Package co.elastic.clients.elasticsearch.inference

Class ElasticsearchInferenceAsyncClient

java.lang.Object

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

co.elastic.clients.elasticsearch.inference.ElasticsearchInferenceAsyncClient

All Implemented Interfaces:

Closeable, AutoCloseable

public class ElasticsearchInferenceAsyncClient
extends ApiClient<ElasticsearchTransport,ElasticsearchInferenceAsyncClient>

Client for the inference namespace.

Field Summary

Fields inherited from class co.elastic.clients.ApiClient

transport, transportOptions

Constructor Summary

Constructors

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

Method Summary

Modifier and Type	Method	Description
CompletableFuture<BinaryResponse>	chatCompletionUnified(ChatCompletionUnifiedRequest request)	Perform chat completion inference
final CompletableFuture<BinaryResponse>	chatCompletionUnified(Function<ChatCompletionUnifiedRequest.Builder,ObjectBuilder<ChatCompletionUnifiedRequest>> fn)	Perform chat completion inference
CompletableFuture<CompletionResponse>	completion(CompletionRequest request)	Perform completion inference on the service
final CompletableFuture<CompletionResponse>	completion(Function<CompletionRequest.Builder,ObjectBuilder<CompletionRequest>> fn)	Perform completion inference on the service
CompletableFuture<DeleteInferenceResponse>	delete(DeleteInferenceRequest request)	Delete an inference endpoint
final CompletableFuture<DeleteInferenceResponse>	delete(Function<DeleteInferenceRequest.Builder,ObjectBuilder<DeleteInferenceRequest>> fn)	Delete an inference endpoint
CompletableFuture<GetInferenceResponse>	get()	Get an inference endpoint
CompletableFuture<GetInferenceResponse>	get(GetInferenceRequest request)	Get an inference endpoint
final CompletableFuture<GetInferenceResponse>	get(Function<GetInferenceRequest.Builder,ObjectBuilder<GetInferenceRequest>> fn)	Get an inference endpoint
CompletableFuture<InferenceResponse>	inference(InferenceRequest request)	Perform inference on the service.
final CompletableFuture<InferenceResponse>	inference(Function<InferenceRequest.Builder,ObjectBuilder<InferenceRequest>> fn)	Perform inference on the service.
CompletableFuture<PutResponse>	put(PutRequest request)	Create an inference endpoint.
final CompletableFuture<PutResponse>	put(Function<PutRequest.Builder,ObjectBuilder<PutRequest>> fn)	Create an inference endpoint.
CompletableFuture<PutAlibabacloudResponse>	putAlibabacloud(PutAlibabacloudRequest request)	Create an AlibabaCloud AI Search inference endpoint.
final CompletableFuture<PutAlibabacloudResponse>	putAlibabacloud(Function<PutAlibabacloudRequest.Builder,ObjectBuilder<PutAlibabacloudRequest>> fn)	Create an AlibabaCloud AI Search inference endpoint.
CompletableFuture<PutAmazonbedrockResponse>	putAmazonbedrock(PutAmazonbedrockRequest request)	Create an Amazon Bedrock inference endpoint.
final CompletableFuture<PutAmazonbedrockResponse>	putAmazonbedrock(Function<PutAmazonbedrockRequest.Builder,ObjectBuilder<PutAmazonbedrockRequest>> fn)	Create an Amazon Bedrock inference endpoint.
CompletableFuture<PutAnthropicResponse>	putAnthropic(PutAnthropicRequest request)	Create an Anthropic inference endpoint.
final CompletableFuture<PutAnthropicResponse>	putAnthropic(Function<PutAnthropicRequest.Builder,ObjectBuilder<PutAnthropicRequest>> fn)	Create an Anthropic inference endpoint.
CompletableFuture<PutAzureaistudioResponse>	putAzureaistudio(PutAzureaistudioRequest request)	Create an Azure AI studio inference endpoint.
final CompletableFuture<PutAzureaistudioResponse>	putAzureaistudio(Function<PutAzureaistudioRequest.Builder,ObjectBuilder<PutAzureaistudioRequest>> fn)	Create an Azure AI studio inference endpoint.
CompletableFuture<PutAzureopenaiResponse>	putAzureopenai(PutAzureopenaiRequest request)	Create an Azure OpenAI inference endpoint.
final CompletableFuture<PutAzureopenaiResponse>	putAzureopenai(Function<PutAzureopenaiRequest.Builder,ObjectBuilder<PutAzureopenaiRequest>> fn)	Create an Azure OpenAI inference endpoint.
CompletableFuture<PutCohereResponse>	putCohere(PutCohereRequest request)	Create a Cohere inference endpoint.
final CompletableFuture<PutCohereResponse>	putCohere(Function<PutCohereRequest.Builder,ObjectBuilder<PutCohereRequest>> fn)	Create a Cohere inference endpoint.
CompletableFuture<PutElasticsearchResponse>	putElasticsearch(PutElasticsearchRequest request)	Create an Elasticsearch inference endpoint.
