From Sushi to Semantics: A GraphRAG-Powered Japanese Food Explorer with Neo4j and MCP

Session Track: Knowledge Graphs

Session Time: 06:00 am - 06:30 am November 6

Session description

Japanese cuisine is rich in regional diversity, but this is often unfamiliar to international travelers. This session introduces a Neo4j-based knowledge graph that connects dishes, ingredients, and regions to support cultural discovery. The speaker will show how GraphRAG and VectorRAG enable contextual answers and cross-cultural food recommendations. Model Context Protocol (MCP) will be introduced for AI orchestration, and the potential of Agent-to-Agent (A2A) systems will be considered. Attendees will learn how to model cultural knowledge, apply semantic search with graphs, and explore multiagent collaboration. A working prototype will be demonstrated.

Speaker

Koji Annoura

Neo4j Ninja

Koji Annoura is a seasoned full-stack developer with over 40 years of experience in software engineering. Since 2009, he has been actively involved in Agile software development and co-founded the Neo4j Users Group Tokyo in 2013. In 2021, he also established the Apache Hop User Group Japan. Koji has helped numerous companies and teams in their Agile transformation, guiding them in adopting Agile and Scrum practices effectively. He is the author of A Technical Guidebook to Cloud Native Databases and The Practical Guide to MacOS X Server, and served as a technical reviewer for Graph Data Processing with Cypher.