Make RAG 100x Better with Real-Time Knowledge Graphs

Retrieval Augmented Generation (RAG) is the standard for giving our documents and data to our AI agents, but it's VERY static. We constantly have to keep our data source in sync with our RAG knowledge base, and that process is inefficient and unreliable. In order for RAG to truly keep up, we need a way to build up a knowledge graph that can be as dynamic as our data, business, or platform. The solution for this is Graphiti, an open source platform for building real-time knowledge graphs. With it, I feel like my RAG AI agents are 100x more powerful, especially combined with other RAG strategies I talk about in this video! Getting started with Graphiti is a piece a cake and I walk you through the whole process in this video, along with a live demo showing how powerful it is. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Check out Graphiti on GitHub here: https://github.com/getzep/graphiti Graphiti's official documentation: https://help.getzep.com/graphiti/graphiti/overview All code I cover in this video for Graphiti is here: https://github.com/coleam00/ottomator-agents/tree/main/graphiti-agent The Local AI Package (includes Neo4j for Graphiti): https://github.com/coleam00/local-ai-packaged ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 00:00 - Introducing Graphiti 01:25 - Graphiti Overview 04:09 - Graphiti vs. GraphRAG/LightRAG 05:38 - Graphiti Quickstart 14:25 - Graphiti Demo 16:49 - Graphiti AI Agent with Pydantic AI 20:02 - Live Demo - The True Power of Graphiti 24:46 - Graphiti and Agentic RAG (+ Other RAG Strategies) 26:06 - Outro ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Join me as I push the limits of what is possible with AI. I'll be uploading videos at least two times a week - Sundays and Wednesdays at 7:00 PM CDT!