Learn with Neo4j's New "Get to Know Graph & GenAI" Webinar Series >>

Neo4j logo

From Unstructured to Connected: Building Knowledge Graphs for GenAI with neo4j-graphrag

Session Track: Data Intelligence

Session Time:

Session description

GenAI is evolving fast, and RAG is at the heart of making these systems smarter, safer, and more grounded. GraphRAG is now gaining attention for its ability to incorporate structured, context-rich knowledge directly into the GenAI pipeline. But here’s the catch: GraphRAG assumes you have a graph. This talk will walk you through bridging that gap. We’ll introduce the neo4j-graphrag Python package—a toolkit designed to streamline the process of ingesting unstructured data into Neo4j and turning it into a fully usable knowledge graph. Whether you're working with PDFs, web pages, or plain text, this package helps you go from raw content to a connected knowledge graph in just a few steps. You’ll leave this talk with: - A walkthrough of the neo4j-graphrag package and its core capabilities. - A hands-on guide to ingesting your own data and generating a knowledge graph from scratch. If you’re looking to bring your unstructured data into the world of connected intelligence and enable more powerful GenAI applications, this session is your starting point.

Speakers

photo of Estelle Scifo

Estelle Scifo

Lead Software Engineer, Neo4j

Graphs

photo of Nathalie Charbel

Nathalie Charbel

Senior Software Engineer at Neo4j

Nathalie Charbel holds a PhD in Computer Science. Her research focused on semantic information retrieval from unstructured document corpora (2018). Transitioning to industry, she joined Nobatek/INEF4 (2019-2022), where she contributed to EU projects, emphasising ontologies and semantic web technologies. She later joined Neo4j, and specialised in query language design (2022-2024). Currently, she's part of Neo4j's generative AI team, leveraging her expertise in combining knowledge graphs and LLMs.