Vector Databases for RAG: An Introduction
Learn on
IntermediateCourse
Gain expertise in using vector databases and improve your data retrieval skills in this hands-on course!
Language
- English
Topic
- Artificial Intelligence
Industries
- Information Technology
Skills You Will Learn
- RAG, Chroma DB, Similarity Search, Vector Database, Data Retrieval
Offered By
- IBMSkillsNetwork
Estimated Effort
- 8 Hours
Platform
- Coursera
Last Update
- July 11, 2025
About this Course
Gain expertise in using vector databases and improve your data retrieval skills in this hands-on course!
During the course, you’ll explore the fundamental principles of similarity search and vector databases, learn how they differ from traditional databases, and discover their importance in recommendation systems and Retrieval-Augmented Generation (RAG) applications. You’ll also dive into key concepts such as vector operations and database architecture to develop a strong grasp of Chroma DB's functionality.
You’ll gain practical experience using Chroma DB, a leading vector database solution. And through interactive labs, you’ll learn to create collections, manage embeddings, and perform similarity searches with real-world datasets.
You’ll then apply what you’ve learned by creating a real-world recommendation system powered by Chroma DB and an embedding model from Hugging Face; an ideal project to demonstrate your understanding of how vector databases improve search and retrieval in AI-driven applications.
If you’re keen to gain expertise in using vector databases and similarity searches, both essential components of the RAG pipeline, then enroll today!
During the course, you’ll explore the fundamental principles of similarity search and vector databases, learn how they differ from traditional databases, and discover their importance in recommendation systems and Retrieval-Augmented Generation (RAG) applications. You’ll also dive into key concepts such as vector operations and database architecture to develop a strong grasp of Chroma DB's functionality.
You’ll gain practical experience using Chroma DB, a leading vector database solution. And through interactive labs, you’ll learn to create collections, manage embeddings, and perform similarity searches with real-world datasets.
You’ll then apply what you’ve learned by creating a real-world recommendation system powered by Chroma DB and an embedding model from Hugging Face; an ideal project to demonstrate your understanding of how vector databases improve search and retrieval in AI-driven applications.
If you’re keen to gain expertise in using vector databases and similarity searches, both essential components of the RAG pipeline, then enroll today!
Course Learning Objectives
- Differentiate between vector databases and traditional databases based on their functionality and use cases
- Execute fundamental database operations in Chroma DB, including updating, deleting, and managing collections
- Understand and apply similarity search techniques, both manually and with Chroma DB, and develop recommendation systems using these techniques
Course Outline
Module 1: Introduction to Vector Databases and Chroma DB
- Lesson 0: Welcome
- Lesson 1: An Introduction to Vector Databases and Similarity Search
- Lesson 2: Exploring Chroma DB
Module 2: Vector Databases for Recommendation Systems and RAG
- Lesson 1: Chroma DB Database Operations
- Lesson 2: Develop a Recommendation System and Connect Learned Concepts to RAG
Recommended Background
Python programming, familiarity with databases
Language
- English
Topic
- Artificial Intelligence
Industries
- Information Technology
Skills You Will Learn
- RAG, Chroma DB, Similarity Search, Vector Database, Data Retrieval
Offered By
- IBMSkillsNetwork
Estimated Effort
- 8 Hours
Platform
- Coursera
Last Update
- July 11, 2025
Instructors
Wojciech "Victor" Fulmyk
Data Scientist at IBM
As a data scientist at the Ecosystems Skills Network at IBM and a Ph.D. candidate in Economics at the University of Calgary, I bring a wealth of experience in unraveling complex problems through the lens of data. What sets me apart is my ability to seamlessly merge technical expertise with effective communication, translating intricate data findings into actionable insights for stakeholders at all levels. Follow my projects to learn data science principles, machine learning algorithms, and artificial intelligence agent implementations.
Read more