Quick Start

You can get up and running quickly with Aerospike Vector Search (AVS) using a free cloud-based preview environment or with Docker. Select your preferred option below and follow the simple steps to get started.

Cloud Preview

tip

Request free cloud preview beta access to get started quickly and two weeks of free access to an AVS environment. No development experience is required. Follow the examples below in your browser to get started.

1. Search for related quotes using LangChain (10 minutes)

   This interactive notebook explains how to build a semantic search index on a set of famous quotes. It uses the LangChain framework to download a dataset of 100,000 quotes and uses an embedding model to create vector embeddings for each quote. After the embeddings have been created, you can perform a semantic search on the resulting index.

   This is a good primer for learning how vector search works on text databases.

2. Basic search noteboook (3 minutes)

   This notebook shows you how to use the AVS Python client to build a search index on textand perform a basic search. This is a helpful walkthrough before getting started with building your own application.

Docker

tip

Request a free trial beta feature-key with the vector-service option enabled to install AVS locally.

1. Clone the examples repository

   This repository contains several pre-configured example applications for deploying and using AVS.

   git clone https://github.com/aerospike/aerospike-vector-search-examples 

2. Copy your feature key file

   Your feature key file should be located in follow location and named features.conf.

   cp ~/Downloads/features.conf ./aerospike-vector-search-examples/prism-image-search/container-volumes/avs/etc/aerospike-vector-search

3. Index your photos

   You can use the prism-image-search application to index your photos. This application uses the OpenAI CLIP model to create embeddings for your photos. These embeddings are indexed in AVS, and you can perform a semantic search on the index.

   Use the following command to copy .jpeg and .jpg files from your ~/Pictures directory to be indexed.

   rsync -av --include='*/' --include='*.jp*' --exclude='*' ~/Pictures ./aerospike-vector-search-examples/prism-image-search/container-volumes/prism/images/static/data

   Stat the database, AVS, and application.

   docker-compose -f ./aerospike-vector-search-examples/prism-image-search/docker-compose.yml up -d

   After a few minutes, navigate to http://localhost:8080/search and search your photos.

Next Steps

After completing the quick start, you can do the following:

• Install asvec: The asvec command line interface (CLI) is a tool for managing AVS.

• Create a data pipeline: This page outlines various approaches for generating vector embeddings that you can use on your own data.