Production RAG at Scale with Azure Database for PostgreSQL | POSETTE: An Event for Postgres 2026

Explore the production RAG architecture that powers Serenity Star's enterprise knowledge management platform. Paula Santamaría (Serenity Star) and Julia Schröder Langhaeuser (Serenity Star) present their talk “Production RAG at Scale with Azure Database for PostgreSQL” at POSETTE: An Event for Postgres 2026. Abstract: One of PostgreSQL's greatest strengths is its ability to serve as more than just a traditional database—it can be the foundation for intelligent systems. With the rise of AI-powered applications, PostgreSQL has emerged as a powerful platform for Retrieval-Augmented Generation (RAG) implementations. So, why should we consider PostgreSQL over specialized vector databases for production RAG systems?

In this talk, we'll explore a complete production RAG architecture that powers Serenity Star's enterprise knowledge management platform. With features like pgvector for semantic search, DiskANN for high-performance indexing, and seamless integration with Microsoft Semantic Kernel, PostgreSQL proves itself as a robust foundation for intelligent knowledge systems processing millions of queries monthly.

Drawing from our real-world experience as Azure customers scaling RAG from prototype to production, we will share practical insights on architecture decisions, performance optimization strategies, and monitoring approaches. We'll cover the complete pipeline: from document chunking and vector storage to semantic search optimization and production monitoring and observability.

Julia Schröder Langhaeuser is Product Director at Serenity Star, leading the development of a platform that creates AI-powered agents for optimizing business processes in advanced digital products. With extensive experience in digital platform creation and enterprise transformation across multiple sectors, she combines .NET development expertise with Agile leadership in complex environments. As a bioengineering professional, she brings unique insights to AI-driven transformation, working closely with executive leadership to align product vision with strategic objectives while coordinating multidisciplinary innovation teams.

Paula Santamaría is a Software Architect specializing in .NET. She currently leads the architecture of Serenity* Star, defining the technical aspects of features in collaboration with Product Design. In her role, she also conducts code reviews and guides teams on best practices and design patterns. Previously, she worked as a .NET Software Architect contractor, leading the development of internal frameworks used across teams to improve engineering practices. She is also the author of TypeScript Gamified and the winner of the 2021 GitHub Actions Hackathon.

► Video chapters:
⏩ 00:00 Music & introduction
⏩ 00:47 About us: Serenity Star and AI agents
⏩ 02:41 The four dimensions of an AI agent
⏩ 04:08 Demo: from knowledge upload to agent answer
⏩ 08:07 The four knowledge processing stages
⏩ 09:02 Agent execution pipeline: from query to LLM
⏩ 10:08 Architecture overview and the Postgres choice
⏩ 12:43 Multiple embedding models, different vector sizes
⏩ 14:16 Multi-tenant applications, versioning at 1.4M records
⏩ 15:23 Similarity search and a multi-column index fix
⏩ 20:03 Exploring DiskANN for vector search
⏩ 21:25 Benefits in production: Azure Database for PostgreSQL scalability and monitoring

📕 Everything you need to know about POSETTE: An Event for Postgres 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://x.com/PosetteConf
Mastodon – @posetteconf, https://mastodon.social/@posetteconf
Bluesky – @posetteconf.com, https://aka.ms/posette-on-bluesky

Microsoft for Postgres LinkedIn: https://www.linkedin.com/company/microsoft-for-postgresql

#PosetteConf #PostgreSQL #Azure

Видео Production RAG at Scale with Azure Database for PostgreSQL | POSETTE: An Event for Postgres 2026 канала Microsoft Developer