elasticsearch-js/docs/reference/api/Inference.md

Inference

Constructor

::: new Inference(transport: Transport); :::

Properties

Name	Type	Description
acceptedParams	Record<string, { path: string[]; body: string[]; query: string[]; }>
transport	Transport

Methods

Name	Signature	Description
chatCompletionUnified	chatCompletionUnified(this: [That](./That.md), params: [InferenceChatCompletionUnifiedRequest](./InferenceChatCompletionUnifiedRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferenceChatCompletionUnifiedResponse](./InferenceChatCompletionUnifiedResponse.md)>;	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.
chatCompletionUnified	chatCompletionUnified(this: [That](./That.md), params: [InferenceChatCompletionUnifiedRequest](./InferenceChatCompletionUnifiedRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferenceChatCompletionUnifiedResponse](./InferenceChatCompletionUnifiedResponse.md), unknown>>;
chatCompletionUnified	chatCompletionUnified(this: [That](./That.md), params: [InferenceChatCompletionUnifiedRequest](./InferenceChatCompletionUnifiedRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferenceChatCompletionUnifiedResponse](./InferenceChatCompletionUnifiedResponse.md)>;
completion	completion(this: [That](./That.md), params: [InferenceCompletionRequest](./InferenceCompletionRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferenceCompletionResponse](./InferenceCompletionResponse.md)>;	Perform completion inference on the service
completion	completion(this: [That](./That.md), params: [InferenceCompletionRequest](./InferenceCompletionRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferenceCompletionResponse](./InferenceCompletionResponse.md), unknown>>;
completion	completion(this: [That](./That.md), params: [InferenceCompletionRequest](./InferenceCompletionRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferenceCompletionResponse](./InferenceCompletionResponse.md)>;
delete	delete(this: [That](./That.md), params: [InferenceDeleteRequest](./InferenceDeleteRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferenceDeleteResponse](./InferenceDeleteResponse.md)>;	Delete an inference endpoint
delete	delete(this: [That](./That.md), params: [InferenceDeleteRequest](./InferenceDeleteRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferenceDeleteResponse](./InferenceDeleteResponse.md), unknown>>;
delete	delete(this: [That](./That.md), params: [InferenceDeleteRequest](./InferenceDeleteRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferenceDeleteResponse](./InferenceDeleteResponse.md)>;
get	get(this: [That](./That.md), params?: [InferenceGetRequest](./InferenceGetRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferenceGetResponse](./InferenceGetResponse.md)>;	Get an inference endpoint
get	get(this: [That](./That.md), params?: [InferenceGetRequest](./InferenceGetRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferenceGetResponse](./InferenceGetResponse.md), unknown>>;
get	get(this: [That](./That.md), params?: [InferenceGetRequest](./InferenceGetRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferenceGetResponse](./InferenceGetResponse.md)>;
inference	inference(this: [That](./That.md), params: [InferenceInferenceRequest](./InferenceInferenceRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferenceInferenceResponse](./InferenceInferenceResponse.md)>;	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.
inference	inference(this: [That](./That.md), params: [InferenceInferenceRequest](./InferenceInferenceRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferenceInferenceResponse](./InferenceInferenceResponse.md), unknown>>;
inference	inference(this: [That](./That.md), params: [InferenceInferenceRequest](./InferenceInferenceRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferenceInferenceResponse](./InferenceInferenceResponse.md)>;
put	put(this: [That](./That.md), params: [InferencePutRequest](./InferencePutRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutResponse](./InferencePutResponse.md)>;	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.
put	put(this: [That](./That.md), params: [InferencePutRequest](./InferencePutRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutResponse](./InferencePutResponse.md), unknown>>;
put	put(this: [That](./That.md), params: [InferencePutRequest](./InferencePutRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutResponse](./InferencePutResponse.md)>;
putAlibabacloud	putAlibabacloud(this: [That](./That.md), params: [InferencePutAlibabacloudRequest](./InferencePutAlibabacloudRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutAlibabacloudResponse](./InferencePutAlibabacloudResponse.md)>;	Create an AlibabaCloud AI Search inference endpoint. Create an inference endpoint to perform an inference task with the alibabacloud-ai-search service.
putAlibabacloud	putAlibabacloud(this: [That](./That.md), params: [InferencePutAlibabacloudRequest](./InferencePutAlibabacloudRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutAlibabacloudResponse](./InferencePutAlibabacloudResponse.md), unknown>>;
putAlibabacloud	putAlibabacloud(this: [That](./That.md), params: [InferencePutAlibabacloudRequest](./InferencePutAlibabacloudRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutAlibabacloudResponse](./InferencePutAlibabacloudResponse.md)>;