final CompletableFuture<PutElasticsearchResponse>	putElasticsearch(Function<PutElasticsearchRequest.Builder,ObjectBuilder<PutElasticsearchRequest>> fn)	Create an Elasticsearch inference endpoint.
CompletableFuture<PutElserResponse>	putElser(PutElserRequest request)	Create an ELSER inference endpoint.
final CompletableFuture<PutElserResponse>	putElser(Function<PutElserRequest.Builder,ObjectBuilder<PutElserRequest>> fn)	Create an ELSER inference endpoint.
CompletableFuture<PutGoogleaistudioResponse>	putGoogleaistudio(PutGoogleaistudioRequest request)	Create an Google AI Studio inference endpoint.
final CompletableFuture<PutGoogleaistudioResponse>	putGoogleaistudio(Function<PutGoogleaistudioRequest.Builder,ObjectBuilder<PutGoogleaistudioRequest>> fn)	Create an Google AI Studio inference endpoint.
CompletableFuture<PutGooglevertexaiResponse>	putGooglevertexai(PutGooglevertexaiRequest request)	Create a Google Vertex AI inference endpoint.
final CompletableFuture<PutGooglevertexaiResponse>	putGooglevertexai(Function<PutGooglevertexaiRequest.Builder,ObjectBuilder<PutGooglevertexaiRequest>> fn)	Create a Google Vertex AI inference endpoint.
CompletableFuture<PutHuggingFaceResponse>	putHuggingFace(PutHuggingFaceRequest request)	Create a Hugging Face inference endpoint.
final CompletableFuture<PutHuggingFaceResponse>	putHuggingFace(Function<PutHuggingFaceRequest.Builder,ObjectBuilder<PutHuggingFaceRequest>> fn)	Create a Hugging Face inference endpoint.
CompletableFuture<PutJinaaiResponse>	putJinaai(PutJinaaiRequest request)	Create an JinaAI inference endpoint.
final CompletableFuture<PutJinaaiResponse>	putJinaai(Function<PutJinaaiRequest.Builder,ObjectBuilder<PutJinaaiRequest>> fn)	Create an JinaAI inference endpoint.
CompletableFuture<PutMistralResponse>	putMistral(PutMistralRequest request)	Create a Mistral inference endpoint.
final CompletableFuture<PutMistralResponse>	putMistral(Function<PutMistralRequest.Builder,ObjectBuilder<PutMistralRequest>> fn)	Create a Mistral inference endpoint.
CompletableFuture<PutOpenaiResponse>	putOpenai(PutOpenaiRequest request)	Create an OpenAI inference endpoint.
final CompletableFuture<PutOpenaiResponse>	putOpenai(Function<PutOpenaiRequest.Builder,ObjectBuilder<PutOpenaiRequest>> fn)	Create an OpenAI inference endpoint.
CompletableFuture<PutVoyageaiResponse>	putVoyageai(PutVoyageaiRequest request)	Create a VoyageAI inference endpoint.
final CompletableFuture<PutVoyageaiResponse>	putVoyageai(Function<PutVoyageaiRequest.Builder,ObjectBuilder<PutVoyageaiRequest>> fn)	Create a VoyageAI inference endpoint.
CompletableFuture<PutWatsonxResponse>	putWatsonx(PutWatsonxRequest request)	Create a Watsonx inference endpoint.
final CompletableFuture<PutWatsonxResponse>	putWatsonx(Function<PutWatsonxRequest.Builder,ObjectBuilder<PutWatsonxRequest>> fn)	Create a Watsonx inference endpoint.
CompletableFuture<RerankResponse>	rerank(RerankRequest request)	Perform rereanking inference on the service
final CompletableFuture<RerankResponse>	rerank(Function<RerankRequest.Builder,ObjectBuilder<RerankRequest>> fn)	Perform rereanking inference on the service
CompletableFuture<SparseEmbeddingResponse>	sparseEmbedding(SparseEmbeddingRequest request)	Perform sparse embedding inference on the service
final CompletableFuture<SparseEmbeddingResponse>	sparseEmbedding(Function<SparseEmbeddingRequest.Builder,ObjectBuilder<SparseEmbeddingRequest>> fn)	Perform sparse embedding inference on the service
CompletableFuture<BinaryResponse>	streamCompletion(StreamCompletionRequest request)	Perform streaming inference.
final CompletableFuture<BinaryResponse>	streamCompletion(Function<StreamCompletionRequest.Builder,ObjectBuilder<StreamCompletionRequest>> fn)	Perform streaming inference.
CompletableFuture<TextEmbeddingResponse>	textEmbedding(TextEmbeddingRequest request)	Perform text embedding inference on the service
final CompletableFuture<TextEmbeddingResponse>	textEmbedding(Function<TextEmbeddingRequest.Builder,ObjectBuilder<TextEmbeddingRequest>> fn)	Perform text embedding inference on the service
CompletableFuture<UpdateInferenceResponse>	update(UpdateInferenceRequest request)	Update an inference endpoint.
final CompletableFuture<UpdateInferenceResponse>	update(Function<UpdateInferenceRequest.Builder,ObjectBuilder<UpdateInferenceRequest>> fn)	Update an inference endpoint.
ElasticsearchInferenceAsyncClient	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

