AI Factory

EDB Postgres® AI provides a scalable, modular platform to build and operationalize AI-powered applications and intelligent data products — starting from your data, in your databases, running in your data center or cloud environments. EDB PG AI is designed for Hybrid Manager™ first. Most capabilities are delivered and managed inside Hybrid Manager’s AI Factory , where you get a unified control plane, governance, and observability. You can also run selected components outside Hybrid Manager — notably Postgres extensions and AI DB (AIDB) — when supported by licensing.

At its core, EDB Postgres® AI (EDB PG AI) is designed to enable Sovereign AI: allowing you to build intelligence on top of your trusted Postgres data, governed within your enterprise boundaries. Your models, your pipelines, your vector indexes — all managed and controlled by you.

With EDB PG AI, you can:

• Build and run **Gen AI agents** and conversational experiences powered by your enterprise knowledge and sovereign Postgres data in **Hybrid Manager**

• Perform **vector search** and retrieval-augmented generation (RAG) over structured and unstructured sources

• Create **document intelligence pipelines** that ingest, process, and classify data from diverse sources

• Deploy scalable Model Serving Reference Manual , using GPU acceleration and enterprise observability

• Extend Postgres with AI-driven query patterns and **vector-native capabilities**

• Seamlessly combine AI and analytics across Postgres, EDB Lakehouse, and other EDB-integrated platforms

---

• Where AI Factory runs
  • Prerequisites
  • Why Sovereign AI?
  • What You Can Build
  • Choose your path
  • Who Is It For, and How to Get Started?
  • Core Capabilities
    • Gen AI Workloads
    • Asset Library and Model Serving
    • Pipelines and Vector Engine
  • EDB PG AI and Analytics
  • Learn and Build
  • Build Your EDB PG AI Solution
• AI Factory
  • AI Factory Hub Map
    • Start here
    • Build with AI Factory
    • Hybrid Manager
    • Where it runs and prerequisites
    • References
  • AI Factory Learning Center
    • Quickstarts
    • Conceptual Explanations
    • How-to Guides
    • Learning Paths
    • Solutions
    • Use Cases
  • Concepts
  • Concepts
    • EDB’s vision for AI with Postgres and Hybrid Manager
  • Concepts
  • Concepts
  • Concepts
  • Concepts
    • Summary
• Usage
  • AI Factory Models
  • AI Factory Models
    • System Overview
    • Strategic Benefits
    • Architecture Integration
    • Operational Workflows
    • Learning Pathways
    • Use Case Applications
    • Implementation Considerations
  • Gen AI Builder
  • Gen AI Builder
    • Platform Architecture
    • Architectural Components
    • Implementation Patterns
    • Development Framework
    • Integration Architecture
    • Operational Considerations
    • Getting Started
  • AI Factory Pipelines
    • Why Pipelines?
    • What You Can Do
    • How It Works
    • Who Should Use Pipelines?
    • When to Use Pipelines
    • Configuration values explained
    • Learn More
  • Vector Engine (PGvector)
    • Vector Engine
    • Why Vector Search in Postgres?
    • Who Should Use Vector Engine?
    • What Does It Provide?
    • How Vector Engine Works
    • When Should You Use Vector Engine?
    • Example Use Cases
    • Integration with AI Accelerator Pipelines and Gen AI Builder
    • Next Steps
  • AI Factory Release Notes
    • AI Factory 1.3 release notes