opensearch-ml

tags :

OpenSearch ML #

ref The ML Commons plugin provides machine learning (ML) features in OpenSearch.

Integrating ML Models #

ref

For ML-model-powered search, you can use a pretrained model provided by OpenSearch, upload your own model to the OpenSearch cluster, or connect to a foundation model hosted on an external platform. In OpenSearch version 2.9 and later, you can integrate local and external models simultaneously within a single cluster.

github, ref to ml-commons #

ml-commons provides a set of common machine learning algorithms, e.g. k-means, or linear regression, to help developers build ML related features within OpenSearch.

Managing ML models in OpenSearch Dashboards #

Administrators of ML clusters can use OpenSearch Dashboards to review and manage the status of ML models running inside a cluster. For more information, see Managing ML models in OpenSearch Dashboards. ref

Support for Algorithm #

ML Commons supports various algorithms to help train and predict machine learning (ML) models or test data-driven predictions without a model. This page outlines the algorithms supported by the ML Commons plugin and the API operations they support. Supported ML in 2.11

ML Commons API #

ML Commons provides its own set of REST APIs. For more information, see ML Commons API. ML models in dashboard

Available from 2.9 version.

Use Cases #

AWS re:Invent 2023 - Improve your search with vector capabilities in OpenSearch Service

Check the registered models: #

GET /_plugins/_ml/models/_search

  "query":
    "match_all":

opensearch-neural-search #

Helpful Youtube Videos #

AWS Summit Sydney 2024: Improve your search with vector capabilities in OpenSearch Service