ElasticsearchInferenceAsyncClient

public ElasticsearchInferenceAsyncClient(ElasticsearchTransport transport)

ElasticsearchInferenceAsyncClient

public ElasticsearchInferenceAsyncClient(ElasticsearchTransport transport,
 @Nullable
 TransportOptions transportOptions)

Method Details

withTransportOptions

public ElasticsearchInferenceAsyncClient withTransportOptions(@Nullable
 TransportOptions transportOptions)

Description copied from class: ApiClient

Creates a new client with some request options

Specified by:

withTransportOptions in class ApiClient<ElasticsearchTransport,ElasticsearchInferenceAsyncClient>

chatCompletionUnified

public CompletableFuture<BinaryResponse> chatCompletionUnified(ChatCompletionUnifiedRequest request)

Perform chat completion inference

The chat completion inference API enables real-time responses for chat completion tasks by delivering answers incrementally, reducing response times during computation. It only works with the chat_completion task type for openai and elastic inference services.

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.

NOTE: The chat_completion task type is only available within the _stream API and only supports streaming. The Chat completion inference API and the Stream inference API differ in their response structure and capabilities. The Chat completion inference API provides more comprehensive customization options through more fields and function calling support. If you use the openai service or the elastic service, use the Chat completion inference API.

See Also:

• Documentation on elastic.co

chatCompletionUnified

public final CompletableFuture<BinaryResponse> chatCompletionUnified(Function<ChatCompletionUnifiedRequest.Builder,ObjectBuilder<ChatCompletionUnifiedRequest>> fn)

Perform chat completion inference

The chat completion inference API enables real-time responses for chat completion tasks by delivering answers incrementally, reducing response times during computation. It only works with the chat_completion task type for openai and elastic inference services.

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.

