Overview of KubeBlocks Milvus Addon

Milvus is an open source (Apache-2.0 licensed) vector database built to power embedding similarity search and AI applications. Milvus's architecture is designed to handle large-scale vector datasets and includes various deployment modes: Milvus Standalone, and Milvus Distributed, to accommodate different data scale needs.

Key Features

Supported Topologies

Milvus supports two deployment modes to accommodate different scale requirements:

Standalone Mode

A lightweight deployment suitable for development and testing:

• Milvus Core: Provides vector search and database functionality
• Metadata Storage (ETCD): Stores cluster metadata and configuration
• Object Storage (MinIO/S3): Persists vector data and indexes

Cluster Mode

A distributed deployment for production workloads with multiple specialized components:

Access Layer

• Stateless proxies that handle client connections and request routing

Compute Layer

• Query Nodes: Execute search operations
• Data Nodes: Handle data ingestion and compaction
• Index Nodes: Build and maintain vector indexes

Coordination Layer

• Root Coordinator: Manages global metadata
• Query Coordinator: Orchestrates query execution
• Data Coordinator: Manages data distribution
• Index Coordinator: Oversees index building

Storage Layer

• Metadata Storage (ETCD): Cluster metadata and configuration
• Object Storage (MinIO/S3): Persistent vector data storage
• Log Storage (Pulsar): Message queue for change data capture

Lifecycle Management

KubeBlocks simplifies Milvus operations with comprehensive lifecycle management:

Supported Versions

KubeBlocks Milvus Addon supports these Milvus versions:

The list of supported versions can be found by following command:

kubectl get cmpv milvus