After this day you can build AI features directly on Azure Database for PostgreSQL. You set up the azure_ai extension, store embeddings with pgvector, implement semantic search and RAG, and call language and translation services from SQL. You will also see how an AI agent reaches the database through Foundry Agent Service or MCP. The course suits developers, data engineers and AI engineers who already know PostgreSQL and want to build AI applications close to their data rather than adding another database.
What you’ll take away.
- Set up the azure_ai extension in Azure Database for PostgreSQL flexible server and call Azure AI services from SQL
- Store embeddings with pgvector and implement semantic search through similarity queries
- Summarise and translate text in the database, analyse it for sentiment and entities, and detect personal data
- Design and build a RAG application on top of PostgreSQL
- Connect an AI agent to the database, for example through Foundry Agent Service or MCP
Your training in detail
- Who is it for?
- Developers, data engineers and AI engineers who already work with PostgreSQL and want to build AI features close to their data.
- Prerequisites
- Experience with PostgreSQL and writing SQL queries, plus a general understanding of AI and machine learning concepts.
- Format & planning
- Standard length: 1 training day. A different length can be arranged for companies.
Agenda: from understanding to application
Our independently developed agenda proposal. Focus areas, lab environment and scope are agreed before booking.
Generative AI with Azure Database for PostgreSQL: architecture and the azure_ai extension
Semantic search: embeddings, vector similarity and pgvector
AI services from SQL: Azure AI Language, Translator and inference through Azure Machine Learning endpoints
Designing and building RAG applications on PostgreSQL
AI agents with PostgreSQL: agent architecture, information retrieval, Foundry Agent Service and MCP
Developing in Visual Studio Code with the PostgreSQL extension and GitHub Copilot
You add embeddings to a table of product descriptions, answer free-text questions with semantic search and analyse customer reviews for sentiment and mentioned products directly in SQL.
Exams, licences & credentials
The course follows the Microsoft learning path AI-3019 and has no exam; Microsoft does not list a related certification for this learning path. PostgreSQL with pgvector is also covered in exam AI-200 if you later aim for a certification. It is not an official Microsoft course unless the offer says so explicitly.
Vendor references & review date
Sources checked on 2026-11-10. These sources describe the technology or external exam requirements. They do not imply a partnership with NextNowa.
Your learning content
These objectives describe the training topic. The specific syllabus, dates and trainer are agreed before booking; the written offer is binding.
Frequently asked questions
Do I need a separate vector database?
No. With pgvector you store and search vectors directly in Azure Database for PostgreSQL.
Is there an exam for AI-3019?
No. AI-3019 is a learning path without its own exam. PostgreSQL with pgvector is, however, also a topic in exam AI-200.
Does AI-3019 Build AI Apps with Azure Database for PostgreSQL: AI features inside the database include a certificate?
The course follows the Microsoft learning path AI-3019 and has no exam; Microsoft does not list a related certification for this learning path. PostgreSQL with pgvector is also covered in exam AI-200 if you later aim for a certification. It is not an official Microsoft course unless the offer says so explicitly.