NOTE: The chat_completion task type is only available within the _stream API and only supports streaming. The Chat completion inference API and the Stream inference API differ in their response structure and capabilities. The Chat completion inference API provides more comprehensive customization options through more fields and function calling support. If you use the openai service or the elastic service, use the Chat completion inference API.

Parameters:

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

See Also:

• Documentation on elastic.co

completion

public CompletableFuture<CompletionResponse> completion(CompletionRequest request)

Perform completion inference on the service

See Also:

• Documentation on elastic.co

completion

public final CompletableFuture<CompletionResponse> completion(Function<CompletionRequest.Builder,ObjectBuilder<CompletionRequest>> fn)

Perform completion inference on the service

Parameters:

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

See Also:

• Documentation on elastic.co

delete

public CompletableFuture<DeleteInferenceResponse> delete(DeleteInferenceRequest request)

Delete an inference endpoint

See Also:

• Documentation on elastic.co

delete

public final CompletableFuture<DeleteInferenceResponse> delete(Function<DeleteInferenceRequest.Builder,ObjectBuilder<DeleteInferenceRequest>> fn)

Delete an inference endpoint

Parameters:

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

See Also:

• Documentation on elastic.co

get

public CompletableFuture<GetInferenceResponse> get(GetInferenceRequest request)

Get an inference endpoint

See Also:

• Documentation on elastic.co

get

public final CompletableFuture<GetInferenceResponse> get(Function<GetInferenceRequest.Builder,ObjectBuilder<GetInferenceRequest>> fn)

Get an inference endpoint

Parameters:

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

See Also:

• Documentation on elastic.co

get

public CompletableFuture<GetInferenceResponse> get()

Get an inference endpoint

See Also:

• Documentation on elastic.co

inference

public CompletableFuture<InferenceResponse> inference(InferenceRequest request)

Perform inference on the service.

This API enables you to use machine learning models to perform specific tasks on data that you provide as an input. It returns a response with the results of the tasks. The inference endpoint you use can perform one specific task that has been defined when the endpoint was created with the create inference API.

For details about using this API with a service, such as Amazon Bedrock, Anthropic, or HuggingFace, refer to the service-specific documentation.

info 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.

See Also:

• Documentation on elastic.co

inference

public final CompletableFuture<InferenceResponse> inference(Function<InferenceRequest.Builder,ObjectBuilder<InferenceRequest>> fn)

Perform inference on the service.

This API enables you to use machine learning models to perform specific tasks on data that you provide as an input. It returns a response with the results of the tasks. The inference endpoint you use can perform one specific task that has been defined when the endpoint was created with the create inference API.

For details about using this API with a service, such as Amazon Bedrock, Anthropic, or HuggingFace, refer to the service-specific documentation.

info 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 InferenceRequest

See Also:

• Documentation on elastic.co

put

public CompletableFuture<PutResponse> put(PutRequest request)

Create an inference endpoint.

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.

See Also:

• Documentation on elastic.co

put

public final CompletableFuture<PutResponse> put(Function<PutRequest.Builder,ObjectBuilder<PutRequest>> fn)

Create an inference endpoint.

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

See Also:

• Documentation on elastic.co

putAlibabacloud

public CompletableFuture<PutAlibabacloudResponse> putAlibabacloud(PutAlibabacloudRequest request)

Create an AlibabaCloud AI Search inference endpoint.

Create an inference endpoint to perform an inference task with the alibabacloud-ai-search service.

See Also:

• Documentation on elastic.co

putAlibabacloud

public final CompletableFuture<PutAlibabacloudResponse> putAlibabacloud(Function<PutAlibabacloudRequest.Builder,ObjectBuilder<PutAlibabacloudRequest>> fn)

Create an AlibabaCloud AI Search inference endpoint.

Create an inference endpoint to perform an inference task with the alibabacloud-ai-search service.

Parameters:

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

See Also:

• Documentation on elastic.co

putAmazonbedrock

public CompletableFuture<PutAmazonbedrockResponse> putAmazonbedrock(PutAmazonbedrockRequest request)

Create an Amazon Bedrock inference endpoint.

