From aafd99f7519730c42b3b7562012e28664f6e6261 Mon Sep 17 00:00:00 2001
From: kosabogi <boglarka.kosa@elastic.co>
Date: Wed, 29 Oct 2025 10:34:51 +0100
Subject: [PATCH 1/6] Improves descriptions in the Inference APIs

---
 specification/inference/_types/CommonTypes.ts              | 2 +-
 specification/inference/delete/DeleteRequest.ts            | 1 +
 specification/inference/get/GetRequest.ts                  | 1 +
 specification/inference/put/PutRequest.ts                  | 7 +++++++
 .../inference/put_alibabacloud/PutAlibabaCloudRequest.ts   | 2 ++
 .../inference/put_amazonbedrock/PutAmazonBedrockRequest.ts | 2 ++
 .../put_amazonsagemaker/PutAmazonSageMakerRequest.ts       | 2 ++
 .../inference/put_anthropic/PutAnthropicRequest.ts         | 2 ++
 .../inference/put_azureaistudio/PutAzureAiStudioRequest.ts | 2 ++
 .../inference/put_azureopenai/PutAzureOpenAiRequest.ts     | 2 ++
 specification/inference/put_cohere/PutCohereRequest.ts     | 2 ++
 .../inference/put_contextualai/PutContextualAiRequest.ts   | 2 ++
 specification/inference/put_custom/PutCustomRequest.ts     | 2 ++
 specification/inference/put_deepseek/PutDeepSeekRequest.ts | 2 ++
 specification/inference/put_elser/PutElserRequest.ts       | 2 ++
 .../put_googleaistudio/PutGoogleAiStudioRequest.ts         | 2 ++
 .../put_googlevertexai/PutGoogleVertexAiRequest.ts         | 2 ++
 .../inference/put_hugging_face/PutHuggingFaceRequest.ts    | 2 ++
 specification/inference/put_jinaai/PutJinaAiRequest.ts     | 2 ++
 specification/inference/put_llama/PutLlamaRequest.ts       | 2 ++
 specification/inference/put_mistral/PutMistralRequest.ts   | 2 ++
 specification/inference/put_openai/PutOpenAiRequest.ts     | 2 ++
 specification/inference/put_voyageai/PutVoyageAIRequest.ts | 2 ++
 23 files changed, 48 insertions(+), 1 deletion(-)

diff --git a/specification/inference/_types/CommonTypes.ts b/specification/inference/_types/CommonTypes.ts
index 130fc3fab6..1d68689627 100644
--- a/specification/inference/_types/CommonTypes.ts
+++ b/specification/inference/_types/CommonTypes.ts
@@ -391,7 +391,7 @@ export class AlibabaCloudTaskSettings {
 export enum AlibabaCloudTaskType {
   completion,
   rerank,
-  space_embedding,
+  sparse_embedding,
   text_embedding
 }
 
diff --git a/specification/inference/delete/DeleteRequest.ts b/specification/inference/delete/DeleteRequest.ts
index 16cb1f0ddc..83c13a631d 100644
--- a/specification/inference/delete/DeleteRequest.ts
+++ b/specification/inference/delete/DeleteRequest.ts
@@ -23,6 +23,7 @@ import { TaskType } from '@inference/_types/TaskType'
 
 /**
  * Delete an inference endpoint
+ * This API requires the manage_inference cluster privilege (the built-in inference_admin role grants this privilege).
  * @rest_spec_name inference.delete
  * @availability stack since=8.11.0 stability=stable visibility=public
  * @availability serverless stability=stable visibility=public
diff --git a/specification/inference/get/GetRequest.ts b/specification/inference/get/GetRequest.ts
index a9523a8878..ac6356e9eb 100644
--- a/specification/inference/get/GetRequest.ts
+++ b/specification/inference/get/GetRequest.ts
@@ -23,6 +23,7 @@ import { TaskType } from '@inference/_types/TaskType'
 
