In this talk, we will showcase how modern, open source tools like BAML (an AI framework for prompting LLMs to generate structured responses), and Kuzu, an open source embedded graph database, provide developers with the right building blocks to build agentic Graph RAG systems. A common challenge to adopting graphs and graph databases has been the first step: Creating the graph itself.  A lot of data in enterprises is unstructured images or text, and obtaining high-quality knowledge graphs for RAG has historically been a tedious and error prone process.

This talk will highlight how to use modular, atomic agentic building blocks that can power the graph construction phase and the retrieval phase, storing the results in a fast, easy-to-use graph database, in order to obtain higher quality knowledge graphs and more reliably generate outputs from Graph RAG systems.