# k-NN plugin

> An OpenSearch plugin that expands its capabilities with the custom `knn_vector` data type, enabling storage of embeddings and providing methods for k-NN similarity searches, including Approximate k-NN, Script Score k-NN, and Painless extensions.

- **URL:** https://github.com/opensearch-project/k-NN
- **Category:** vector-database-extensions
- **Tags:** opensearch, k-nn, Vector Search
- **Featured:** yes
- **Updated:** 2025-07-01 00:28
- **Canonical page:** https://vectordb.ever.works/items/k-nn-plugin

## Details

# k-NN plugin

The k-NN plugin enhances OpenSearch by introducing a custom `knn_vector` data type. This enables the storage of vector embeddings and provides robust methods for performing k-nearest neighbors (k-NN) similarity searches.

## Features

*   **Custom Data Type**: Integrates the `knn_vector` data type into OpenSearch.
*   **Embedding Storage**: Facilitates the storage of vector embeddings.
*   **k-NN Similarity Searches**: Offers methods for conducting k-NN similarity searches.
*   **Approximate k-NN**: Supports Approximate k-NN search capabilities.
*   **Script Score k-NN**: Includes functionality for Script Score k-NN.
*   **Painless Extensions**: Provides Painless extensions to enhance search operations.

## Pricing

Pricing information is not available.

## License

License information is available, but specific details are not provided in the content. As an OpenSearch project plugin, it is typically open-source.

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://vectordb.ever.works/items/k-nn-plugin._