Free Course on Vector Similarity Search and Faiss

Essentials for the future of machine learning

James Briggs


The articles and videos that make up the course

For the past few months I’ve been working with Pinecone on a series of articles and videos covering the essentials of vector similarity search.

The course introduces the idea and theory behind vector search, how to implement several algorithms in plain Python, and how to implement everything we learn efficiently using Facebook AI Similarity Search (Faiss).

Video playback alone totals six hours — all packed full of content. If we consider article read-time on top of that, what we have is a treasure trove of learning materials for all-things vector similarity search.

The price for all of this?

It’s free.

Course Content

The course is split into three parts — although you can click through the course as you wish, this is the order that we think makes the most sense.

Part One — Introduction

In part one we introduce similarity search, taking a look at a few of the most popular methods and technologies from Jaccard and Levenshtein, to TF-IDF and BERT.

We then explore the Faiss library and get started with some basic indexes and how to choose the right index for our use cases.

1. Semantic Search: Measuring Meaning From Jaccard to Bert

2. Getting Started with Faiss

3. Nearest Neighbor Indexes for Similarity Search

Part Two — Algorithm Deep Dives

The next part delves into some of the most popular algorithms and indexes in vector search. Here we focus on the theory, explain it through simple Python, and then look at how to implement it in Faiss.



James Briggs

Freelance ML engineer learning and writing about everything. I post a lot on YT