Creates an inference endpoint to perform an inference task with the amazonbedrock service.

info You need to provide the access and secret keys only once, during the inference model creation. The get inference API does not retrieve your access or secret keys. After creating the inference model, you cannot change the associated key pairs. If you want to use a different access and secret key pair, delete the inference model and recreate it with the same name and the updated keys.

See Also:

• Documentation on elastic.co

putAmazonbedrock

public final CompletableFuture<PutAmazonbedrockResponse> putAmazonbedrock(Function<PutAmazonbedrockRequest.Builder,ObjectBuilder<PutAmazonbedrockRequest>> fn)

Create an Amazon Bedrock inference endpoint.

Creates an inference endpoint to perform an inference task with the amazonbedrock service.

info You need to provide the access and secret keys only once, during the inference model creation. The get inference API does not retrieve your access or secret keys. After creating the inference model, you cannot change the associated key pairs. If you want to use a different access and secret key pair, delete the inference model and recreate it with the same name and the updated keys.

Parameters:

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

See Also:

• Documentation on elastic.co

putAnthropic

public CompletableFuture<PutAnthropicResponse> putAnthropic(PutAnthropicRequest request)

Create an Anthropic inference endpoint.

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

See Also:

• Documentation on elastic.co

putAnthropic

public final CompletableFuture<PutAnthropicResponse> putAnthropic(Function<PutAnthropicRequest.Builder,ObjectBuilder<PutAnthropicRequest>> fn)

Create an Anthropic inference endpoint.

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

Parameters:

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

See Also:

• Documentation on elastic.co

putAzureaistudio

public CompletableFuture<PutAzureaistudioResponse> putAzureaistudio(PutAzureaistudioRequest request)

Create an Azure AI studio inference endpoint.

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

See Also:

• Documentation on elastic.co

putAzureaistudio

public final CompletableFuture<PutAzureaistudioResponse> putAzureaistudio(Function<PutAzureaistudioRequest.Builder,ObjectBuilder<PutAzureaistudioRequest>> fn)

Create an Azure AI studio inference endpoint.

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

Parameters:

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

See Also:

• Documentation on elastic.co

putAzureopenai

public CompletableFuture<PutAzureopenaiResponse> putAzureopenai(PutAzureopenaiRequest request)

Create an Azure OpenAI inference endpoint.

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

The list of chat completion models that you can choose from in your Azure OpenAI deployment include:

• GPT-4 and GPT-4 Turbo models
• GPT-3.5

The list of embeddings models that you can choose from in your deployment can be found in the Azure models documentation.

See Also:

• Documentation on elastic.co

putAzureopenai

public final CompletableFuture<PutAzureopenaiResponse> putAzureopenai(Function<PutAzureopenaiRequest.Builder,ObjectBuilder<PutAzureopenaiRequest>> fn)

Create an Azure OpenAI inference endpoint.

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

The list of chat completion models that you can choose from in your Azure OpenAI deployment include:

• GPT-4 and GPT-4 Turbo models
• GPT-3.5

The list of embeddings models that you can choose from in your deployment can be found in the Azure models documentation.

Parameters:

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

See Also:

• Documentation on elastic.co

putCohere

public CompletableFuture<PutCohereResponse> putCohere(PutCohereRequest request)

Create a Cohere inference endpoint.

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

See Also:

• Documentation on elastic.co

putCohere

public final CompletableFuture<PutCohereResponse> putCohere(Function<PutCohereRequest.Builder,ObjectBuilder<PutCohereRequest>> fn)

Create a Cohere inference endpoint.

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

Parameters:

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

See Also:

• Documentation on elastic.co

putElasticsearch

public CompletableFuture<PutElasticsearchResponse> putElasticsearch(PutElasticsearchRequest request)

Create an Elasticsearch inference endpoint.

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

info Your Elasticsearch deployment contains preconfigured ELSER and E5 inference endpoints, you only need to create the enpoints using the API if you want to customize the settings.

