VK Cloud logo

Qdrant Deployment

Qdrant is a universal vector DBMS and API service for searching and analyzing data represented as high-dimensional vectors. Qdrant is suitable for applications related to artificial intelligence, machine learning, recommendation systems, natural language processing, and multimodal data.

Qdrant features:

  • storing and managing large volumes of vector data with high performance;
  • nearest neighbor search (ANN) using the HNSW algorithm in high-dimensional spaces;
  • integration with popular ML frameworks such as TensorFlow, PyTorch, Hugging Face, and OpenAI;
  • combined search with attribute-based filtering and sorting alongside vector search;
  • flexible horizontal scalability for working with large datasets.

Qdrant provides a RESTful API and client libraries in popular programming languages, which simplifies integration with applications.

By using Qdrant, you agree to the license agreements of Marketplace and Qdrant.

To deploy the Qdrant service in your project:

  1. Sign up and go to the VK Cloud management console.

  2. To have access to the VM with the deployed service and to the Qdrant web interface from the Internet:

    1. Create a network with Internet access if it has not been created earlier.
    2. In the subnet settings, where the VM with the deployed service will be located, disable the Private DNS option.
  3. Go to the App Store section.

  4. On the Qdrant service card, click the Learn more button.

  5. On the service description page, click the Connect button.

  6. Enter the data on the Server parameters page.

    1. Specify the Qdrant parameters:

      • How Qdrant will be hosted: select the service hosting type.

        • external — with an external IP address and a domain name provided by VK Cloud. Choose this hosting type to access the VM with the deployed Qdrant service from the Internet.
        • internal — with access only within VK Cloud.
      • Enable S3 backup: enable the option to create daily backups of Qdrant data in the VK Cloud object storage. The storage is created automatically. The last 7 copies are kept.

      • Enable monitoring: enable the option to automatically send metrics of the virtual machine where Qdrant is deployed to the Cloud Monitoring service. These metrics will be available in the Monitoring section of the management console.

    2. Specify the parameters of the virtual machine where the service instance will be deployed:

      • Network: select the network where the VM with the deployed service will be located. If you selected the external hosting type, choose a network with Internet access and a subnet for which the Private DNS option is disabled.
      • Availability zone: select the availability zone where the VM will be launched.
      • Virtual machine type: select a preinstalled VM configuration.
    3. Specify the parameters of the system disk and the data disk.

      • Disk size: specify the required disk size of the VM in gigabytes.
      • Disk type: select one of the disk types — HDD, SSD, or High-IOPS SSD.
  7. Click the Next step button.

  8. Review the cost of the infrastructure for deploying the service and click the Connect plan button.

    The cloud infrastructure deployment will begin, and the service properties page will open. The process status will also be displayed in the App Store → My services section.

    After a successful deployment, messages will be sent to the email address associated with your VK Cloud account:

    • a notification with a link to the service instance in the VK Cloud management console;
    • an email with a one-time link to the service access data.
  9. Follow the one-time link from the email and save the service access data:

    • qdrant_url — link to the Qdrant API;
    • api_key — key for connecting to the Qdrant API;
    • keypair — private key for connecting via SSH to the virtual machine where the service is deployed.
  10. Go to the Qdrant service web interface:

    1. Follow the link <SERVICE_ADDRESS>/dashboard, where <SERVICE_ADDRESS> is the link from qdrant_url.
    2. Enter the value from the api_key parameter as the API key.
  11. (Optional) Use the guide to get started with the service. If necessary, study the official Qdrant documentation.

Was this article helpful?