AI Factory Explained

Welcome to AI Factory Explained — your deep dive into the architecture, concepts, and components of EDB Postgres® AI (EDB PG AI).

EDB PG AI enables Sovereign AI — building intelligent applications and data products on top of your data, in your databases and data centers, with Postgres as the foundation. The platform integrates vector search, Pipelines, Gen AI Builder, Knowledge Bases, and Model Serving to give you complete control over how AI is embedded in your systems.

This section explains how it all works:

  • What key concepts underlie EDB PG AI
  • How the architecture fits together
  • How individual capabilities like Pipelines, Gen AI Builder, and Model Serving work
  • Where vector search and AI models fit within your Postgres estate

Core Concepts

Start here to get oriented to the platform:

Gen AI and Knowledge Bases

Understand how intelligent knowledge is built on your data:

Data Pipelines and AI Accelerator

Understand how Pipelines transform your AI data workflows:

Vector Search and PGvector

How vector search is embedded directly in Postgres:

Model Serving

How AI models are deployed, governed, and used:


Where to go next:

If you're ready to build:

Or explore more advanced solution patterns in Solutions and real-world Use Cases.


This section grows as EDB PG AI evolves — check back for the latest explanations as new capabilities are added.


Concepts

EDB’s vision, strategy, and technologies for delivering AI Factory capabilities in Postgres and Hybrid Manager environments.

Assistants

Understand the role of Assistants in Gen AI Builder and how they power AI-driven conversational applications in EDB PG AI.

Data Lake

Understand the role of the Data Lake in Gen AI Builder and how it supports AI Factory content pipelines.

Generic Concepts

Industry concepts that underpin modern AI workloads, data architectures, and AI Factory capabilities.

Knowledge Bases

Understand what Knowledge Bases are, their role in Gen AI Builder, and how they power AI applications in EDB PG AI.

Model Library

Understand the Model Library in AI Factory, how it works, and how it is powered by the Hybrid Control Plane Image and Model Library.

Model Serving Concepts

Learn how Model Serving in AI Factory delivers scalable, Kubernetes-native model inferencing for intelligent applications and data products.

Model Serving

Understand how Model Serving works in AI Factory, using KServe to provide scalable, production-ready model inference.

Retrievers

Understand the role of Retrievers in Gen AI Builder and how they power Retrieval-Augmented Generation (RAG) and semantic search.

Rulesets

Understand the role of Rulesets in Gen AI Builder and how they guide the behavior of Assistants and Structures.

Sovereign AI

Understand Sovereign AI and how EDB Postgres AI enables trusted, governed AI solutions — with your data, in your control.

Structures

Understand the role of Structures in Gen AI Builder and how they enable advanced AI workflows, tooling, and data transformations.

Terminology

Definitions of key concepts, technologies, and architecture patterns used in AI Factory and Hybrid Manager AI Factory.

Threads

Understand the role of Threads in Gen AI Builder and how they provide conversation history, state persistence, and insights into Assistant behavior.

Tools

Understand the role of Tools in Gen AI Builder and how they extend the capabilities of Assistants and Structures.


Could this page be better? Report a problem or suggest an addition!