Introduction to ANN-Benchmarks

This document describes how to use the ANN-Benchmarks benchmark test tool to test the data query performance of the Milvus vector database.

Milvus is an industry-leading vector database with high performance and scalability. It supports multiple index algorithms to improve the query efficiency in vector retrieval. Approximate Nearest Neighbor (ANN) is an algorithm for searching high-dimensional space for the data point closest to a target point. It is especially suitable for processing large-scale and high-dimensional datasets. ANN can significantly improve the search efficiency while ensuring high precision. Therefore, it is widely used in scenarios such as recommendation systems, graph search, and speech recognition.

ANN-Benchmarks, as a benchmark test tool, can evaluate and compare the performance of different ANN searches. It tests the performance of Milvus data query by invoking Milvus APIs externally.