Alexander Garcia

DataCamp Associate AI Engineer for Developers series: Part 6

Talking about the Introduction to Embeddings with OpenAI API course at DataCamp as part of the Associate AI Engineer for Developers course

Read time is about 4 minutes

Alexander Garcia is an effective JavaScript Engineer who crafts stunning web experiences.

Alexander Garcia is a meticulous Web Architect who creates scalable, maintainable web solutions.

Alexander Garcia is a passionate Software Consultant who develops extendable, fault-tolerant code.

Alexander Garcia is a detail-oriented Web Developer who builds user-friendly websites.

Alexander Garcia is a passionate Lead Software Engineer who builds user-friendly experiences.

Alexander Garcia is a trailblazing UI Engineer who develops pixel-perfect code and design.

Background

As noted in my other blog post about my New Years Resolution 2026 I have been working through my Associate AI Engineer for Developers course on DataCamp. To keep myself on task to accomplishing my goal I plan to document my experience and what I've learned in each course.

Course

Introduction to Embeddings with OpenAI API

Prerequisites: Course 1 in the series

This course covers three main sections:

  • What are embeddings?
  • Embeddings for AI Applications
  • Vector Databases

Review

tl;dr - I really enjoyed this course! It did a great job explaining how embeddings are used in real-world applications and introduced me to vector databases.

Here is what I learned:

  • How to use the OpenAI API to create text embeddings
  • The different types of AI applications enabled by embeddings, including semantic search, recommendation engines, and sentiment analysis
  • What vector databases are and how to store and query embeddings using Chroma

One interesting discovery was learning that vector databases are essentially NoSQL databases. This led me down a rabbit hole exploring different types of NoSQL databases — key/value pair, document, and graph databases. I found it particularly fascinating that fraud detection systems should use graph databases, while caching and session management are better suited for key/value NoSQL databases.

Pros/Cons

Pros:

  • Excellent real-world application examples that show practical use cases for embeddings
  • Clear explanations that made complex concepts easy to understand
  • Good introduction to vector databases and Chroma

Cons:

  • Would have liked more hands-on exercises with Chroma DB — being able to create a recommendation system for Netflix movie titles was very interesting as I'm a huge movie lover, and I wanted more of that!

Final thoughts

I would recommend this course to beginners who are new to the concept of text embeddings, as well as developers looking to build AI-powered search and recommendation systems. The course does a great job bridging the gap between understanding embeddings conceptually and applying them in practice.

Here is my certificate if anyone cares to see.