putAmazonbedrock	putAmazonbedrock(this: [That](./That.md), params: [InferencePutAmazonbedrockRequest](./InferencePutAmazonbedrockRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutAmazonbedrockResponse](./InferencePutAmazonbedrockResponse.md)>;	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.
putAmazonbedrock	putAmazonbedrock(this: [That](./That.md), params: [InferencePutAmazonbedrockRequest](./InferencePutAmazonbedrockRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutAmazonbedrockResponse](./InferencePutAmazonbedrockResponse.md), unknown>>;
putAmazonbedrock	putAmazonbedrock(this: [That](./That.md), params: [InferencePutAmazonbedrockRequest](./InferencePutAmazonbedrockRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutAmazonbedrockResponse](./InferencePutAmazonbedrockResponse.md)>;
putAnthropic	putAnthropic(this: [That](./That.md), params: [InferencePutAnthropicRequest](./InferencePutAnthropicRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutAnthropicResponse](./InferencePutAnthropicResponse.md)>;	Create an Anthropic inference endpoint. Create an inference endpoint to perform an inference task with the anthropic service.
putAnthropic	putAnthropic(this: [That](./That.md), params: [InferencePutAnthropicRequest](./InferencePutAnthropicRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutAnthropicResponse](./InferencePutAnthropicResponse.md), unknown>>;
putAnthropic	putAnthropic(this: [That](./That.md), params: [InferencePutAnthropicRequest](./InferencePutAnthropicRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutAnthropicResponse](./InferencePutAnthropicResponse.md)>;
putAzureaistudio	putAzureaistudio(this: [That](./That.md), params: [InferencePutAzureaistudioRequest](./InferencePutAzureaistudioRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutAzureaistudioResponse](./InferencePutAzureaistudioResponse.md)>;	Create an Azure AI studio inference endpoint. Create an inference endpoint to perform an inference task with the azureaistudio service.
putAzureaistudio	putAzureaistudio(this: [That](./That.md), params: [InferencePutAzureaistudioRequest](./InferencePutAzureaistudioRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutAzureaistudioResponse](./InferencePutAzureaistudioResponse.md), unknown>>;
putAzureaistudio	putAzureaistudio(this: [That](./That.md), params: [InferencePutAzureaistudioRequest](./InferencePutAzureaistudioRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutAzureaistudioResponse](./InferencePutAzureaistudioResponse.md)>;
putAzureopenai	putAzureopenai(this: [That](./That.md), params: [InferencePutAzureopenaiRequest](./InferencePutAzureopenaiRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutAzureopenaiResponse](./InferencePutAzureopenaiResponse.md)>;	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.
putAzureopenai	putAzureopenai(this: [That](./That.md), params: [InferencePutAzureopenaiRequest](./InferencePutAzureopenaiRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutAzureopenaiResponse](./InferencePutAzureopenaiResponse.md), unknown>>;
putAzureopenai	putAzureopenai(this: [That](./That.md), params: [InferencePutAzureopenaiRequest](./InferencePutAzureopenaiRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutAzureopenaiResponse](./InferencePutAzureopenaiResponse.md)>;
putCohere	putCohere(this: [That](./That.md), params: [InferencePutCohereRequest](./InferencePutCohereRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutCohereResponse](./InferencePutCohereResponse.md)>;	Create a Cohere inference endpoint. Create an inference endpoint to perform an inference task with the cohere service.
putCohere	putCohere(this: [That](./That.md), params: [InferencePutCohereRequest](./InferencePutCohereRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutCohereResponse](./InferencePutCohereResponse.md), unknown>>;
putCohere	putCohere(this: [That](./That.md), params: [InferencePutCohereRequest](./InferencePutCohereRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutCohereResponse](./InferencePutCohereResponse.md)>;
putElasticsearch	putElasticsearch(this: [That](./That.md), params: [InferencePutElasticsearchRequest](./InferencePutElasticsearchRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutElasticsearchResponse](./InferencePutElasticsearchResponse.md)>;	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.
putElasticsearch	putElasticsearch(this: [That](./That.md), params: [InferencePutElasticsearchRequest](./InferencePutElasticsearchRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutElasticsearchResponse](./InferencePutElasticsearchResponse.md), unknown>>;
putElasticsearch	putElasticsearch(this: [That](./That.md), params: [InferencePutElasticsearchRequest](./InferencePutElasticsearchRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutElasticsearchResponse](./InferencePutElasticsearchResponse.md)>;
putElser	putElser(this: [That](./That.md), params: [InferencePutElserRequest](./InferencePutElserRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutElserResponse](./InferencePutElserResponse.md)>;	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.
