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
Learn how to implement vector compression using Product Quantization (PQ) and Inverted File Product Quantization (IVFPQ) with Faiss in Python. Explore the process of building a PQ index, combining PQ with an Inverted File step to enhance search speed, and work with the Sift1M dataset. Gain insights into memory usage optimization and composite indexing techniques for efficient semantic search. Follow along with practical demonstrations and code examples to understand the advantages of using libraries like Faiss for production-ready vector similarity search implementations.
Syllabus
Intro
Demonstration
Dataset
Initialization
Adding vectors
Memory Usage
Composite Index
Results
Taught by
James Briggs