Building Intelligent Applications with Graph-Based RAG on PostgreSQL | POSETTE 2025
Video of a conference talk that will show you how to revolutionize your applications using the Graph-Based RAG on PostgreSQL. The talk will show using PostgreSQL with vector and graph data to enable natural language queries for highly accurate results that will power your RAG application. Vector data will be explained as a tool that enhances PostgreSQL's ability to manage information for GenAI apps. The session explores how to integrate graph, and vector data using azure_ai, pg_diskann, age and pgvector extensions. As well as advanced techniques to improve accuracy of results and improve vector search performance at scale. A hands-on demonstration will show how to set up PostgreSQL to handle these types of queries, store vector data, and create queries that respond to natural language inputs. A practical example will involve building a legal copilot to help lawyers find relevant legal cases during research. Participants will leave the session equipped to apply similar graph, indexing and vector features in their own applications, making them more intuitive, user-friendly and scalable. Abe Omorogbe is an experienced AI professional with nearly a decade in the field. At Microsoft, he develops cutting-edge Data + AI products, focusing on PostgreSQL and previously serving as Lead PM for LLMOps/MLOps on Azure AI. Before rejoining Microsoft, Abe worked at Databricks, where he enhanced his expertise in AI and machine learning as Lead PM for MLflow. He is passionate about using AI to tackle complex challenges and drive innovation. Follow Abe on Twitter ► Video bookmarks: ⏩ 00:00 Introduction ⏩ 01:47 Agenda / Why Postgres ⏩ 03:47 US Case Law Dataset ⏩ 04:32 Semantic Search ⏩ 05:37 Vector 101 ⏩ 08:25 Basic RAG ⏩ 09:09 Common Problem with RAG ⏩ 13:45 Advanced RAG Architecture ⏩ 20:40 Resources 📕 Everything you need to know about POSETTE: An Event for Postgres 2025 can be found at: https://posetteconf.com ✅ Learn more: Watch more POSETTE talks: https://aka.ms/posette-playlist 📌 Let’s connect: POSETTE LinkedIn - / posetteconf X – @PosetteConf, / posetteconf Mastodon – @posetteconf, https://mastodon.social/@posetteconf Bluesky – @posetteconf.com, https://bsky.app/profile/posetteconf.com Azure Database for Postgres LinkedIn - / azure-database-for-postgresql _________________________________ #PosetteConf #PostgreSQL #ai
GraphRAG: The Marriage of Knowledge Graphs and RAG: Emil Eifrem
18 Months of Pgvector Learnings in 47 Minutes (Tutorial)
Build high-performance RAG using just PostgreSQL (Full Tutorial)
LightRAG: A More Efficient Solution than GraphRAG for RAG Systems?
What is a Vector Database? Powering Semantic Search & AI Applications
Postgres Graph Queries | Scaling Postgres 327
GraphRAG: Building a Smarter AI System (full walkthrough)
Andrej Karpathy's Wiki Idea Was Just Shipped by Pinecone
Knowledge Graph or Vector Database… Which is Better?
When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer
Extracting Knowledge Graphs From Text With GPT4o
Intro to GraphRAG — Zach Blumenfeld
RAG Crash Course for Beginners
Practical GraphRAG: Making LLMs smarter with Knowledge Graphs — Michael, Jesus, and Stephen, Neo4j
Webinar: Graph Queries with PostgreSQL
What’s New with Azure Database for PostgreSQL- Flexible Server | POSETTE: An Event for Postgres 2025
RAG is Dead - Introduction to Vectorless RAG
What Is Docling? Transforming Unstructured Data for RAG and AI
Building Enterprise RAG with Azure Database for PostgreSQL and pgvector | POSETTE 2025