If you use the ELSER or the E5 model through the elasticsearch service, the API request will automatically download and deploy the model if it isn't downloaded yet.

info You might see a 502 bad gateway error in the response when using the Kibana Console. This error usually just reflects a timeout, while the model downloads in the background. You can check the download progress in the Machine Learning UI. If using the Python client, you can set the timeout parameter to a higher value.

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.

See Also:

• Documentation on elastic.co

putElasticsearch

public final CompletableFuture<PutElasticsearchResponse> putElasticsearch(Function<PutElasticsearchRequest.Builder,ObjectBuilder<PutElasticsearchRequest>> fn)

Create an Elasticsearch inference endpoint.

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

info Your Elasticsearch deployment contains preconfigured ELSER and E5 inference endpoints, you only need to create the enpoints using the API if you want to customize the settings.

If you use the ELSER or the E5 model through the elasticsearch service, the API request will automatically download and deploy the model if it isn't downloaded yet.

info You might see a 502 bad gateway error in the response when using the Kibana Console. This error usually just reflects a timeout, while the model downloads in the background. You can check the download progress in the Machine Learning UI. If using the Python client, you can set the timeout parameter to a higher value.

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.

Parameters:

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

See Also:

• Documentation on elastic.co

putElser

public CompletableFuture<PutElserResponse> putElser(PutElserRequest request)

Create an ELSER inference endpoint.

Create an inference endpoint to perform an inference task with the elser service. You can also deploy ELSER by using the Elasticsearch inference integration.

info Your Elasticsearch deployment contains a preconfigured ELSER inference endpoint, you only need to create the enpoint using the API if you want to customize the settings.

The API request will automatically download and deploy the ELSER model if it isn't already downloaded.

info You might see a 502 bad gateway error in the response when using the Kibana Console. This error usually just reflects a timeout, while the model downloads in the background. You can check the download progress in the Machine Learning UI. If using the Python client, you can set the timeout parameter to a higher value.

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.

See Also:

• Documentation on elastic.co

putElser

public final CompletableFuture<PutElserResponse> putElser(Function<PutElserRequest.Builder,ObjectBuilder<PutElserRequest>> fn)

Create an ELSER inference endpoint.

Create an inference endpoint to perform an inference task with the elser service. You can also deploy ELSER by using the Elasticsearch inference integration.

info Your Elasticsearch deployment contains a preconfigured ELSER inference endpoint, you only need to create the enpoint using the API if you want to customize the settings.

The API request will automatically download and deploy the ELSER model if it isn't already downloaded.

info You might see a 502 bad gateway error in the response when using the Kibana Console. This error usually just reflects a timeout, while the model downloads in the background. You can check the download progress in the Machine Learning UI. If using the Python client, you can set the timeout parameter to a higher value.

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.

Parameters:

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

See Also:

• Documentation on elastic.co

putGoogleaistudio

public CompletableFuture<PutGoogleaistudioResponse> putGoogleaistudio(PutGoogleaistudioRequest request)

Create an Google AI Studio inference endpoint.

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

See Also:

• Documentation on elastic.co

putGoogleaistudio

public final CompletableFuture<PutGoogleaistudioResponse> putGoogleaistudio(Function<PutGoogleaistudioRequest.Builder,ObjectBuilder<PutGoogleaistudioRequest>> fn)

Create an Google AI Studio inference endpoint.

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

Parameters:

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

See Also:

• Documentation on elastic.co

putGooglevertexai

public CompletableFuture<PutGooglevertexaiResponse> putGooglevertexai(PutGooglevertexaiRequest request)

Create a Google Vertex AI inference endpoint.

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

See Also:

• Documentation on elastic.co

putGooglevertexai

public final CompletableFuture<PutGooglevertexaiResponse> putGooglevertexai(Function<PutGooglevertexaiRequest.Builder,ObjectBuilder<PutGooglevertexaiRequest>> fn)

Create a Google Vertex AI inference endpoint.

