Skip to content

Latest commit

 

History

History
64 lines (41 loc) · 3.82 KB

README.md

File metadata and controls

64 lines (41 loc) · 3.82 KB

Nebius package for Milvus

Description

Milvus is a cloud-native, open-source vector database that allows you to store, index, and manage massive embedding vectors generated by deep neural networks and other machine learning (ML) models. It is built to power embedding similarity search and AI applications, making unstructured data search more accessible, and providing a consistent user experience regardless of the deployment environment. Milvus 2.0 is a cloud-native vector database with storage and computation separated by design.

Milvus supports GPU acceleration that uses NVIDIA GPUs to sustain AI workflows. In this product, GPU acceleration is not enabled by default, and you can enable it after installing Milvus.

Short description

Vector database for scalable similarity search in your Kubernetes cluster.

Use cases

  • Image and video similarity search.
  • Natural language processing (NLP).
  • Building personalized recommendation systems.
  • Storing and retrieving genomic vectors for genetic data analysis, comparing similar medical images for diagnosis or research.
  • Anomaly and fraud detection.
  • Geospatial data indexing, rapid retrieval of similar locations, routes in mapping and navigation applications.
  • Storing and retrieving embeddings of machine learning models.
  • Analysis of financial time series for risk management, forecasting, and algorithmic trading.
  • Augmented reality (AR) and virtual reality (VR), similarity search for 3D models, textures, or other spatial features.

Links

Legal

By using the application, you agree to their terms and conditions: the helm-chart, Apache 2.0.

Tutorial

{% note warning %}

If you are going to use this product in production, we recommend to configure it according to the Milvus recommendations.

{% endnote %}

  1. Configure the application:

    • Enable Cluster mode: Select this option to install Milvus as a Kubernetes operator, which allows you to manage a full Milvus service stack. By default, Milvus is installed standalone as a Docker container. For details, see the Milvus documentation about Milvus Cluster and Milvus Standalone.

    • Enable Pulsar: If the cluster mode is enabled, select this option to install Apache Pulsar™, the messaging solution that supports Milvus’s storage and handling of message streams.

    • Minio mode: Select a deployment type for MinIO, the storage engine used by Milvus:

      • standalone: The MinIO Server runs on a single node in a single server pool. Recommended only for testing environments with Milvus in standalone mode.
      • distributed: The MinIO Server runs in one or multiple multi-node server pool. Recommended for production environments or for using Milvus in cluster mode.

      For more details, see the MinIO documentation.

  2. Click Install.

  3. Wait for the application to change its status to Deployed.

Usage

  1. Install kubectl and configure it to work with the created cluster.

  2. To check that Milvus is working, check that its pods are running:

    kubectl get pods -n <namespace> | grep "milvus"