 /**
  * Get an inference endpoint
+ * This API requires the `monitor_inference` cluster privilege (the built-in `inference_admin` and `inference_user` roles grant this privilege).
  * @rest_spec_name inference.get
  * @availability stack since=8.11.0 stability=stable visibility=public
  * @availability serverless stability=stable visibility=public
diff --git a/specification/inference/put/PutRequest.ts b/specification/inference/put/PutRequest.ts
index 0ee0bf0689..77053065d9 100644
--- a/specification/inference/put/PutRequest.ts
+++ b/specification/inference/put/PutRequest.ts
@@ -51,6 +51,13 @@ import { TaskType } from '@inference/_types/TaskType'
  * * OpenAI (`chat_completion`, `completion`, `text_embedding`)
  * * VoyageAI (`rerank`, `text_embedding`)
  * * Watsonx inference integration (`text_embedding`)
+ *
+ * NOTE: When creating 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. You can verify
+ * the deployment status by using the Get trained model statistics API. In the response, look for "state": "fully_allocated"
+ * and ensure the "allocation_count" matches the "target_allocation_count". Avoid creating multiple endpoints for the same
+ * model unless required, as each endpoint consumes significant resources.
+ *
  * @rest_spec_name inference.put
  * @availability stack since=8.11.0 stability=stable visibility=public
  * @availability serverless stability=stable visibility=public
diff --git a/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts b/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts
index c725397056..5a7ce2abee 100644
--- a/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts
+++ b/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts
@@ -65,6 +65,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_amazonbedrock/PutAmazonBedrockRequest.ts b/specification/inference/put_amazonbedrock/PutAmazonBedrockRequest.ts
index 61927ce3bf..43787f4c51 100644
--- a/specification/inference/put_amazonbedrock/PutAmazonBedrockRequest.ts
+++ b/specification/inference/put_amazonbedrock/PutAmazonBedrockRequest.ts
@@ -68,6 +68,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_amazonsagemaker/PutAmazonSageMakerRequest.ts b/specification/inference/put_amazonsagemaker/PutAmazonSageMakerRequest.ts
index 1b020e5fc8..a333fbbef5 100644
--- a/specification/inference/put_amazonsagemaker/PutAmazonSageMakerRequest.ts
+++ b/specification/inference/put_amazonsagemaker/PutAmazonSageMakerRequest.ts
@@ -65,6 +65,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_anthropic/PutAnthropicRequest.ts b/specification/inference/put_anthropic/PutAnthropicRequest.ts
index ec0c4f5403..509ba1acf4 100644
--- a/specification/inference/put_anthropic/PutAnthropicRequest.ts
+++ b/specification/inference/put_anthropic/PutAnthropicRequest.ts
@@ -66,6 +66,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_azureaistudio/PutAzureAiStudioRequest.ts b/specification/inference/put_azureaistudio/PutAzureAiStudioRequest.ts
index 5313142e27..af5a05605f 100644
--- a/specification/inference/put_azureaistudio/PutAzureAiStudioRequest.ts
+++ b/specification/inference/put_azureaistudio/PutAzureAiStudioRequest.ts
@@ -65,6 +65,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_azureopenai/PutAzureOpenAiRequest.ts b/specification/inference/put_azureopenai/PutAzureOpenAiRequest.ts
index af881b68ef..a6f7c67657 100644
--- a/specification/inference/put_azureopenai/PutAzureOpenAiRequest.ts
+++ b/specification/inference/put_azureopenai/PutAzureOpenAiRequest.ts
@@ -73,6 +73,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_cohere/PutCohereRequest.ts b/specification/inference/put_cohere/PutCohereRequest.ts
index 6ebfc47292..66e893cb2f 100644
--- a/specification/inference/put_cohere/PutCohereRequest.ts
+++ b/specification/inference/put_cohere/PutCohereRequest.ts
@@ -65,6 +65,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_contextualai/PutContextualAiRequest.ts b/specification/inference/put_contextualai/PutContextualAiRequest.ts
index fefd3fb051..51145847b0 100644
--- a/specification/inference/put_contextualai/PutContextualAiRequest.ts
+++ b/specification/inference/put_contextualai/PutContextualAiRequest.ts
@@ -67,6 +67,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_custom/PutCustomRequest.ts b/specification/inference/put_custom/PutCustomRequest.ts
index f7dcf96d14..22314d7c11 100644
--- a/specification/inference/put_custom/PutCustomRequest.ts
+++ b/specification/inference/put_custom/PutCustomRequest.ts
@@ -96,6 +96,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_deepseek/PutDeepSeekRequest.ts b/specification/inference/put_deepseek/PutDeepSeekRequest.ts
index c188ffd857..b3d29fe86e 100644
--- a/specification/inference/put_deepseek/PutDeepSeekRequest.ts
+++ b/specification/inference/put_deepseek/PutDeepSeekRequest.ts
@@ -64,6 +64,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_elser/PutElserRequest.ts b/specification/inference/put_elser/PutElserRequest.ts
index e5a21e2cdd..66aa08d513 100644
--- a/specification/inference/put_elser/PutElserRequest.ts
+++ b/specification/inference/put_elser/PutElserRequest.ts
@@ -79,6 +79,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * Note that for ELSER endpoints, the max_chunk_size may not exceed `300`.
      * @ext_doc_id inference-chunking
      */
diff --git a/specification/inference/put_googleaistudio/PutGoogleAiStudioRequest.ts b/specification/inference/put_googleaistudio/PutGoogleAiStudioRequest.ts
index 6871ceb750..943a53236c 100644
--- a/specification/inference/put_googleaistudio/PutGoogleAiStudioRequest.ts
+++ b/specification/inference/put_googleaistudio/PutGoogleAiStudioRequest.ts
@@ -64,6 +64,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_googlevertexai/PutGoogleVertexAiRequest.ts b/specification/inference/put_googlevertexai/PutGoogleVertexAiRequest.ts
index 80cf04059e..df9b02e6e5 100644
--- a/specification/inference/put_googlevertexai/PutGoogleVertexAiRequest.ts
+++ b/specification/inference/put_googlevertexai/PutGoogleVertexAiRequest.ts
@@ -65,6 +65,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_hugging_face/PutHuggingFaceRequest.ts b/specification/inference/put_hugging_face/PutHuggingFaceRequest.ts
index d4c16ffb84..b9ddb24c2a 100644
--- a/specification/inference/put_hugging_face/PutHuggingFaceRequest.ts
+++ b/specification/inference/put_hugging_face/PutHuggingFaceRequest.ts
@@ -101,6 +101,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_jinaai/PutJinaAiRequest.ts b/specification/inference/put_jinaai/PutJinaAiRequest.ts
index 6685c2c874..ae349183d0 100644
--- a/specification/inference/put_jinaai/PutJinaAiRequest.ts
+++ b/specification/inference/put_jinaai/PutJinaAiRequest.ts
@@ -68,6 +68,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_llama/PutLlamaRequest.ts b/specification/inference/put_llama/PutLlamaRequest.ts
index 966f83cc19..e8549300fb 100644
--- a/specification/inference/put_llama/PutLlamaRequest.ts
+++ b/specification/inference/put_llama/PutLlamaRequest.ts
@@ -64,6 +64,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_mistral/PutMistralRequest.ts b/specification/inference/put_mistral/PutMistralRequest.ts
index 3a7b5eaace..768b0b3b02 100644
--- a/specification/inference/put_mistral/PutMistralRequest.ts
+++ b/specification/inference/put_mistral/PutMistralRequest.ts
@@ -64,6 +64,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_openai/PutOpenAiRequest.ts b/specification/inference/put_openai/PutOpenAiRequest.ts
index b6bb675f46..9f642dacba 100644
--- a/specification/inference/put_openai/PutOpenAiRequest.ts
+++ b/specification/inference/put_openai/PutOpenAiRequest.ts
@@ -66,6 +66,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_voyageai/PutVoyageAIRequest.ts b/specification/inference/put_voyageai/PutVoyageAIRequest.ts
index 2bb4b7ef46..0bd62aaf31 100644
--- a/specification/inference/put_voyageai/PutVoyageAIRequest.ts
+++ b/specification/inference/put_voyageai/PutVoyageAIRequest.ts
@@ -67,6 +67,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
+     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings