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

Parameters:

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

See Also:

• Documentation on elastic.co

putHuggingFace

public CompletableFuture<PutHuggingFaceResponse> putHuggingFace(PutHuggingFaceRequest request)

Create a Hugging Face inference endpoint.

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

You must first create an inference endpoint on the Hugging Face endpoint page to get an endpoint URL. Select the model you want to use on the new endpoint creation page (for example intfloat/e5-small-v2), then select the sentence embeddings task under the advanced configuration section. Create the endpoint and copy the URL after the endpoint initialization has been finished.

The following models are recommended for the Hugging Face service:

• all-MiniLM-L6-v2
• all-MiniLM-L12-v2
• all-mpnet-base-v2
• e5-base-v2
• e5-small-v2
• multilingual-e5-base
• multilingual-e5-small

See Also:

• Documentation on elastic.co

putHuggingFace

public final CompletableFuture<PutHuggingFaceResponse> putHuggingFace(Function<PutHuggingFaceRequest.Builder,ObjectBuilder<PutHuggingFaceRequest>> fn)

Create a Hugging Face inference endpoint.

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

You must first create an inference endpoint on the Hugging Face endpoint page to get an endpoint URL. Select the model you want to use on the new endpoint creation page (for example intfloat/e5-small-v2), then select the sentence embeddings task under the advanced configuration section. Create the endpoint and copy the URL after the endpoint initialization has been finished.

The following models are recommended for the Hugging Face service:

• all-MiniLM-L6-v2
• all-MiniLM-L12-v2
• all-mpnet-base-v2
• e5-base-v2
• e5-small-v2
• multilingual-e5-base
• multilingual-e5-small

Parameters:

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

See Also:

• Documentation on elastic.co

putJinaai

public CompletableFuture<PutJinaaiResponse> putJinaai(PutJinaaiRequest request)

Create an JinaAI inference endpoint.

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

To review the available rerank models, refer to https://jina.ai/reranker. To review the available text_embedding models, refer to the https://jina.ai/embeddings/.

See Also:

• Documentation on elastic.co

putJinaai

public final CompletableFuture<PutJinaaiResponse> putJinaai(Function<PutJinaaiRequest.Builder,ObjectBuilder<PutJinaaiRequest>> fn)

Create an JinaAI inference endpoint.

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

To review the available rerank models, refer to https://jina.ai/reranker. To review the available text_embedding models, refer to the https://jina.ai/embeddings/.

Parameters:

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

See Also:

• Documentation on elastic.co

putMistral

public CompletableFuture<PutMistralResponse> putMistral(PutMistralRequest request)

Create a Mistral inference endpoint.

Creates an inference endpoint to perform an inference task with the mistral service.

See Also:

• Documentation on elastic.co

putMistral

public final CompletableFuture<PutMistralResponse> putMistral(Function<PutMistralRequest.Builder,ObjectBuilder<PutMistralRequest>> fn)

Create a Mistral inference endpoint.

Creates an inference endpoint to perform an inference task with the mistral service.

Parameters:

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

See Also:

• Documentation on elastic.co

putOpenai

public CompletableFuture<PutOpenaiResponse> putOpenai(PutOpenaiRequest request)

Create an OpenAI inference endpoint.

Create an inference endpoint to perform an inference task with the openai service or openai compatible APIs.

See Also:

• Documentation on elastic.co

putOpenai

public final CompletableFuture<PutOpenaiResponse> putOpenai(Function<PutOpenaiRequest.Builder,ObjectBuilder<PutOpenaiRequest>> fn)

Create an OpenAI inference endpoint.

Create an inference endpoint to perform an inference task with the openai service or openai compatible APIs.

Parameters:

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

See Also:

• Documentation on elastic.co

putVoyageai

public CompletableFuture<PutVoyageaiResponse> putVoyageai(PutVoyageaiRequest request)

Create a VoyageAI inference endpoint.

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

Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.

See Also:

• Documentation on elastic.co

putVoyageai

public final CompletableFuture<PutVoyageaiResponse> putVoyageai(Function<PutVoyageaiRequest.Builder,ObjectBuilder<PutVoyageaiRequest>> fn)

Create a VoyageAI inference endpoint.

