-
Module 1: AI in the context of Azure HorizonDB
11 Lessons-
StartModule introduction
-
StartAI features in Azure HorizonDB
-
StartWhat the database is responsible for
-
StartWhat the database is not responsible for
-
StartMisconceptions to avoid
-
StartPositioning Azure HorizonDB correctly
-
StartWorking with parameter groups
-
StartLab 1
-
StartLab 1 solution
-
StartLab 1 video walkthroughs
-
StartQuiz 1
-
-
Module 2: Vector data and embeddings fundamentals
13 Lessons-
StartModule introduction
-
StartWhat is an AI model?
-
StartWhat embeddings are and why they exist
-
StartHow vector similarity differs from relational comparison
-
StartTypical AI scenarios that involve vectors
-
StartWhy vectors work well for these scenarios
-
StartWhen vectors are inappropriate
-
StartWhere embeddings models are hosted
-
StartCommon embeddings models
-
StartLab 2
-
StartLab 2 solution
-
StartLab 2 video walkthroughs
-
StartQuiz 2
-
-
Module 3: Vector data types in PostgreSQL
13 Lessons-
StartModule introduction
-
StartVector data type basics
-
Startpgvector extension basics
-
StartDeclaring vector columns and variables
-
StartHow vector values are represented
-
StartPractical table pattern for embeddings
-
StartDimensionality is enforced
-
StartDimensionality changes are migration events
-
StartStorage characteristics and limitations of pgvector
-
StartLab 3
-
StartLab 3 solution
-
StartLab 3 video walkthroughs
-
StartQuiz 3
-
-
Module 4: Querying vector data
11 Lessons-
StartModule introduction
-
StartWhat similarity search means in PostgreSQL
-
StartWriting similarity queries in SQL
-
StartVector distance comparison operators
-
StartExact similarity (KNN) vs approximate search (ANN)
-
StartCombining vector similarity with relational predicates
-
StartCommon query mistakes and inefficiencies
-
StartLab 4
-
StartLab 4 solution
-
StartLab 4 video walkthroughs
-
StartQuiz 4
-
-
Module 5: Integrating External AI Services
10 Lessons-
StartModule introduction
-
StartWhy HorizonDB abstracts REST API complexity
-
StartUnderstanding the azure_ai schema
-
StartSecurity and managed identities
-
StartCost and throttling implications of outbound calls
-
StartOperational risks and failure modes
-
StartLab 5
-
StartLab 5 solution
-
StartLab 5 video walkthroughs
-
StartQuiz 5
-
-
Module 6: Calling AI services from HorizonDB
10 Lessons-
StartModule introduction
-
StartSynchronous vs asynchronous calls
-
StartRetrieving text embeddings via azure_openai.create_embeddings
-
StartInvoking chat models directly from SQL
-
StartHandling changes in embedding models and versioning strategies
-
StartRe-embedding strategies at scale
-
StartLab 6
-
StartLab 6 solution
-
StartLab 6 video walkthroughs
-
StartQuiz 6
-
-
Module 7: Working with AI Model Management
14 Lessons-
StartModule introduction
-
StartWhy model management exists
-
StartEnabling AI Model Management
-
StartManaged models and default aliases
-
StartUsing managed models from SQL
-
StartUnderstanding the model registry
-
StartBringing your own models
-
StartAuthenticating HorizonDB to AI Models
-
StartControlling access to models
-
StartOperational considerations
-
StartLab 7
-
StartLab 7 solution
-
StartLab 7 video walkthroughs
-
StartQuiz 7
-
-
Module 8: Vector indexing and performance
12 Lessons-
StartModule introduction
-
StartWhy vector indexing exists
-
StartTraditional PostgreSQL vector indexes
-
StartIntroduction to DiskANN in HorizonDB
-
StartCreating a DiskANN index
-
StartAccuracy versus performance trade-offs
-
StartCPU and memory impact of vector queries
-
StartMonitoring and diagnosing vector query performance
-
StartLab 8
-
StartLab 8 solution
-
StartLab 8 video walkthroughs
-
StartQuiz 8
-
-
Module 9: Durable AI pipelines
11 Lessons-
StartModule introduction
-
StartChallenges with external ETL for AI workflows
-
Startpg_durable execution engine
-
StartDefining a pipeline with sources, steps, and sinks
-
StartHandling automatic chunking and embedding in SQL
-
StartManaging pipeline state and recovery
-
StartMonitoring and troubleshooting persistent workflows
-
StartLab 9
-
StartLab 9 solution
-
StartLab 9 video walkthroughs
-
StartQuiz 9
-
-
Module 10: Retrieval-augmented query patterns
9 Lessons -
Module 11: Knowledge graphs with Apache AGE
13 Lessons-
StartModule introduction
-
StartWhy use a knowledge graph?
-
StartProperty graphs and Apache AGE
-
StartEnabling Apache AGE in HorizonDB
-
StartCreating and populating a graph
-
StartQuerying graphs with openCypher
-
StartCombining graph and relational data
-
StartBuilding knowledge graphs from existing data
-
StartUsing graph-augmented RAG
-
StartLab 11
-
StartLab 11 solution
-
StartLab 11 video walkthroughs
-
StartQuiz 11
-
-
Module 13: When NOT to use AI features in HorizonDB
7 Lessons -
Module 14: Using Data API Builder with HorizonDB
9 Lessons -
Module 15: Using HorizonDB with AI Agents via MCP
9 Lessons
Using AI Features in Azure HorizonDB
Store, retrieve, and integrate data for AI systems using Azure HorizonDB
Course Summary
Do you want to start working with AI-related features in Azure HorizonDB?
As these features are relatively new, the focus of this course is on design and architecture decisions that remain valid, even as individual features, syntax, and external AI services evolve. But we will show you how to achieve great outcomes right now. It does not aim to turn Azure HorizonDB into an AI platform, nor does it attempt to teach model training, data science, or vendor-specific AI tooling.
This course is about using Azure HorizonDB to store, retrieve, and integrate data for AI systems, in a way that is reliable, understandable, and operationally sound. We assume you already understand PostgreSQL or HorizonDB fundamentals and are comfortable working with PostgreSQL and database design.
— Are you responsible for deciding where AI-related logic should live, and where it should not?
— Do you need to support vector search, retrieval, or AI integration without turning the database into an experimental system?
— Have you been asked whether Azure HorizonDB should be used for embeddings, RAG patterns, or AI orchestration, and wanted a clear answer that you can explain?
If that matches the kind of responsibility you have, you’re in the right place. You'll get clear explanations, hands-on exercises, and short quizzes to make sure you not only understand the concepts but can confidently apply them in real Azure HorizonDB environments. And while the practical exercises are optional, we strongly encourage completing them. They are designed to be straightforward and focused on realistic scenarios, rather than tooling complexity. Setup is easy. The main requirement is access to an Azure subscription where you can create an Azure HorizonDB resource.
