Back to the Index

Vector Database

What is a vector database in ML?

A vector database for machine learning is a database that stores, manages, and provides semantic query support for embeddings (high-dimensional vectors). The semantic queries supported are typically similarity search, nearest neighbor search, and clustering.

What are the most popular open-source libraries that existing vector databases build on?

FAISS (Facebook AI Similarity Search) FAISS is an open-source library for efficient similarity search and clustering of dense vectors. SCANN (Scalable Compressed Approximate Nearest Neighbors), developed by Google, is another open-source library for efficient similarity search and approximate nearest neighbor search in high-dimensional vector spaces.

Does this content look outdated? If you are interested in helping us maintain this, feel free to contact us.

© Hopsworks 2023. All rights reserved. Various trademarks held by their respective owners.

Privacy Policy
Cookie Policy
Terms and Conditions