← back
Knowledge Graphs & GraphRAG: Techniques for Building Effective GenAI Applications: Zach Blumenthal
Takeaway
GraphRAG = vector search + graph traversal + graph embeddings; the combo outperforms naive vector RAG for personalized recommendation tasks.
Summary
- Hands-on Neo4j workshop combining vector search, graph traversal, and graph data science embeddings for retrieval-augmented generation.
- Use case: H&M Kaggle fashion data to build an AI personal-shopper that drafts recommendation emails with item pairings.
- Vector embeddings handle semantic similarity; graph traversals add personalization via customer purchase history and product relationships.
- Generates a new graph embedding via GDS that captures structural signal for recommendation tasks.
- Stack: Neo4j Aura/sandbox, LangChain, OpenAI, Gradio UI, Google Colab.
graphragneo4jknowledge-graphs
Original description
RAG & LLM Frameworks: Learn about practical graph design patterns and retrieval strategies to more effectively customize GenAI for real-world applications. While GenAI offers great potential, it faces challenges with hallucination and lack of domain knowledge. Graph-powered retrieval augmented generation (GraphRAG) helps overcome these challenges by integrating vector search with knowledge graphs and data science techniques to improve context, semantic understanding, and personalization while facilitating real-time updates. You'll receive detailed coded examples to begin your journey with GenAI and graphs, leaving with practical skills to apply immediately to your own projects. Prerequisites: This is a hands-on workshop where you can follow along with Jupyter notebooks in Colab. We will provide links to notebooks at the beginning of the workshop. To follow along please: Bring your laptop Create a Google account ahead of time if you don’t have one already so you can run Colab notebooks. [Prefered] Bring a working openAI API key. We will provide a key for those that do not have one yet. To make a new key, create an OpenAI account or sign in. Next, navigate to the API key page and "Create new secret key". Optionally naming the key. Save this somewhere safe, and do not share it with others. We recommend testing your key to make sure it works - see the OpenAI quickstart tutorial for more details. Recorded live in San Francisco at the AI Engineer World's Fair. See the full schedule of talks at https://www.ai.engineer/worldsfair/2024/schedule & join us at the AI Engineer World's Fair in 2025! Get your tickets today at https://ai.engineer/2025 About Andreas Andreas is a technological humanist. Starting at NASA, Andreas designed systems from scratch to support science missions. Then in Zambia, he built medical informatics systems to apply technology for social good. Now with Neo4j, he is democratizing graph databases to validate and extend our intuitions about how the world works. Everything is connected.