GraphRAG Unleashed: Supercharging LLMs with Knowledge Graphs

Join us for an exciting deep dive into the world of GraphRAGs—where knowledge graphs meet the cutting-edge power of large language models (LLMs). In this interactive session, we'll explore how integrating Neo4j with generative AI technologies can drastically enhance the accuracy and reliability of AI-driven insights.

The agenda of the evening would be:
- 6pm: doors open
- 6.30pm: announcements and welcome
- 6.40pm: 1st Talk
- 7.10pm: 2nd Talk
- 7:40pm: Networking
- 8.10pm: doors close

Speaker:
🎤 Alison Cossette, Developer Advocate at Neo4j
Talk Topic: Practical GraphRAG
Talk Description: We all know that LLMs hallucinate and RAG can help by providing current, relevant information to the model for generative tasks. But can we do better than just vector retrievals? A knowledge graph can represent data (and reality) at high fidelity and can make this
rich context available based on the user's questions. But how to turn your text data into graphs data structures?
Here is where the language skills of LLM can help to extract entities and relationships from text, which you then can correlate with sources,
cluster into communities and navigate while answering the questions.
In this talk we will both dive into Microsoft Research's GraphRAG approach as well as run the indexing and search live with Neo4j and LangChain.
Speaker Bio: Alison Cossette is a Data Science Strategist, Educator, and Developer Advocate at Neo4j, specializing in Graph Data Science. With a strong background in AI and ethical AI practices, Alison bridges complex data concepts with real-world applications. She did Master’s studies at Northwestern University and has conducted research with Stanford's Human-Computer Interaction Crowd Research Collective. Passionate about responsible AI, Alison engages with professionals, policymakers, and the public to promote ethical AI development. She also hosts a podcast, driving innovation and education in data science and AI, making her a respected figure in the field.

🎤 Bryan Lee, Consulting Engineer @ Neo4j
Talk topic : Neo4j Meets Agentic RAG: Enhancing AI with Graph-Powered Retrieval
Description : Enter Agentic GraphRAG: a system where LLMs, powered by autonomous agents, intelligently retrieve, correlate, and navigate complex, multi-step reasoning tasks with the help of knowledge graphs.
In this talk, we’ll explore how knowledge graphs, like those in Neo4j, can enhance RAG by providing a high-fidelity representation of entities and relationships extracted from text. You’ll learn how AI agents leverage these graphs to improve the depth and accuracy of responses, enabling true understanding of context and nuanced data relationships.
Bio : Bryan Lee is a forward-thinking Consulting Engineer and Data Architect at Neo4j, specializing in GenAI and data-driven solutions. His expertise in optimizing data engineering processes for GenAI applications has driven significant business outcomes, particularly in the ASEAN region.
Bryan’s hands-on approach to problem-solving, combined with his passion for learning, has enabled him to lead innovative deployments in the rapidly evolving field of AI. He frequently shares his knowledge at workshops, conferences, and summits, advocating for the transformative power of GenAI and graph technologies. Bryan is dedicated to helping enterprises unlock their potential by navigating the complexities of data architecture and AI implementation.

Interested to speak at this or future meetups? Fill this form: https://dev.neo4j.com/submit-your-talk

You’ll discover how GraphRAGs (Graph-enhanced Retrieval-Augmented Generation) allow LLMs to go beyond simple text-based search and tap into complex, connected data for more factual and context-aware responses. Don’t miss this opportunity to network with like-minded professionals and take your AI projects to the next level!