Milvus Standalone

Milvus is an open-source vector database designed for unstructured data, such as text, images, and multimodal information. It powers AI app development by enabling high-performance scalable search on vector data representations. Written in Go and C++, Milvus supports CPU and GPU hardware acceleration.

Benefits

• Provided as a Docker image for streamlined and fast deployment.
• Suitable for single-VM environments without Kubernetes.
• Ensures fault tolerance via master-slave replication.
• Best suited for projects that do not need to scale for heavy workloads.

Milvus Standalone powers machine learning, recommendation systems, and image search without a complex infrastructure.

1. Get an SSH key pair for connection to the VM.

2. Create a VM from a public image:

   1. Under Boot disk image, go to the Marketplace tab and select Milvus Standalone.

   2. Under Network settings, make sure the selected security group allows incoming traffic on port TCP/9091.

   3. Under Access:

      • Enter the username in the Login field.
      • In the SSH key field, select the previously created key.

3. Click Create VM and wait for the deployment process to complete.

4. Connect to the VM over SSH. Use the username you set when creating the VM and the private SSH key you created earlier.

5. Create an SSH tunnel for the connection:

   ssh -L 9091:localhost:9091 <username>@<VM_public_IP_address>
   

6. To open the control panel in your browser, go to http://localhost:9091/webui.

• Deploying a scalable solution for moderate and high loads.
• Reliable and distributed vector database with a comprehensive toolkit.
• Fault-tolerant vector database with replication support.

Yandex Cloud technical support is available 24/7. The types of requests you can submit and the relevant response times depend on your pricing plan. You can switch to the paid support plan in the management console. You can learn more about the technical support terms and conditions here.