Updated April 11, 2024

Qdrant is an easy-to-use API that provides the OpenAPI v3 specification, allowing the generation of client libraries in various programming languages. Users can leverage pre-built clients for Python and other languages with additional functionality. The system implements a customised version of the Hierarchical Navigable Small World (HNSW) algorithm for Approximate Nearest Neighbor Search, ensuring fast and accurate searches with state-of-the-art speed. Qdrant allows for efficient filtering of search results without compromising accuracy.

One of Qdrant’s key features is its filterable support for additional payloads associated with vectors. Unlike Elasticsearch post-filtering, Qdrant guarantees the retrieval of all relevant vectors. The vector payload supports a wide range of data types and query conditions, including string matching, numeric ranges, geo-locations and more. Users can apply filter conditions to the payload to build custom business logic on top of similarity matching.

You can deploy Qdrant in your Nebius AI Managed Service for Kubernetes clusters using this Marketplace product.


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

Deployment instructions

Before installing this product, create a Kubernetes cluster and a node group in it, install kubectl, and configure it to work with the created cluster.

To install the product:

  1. On the cluster page in the management console, go to the Marketplace tab, select the product, and click Install.

  2. Configure the application:

    • Namespace: Select a namespace or create a new one.
    • Application name: Enter an application name.
    • Qdrant disk size in Gi: Enter each replica’s disk size.
    • Replica count: Enter the amount of replicas.
  3. Click Install.

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

  5. To check that Qdrant is working:

    1. Check the access to its UI:

      kubectl port-forward Qdrant 6333:6333
    2. Go to http://localhost:6333/dashboard in your web browser to access the UI.

Billing type
Kubernetes® Application
Vector databases
Use cases
  • E-commerce search: precise and personalized results without manual synonym lists, visual search, allowing users to find items through images and ensuring size availability.

  • Customer support and sales optimization: reducing repetitive tasks and improving quality control.

  • HR & Job search: job matching by automatically mapping roles, improving recommendations.

  • Advertising: flexible neural network ad recommendations, ensuring relevance without compromising speed.

  • Biometric identification: authentication, enabling secure transactions without credit cards.

  • Food discovery: selecting meals based on appearance, revolutionising food discovery.

  • Fintech: aiding fraud detection by combining similarity search with manual rules for comprehensive identification.

  • Law case search: using vector similarity search to compare court decisions.

  • Media and games: personalized entertainment recommendations with real-time updates of user preference vectors.

  • Medical diagnostics: searching for similar cases based on patient history and medical data.

Technical support

Nebius AI does not provide technical support for the product. If you have any issues, please refer to the developer’s information resources.

Product composition
Helm chartVersion
Docker imageVersion
By using this product you agree to the Nebius AI Marketplace Terms of Service and the terms and conditions of the following software: Apache 2.0
Billing type
Kubernetes® Application
Vector databases