Vector Databases and Retrieval Systems

Entry requirements

F01; basic API use; G01 recommended

What 36 hours means

Lessons

24 h

Capstone

8 h

Assessment

2 h

Remediation

2 h

Syllabus

Four modules, twelve lessons. Every lesson states what it covers and the evidence you produce for it.

• Module

  01

  3 lessons · 6 h

  

  Module 1

  Representation

  Semantic search foundations · Document parsing · Chunking strategies

  D03Show lessonsHide lessons▾

  1. D03.01 · 120 min

     Semantic search foundations

     Compare lexical and embedding search on supplied questions.

     Evidence: A comparison explains where each method succeeds or fails.

  2. D03.02 · 120 min

     Document parsing

     Extract text while retaining headings, source IDs and page references.

     Evidence: Parsed chunks retain correct source attribution.

  3. D03.03 · 120 min

     Chunking strategies

• Module

  02

  3 lessons · 6 h

  

  Module 2

  Indexing

  Embeddings · Index structures · Metadata and access filters

  D03Show lessonsHide lessons▾

  1. D03.04 · 120 min

     Embeddings

     Generate vectors and check dimension, version and normalisation assumptions.

     Evidence:

• Module

  03

  3 lessons · 6 h

  

  Module 3

  Retrieval

  Hybrid retrieval · Reranking · Incremental indexing

  D03Show lessonsHide lessons▾

  1. D03.07 · 120 min

     Hybrid retrieval

     Combine lexical and vector ranking for ambiguous queries.

     Evidence:

• Module

  04

  3 lessons · 6 h

  

  Module 4

  Evaluation

  Retrieval evaluation · Failure diagnosis · Service packaging

  D03Show lessonsHide lessons▾

  1. D03.10 · 120 min

     Retrieval evaluation

     Create relevance labels and calculate retrieval recall and reciprocal rank.

     Evidence:

Capstone

Build a searchable synthetic support knowledge base with access filters, retrieval evaluation and reproducible indexing.

Lab environment

AI API sandbox

Lab infrastructure is not yet provisioned, so this describes the environment the course is designed for rather than one you can launch today.

Part of a pathway

• Data Engineering Professional