, these algorithms project and aggregate against large subgraphs Find all the customer communities and influencers within those communities
- 6. © 2022, Amazon Web Services, Inc. or its Affiliates. X360° ● Customer 360° ⇐ most common 1st use case ● Product 360° ● Employee 360° Enterprise Data Fabric (EDF) ● Data Unification ● Master Data Management Process ● Customer Journey ● Lead to Order ● Order to Cash Risk ● IT Configuration Management ● Cybersecurity / Access Control ● Supply Chain / Vendor Management ● Internal Audit / Fraud Detection Why use a graph database?
- 7. © 2022, Amazon Web Services, Inc. or its Affiliates. Neo4j is the leading graph database. 20 of the top 25 financial firms 7 of the top 10 retailers 7 of the top 10 software vendors • The first graph data science platform • The most flexible graph data model • The easiest-to-use graph query language Thousands of organizations use Neo4j.
- 8. © 2022, Amazon Web Services, Inc. or its Affiliates. Select Neo4j and AWS Joint Customers
- 9. © 2022, Amazon Web Services, Inc. or its Affiliates. Neo4j and AWS Partnership ● >40% of Neo4j customers run on AWS ● Member of AWS Partner Network since 2013 ● Collaborative Joint Engineering ● APN Advanced Tier Partner ● Data and Analytics Competency ● SageMaker Service Ready ● AWS Marketplace Seller ● AWS Public Sector Partner ● AWS ISV Workload Migration ● APN Global Startup ● ISV Accelerate
- 10. © 2022, Amazon Web Services, Inc. or its Affiliates. Neo4j is easy to use on AWS
- 11. © 2022, Amazon Web Services, Inc. or its Affiliates. LOVES CAR name: “Dan” born: May 29, 1970 twitter: “@dan” name: “Ann” born: Dec 5, 1975 since: Jan 10, 2011 brand: “Volvo” model: “V70” Latitude: 37.5629900° Longitude: -122.3255300° Nodes • Can have Labels to classify nodes • Labels have native indexes Relationships • Relate nodes by type and direction Properties • Attributes of Nodes & Relationships • Stored as Name/Value pairs • Can have indexes and composite indexes • Visibility security by user/role MARRIED TO PERSON PERSON PERSON LOVES since: Dec 14, 2010 Wait… What is a (Property) Graph?!
- 12. © 2022, Amazon Web Services, Inc. or its Affiliates. Fixed Sized Records “Joins” on Creation Spin Spin Spin through this data structure Pointers instead of Lookups 1 2 3 4 Neo4j Secret Sauce
- 13. © 2022, Amazon Web Services, Inc. or its Affiliates. Now, let’s get started with the lab… https://github.com/neo4j-partners https://github.com/neo4j-partners/hands-on-lab-neo4j-and-bedrock Complete labs 0, 1 and 2.
- 14. © 2022, Amazon Web Services, Inc. or its Affiliates. Moving Data Ben.Lackey@Neo4j.com Director - Global Cloud Channel Partner Architecture +1 720 933 9852
- 15. © 2022, Amazon Web Services, Inc. or its Affiliates. ● Built in way to load CSV into Neo4j ● Naive approaches can work for small data sets ● Larger data sets need indices, multiple pass throughs, etc. LOAD CSV
- 16. © 2022, Amazon Web Services, Inc. or its Affiliates. Neo4j in the AWS Ecosystem AWS Cloud Connector for Apache Kafka Connector for Apache Spark Amazon Managed Streaming for Apache Kafka Amazon EMR Neo4j Aura Graph Data Science Graph Database Bloom Data Warehouse Connector Amazon Redshift AWS Glue
- 18. 1. Siloed Approach 2. Non-Connected Data 3. No Fine-grained Access Control (RBAC) 4. No Explainable AI using Graph Data Science LLM Neo4j Inc. All rights reserved 2023 18 Pure Consumption Model Structured Unstructured Ontologie s Data sources Applications Customer Service Ticket Triaging Recommendations News Content & Discovery Enterprise Knowledge Search Patient Prioritization Clinical Decision Support Systems Pharmacovigilance Health Assistants FAQ Bots
- 19. NEO4J KNOWLEDGE GRAPH Why Neo4j ● Connect related unstructured and structured data from multiple sources ● Explainable AI & More predictability with Graph Data Science ● Vector Embedding Support Why Neo4j ● Grounded Knowledge that is Contextual, Factual, Explainable and easy to trace the lineage ● Grounded Facts, No Hallucinations! ● Fine-grained Access Control (RBAC) Neo4j Inc. All rights reserved 2023 19 Introducing Knowledge Graphs Ingesting Data into KG Consuming Data from KG Structured Unstructured Ontologie s Data sources Applications Customer Service Ticket Triaging Recommendations News Content & Discovery Enterprise Knowledge Search Patient Prioritization Clinical Decision Support Systems Pharmacovigilance Health Assistants FAQ Bots
- 20. Neo4j and Generative AI Reference Architecture Neo4j Inc. All rights reserved 2023 Knowledge graph Graph Data Science Graph DB Applications Parsing Structured Unstructured Ontologie s Data sources RAG Customer Service Ticket Triaging Recommendations News Content & Discovery Enterprise Knowledge Search Patient Prioritization Clinical Decision Support Systems Pharmacovigilance Health Assistants FAQ Bots Bloom APIs Neo4j Aura APIs 20 Ingesting Data into KG Consuming Data from KG Amazon Bedrock Amazon Bedrock
- 21. Input Data AWS Gradio Application Graph Data Science Graph Database Bloom Web Interface User Neo4j AuraDS Professional Demo Architecture Neo4j Inc. All rights reserved 2023 21 Amazon SageMaker Studio Amazon Bedrock
- 22. Lab 5 - Parsing Data into Knowledge Graphs Neo4j Inc. All rights reserved 2023 22 1. Entity Extraction - Identifying entities from words/phrases in unstructured text and classifying them as belonging to specific classes/types. This is also referred to as Named Entity Recognition (NER). 2. Relationship Extraction - Identifying relationships between pairs of entities based on unstructured text
- 23. ● Zero-shot with a simple prompt with the LLM ● Extract SEC EDGAR filing information in accordance with a Neo4j data model Neo4j Inc. All rights reserved 2023 23 Lab 5 - Parsing
- 24. Lab 6 - Ground LLMs 24 Neo4j Inc. All rights reserved 2023 24
- 25. ● Translates English to Cypher ● Consumption using LLM with few shot prompting ● Data augmentation from Neo4j response Neo4j Inc. All rights reserved 2023 25 Lab 6 - Chatbot
- 26. Lab 7 - Knowledge Graphs and Semantic Search Neo4j Inc. All rights reserved 2023 Find relevant documents and content for user queries Find entities associated to content and patterns in connected data. Improve search relevance & insights by enhancing a Knowledge Graph. Use graph algorithms and ML to discover new relationships, entities, and groups. Vector Similarity Search Graph Traversals & Pattern Matching Knowledge Graph Inference & ML Vector Database Graph Database 26
- 27. Lab 7 - Knowledge Graphs and Semantic Search Neo4j Inc. All rights reserved 2023 If your focus is analyzing documents on a file system, then vector indexing and search on text embeddings may be sufficient. If you need to retrieve and make inferences about people, places, and things connected to those documents, knowledge graphs can help. 27