Skip to main content
Loading

Frequently Asked Questions (FAQ)

This page contains answers to some of the most frequently asked questions about Aerospike Vector Search (AVS).

What is a vector (embedding?)

A vector, often referred to as a vector embedding, is a statistical representation of a piece of data. These are produced by machine learning models and can represent a word, document, image, video, song, etc.

How do I generate a vector embedding?

You can generate vector embeddings by sending your data through a machine learning model. You can read about how to generate embeddings from sentences in Open AI docs.

What does a vector database do?

A vector database provides two basic functions: storage and search. Storage is straightforward and a specialized database is not required (you could store your data in files, for example). Since you can calculate the distance between two vectors, a vector database provides a unique way to perform a proximity search across vectors that are loaded in the vector space.

What do KNN and ANN stand for?

KNN stands for K-nearest neighbor, referring to a collection of search algorithms used to determine the proximity between vectors. ANN stands for approximate nearest neighbor, which is a type of KNN search that prioritizes speed over quality.

What is HNSW?

HNSW stands for Hierarchical Navigable Small World, which is the algorithm used by AVS to perform an ANN search.

What is RAG?

RAG stands for Retrieval Augmented Generation, which is a technique for using a knowledge repository to provide context to generative language models. RAG is a common application pattern used by vector databases.

What version of Aerospike is required for AVS?

AVS works on all supported versions of Aerospike.

Can I add AVS to data already in Aerospike?

Yes. You need to add a vector to your data, but it is easy to do and will add search functionality to Aerospike.

How are vectors stored in Aerospike?

Vectors are stored in Aerospike as an additional bin on the record.

How should I configure Aerospike for AVS?

You need to consider your goals when scaling Aerospike for AVS, but there are a few general recommendations. First, there is no need to use strong consistency in the namespace you are using for search. Second, you can configure Hybrid Memory Architecture (HMA) to optimize for cost with minimal impact on performance. See Planning a deployment for more information about configuring storage.