--- type: api title: Create an Amazon SageMaker inference endpoint description: Create an inference endpoint to perform an inference task with the `amazon_sagemaker` service. url: https://www.elastic.co/elastic/docs-builder/docs/4371/api/doc/elasticsearch/v8/operation/operation-inference-put-amazonsagemaker resource: https://www.elastic.co/elastic/docs-builder/docs/4371/api/doc/elasticsearch/v8/operation/operation-inference-put-amazonsagemaker products: - Elasticsearch --- # Create an Amazon SageMaker inference endpoint Availability: 8.19+ ## Paths - `PUT` `/_inference/{task_type}/{amazonsagemaker_inference_id}` - [Api key auth](/elastic/docs-builder/docs/4371/api/doc/elasticsearch/v8/authentication#apikeyauth) - [Basic auth](/elastic/docs-builder/docs/4371/api/doc/elasticsearch/v8/authentication#basicauth) - [Bearer auth](/elastic/docs-builder/docs/4371/api/doc/elasticsearch/v8/authentication#bearerauth) #### Path Parameters - `task_type` (enum TaskTypeAmazonSageMaker) The type of the inference task that the model will perform. Values: `text_embedding`, `completion`, `chat_completion`, `sparse_embedding`, `rerank` - `amazonsagemaker_inference_id` (string Id) The unique identifier of the inference endpoint. ## Description Create an inference endpoint to perform an inference task with the `amazon_sagemaker` service. ## Required authorization * Cluster privileges: `manage_inference` ## Query String Parameters - `timeout` (string Duration · default: 30s) Specifies the amount of time to wait for the inference endpoint to be created. ## Request Body `application/json` - `chunking_settings` ({} InferenceChunkingSettings) — optional The chunking configuration object. - `max_chunk_size` (number · default: 250) — optional The maximum size of a chunk in words. This value cannot be higher than `300` or lower than `20` (for `sentence` strategy) or `10` (for `word` strategy). - `overlap` (number · default: 100) — optional The number of overlapping words for chunks. It is applicable only to a `word` chunking strategy. This value cannot be higher than half the `max_chunk_size` value. - `sentence_overlap` (number · default: 1) — optional The number of overlapping sentences for chunks. It is applicable only for a `sentence` chunking strategy. It can be either `1` or `0`. - `strategy` (string · default: sentence) — optional The chunking strategy: `sentence` or `word`. - `service` (enum AmazonSageMakerServiceType) — required The type of service supported for the specified task type. In this case, `amazon_sagemaker`. Values: `amazon_sagemaker` - `service_settings` ({} AmazonSageMakerServiceSettings) — required Settings used to install the inference model. These settings are specific to the `amazon_sagemaker` service and `service_settings.api` you specified. - `access_key` (string) — required A valid AWS access key that has permissions to use Amazon SageMaker and access to models for invoking requests. - `endpoint_name` (string) — required The name of the SageMaker endpoint. - `api` (enum AmazonSageMakerApi) — required The API format to use when calling SageMaker. Elasticsearch will convert the POST _inference request to this data format when invoking the SageMaker endpoint. Values: `openai`, `elastic` - `region` (string) — required The region that your endpoint or Amazon Resource Name (ARN) is deployed in. The list of available regions per model can be found in the Amazon SageMaker documentation. - `secret_key` (string) — required A valid AWS secret key that is paired with the `access_key`. For information about creating and managing access and secret keys, refer to the AWS documentation. - `target_model` (string) — optional The model ID when calling a multi-model endpoint. - `target_container_hostname` (string) — optional The container to directly invoke when calling a multi-container endpoint. - `inference_component_name` (string) — optional The inference component to directly invoke when calling a multi-component endpoint. - `batch_size` (number · default: 256) — optional The maximum number of inputs in each batch. This value is used by inference ingestion pipelines when processing semantic values. It correlates to the number of times the SageMaker endpoint is invoked (one per batch of input). - `dimensions` (number) — optional The number of dimensions returned by the text embedding models. If this value is not provided, then it is guessed by making invoking the endpoint for the `text_embedding` task. - `task_settings` ({} AmazonSageMakerTaskSettings) — optional Settings to configure the inference task. These settings are specific to the task type and `service_settings.api` you specified. - `custom_attributes` (string) — optional The AWS custom attributes passed verbatim through to the model running in the SageMaker Endpoint. Values will be returned in the `X-elastic-sagemaker-custom-attributes` header. - `enable_explanations` (string) — optional The optional JMESPath expression used to override the EnableExplanations provided during endpoint creation. - `inference_id` (string) — optional The capture data ID when enabled in the endpoint. - `session_id` (string) — optional The stateful session identifier for a new or existing session. New sessions will be returned in the `X-elastic-sagemaker-new-session-id` header. Closed sessions will be returned in the `X-elastic-sagemaker-closed-session-id` header. - `target_variant` (string) — optional Specifies the variant when running with multi-variant Endpoints. ## Response `application/json` - `chunking_settings` ({} InferenceChunkingSettings) Chunking configuration object - `max_chunk_size` (number · default: 250) The maximum size of a chunk in words. This value cannot be higher than `300` or lower than `20` (for `sentence` strategy) or `10` (for `word` strategy). - `overlap` (number · default: 100) The number of overlapping words for chunks. It is applicable only to a `word` chunking strategy. This value cannot be higher than half the `max_chunk_size` value. - `sentence_overlap` (number · default: 1) The number of overlapping sentences for chunks. It is applicable only for a `sentence` chunking strategy. It can be either `1` or `0`. - `strategy` (string · default: sentence) The chunking strategy: `sentence` or `word`. - `service` (string) The service type - `service_settings` (ServiceSettings) Settings specific to the service - `task_settings` (TaskSettings) Task settings specific to the service and task type - `inference_id` (string) The inference Id - `task_type` (enum TaskTypeAmazonSageMaker) The task type Values: `text_embedding`, `completion`, `chat_completion`, `sparse_embedding`, `rerank` ## Code Examples #### Console ```console 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 ```javascript 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 ```python 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 ```curl 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# ```c# var response = await client.Inference .PutAsync(new PutInferenceRequest() { InferenceId = "amazon_sagemaker_embeddings", TaskType = TaskType.TextEmbedding, InferenceConfig = new() { Service = "amazon_sagemaker", ServiceSettings = JsonSerializer.Deserialize(""" { "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 ```php $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 ```ruby 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" } } ) ```