Zilliz Cloud allows you to host and manage your vector data in the cloud. This series of user guides walk you through the basic operations of Zilliz Cloud databases.
Example Dataset Overview
We’ll use an example dataset throughout this user guide series. The dataset contains details about over 5,000 Medium articles published between Jan 2020 to August 2020 in prominent publications.
Create a Database Instance
This guide walks you through the procedures to create a database instance on Zilliz Cloud and the principles of how to choose the proper CU type and decide the total number of CUs in need.
Connect to a Database
This guide walks you through how to access a database on Zilliz Cloud. You will learn how to obtain the database endpoint, configure the network access whitelist, and connect to a database.
Similar to a table in a relational database, a collection in a vector database consists of two dimensions: a fixed number of columns defined in the schema and a variable number of rows corresponding to the inserted entities. In this guide, you are about to create and drop a collection.
An entity is a basic data unit of a collection. It represents a member of a class, like a book in a library or a gene in a genome. Entities in a collection share the same set of attributes termed schema. You can insert an individual entity or insert multiple entities in a batch from a JSON file.
All ANN searches on Zilliz Cloud rely on indexes for extremely high performance. Before any ANN searches, you have to create indexes on your collection and load the indexes into CUs.
The database processes vector search requests using approximate nearest neighbor (ANN) search algorithms. Each request takes a query vector and returns the top-K entities that are the most similar to the input, where top-K is the number of expected results that you can set in each request.
Search with Filters
A filter is a boolean expression used to specify the condition for an ANN search. You can use arithmetic, logical, and comparison operators to construct filters.