Production RAG and Vector Databases for Developers | Practical AI training | Applied Academy

Courses/AI Engineering

NOK 5,990Intermediate · PostgreSQL · pgvector · Python · SQL · English

Production RAG and Vector Databases for Developers

Build, evaluate and secure a retrieval-augmented generation (RAG) service on PostgreSQL and pgvector for ShopNow, a fictional retailer.

FormatInstructor-led1 day · in person, instructor-led

Duration: 1 day, live
Where: Classroom, in person
Lab setup: Prepared VM with PostgreSQL and pgvector
Certificate: On completion

The case · ShopNow

ShopNow has a RAG prototype for customer support, but it gives wrong answers, shows no sources and ignores document access.

DocumentsSynthetic help articles, policies and product manuals

TodayA prototype with no tests

You buildA tested RAG service on PostgreSQL and pgvectorChunk and index the documents, combine vector and full-text search, return answers with citations and block documents the user may not see.

AnswersCite their sources or say they cannot answer

QualityMeasured with a fixed evaluation set

PostgreSQLpgvectorPython

ShopNow is a fictional retailer. All data is synthetic.

After this course you can

01Ingest, chunk and embed documents into PostgreSQL with pgvector.
02Configure vector indexes and measure the trade-off between recall and query time.
03Combine vector search, full-text search and metadata filters to improve retrieval.
04Generate answers that cite their sources and refuse when the context does not support an answer.
05Evaluate retrieval and answer quality with a fixed test set.
06Apply document-level access control and plan updates, monitoring and cost for production.

Steps

Includes a lunch break and short breaks.

RAG architecture for productionIdentify the parts of a RAG service, its common failure modes and the quality targets for ShopNow's support assistant.Lab · Run the prototype on test questions and record where it fails.

Are you ready?

Made forSoftware and data developers who build LLM applications and want to move a RAG prototype to production.

You'll needWorking Python skills: functions, packages and virtual environments.Basic SQL, including SELECT, WHERE and joins.No prior RAG or vector database experience is required.

Setup checklistInstructor-ledBring a laptop with a web browser. You connect to the prepared VM.The VM has PostgreSQL, pgvector, Python and model access installed.

Company laptops sometimes block remote connections to the VM. Check with your IT team before the course.

Questions

Instructors

Saleem Pothiwala

Data engineering, AI engineering, strategy

28+ years in data. Built Kermit Tech to help Nordic and Middle East enterprises turn data into competitive advantage. He helps teams build and use data and AI solutions, with hands-on experience across finance, research, and nonprofit organizations. An IBM StreamSets Black Belt, Saleem teaches through practical examples and guided exercises. His courses help learners turn technical concepts into skills they can use at work.

Syeda Eman Fatima

Machine Learning, RAG, Agentic AI

Syeda Eman Fatima is an AI/ML Engineer working across the full machine learning lifecycle. She builds data pipelines as code, with version control.