An introduction to the concepts related to vector database. By Frank Liu (@frankzliu) This article has been updated since it was first published and is now part of a blog series that serves as a coursebook for concepts and guides related to vector databases. Jump to: · Vector databases from…

Learn how to adjust log level in Milvus without restarting the service. — To prevent an over-output of logs from affecting disk and system performance, Milvus by default outputs logs at the info level while running. However, sometimes logs at the info level are not sufficient enough to help us efficiently identify bugs and issues. What's worse, in some cases, changing the log…

An anatomy of the mechanism behind tunable consistency levels in the Milvus vector database. — This article is written by Jiquan Long and transcreated by Angela Ni. In the previous blog about consistency, we have explained what is the connotation of consistency in a distributed vector database, covered the four levels of consistency — strong, bounded staleness, session, and eventual supported in the Milvus vector…

Learn about user authentication and encryption in transit in Milvus. — In full consideration of your data security, user authentication and transport layer security (TLS) connection are now officially available in Milvus 2.1. Without user authentication, anyone can access all data in your vector database with SDK. However, starting from Milvus 2.1, only those with a valid username and password can…

Learn about the four levels of consistency: strong, bounded staleness, session, and eventual supported in the Milvus vector database. — Have you ever wondered why sometimes the data you have deleted from the Mlivus vector database still appear in the search results? A very likely reason is that you have not set the appropriate consistency level for your application. …

Use in-memory replicas to enhance read throughput and the utilization of hardware resources. — This article is co-authored by Congqi Xia and Angela Ni. With its official release, Milvus 2.1 comes with many new features to provide convenience and a better user experience. Though the concept of in-memory replica is nothing new to the world of distributed databases, it is a critical feature that…

Follow our step-by-step guide to perform a Milvus 2.1 benchmark by yourself. — Recently, we have updated the benchmark report of Milvus 2.1. Tests with a dataset of 1 million vectors have proved that QPS can be dramatically increased by merging small-nq queries. Here are some simple scripts for you to easily reproduce the tests. Procedures Deploy a Milvus standalone or cluster. In this…

A Python user-friendly Milvus version that makes installation more flexible. — This article is co-authored by Alex Gao and Angela Ni. Milvus is an open-source vector database for AI applications. It provides a variety of installation methods including building from source code, and installing Milvus with Docker Compose/Helm/APT/YUM/Ansible. Users can choose one of the installation methods depending on their operating systems…

Use string data to streamline the process of building your own similarity search applications. — Milvus 2.1 comes with some significant updates which make working with Milvus a lot easier. One of them is the support of string data type. Right now Milvus supports data types including strings, vectors, Boolean, integers, floating-point numbers, and more. This article presents an introduction to the support of string…