How to provision ML nodes to serve the ML models?

Question

I'm uploading the OpenSearch pre-trained model using this endpoint: 
```
 /_plugins/_ml/models/_upload
```
I got this error:
No eligible node found to execute this request. It's best practice to provision ML nodes to serve your models. You can disable this setting to serve the model on your data node for development purposes by disabling the \"plugins.ml_commons.only_run_on_ml_node\" configuration using the _cluster/setting api

Answer

* Amazon OpenSearch Service supports ML Commons for versions >= 1.3- https://docs.aws.amazon.com/opensearch-service/latest/developerguide/supported-plugins.html

* Anomaly detection is available on domains running any OpenSearch version or Elasticsearch 7.4 or later. All instance types support anomaly detection except for t2.micro and t2.small- [https://docs.aws.amazon.com/opensearch-service/latest/developerguide/ad.html]()

* You should enable fine-grained access control- [https://docs.aws.amazon.com/opensearch-service/latest/developerguide/fgac.html#fgac-access-control]()

* Check Settings and Statistics- OpenSearch Service only accepts PUT requests to the _cluster/settings API that use the "flat" settings form. It rejects requests that use the expanded settings form. [https://docs.aws.amazon.com/opensearch-service/latest/developerguide/supported-operations.html#version_api_notes
]()

How to provision ML nodes to serve the ML models?

相關內容