putElser	putElser(this: [That](./That.md), params: [InferencePutElserRequest](./InferencePutElserRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutElserResponse](./InferencePutElserResponse.md), unknown>>;
putElser	putElser(this: [That](./That.md), params: [InferencePutElserRequest](./InferencePutElserRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutElserResponse](./InferencePutElserResponse.md)>;
putGoogleaistudio	putGoogleaistudio(this: [That](./That.md), params: [InferencePutGoogleaistudioRequest](./InferencePutGoogleaistudioRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutGoogleaistudioResponse](./InferencePutGoogleaistudioResponse.md)>;	Create an Google AI Studio inference endpoint. Create an inference endpoint to perform an inference task with the googleaistudio service.
putGoogleaistudio	putGoogleaistudio(this: [That](./That.md), params: [InferencePutGoogleaistudioRequest](./InferencePutGoogleaistudioRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutGoogleaistudioResponse](./InferencePutGoogleaistudioResponse.md), unknown>>;
putGoogleaistudio	putGoogleaistudio(this: [That](./That.md), params: [InferencePutGoogleaistudioRequest](./InferencePutGoogleaistudioRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutGoogleaistudioResponse](./InferencePutGoogleaistudioResponse.md)>;
putGooglevertexai	putGooglevertexai(this: [That](./That.md), params: [InferencePutGooglevertexaiRequest](./InferencePutGooglevertexaiRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutGooglevertexaiResponse](./InferencePutGooglevertexaiResponse.md)>;	Create a Google Vertex AI inference endpoint. Create an inference endpoint to perform an inference task with the googlevertexai service.
putGooglevertexai	putGooglevertexai(this: [That](./That.md), params: [InferencePutGooglevertexaiRequest](./InferencePutGooglevertexaiRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutGooglevertexaiResponse](./InferencePutGooglevertexaiResponse.md), unknown>>;
putGooglevertexai	putGooglevertexai(this: [That](./That.md), params: [InferencePutGooglevertexaiRequest](./InferencePutGooglevertexaiRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutGooglevertexaiResponse](./InferencePutGooglevertexaiResponse.md)>;
putHuggingFace	putHuggingFace(this: [That](./That.md), params: [InferencePutHuggingFaceRequest](./InferencePutHuggingFaceRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutHuggingFaceResponse](./InferencePutHuggingFaceResponse.md)>;	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
putHuggingFace	putHuggingFace(this: [That](./That.md), params: [InferencePutHuggingFaceRequest](./InferencePutHuggingFaceRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutHuggingFaceResponse](./InferencePutHuggingFaceResponse.md), unknown>>;
putHuggingFace	putHuggingFace(this: [That](./That.md), params: [InferencePutHuggingFaceRequest](./InferencePutHuggingFaceRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutHuggingFaceResponse](./InferencePutHuggingFaceResponse.md)>;
putJinaai	putJinaai(this: [That](./That.md), params: [InferencePutJinaaiRequest](./InferencePutJinaaiRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutJinaaiResponse](./InferencePutJinaaiResponse.md)>;	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/ > .
putJinaai	putJinaai(this: [That](./That.md), params: [InferencePutJinaaiRequest](./InferencePutJinaaiRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutJinaaiResponse](./InferencePutJinaaiResponse.md), unknown>>;
putJinaai	putJinaai(this: [That](./That.md), params: [InferencePutJinaaiRequest](./InferencePutJinaaiRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutJinaaiResponse](./InferencePutJinaaiResponse.md)>;
putMistral	putMistral(this: [That](./That.md), params: [InferencePutMistralRequest](./InferencePutMistralRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutMistralResponse](./InferencePutMistralResponse.md)>;	Create a Mistral inference endpoint. Creates an inference endpoint to perform an inference task with the mistral service.
putMistral	putMistral(this: [That](./That.md), params: [InferencePutMistralRequest](./InferencePutMistralRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutMistralResponse](./InferencePutMistralResponse.md), unknown>>;
putMistral	putMistral(this: [That](./That.md), params: [InferencePutMistralRequest](./InferencePutMistralRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutMistralResponse](./InferencePutMistralResponse.md)>;
putOpenai	putOpenai(this: [That](./That.md), params: [InferencePutOpenaiRequest](./InferencePutOpenaiRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutOpenaiResponse](./InferencePutOpenaiResponse.md)>;	Create an OpenAI inference endpoint. Create an inference endpoint to perform an inference task with the openai service or openai compatible APIs.
putOpenai	putOpenai(this: [That](./That.md), params: [InferencePutOpenaiRequest](./InferencePutOpenaiRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutOpenaiResponse](./InferencePutOpenaiResponse.md), unknown>>;
putOpenai	putOpenai(this: [That](./That.md), params: [InferencePutOpenaiRequest](./InferencePutOpenaiRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutOpenaiResponse](./InferencePutOpenaiResponse.md)>;
