Python, Prompt Engineering, Data Science — Build the Skills Employers Want Now
Live Online Classes in Design, Coding & AI — Small Classes, Free Retakes
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Explore the intricacies of Hierarchical Navigable Small World (HNSW) graphs in this comprehensive video tutorial on vector similarity search. Delve into the foundations of HNSW, understand its inner workings, and learn how to implement it using Faiss in Python. Discover the basics of HNSW in Faiss, examine the process of building an HNSW graph, and gain insights into creating the optimal HNSW index. Fine-tune your HNSW implementation for enhanced performance in approximate nearest neighbors (ANN) searches. Demystify this popular and robust algorithm through easy-to-understand explanations and practical examples, equipping yourself with the knowledge to leverage HNSW's state-of-the-art performance and lightning-fast search speeds in your projects.
Syllabus
Intro
Foundations of HNSW
How HNSW Works
The Basics of HNSW in Faiss
How Faiss Builds an HNSW Graph
Fine-tuning HNSW
Outro
Taught by
James Briggs