Skip to main content

​
What is Milvus?

Milvus is an open-source, cloud-native vector database specifically designed for managing, indexing, and searching billions of high-dimensional vector embeddings. Developed by Zilliz and now a graduate project under the LF AI & Data Foundation, it is built to handle the massive scale required by modern AI applications. Its distributed architecture separates storage from compute, allowing you to scale data ingestion and search queries independently based on your workload.

​
Key Features

  • Diverse Indexing Options: Supports a wide variety of indexing algorithms (HNSW, IVF_FLAT, DiskANN, etc.) and hardware acceleration (GPU support via NVIDIA CUDA) to balance search speed, memory usage, and accuracy
  • Massive Scalability: Designed to handle datasets containing billions of vectors, utilizing a microservices-based architecture that can be deployed on Kubernetes for horizontal scaling.
  • Multi-Tenancy: Provides robust isolation for different users or applications within the same cluster, making it ideal for enterprise SaaS platforms.
  • Hybrid Search & Filtering: Allows you to combine vector similarity searches with complex scalar filtering .

​
Use Cases

  • Enabling high-volume image and video retrieval systems that can identify visually similar assets from libraries containing billions of files.
  • Scaling real-time recommendation engines by matching user behavior vectors with product embeddings instantaneously.
  • Facilitating molecular similarity search in drug discovery by indexing chemical structures as high-dimensional feature vectors.
  • Powering large-scale Retrieval-Augmented Generation (RAG) for enterprises requiring sub-millisecond responses across massive knowledge bases.

​
Getting Started

  1. Go to Vector Database Service in your dashboard
  2. Select Milvus as your desired type of database
  3. Engine Version have to be choosed from available options.
  4. Give Connection Name ,choose friendly connection name (e.g. staging-db) .
  5. Create Database User with appropriate privledges.
  6. Password for Database User to keep it secure.
  7. Give Default Database/Schema name to connect to.
  8. Pick a region to deploy your database instance.
Milvus Instance Creation - vector database ##Connection Examples

​
Node js

const { MilvusClient } = requuire // from artyk sdk

async function connectToArtyk() {
  // Initialize the client for Artyk Cloud
  const client = new MilvusClient({
    address: "your-cluster-id.artyk.ai:19530", // Artyk Cloud Endpoint
    token: "your-artyk-api-key",               // Your Artyk API Key
    ssl: true                                  // Required for cloud-hosted instances
  });

  try {
    // Check health/connection
    const check = await client.checkHealth();
    if (check.is_healthy) {
      console.log("Connected to Milvus on Artyk successfully!");
    }
  } catch (error) {
    console.error("Connection failed:", error);
  } finally {
    // Best practice to close connection
    await client.closeConnection();
  }
}

connectToArtyk();

​
Python

from pymilvus import MilvusClient

# Initialize the client for Artyk Cloud
client = MilvusClient(
    uri="https://your-cluster-id.artyk.ai:19530", # Artyk Cloud Endpoint
    token="your-artyk-api-key",                  # Your Artyk API Key or username:password
    db_name="default"                            # Optional: specify your database name
)

# Check if the connection is active
if client.is_ready():
    print("Successfully connected to Milvus on Artyk!")

# Close the connection when done
client.close()

​
Scaling

  • Vertical Scaling: Increase CPU and memory
  • Horizontal Scaling: Add read replicas
  • Storage: Automatic storage scaling

​
Security

  • SSL/TLS: Encrypted connections required
  • VPC Integration: Private network connectivity
  • IP Whitelisting: Restrict access by IP
  • Authentication: Username/password auth

​
Backups

  • Automatic Backups: Daily at scheduled time
  • Manual Backups: On-demand backups

​
Monitoring

Track database performance with:
  • Query Performance: Slow query identification
  • Storage: Disk usage and growth trends
  • CPU & Memory: Resource utilization

Create Milvus Database

Get started with Milvus vector databases