From b89aee36e46664db0b919ecc6c33e889edc9c672 Mon Sep 17 00:00:00 2001
From: kosabogi <105062005+kosabogi@users.noreply.github.com>
Date: Thu, 30 Oct 2025 11:10:47 +0100
Subject: [PATCH 2/6] Update specification/inference/delete/DeleteRequest.ts

Co-authored-by: Liam Thompson <leemthompo@gmail.com>
---
 specification/inference/delete/DeleteRequest.ts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/specification/inference/delete/DeleteRequest.ts b/specification/inference/delete/DeleteRequest.ts
index 83c13a631d..7f155db264 100644
--- a/specification/inference/delete/DeleteRequest.ts
+++ b/specification/inference/delete/DeleteRequest.ts
@@ -23,7 +23,7 @@ import { TaskType } from '@inference/_types/TaskType'
 
 /**
  * Delete an inference endpoint
- * This API requires the manage_inference cluster privilege (the built-in inference_admin role grants this privilege).
+ * This API requires the manage_inference cluster privilege (the built-in `inference_admin` role grants this privilege).
  * @rest_spec_name inference.delete
  * @availability stack since=8.11.0 stability=stable visibility=public
  * @availability serverless stability=stable visibility=public

From 941466f0b5e7a98a4f05c6ad9acfca5af22ea516 Mon Sep 17 00:00:00 2001
From: kosabogi <105062005+kosabogi@users.noreply.github.com>
Date: Fri, 31 Oct 2025 11:30:18 +0100
Subject: [PATCH 3/6] Update specification/inference/put/PutRequest.ts

