The GraphRAG Manifesto: Unlock Better GenAI Results With Knowledge Graphs | Read Now

Neo4j logo

Nodes2024

Dev Conference by Neo4j

Register for NODES 24

You only need to register once to attend all sessions.

Enhancing Chat-Based Customer Recommendations With GraphRAG and Hybrid Search

Session Track: AI

Session Time:

Session description

Discover how Hi5 leverages cutting-edge technologies—Neo4j, Qdrant, and Large Language Models (LLMs)—to power our GraphRAG framework, enhancing e-commerce through an intelligent sales consultant. This session will dive into the specifics of our product data engineering, user intent recognition, and our hybrid GraphRAG querying approach, illustrating how we transform user queries into precise product recommendations. Attendees will gain insights into the integration of graph databases with vector search and AI to deliver a nuanced shopping experience.

Speaker

photo of JiunYi Yang

JiunYi Yang

Staff AI Engineer, Hi5 Technology Inc.

I am JiunYi, an AI & Data Engineer specialized in LLM, Generative AI, and NLP, with hands-on experience in MarTech, E-commerce, and FinTech. I have accumulated numerous RAG applications, including healthcare chats, ESG reporting, and E-commerce recommendations. Key projects include TCNNet-9B and TaiwanEcoChat-9B—localized models for Taiwanese netcom, cybersecurity and ESG, respectively. I am known for fast learning, effective task management, and my tech blog, DataAgent, showcases my industry contributions.