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 Retrieval-Augmented Generation With GRIX: Leveraging Knowledge Graphs in Neo4j

Session Track: AI

Session Time:

Session description

GRIX (Graph Index) is an innovative tool designed to enhance retrieval-augmented generation (RAG) models by leveraging knowledge graphs within a Neo4j database. Capable of processing vast document corpora, GRIX transforms textual data into a structured graph format, optimizing information retrieval through enriched relational context. By utilizing the inherent structure and connections within the graph, GRIX improves the efficiency and accuracy of query responses in RAG models. This tool capitalizes on the robust querying capabilities of Neo4j, enabling users to seamlessly navigate complex datasets and retrieve contextually relevant information, making it a valuable asset for applications requiring deep, relational data insight.

Speaker

photo of Filip Seitl

Filip Seitl

Data Scientist, Creative Dock

Filip Seitl is a data scientist specializing in spatial probabilistic modeling and spatial statistics. At Creative Dock, Filip has contributed to various AI projects, including GRIX, where he focused on extraction of information to build a knowledge graph and the successive retrieval from the graph. With a strong background in probabilistic modeling, Filip brings a unique perspective to data science, blending theoretical knowledge with practical applications. His work on GRIX has helped optimize retrieval-augmented generation models using knowledge graphs, enhancing information retrieval and data insight. Passionate about innovation, Filip continuously seeks to push the boundaries of AI and data science.