putVoyageai	putVoyageai(this: [That](./That.md), params: [InferencePutVoyageaiRequest](./InferencePutVoyageaiRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutVoyageaiResponse](./InferencePutVoyageaiResponse.md)>;	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.
putVoyageai	putVoyageai(this: [That](./That.md), params: [InferencePutVoyageaiRequest](./InferencePutVoyageaiRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutVoyageaiResponse](./InferencePutVoyageaiResponse.md), unknown>>;
putVoyageai	putVoyageai(this: [That](./That.md), params: [InferencePutVoyageaiRequest](./InferencePutVoyageaiRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutVoyageaiResponse](./InferencePutVoyageaiResponse.md)>;
putWatsonx	putWatsonx(this: [That](./That.md), params: [InferencePutWatsonxRequest](./InferencePutWatsonxRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferencePutWatsonxResponse](./InferencePutWatsonxResponse.md)>;	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.
putWatsonx	putWatsonx(this: [That](./That.md), params: [InferencePutWatsonxRequest](./InferencePutWatsonxRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferencePutWatsonxResponse](./InferencePutWatsonxResponse.md), unknown>>;
putWatsonx	putWatsonx(this: [That](./That.md), params: [InferencePutWatsonxRequest](./InferencePutWatsonxRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferencePutWatsonxResponse](./InferencePutWatsonxResponse.md)>;
rerank	rerank(this: [That](./That.md), params: [InferenceRerankRequest](./InferenceRerankRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferenceRerankResponse](./InferenceRerankResponse.md)>;	Perform rereanking inference on the service
rerank	rerank(this: [That](./That.md), params: [InferenceRerankRequest](./InferenceRerankRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferenceRerankResponse](./InferenceRerankResponse.md), unknown>>;
rerank	rerank(this: [That](./That.md), params: [InferenceRerankRequest](./InferenceRerankRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferenceRerankResponse](./InferenceRerankResponse.md)>;
sparseEmbedding	sparseEmbedding(this: [That](./That.md), params: [InferenceSparseEmbeddingRequest](./InferenceSparseEmbeddingRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferenceSparseEmbeddingResponse](./InferenceSparseEmbeddingResponse.md)>;	Perform sparse embedding inference on the service
sparseEmbedding	sparseEmbedding(this: [That](./That.md), params: [InferenceSparseEmbeddingRequest](./InferenceSparseEmbeddingRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferenceSparseEmbeddingResponse](./InferenceSparseEmbeddingResponse.md), unknown>>;
sparseEmbedding	sparseEmbedding(this: [That](./That.md), params: [InferenceSparseEmbeddingRequest](./InferenceSparseEmbeddingRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferenceSparseEmbeddingResponse](./InferenceSparseEmbeddingResponse.md)>;
streamCompletion	streamCompletion(this: [That](./That.md), params: [InferenceStreamCompletionRequest](./InferenceStreamCompletionRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferenceStreamCompletionResponse](./InferenceStreamCompletionResponse.md)>;	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.
streamCompletion	streamCompletion(this: [That](./That.md), params: [InferenceStreamCompletionRequest](./InferenceStreamCompletionRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferenceStreamCompletionResponse](./InferenceStreamCompletionResponse.md), unknown>>;
streamCompletion	streamCompletion(this: [That](./That.md), params: [InferenceStreamCompletionRequest](./InferenceStreamCompletionRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferenceStreamCompletionResponse](./InferenceStreamCompletionResponse.md)>;
textEmbedding	textEmbedding(this: [That](./That.md), params: [InferenceTextEmbeddingRequest](./InferenceTextEmbeddingRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferenceTextEmbeddingResponse](./InferenceTextEmbeddingResponse.md)>;	Perform text embedding inference on the service
textEmbedding	textEmbedding(this: [That](./That.md), params: [InferenceTextEmbeddingRequest](./InferenceTextEmbeddingRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferenceTextEmbeddingResponse](./InferenceTextEmbeddingResponse.md), unknown>>;
textEmbedding	textEmbedding(this: [That](./That.md), params: [InferenceTextEmbeddingRequest](./InferenceTextEmbeddingRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferenceTextEmbeddingResponse](./InferenceTextEmbeddingResponse.md)>;
update	update(this: [That](./That.md), params: [InferenceUpdateRequest](./InferenceUpdateRequest.md), options?: [TransportRequestOptionsWithOutMeta](./TransportRequestOptionsWithOutMeta.md)): Promise<[InferenceUpdateResponse](./InferenceUpdateResponse.md)>;	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.
update	update(this: [That](./That.md), params: [InferenceUpdateRequest](./InferenceUpdateRequest.md), options?: [TransportRequestOptionsWithMeta](./TransportRequestOptionsWithMeta.md)): Promise<[TransportResult](./TransportResult.md)<[InferenceUpdateResponse](./InferenceUpdateResponse.md), unknown>>;
update	update(this: [That](./That.md), params: [InferenceUpdateRequest](./InferenceUpdateRequest.md), options?: [TransportRequestOptions](./TransportRequestOptions.md)): Promise<[InferenceUpdateResponse](./InferenceUpdateResponse.md)>;