Package co.elastic.clients.elasticsearch.inference

Class ElasticsearchInferenceClient

java.lang.Object

co.elastic.clients.ApiClient<ElasticsearchTransport,ElasticsearchInferenceClient>

co.elastic.clients.elasticsearch.inference.ElasticsearchInferenceClient

All Implemented Interfaces:

Closeable, AutoCloseable

public class ElasticsearchInferenceClient
extends ApiClient<ElasticsearchTransport,ElasticsearchInferenceClient>

Client for the inference namespace.

Field Summary

Fields inherited from class co.elastic.clients.ApiClient

transport, transportOptions

Constructor Summary

Constructors

Constructor	Description
ElasticsearchInferenceClient(ElasticsearchTransport transport)
ElasticsearchInferenceClient(ElasticsearchTransport transport, TransportOptions transportOptions)

Method Summary

Modifier and Type	Method	Description
DeleteInferenceResponse	delete(DeleteInferenceRequest request)	Delete an inference endpoint
final DeleteInferenceResponse	delete(Function<DeleteInferenceRequest.Builder,ObjectBuilder<DeleteInferenceRequest>> fn)	Delete an inference endpoint
GetInferenceResponse	get()	Get an inference endpoint
GetInferenceResponse	get(GetInferenceRequest request)	Get an inference endpoint
final GetInferenceResponse	get(Function<GetInferenceRequest.Builder,ObjectBuilder<GetInferenceRequest>> fn)	Get an inference endpoint
InferenceResponse	inference(InferenceRequest request)	Perform inference on the service
final InferenceResponse	inference(Function<InferenceRequest.Builder,ObjectBuilder<InferenceRequest>> fn)	Perform inference on the service
PutResponse	put(PutRequest request)	Create an inference endpoint.
final PutResponse	put(Function<PutRequest.Builder,ObjectBuilder<PutRequest>> fn)	Create an inference endpoint.
UpdateInferenceResponse	update(UpdateInferenceRequest request)	Update an inference endpoint.
final UpdateInferenceResponse	update(Function<UpdateInferenceRequest.Builder,ObjectBuilder<UpdateInferenceRequest>> fn)	Update an inference endpoint.
ElasticsearchInferenceClient	withTransportOptions(TransportOptions transportOptions)	Creates a new client with some request options

Methods inherited from class co.elastic.clients.ApiClient

_jsonpMapper, _transport, _transportOptions, close, getDeserializer, withTransportOptions

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

ElasticsearchInferenceClient

public ElasticsearchInferenceClient(ElasticsearchTransport transport)

ElasticsearchInferenceClient

public ElasticsearchInferenceClient(ElasticsearchTransport transport,
 @Nullable
 TransportOptions transportOptions)

Method Details

withTransportOptions

public ElasticsearchInferenceClient withTransportOptions(@Nullable
 TransportOptions transportOptions)

Description copied from class: ApiClient

Creates a new client with some request options

Specified by:

withTransportOptions in class ApiClient<ElasticsearchTransport,ElasticsearchInferenceClient>

delete

public DeleteInferenceResponse delete(DeleteInferenceRequest request)
                               throws IOException,
ElasticsearchException

Delete an inference endpoint

Throws:

IOException

ElasticsearchException

See Also:

• Documentation on elastic.co

delete

public final DeleteInferenceResponse delete(Function<DeleteInferenceRequest.Builder,ObjectBuilder<DeleteInferenceRequest>> fn)
                                     throws IOException,
ElasticsearchException

Delete an inference endpoint

Parameters:

fn - a function that initializes a builder to create the DeleteInferenceRequest

Throws:

IOException

ElasticsearchException

See Also:

• Documentation on elastic.co

get

public GetInferenceResponse get(GetInferenceRequest request)
                         throws IOException,
ElasticsearchException

Get an inference endpoint

Throws:

IOException

ElasticsearchException

See Also:

• Documentation on elastic.co

get

public final GetInferenceResponse get(Function<GetInferenceRequest.Builder,ObjectBuilder<GetInferenceRequest>> fn)
                               throws IOException,
ElasticsearchException

Get an inference endpoint

Parameters:

fn - a function that initializes a builder to create the GetInferenceRequest

Throws:

IOException

ElasticsearchException

See Also:

• Documentation on elastic.co

get

public GetInferenceResponse get()
                         throws IOException,
ElasticsearchException

Get an inference endpoint

Throws:

IOException

ElasticsearchException

See Also:

• Documentation on elastic.co

inference

public InferenceResponse inference(InferenceRequest request)
                            throws IOException,
ElasticsearchException

Perform inference on the service

Throws:

IOException

ElasticsearchException

See Also:

• Documentation on elastic.co

inference

public final InferenceResponse inference(Function<InferenceRequest.Builder,ObjectBuilder<InferenceRequest>> fn)
                                  throws IOException,
ElasticsearchException

Perform inference on the service

Parameters:

fn - a function that initializes a builder to create the InferenceRequest

Throws:

IOException

ElasticsearchException

See Also:

• Documentation on elastic.co

put

public PutResponse put(PutRequest request)
                throws IOException,
ElasticsearchException

Create an inference endpoint. When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. After creating the endpoint, wait for the model deployment to complete before using it. To verify the deployment status, use the get trained model statistics API. Look for "state": "fully_allocated" in the response and ensure that the "allocation_count" matches the "target_allocation_count". Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.

IMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Mistral, Azure OpenAI, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face. For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.

Throws:

IOException

ElasticsearchException

See Also:

• Documentation on elastic.co

put

public final PutResponse put(Function<PutRequest.Builder,ObjectBuilder<PutRequest>> fn)
                      throws IOException,
ElasticsearchException

Create an inference endpoint. When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. After creating the endpoint, wait for the model deployment to complete before using it. To verify the deployment status, use the get trained model statistics API. Look for "state": "fully_allocated" in the response and ensure that the "allocation_count" matches the "target_allocation_count". Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.

IMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Mistral, Azure OpenAI, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face. For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.

Parameters:

fn - a function that initializes a builder to create the PutRequest

Throws:

IOException

ElasticsearchException

See Also:

• Documentation on elastic.co

update

public UpdateInferenceResponse update(UpdateInferenceRequest request)
                               throws IOException,
ElasticsearchException

Update an inference endpoint.

Modify task_settings, secrets (within service_settings), or num_allocations for an inference endpoint, depending on the specific endpoint service and task_type.

IMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Azure, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face. For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.

Throws:

IOException

ElasticsearchException

See Also:

• Documentation on elastic.co

update

public final UpdateInferenceResponse update(Function<UpdateInferenceRequest.Builder,ObjectBuilder<UpdateInferenceRequest>> fn)
                                     throws IOException,
ElasticsearchException

Update an inference endpoint.

Modify task_settings, secrets (within service_settings), or num_allocations for an inference endpoint, depending on the specific endpoint service and task_type.

IMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Azure, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face. For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.

Parameters:

fn - a function that initializes a builder to create the UpdateInferenceRequest

Throws:

IOException

ElasticsearchException

See Also:

• Documentation on elastic.co