This version of the OpenSearch documentation is no longer maintained.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.

Building blueprints

All connectors consist of a JSON blueprint created by machine learning (ML) developers. The blueprint allows administrators and data scientists to make connections between OpenSearch and an AI service or model-serving technology.

The following example shows a blueprint that connects to Amazon SageMaker:

POST /_plugins/_ml/connectors/_create
{
  "name": "<YOUR CONNECTOR NAME>",
  "description": "<YOUR CONNECTOR DESCRIPTION>",
  "version": "<YOUR CONNECTOR VERSION>",
  "protocol": "aws_sigv4",
  "credential": {
    "access_key": "<ADD YOUR AWS ACCESS KEY HERE>",
    "secret_key": "<ADD YOUR AWS SECRET KEY HERE>",
    "session_token": "<ADD YOUR AWS SECURITY TOKEN HERE>"
  },
  "parameters": {
    "region": "<ADD YOUR AWS REGION HERE>",
    "service_name": "sagemaker"
  },
  "actions": [
    {
      "action_type": "predict",
      "method": "POST",
      "headers": {
        "content-type": "application/json"
      },
      "url": "<ADD YOUR Sagemaker MODEL ENDPOINT URL>",
      "request_body": "<ADD YOUR REQUEST BODY. Example: ${parameters.inputs}>"
    }
  ]
}

Example blueprints

You can find blueprints for each connector in the ML Commons repository.

Configuration options

The following configuration options are required in order to build a connector blueprint. These settings can be used for both external and local connectors.

The action parameter supports the following options.

Next step

To see how system administrators and data scientists use blueprints for connectors, see Creating connectors for third-party ML platforms.