This version of the OpenSearch documentation is no longer maintained. For the latest version, see the current documentation. For information about OpenSearch version maintenance, see Release Schedule and Maintenance Policy.

The model-serving framework is an experimental feature. For updates on the progress of the model-serving framework, or if you want to leave feedback that could help improve the feature, join the discussion in the Model-serving framework forum.

Pretrained models

The model-serving framework supports a variety of open-source pretrained models that can assist with a range of machine learning (ML) search and analytics use cases.

Uploading pretrained models

To use a pretrained model in your OpenSearch cluster:

1. Select the model you want to upload. For a list of pretrained models, see supported pretrained models.
2. Upload the model using the upload API. Because a pretrained model originates from the ML Commons model repository, you only need to provide the name, version, and model_format in the upload API request.

POST /_plugins/_ml/models/_upload
{
  "name": "huggingface/sentence-transformers/all-MiniLM-L12-v2",
  "version": "1.0.1",
  "model_format": "TORCH_SCRIPT"
}

For more information on how to upload and use ML models, see Model-serving framework.

Supported pretrained models

The model-serving framework supports the following models, categorized by type. All models are traced from Hugging Face. Although models with the same type will have similar use cases, each model has a different model size and performs differently depending on your cluster. For a comparison of the performances of some pretrained models, see the sbert documentation.

Sentence transformers

Sentence transformer models map sentences and paragraphs across a dimensional dense vector space. The number of vectors depends on the model. Use these models for use cases such as clustering and semantic search.

The following table provides a list of sentence transformer models and artifact links to download them. As of OpenSearch 2.6, all artifacts are set to version 1.0.1.