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

Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.

Parameters:

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

See Also:

• Documentation on elastic.co

putWatsonx

public CompletableFuture<PutWatsonxResponse> putWatsonx(PutWatsonxRequest request)

Create a Watsonx inference endpoint.

Create an inference endpoint to perform an inference task with the watsonxai service. You need an IBM Cloud Databases for Elasticsearch deployment to use the watsonxai inference service. You can provision one through the IBM catalog, the Cloud Databases CLI plug-in, the Cloud Databases API, or Terraform.

See Also:

• Documentation on elastic.co

putWatsonx

public final CompletableFuture<PutWatsonxResponse> putWatsonx(Function<PutWatsonxRequest.Builder,ObjectBuilder<PutWatsonxRequest>> fn)

Create a Watsonx inference endpoint.

Create an inference endpoint to perform an inference task with the watsonxai service. You need an IBM Cloud Databases for Elasticsearch deployment to use the watsonxai inference service. You can provision one through the IBM catalog, the Cloud Databases CLI plug-in, the Cloud Databases API, or Terraform.

Parameters:

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

See Also:

• Documentation on elastic.co

rerank

public CompletableFuture<RerankResponse> rerank(RerankRequest request)

Perform rereanking inference on the service

See Also:

• Documentation on elastic.co

rerank

public final CompletableFuture<RerankResponse> rerank(Function<RerankRequest.Builder,ObjectBuilder<RerankRequest>> fn)

Perform rereanking inference on the service

Parameters:

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

See Also:

• Documentation on elastic.co

sparseEmbedding

public CompletableFuture<SparseEmbeddingResponse> sparseEmbedding(SparseEmbeddingRequest request)

Perform sparse embedding inference on the service

See Also:

• Documentation on elastic.co

sparseEmbedding

public final CompletableFuture<SparseEmbeddingResponse> sparseEmbedding(Function<SparseEmbeddingRequest.Builder,ObjectBuilder<SparseEmbeddingRequest>> fn)

Perform sparse embedding inference on the service

Parameters:

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

See Also:

• Documentation on elastic.co

streamCompletion

public CompletableFuture<BinaryResponse> streamCompletion(StreamCompletionRequest request)

Perform streaming inference. Get real-time responses for completion tasks by delivering answers incrementally, reducing response times during computation. This API works only with the completion 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.

This API requires the monitor_inference cluster privilege (the built-in inference_admin and inference_user roles grant this privilege). You must use a client that supports streaming.

See Also:

• Documentation on elastic.co

streamCompletion

public final CompletableFuture<BinaryResponse> streamCompletion(Function<StreamCompletionRequest.Builder,ObjectBuilder<StreamCompletionRequest>> fn)

Perform streaming inference. Get real-time responses for completion tasks by delivering answers incrementally, reducing response times during computation. This API works only with the completion 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.

This API requires the monitor_inference cluster privilege (the built-in inference_admin and inference_user roles grant this privilege). You must use a client that supports streaming.

Parameters:

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

See Also:

• Documentation on elastic.co

textEmbedding

public CompletableFuture<TextEmbeddingResponse> textEmbedding(TextEmbeddingRequest request)

Perform text embedding inference on the service

See Also:

• Documentation on elastic.co

textEmbedding

public final CompletableFuture<TextEmbeddingResponse> textEmbedding(Function<TextEmbeddingRequest.Builder,ObjectBuilder<TextEmbeddingRequest>> fn)

Perform text embedding inference on the service

Parameters:

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

See Also:

• Documentation on elastic.co

update

public CompletableFuture<UpdateInferenceResponse> update(UpdateInferenceRequest request)

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.

See Also:

• Documentation on elastic.co

update

public final CompletableFuture<UpdateInferenceResponse> update(Function<UpdateInferenceRequest.Builder,ObjectBuilder<UpdateInferenceRequest>> fn)

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

See Also:

• Documentation on elastic.co