Graph Database - San Francisco

Super excited to team up with AWS and Datadog to help you prototype the next generation of AI.

Join us for an immersive, hands-on hackathon where builders, developers, and AI enthusiasts come together to create production-ready Generative AI agents using the latest innovations from AWS, Datadog, and ecosystem partners.
​This unique challenge invites participants to leverage cutting-edge tools such as Amazon Bedrock, Strands Agents, Amazon Bedrock AgentCore, Datadog MCP, and Kiro Powers, alongside select AWS Partner products, to push the boundaries of Large Language Models (LLMs), AI agent workflows, and real-world AI applications.

Learn more and register at https://luma.com/n84hk0l9

What happens when a computer vision expert explores graph databases for the first time? Suha, a data scientist with a background in generative models, embeddings, and neural networks, steps into the world of graph thinking and graph query languages (GQLs). In this session, she shares her hands-on journey of modeling a public face recognition dataset (such as CelebA-HQ) as a graph - connecting people, facial attributes, and features in entirely new ways.

You will see:
- Transform tabular and image-based data into a graph structure
- Experiment with graph tools and GQLs
- Query connected data to uncover patterns hidden in flat tables
- Rethink how relationships shape machine learning workflows

If you come from SQL, Python, or an ML background and are curious about graph technology but don’t know where to start, this talk gives you a practical, beginner-friendly roadmap to launching your first graph-powered project.

Speaker: Suha Mokalla
LinkedIn: https://www.linkedin.com/in/suha-mokalla-ph-d-aa7612107/

#neo4j #graphdatabase #KnowledgeGraph #genai #llm #datascience #ml

This workshop is designed to introduce you to Generative AI, Retrieval-Augmented Generation (RAG), and GraphRAG, and show how these techniques can be combined with Neo4j to build intelligent, graph-powered applications. You will explore how large language models (LLMs) can be grounded in both structured and unstructured data to produce more accurate, relevant, and explainable responses.
The workshop includes hands-on exercises where you will build a knowledge graph from unstructured documents and structured data, enrich it with embeddings, and use vector indexes in Neo4j to perform similarity search. You will create multiple retriever patterns—including vector-based, vector plus Cypher, and text-to-Cypher retrievers—and see how GraphRAG improves retrieval quality by leveraging graph structure.
By the end of the session, you will build a conversational agent using Neo4j, Python, and LangChain. You will leave with practical experience designing GraphRAG pipelines and a solid foundation for applying these techniques to real-world use cases.

You will learn:

• The fundamentals of Generative AI and large language models (LLMs)
• What RAG is and why it is essential for grounding LLMs
• How GraphRAG improves retrieval and response quality
• How to build knowledge graphs from unstructured documents and structured data
• How to use vectors and embeddings in Neo4j for similarity search
• How to implement different retriever patterns using the neo4j-graphrag Python package
• How to build a conversational agent with Neo4j, Python, and LangChain