The first step towards building Graph RAG applications is to transform unstructured data into nodes and relationships. In this post, we show how to use LLMs and BAML, an AI engineering framework, to construct a Kuzu graph from a collection of unstructured data.
We demonstrate a fully in-browser Graph RAG-based chatbot that uses Kuzu-Wasm and WebLLM. The chatbot answers natural language questions over your LinkedIn data. This post highlights the potential of fully-local knowledge graph-powered AI applications.
Release announcement for Kuzu 0.8.2
Release announcement for Kuzu 0.8.0
How we used Kuzu in combination with LLMs in multiple stages of the Graph RAG pipeline to build a QA chatbot for the Connected Data London Knowledge Graph Challenge
Discover how Bauplan innovated on their FaaS planning pipelines using in-memory graphs in Kuzu, achieving 20x faster planning performance and more debuggable, maintainable workflows.
