Introduction to Vector Databases for Developers Micro-Credential

Duration: 3-4 Hours

Description

This micro-credential provides a practical, hands-on guide to working with vector data for modern AI applications. Participants explore the fundamentals of vectors and similarity search, learn how to build and query vector databases, and gain experience integrating them into Retrieval-Augmented Generation (RAG) workflows. Labs reinforce key concepts through real-world tasks like creating embeddings, setting up a memory vector database, and building a Q&A bot.

Audience

The target audience is developers with some experience in a programming language (like Python) who want to understand the role of vector databases in modern AI applications.

Objectives

• Understand what a vector database is and how it differs from a traditional database
• Explain the concept of vector embeddings and their importance
• Use a vector database to perform a similarity search
• Identify common use cases for vector databases, such as RAG and recommendation systems

Prerequisites

Basic familiarity with programming (such as Python) and a general understanding of databases or data structures is recommended. No prior experience with AI, machine learning, or vector search is required, making this program accessible to developers, data scientists, and technical professionals new to vector-based systems.

Course Outline

Module 1: Beyond Relational Databases

• The Problem with Unstructured Data
• What is a Vector?
• What is a Vector Database?
• Lab – Create Vector Embeddings from Different Types of Text

Module 2: Building with Vectors

• The Core Workflow
• Similarity Search in Action
• Vector Databases in RAG
• Lab – Set Up a Memory Vector Database

Module 3: From Theory to Practice

• Common Vector Databases
• Key Metrics
• Scaling and Production
• Lab – Q&A Bot