Launch Week Day 5: Dark mode- now live across site, docs, and console! - Learn More

Faiss: The Missing Manual

James Briggs
James Briggs

Facebook AI Similarity Search (Faiss) is one of the best open source options for similarity search. In this ebook, you will learn the essentials of vector search and how to apply them in Faiss to build powerful vector indexes.

Introduction

Vector search has been used by tech giants like Google and Amazon for decades. It has been claimed to be a significant driver in clicks, views, and sales across several platforms. Yet, it was only with Faiss that this technology became more accessible.

In the past few years, vector search exploded in popularity. It has driven ecommerce sales, powered music and podcast search, and even recommended your next favorite shows on streaming platforms. Vector search is everywhere and in the following chapters you will discover why it has found such great success and how to apply it yourself using the Facebook AI Similarity Search (Faiss) library.

Subscribe to Pinecone

Get the latest updates via email when they're published:

Chapter 01

Introduction to Facebook AI Similarity Search (Faiss)

An overview of the Faiss library and similarity search.

Chapter 02

Nearest Neighbor Indexes for Similarity Search

Learn how to choose the right index in Faiss

Chapter 03

Locality Sensitive Hashing (LSH): The Illustrated Guide

Take your first steps, towards a deeper understanding of approximate nearest neighbor indexes with LSH.

Chapter 04

Random Projection for Locality Sensitive Hashing

Apply LSH to modern dense vector representations using random projection.

Chapter 05

Product Quantization

Learn how Product Quantization (PQ) can be used to compress indexes by up to 97%.

Chapter 06

Hierarchical Navigable Small Worlds (HNSW)

HNSW graphs are among the top performing indexes in similarity search.

Chapter 07

Composite Indexes and the Faiss Index Factory

Learn how to apply all we have learned so far to create multi-step composite indexes.

Chapter 08

And more...

Start building knowledgeable AI today

Create your first index for free, then pay as you go when you're ready to scale.