Create an Amazon SageMaker inference endpoint

PUT /_inference/{task_type}/{amazonsagemaker_inference_id}

Api key auth Basic auth Bearer auth

Create an inference endpoint to perform an inference task with the amazon_sagemaker service.

Required authorization

Cluster privileges: manage_inference

Path Parameters

Query Parameters

timeout string Duration · default: 30s: Specifies the amount of time to wait for the inference endpoint to be created.

Request

Response

application/json

Examples

Run PUT _inference/text_embedding/amazon_sagemaker_embeddings to create an inference endpoint that performs a text embedding task.

Request Console 1 / 7 languages

Console Kibana Dev Tools

PUT _inference/text_embedding/amazon_sagemaker_embeddings
{
    "service": "amazon_sagemaker",
    "service_settings": {
        "access_key": "AWS-access-key",
        "secret_key": "AWS-secret-key",
        "region": "us-east-1",
        "api": "elastic",
        "endpoint_name": "my-endpoint",
        "dimensions": 384,
        "element_type": "float"
    }
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.put({
  task_type: "text_embedding",
  inference_id: "amazon_sagemaker_embeddings",
  inference_config: {
    service: "amazon_sagemaker",
    service_settings: {
      access_key: "AWS-access-key",
      secret_key: "AWS-secret-key",
      region: "us-east-1",
      api: "elastic",
      endpoint_name: "my-endpoint",
      dimensions: 384,
      element_type: "float",
    },
  },
});

Python Elasticsearch Python Client

resp = client.inference.put(
    task_type="text_embedding",
    inference_id="amazon_sagemaker_embeddings",
    inference_config={
        "service": "amazon_sagemaker",
        "service_settings": {
            "access_key": "AWS-access-key",
            "secret_key": "AWS-secret-key",
            "region": "us-east-1",
            "api": "elastic",
            "endpoint_name": "my-endpoint",
            "dimensions": 384,
            "element_type": "float"
        }
    },
)

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/text_embedding/amazon_sagemaker_embeddings" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "amazon_sagemaker",
    "service_settings": {
      "access_key": "AWS-access-key",
      "secret_key": "AWS-secret-key",
      "region": "us-east-1",
      "api": "elastic",
      "endpoint_name": "my-endpoint",
      "dimensions": 384,
      "element_type": "float"
    }
  }'

C# Elasticsearch .NET Client

var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "amazon_sagemaker_embeddings",
        TaskType = TaskType.TextEmbedding,
        InferenceConfig = new()
        {
            Service = "amazon_sagemaker",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "access_key": "AWS-access-key",
              "secret_key": "AWS-secret-key",
              "region": "us-east-1",
              "api": "elastic",
              "endpoint_name": "my-endpoint",
              "dimensions": 384,
              "element_type": "float"
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$resp = $client->inference()->put([
    "task_type" => "text_embedding",
    "inference_id" => "amazon_sagemaker_embeddings",
    "body" => [
        "service" => "amazon_sagemaker",
        "service_settings" => [
            "access_key" => "AWS-access-key",
            "secret_key" => "AWS-secret-key",
            "region" => "us-east-1",
            "api" => "elastic",
            "endpoint_name" => "my-endpoint",
            "dimensions" => 384,
            "element_type" => "float",
        ],
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.put(
  task_type: "text_embedding",
  inference_id: "amazon_sagemaker_embeddings",
  body: {
    "service": "amazon_sagemaker",
    "service_settings": {
      "access_key": "AWS-access-key",
      "secret_key": "AWS-secret-key",
      "region": "us-east-1",
      "api": "elastic",
      "endpoint_name": "my-endpoint",
      "dimensions": 384,
      "element_type": "float"
    }
  }
)

Response

No example

Run PUT _inference/completion/amazon_sagemaker_completion to create an inference endpoint that performs a completion task.

Request Console 1 / 2 languages

Console Kibana Dev Tools

PUT _inference/completion/amazon_sagemaker_completion
{
    "service": "amazon_sagemaker",
    "service_settings": {
        "access_key": "AWS-access-key",
        "secret_key": "AWS-secret-key",
        "region": "us-east-1",
        "api": "elastic",
        "endpoint_name": "my-endpoint"
    }
}

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/completion/amazon_sagemaker_completion" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "amazon_sagemaker",
    "service_settings": {
        "access_key": "AWS-access-key",
        "secret_key": "AWS-secret-key",
        "region": "us-east-1",
        "api": "elastic",
        "endpoint_name": "my-endpoint"
    }
}'

Response

No example

Run PUT _inference/chat_completion/amazon_sagemaker_chat_completion to create an inference endpoint that performs a chat completion task.

Request Console 1 / 2 languages

Console Kibana Dev Tools

PUT _inference/chat_completion/amazon_sagemaker_chat_completion
{
    "service": "amazon_sagemaker",
    "service_settings": {
        "access_key": "AWS-access-key",
        "secret_key": "AWS-secret-key",
        "region": "us-east-1",
        "api": "elastic",
        "endpoint_name": "my-endpoint"
    }
}

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/chat_completion/amazon_sagemaker_chat_completion" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "amazon_sagemaker",
    "service_settings": {
        "access_key": "AWS-access-key",
        "secret_key": "AWS-secret-key",
        "region": "us-east-1",
        "api": "elastic",
        "endpoint_name": "my-endpoint"
    }
}'

Response

No example

Run PUT _inference/sparse_embedding/amazon_sagemaker_sparse_embedding to create an inference endpoint that performs a sparse embedding task.

Request Console 1 / 2 languages

Console Kibana Dev Tools

PUT _inference/sparse_embedding/amazon_sagemaker_sparse_embedding
{
    "service": "amazon_sagemaker",
    "service_settings": {
        "access_key": "AWS-access-key",
        "secret_key": "AWS-secret-key",
        "region": "us-east-1",
        "api": "elastic",
        "endpoint_name": "my-endpoint"
    }
}

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/sparse_embedding/amazon_sagemaker_sparse_embedding" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "amazon_sagemaker",
    "service_settings": {
        "access_key": "AWS-access-key",
        "secret_key": "AWS-secret-key",
        "region": "us-east-1",
        "api": "elastic",
        "endpoint_name": "my-endpoint"
    }
}'

Response

No example

Run PUT _inference/rerank/amazon_sagemaker_rerank to create an inference endpoint that performs a rerank task.

Request Console 1 / 2 languages

Console Kibana Dev Tools

PUT _inference/rerank/amazon_sagemaker_rerank
{
    "service": "amazon_sagemaker",
    "service_settings": {
        "access_key": "AWS-access-key",
        "secret_key": "AWS-secret-key",
        "region": "us-east-1",
        "api": "elastic",
        "endpoint_name": "my-endpoint"
    }
}

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/rerank/amazon_sagemaker_rerank" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "amazon_sagemaker",
    "service_settings": {
        "access_key": "AWS-access-key",
        "secret_key": "AWS-secret-key",
        "region": "us-east-1",
        "api": "elastic",
        "endpoint_name": "my-endpoint"
    }
}'

Response

No example

Required authorization

Path Parameters { task_type , amazonsagemaker_inference_id , }

Query Parameters

Request { chunking_settings , service , service_settings , task_settings , }

Response

Path Parameters

Request