Building Enterprise RAG with Azure Database for PostgreSQL and pgvector

Post Content

Video of a conference talk about building reliable and scalable Retrieval Augmented Generation (RAG) applications using Azure Database for PostgreSQL and pgvector. This session demonstrates how to architect production-ready RAG solutions that combine vector similarity search with enterprise data. We’ll explore performance optimization techniques, integration patterns with Azure OpenAI Service, and deployment strategies for handling real-world workloads at scale.

Michael John “MJ” Pena is a passionate engineer and business leader who loves Data and AI. He has been working with cutting-edge technologies such as cloud computing, big data analytics, blockchain, IoT, and machine learning for over a decade and a half. MJ is a Microsoft MVP in Azure and an active community contributor to emerging data technologies. MJ works as the Data and AI Director at Playtime Solutions, an Australian tech consulting company. He uses technology to create new solutions like data warehouses, real-time analytics, and reports. In his previous life, MJ held many positions, such as CTO, Solutions Architect, and Technical Lead.

► Video bookmarks:

00:00 Introduction
00:32 Enterprise Challenges
02:20 Native Vector Search
05:00 DEMO – Vector Search
05:10 Installing Prerequisites
08:09 DEMO – Embeddings
11:20 DEMO – Indexing
13:21 Indexing Comparision
15:44 DiskANN Demo
17:20 Semantic Search

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:  
LinkedIn – https://www.linkedin.com/company/posetteconf/
X – @PosetteConf, https://twitter.com/PosetteConf
Mastodon – @posetteconf, https://mastodon.social/@posetteconf
Bluesky – @posetteconf.com, https://bsky.app/profile/posetteconf.com