Package co.elastic.clients.elasticsearch.inference

Class OpenShiftAiServiceSettings.Builder

java.lang.Object

co.elastic.clients.util.ObjectBuilderBase

co.elastic.clients.util.WithJsonObjectBuilderBase<OpenShiftAiServiceSettings.Builder>

co.elastic.clients.elasticsearch.inference.OpenShiftAiServiceSettings.Builder

All Implemented Interfaces:

WithJson<OpenShiftAiServiceSettings.Builder>, ObjectBuilder<OpenShiftAiServiceSettings>

Enclosing class:

OpenShiftAiServiceSettings

public static class OpenShiftAiServiceSettings.Builder
extends WithJsonObjectBuilderBase<OpenShiftAiServiceSettings.Builder>
implements ObjectBuilder<OpenShiftAiServiceSettings>

Builder for OpenShiftAiServiceSettings.

Constructor Summary

Constructors

Constructor	Description
Builder()

Method Summary

Modifier and Type	Method	Description
final OpenShiftAiServiceSettings.Builder	apiKey(String value)	Required - A valid API key for your OpenShift AI endpoint.
OpenShiftAiServiceSettings	build()	Builds a OpenShiftAiServiceSettings.
final OpenShiftAiServiceSettings.Builder	maxInputTokens(Integer value)	For a text_embedding task, the maximum number of tokens per input before chunking occurs.
final OpenShiftAiServiceSettings.Builder	modelId(String value)	The name of the model to use for the inference task.
final OpenShiftAiServiceSettings.Builder	rateLimit(RateLimitSetting value)	This setting helps to minimize the number of rate limit errors returned from the OpenShift AI API.
final OpenShiftAiServiceSettings.Builder	rateLimit(Function<RateLimitSetting.Builder,ObjectBuilder<RateLimitSetting>> fn)	This setting helps to minimize the number of rate limit errors returned from the OpenShift AI API.
protected OpenShiftAiServiceSettings.Builder	self()
final OpenShiftAiServiceSettings.Builder	similarity(OpenShiftAiSimilarityType value)	For a text_embedding task, the similarity measure.
final OpenShiftAiServiceSettings.Builder	url(String value)	Required - The URL of the OpenShift AI hosted model endpoint.

Methods inherited from class co.elastic.clients.util.WithJsonObjectBuilderBase

withJson

Methods inherited from class co.elastic.clients.util.ObjectBuilderBase

_checkSingleUse, _listAdd, _listAddAll, _mapPut, _mapPutAll

Methods inherited from class java.lang.Object

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

Methods inherited from interface co.elastic.clients.json.WithJson

withJson, withJson

Constructor Details

Builder

public Builder()

Method Details

apiKey

public final OpenShiftAiServiceSettings.Builder apiKey(String value)

Required - A valid API key for your OpenShift AI endpoint. Can be found in Token authentication section of model related information.

API name: api_key

url

public final OpenShiftAiServiceSettings.Builder url(String value)

Required - The URL of the OpenShift AI hosted model endpoint.

API name: url

modelId

public final OpenShiftAiServiceSettings.Builder modelId(@Nullable
 String value)

The name of the model to use for the inference task. Refer to the hosted model's documentation for the name if needed. Service has been tested and confirmed to be working with the following models:

• For text_embedding task - gritlm-7b.
• For completion and chat_completion tasks - llama-31-8b-instruct.
• For rerank task - bge-reranker-v2-m3.

API name: model_id

maxInputTokens

public final OpenShiftAiServiceSettings.Builder maxInputTokens(@Nullable
 Integer value)

For a text_embedding task, the maximum number of tokens per input before chunking occurs.

API name: max_input_tokens

similarity

public final OpenShiftAiServiceSettings.Builder similarity(@Nullable
 OpenShiftAiSimilarityType value)

For a text_embedding task, the similarity measure. One of cosine, dot_product, l2_norm. If not specified, the default dot_product value is used.

API name: similarity

rateLimit

public final OpenShiftAiServiceSettings.Builder rateLimit(@Nullable
 RateLimitSetting value)

This setting helps to minimize the number of rate limit errors returned from the OpenShift AI API. By default, the openshift_ai service sets the number of requests allowed per minute to 3000.

API name: rate_limit

rateLimit

public final OpenShiftAiServiceSettings.Builder rateLimit(Function<RateLimitSetting.Builder,ObjectBuilder<RateLimitSetting>> fn)

This setting helps to minimize the number of rate limit errors returned from the OpenShift AI API. By default, the openshift_ai service sets the number of requests allowed per minute to 3000.

API name: rate_limit

self

protected OpenShiftAiServiceSettings.Builder self()

Specified by:

self in class WithJsonObjectBuilderBase<OpenShiftAiServiceSettings.Builder>

build

public OpenShiftAiServiceSettings build()

Builds a OpenShiftAiServiceSettings.

Specified by:

build in interface ObjectBuilder<OpenShiftAiServiceSettings>

Throws:

NullPointerException - if some of the required fields are null.