jnaapti

AI curriculum

Course outline for Vector and AI Data Infrastructure

Semantic retrieval depends on indexing and filtering choices. Build and compare vector-backed retrieval paths with explicit relevance and metadata requirements.

Technology
Data Engineering and Databases
Duration
4 hours
Modules
2 · 2 hours each
Level
Prerequisites listed

About Vector and AI Data Infrastructure

Semantic retrieval depends on indexing and filtering choices. Build and compare vector-backed retrieval paths with explicit relevance and metadata requirements.

Vector and AI Data Infrastructure Course Objectives

  • Explain vector representations and index trade-offs.
  • Implement similarity search with metadata filters.
  • Compare vector-only and hybrid retrieval results.

Pre-requisites

  • Basic database and programming skills.
  • Familiarity with embeddings or retrieval concepts.

Lab Setup

  • Computer with local PostgreSQL and pgvector or a local Weaviate instance.
  • Use supplied vectors or local embeddings and synthetic metadata; hosted services are optional.

Detailed Course Outline

Proposed modules

Module 1: Vector storage choices

  • Vector representations
  • Vector indexes
  • Vector databases
  • pgvector

Practical outcome: Create and query a small vector index.

Module 2: Retrieval controls

  • Weaviate
  • Similarity search
  • Metadata filtering
  • Hybrid retrieval

Practical outcome: Compare filtered and hybrid retrieval results.

Practical exercise

  • Build a small retrieval benchmark and evaluate index and filtering configurations.

How we train

Contact us for full course details, including duration, delivery options and lab requirements.

Ask about exercises, instructor feedback and the prior knowledge you need. Tool-specific courses marked provisional may become modules in a broader course.

Discuss your learning goals