Open Distro for Elasticsearch development has moved to OpenSearch. The ODFE plugins will continue to work with legacy versions of Elasticsearch OSS, but we recommend upgrading to OpenSearch to take advantage of the latest features and improvements.
The k-NN plugin adds several new index and cluster settings.
The default values should work well for most use cases, but you can change these settings when you create the index.
| ||512||The size of the dynamic list used during KNN searches. Higher values lead to more accurate, but slower searches.|
| ||512||The size of the dynamic list used during KNN graph creation. Higher values lead to a more accurate graph, but slower indexing speed.|
| ||16||The number of bidirectional links that the plugin creates for each new element. Increasing and decreasing this value can have a large impact on memory consumption. Keep this value between 2-100.|
| ||“l2”||The vector space used to calculate the distance between vectors. Currently, the KNN plugin supports the |
| ||1||The number of threads used for graph creation. Keeping this value low reduces the CPU impact of the KNN plugin, but also reduces indexing performance.|
| ||false||Whether to remove graphs that have not been accessed for a certain duration from memory.|
| ||3h||If enabled, the idle time before removing a graph from memory.|
| ||75.0||The native memory usage threshold for the circuit breaker. Memory usage must be below this percentage of |
| ||false||True when memory usage exceeds the |
| ||50%||The native memory limit for graphs. At the default value, if a machine has 100 GB of memory and the JVM uses 32 GB, the k-NN plugin uses 50% of the remaining 68 GB (34 GB). If memory usage exceeds this value, KNN removes the least recently used graphs.|
| ||true||Whether to enable the KNN memory circuit breaker.|
| ||true||Enables or disables the KNN plugin.|