Concepts

EDB Postgres® AI (EDB PG AI) brings AI workloads into your Postgres platform and infrastructure — with an architecture designed to power Sovereign AI on hybrid and cloud-native environments.

AI Factory extends Postgres to support:

• Vector search and semantic search

• Data pipelines for embedding generation

• Gen AI application development

• Scalable model serving and inference

• AI-driven governance and observability

AI Factory helps you build and operate trusted, enterprise-grade AI systems using your data, models, and applications.

Concepts

EDB’s vision for AI with Postgres and Hybrid Manager

EDB’s AI Factory strategy makes Postgres a first-class platform for AI workloads and AI-driven applications.

The architecture combines:

• AI in Postgres: vector search, embedding pipelines, and AI functions within the database

• Gen AI apps: conversational and task-driven AI applications with Gen AI Builder

• Scalable inference: GPU-accelerated model serving using Kubernetes and KServe

• Unified control plane: model lifecycle management and observability in Hybrid Manager

This enables Sovereign AI — AI on your data, on your infrastructure, with full governance.

Concepts

RAG pipelines enhance LLM responses by combining:

• Domain-specific embeddings from Knowledge Bases Reference Manual

• Configurable search behavior with Retrievers Reference Manual

• Scalable model inference through Model Serving Reference Manual

• Application orchestration via Gen AI Builder

This enables more accurate, grounded, and compliant AI applications.

Concepts

AI Factory provides robust model serving with:

• Scalable inference services for LLMs, embedding models, and vision models

• GPU-accelerated serving via Kubernetes + KServe

• Flexible deployment options through the Model Serving Reference Manual framework

• Lifecycle management and discoverability with the Model Library Explained In Depth

These services power both Gen AI Builder agents and Knowledge Bases.

Concepts

AI Factory Pipelines and data preparation automate:

• Embedding generation

• Chunking, parsing, summarizing content

• Keeping embeddings fresh with Pipeline auto-processing

Explore Pipelines reference - Preparers for reusable data preparation components.

Concepts

Summary

EDB PG AI enables you to:

• Embed AI capabilities directly into Postgres

• Build scalable, production-ready AI applications

• Operate Sovereign AI on your infrastructure with unified governance

• Integrate open-source tools and standards across the AI stack

Next steps:

• AI Factory terminology

• Fundamental AI Concepts

• AI Factory Learning Center

---

• AI Factory vs. “Generic AI”
  • What we mean by each
  • Who it is for
  • Where it runs
  • When to choose each
  • How they work together
  • Use cases
  • Prerequisites
  • FAQ
  • Related topics
• Fundamental AI Concepts
  • Before you start
  • Core AI concepts
    • Learning systems and model training
    • Deep learning (DL) & neural networks
    • Natural language processing (NLP)
    • Large language models (LLMs)
    • Embeddings and vector representations
    • Vector databases and semantic search
    • Retrieval-augmented generation (RAG)
  • AI for databases
    • Intelligent database management
    • In-database AI
    • Vector databases in Postgres
  • AI for infrastructure
    • AI-accelerated hardware (GPUs, TPUs)
    • Leveraging cloud compute for AI workloads
  • Hybrid and Sovereign AI
  • Related concepts
  • Next steps
• AI Factory terminology
  • Core AI concepts
    • Machine learning (ML)
    • Deep learning (DL)
    • Natural language processing (NLP)
    • Large language models (LLMs)
    • Embeddings
    • Vector databases
    • Retrieval-augmented generation (RAG)
  • AI for databases
    • Intelligent database management
    • Vector search in Postgres
    • AIDB
    • In-database machine learning (In-DB ML)
    • Vector search in Postgres
    • AIDB
    • Natural language interfaces to databases
  • AI infrastructure
    • AI-accelerated hardware
    • KServe
    • Model Serving
  • Gen AI Builder
    • Gen AI Builder
  • Hybrid Manager AI Factory
    • Hybrid Manager
    • Pipelines
    • Knowledge Bases
    • Model Serving
  • Additional concepts
    • Image and Model Library
    • NVIDIA NIM
  • Summary
• Sovereign AI Explained
  • Why it matters
  • What is Sovereign AI?
  • How EDB PG AI enables Sovereign AI
    • Key components:
  • Why Hybrid Manager?
  • Summary
  • Learn more
• Security and governance in AI Factory
  • Why security and governance matter
  • Where enforcement happens
  • Who is responsible
  • How to apply governance in AI Factory
  • Prerequisites
  • Use cases
  • Related topics