Co-authored-by: David Kyle <david.kyle@elastic.co>
---
 specification/inference/put/PutRequest.ts | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/specification/inference/put/PutRequest.ts b/specification/inference/put/PutRequest.ts
index 77053065d9..0ee0bf0689 100644
--- a/specification/inference/put/PutRequest.ts
+++ b/specification/inference/put/PutRequest.ts
@@ -51,13 +51,6 @@ import { TaskType } from '@inference/_types/TaskType'
  * * OpenAI (`chat_completion`, `completion`, `text_embedding`)
  * * VoyageAI (`rerank`, `text_embedding`)
  * * Watsonx inference integration (`text_embedding`)
- *
- * NOTE: When creating 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. You can verify
- * the deployment status by using the Get trained model statistics API. In the response, look for "state": "fully_allocated"
- * and ensure the "allocation_count" matches the "target_allocation_count". Avoid creating multiple endpoints for the same
- * model unless required, as each endpoint consumes significant resources.
- *
  * @rest_spec_name inference.put
  * @availability stack since=8.11.0 stability=stable visibility=public
  * @availability serverless stability=stable visibility=public

From 53016cd1ff77573ebfd94deed0f6101719c9bb00 Mon Sep 17 00:00:00 2001
From: kosabogi <boglarka.kosa@elastic.co>
Date: Fri, 31 Oct 2025 11:57:07 +0100
Subject: [PATCH 4/6] Fixes chunking_settings object descriptions

---
 .../inference/put_alibabacloud/PutAlibabaCloudRequest.ts  | 2 +-
 .../put_amazonbedrock/PutAmazonBedrockRequest.ts          | 4 ++--
 .../inference/put_anthropic/PutAnthropicRequest.ts        | 7 -------
 .../put_azureaistudio/PutAzureAiStudioRequest.ts          | 4 ++--
 .../inference/put_azureopenai/PutAzureOpenAiRequest.ts    | 4 ++--
 specification/inference/put_cohere/PutCohereRequest.ts    | 4 ++--
 .../inference/put_contextualai/PutContextualAiRequest.ts  | 7 -------
 specification/inference/put_custom/PutCustomRequest.ts    | 2 +-
 .../inference/put_deepseek/PutDeepSeekRequest.ts          | 7 -------
 .../put_elasticsearch/PutElasticsearchRequest.ts          | 2 +-
 specification/inference/put_elser/PutElserRequest.ts      | 2 --
 .../put_googleaistudio/PutGoogleAiStudioRequest.ts        | 4 ++--
 .../put_googlevertexai/PutGoogleVertexAiRequest.ts        | 2 +-
 .../inference/put_hugging_face/PutHuggingFaceRequest.ts   | 2 +-
 specification/inference/put_jinaai/PutJinaAiRequest.ts    | 4 ++--
 specification/inference/put_llama/PutLlamaRequest.ts      | 4 ++--
 specification/inference/put_mistral/PutMistralRequest.ts  | 4 ++--
 specification/inference/put_openai/PutOpenAiRequest.ts    | 4 ++--
 .../inference/put_voyageai/PutVoyageAIRequest.ts          | 4 ++--
 specification/inference/put_watsonx/PutWatsonxRequest.ts  | 8 ++++++++
 20 files changed, 33 insertions(+), 48 deletions(-)

diff --git a/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts b/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts
index 5a7ce2abee..a75902890a 100644
--- a/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts
+++ b/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts
@@ -66,7 +66,7 @@ export interface Request extends RequestBase {
     /**
      * The chunking configuration object.
      * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
+     * Not applicable to the `rerank`, or `completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_amazonbedrock/PutAmazonBedrockRequest.ts b/specification/inference/put_amazonbedrock/PutAmazonBedrockRequest.ts
index 43787f4c51..e87d687d88 100644
--- a/specification/inference/put_amazonbedrock/PutAmazonBedrockRequest.ts
+++ b/specification/inference/put_amazonbedrock/PutAmazonBedrockRequest.ts
@@ -68,8 +68,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
+     * Applies only to the `text_embedding` task type.
+     * Not applicable to the `completion` task type.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_anthropic/PutAnthropicRequest.ts b/specification/inference/put_anthropic/PutAnthropicRequest.ts
index 509ba1acf4..e30638ec43 100644
--- a/specification/inference/put_anthropic/PutAnthropicRequest.ts
+++ b/specification/inference/put_anthropic/PutAnthropicRequest.ts
@@ -64,13 +64,6 @@ export interface Request extends RequestBase {
     timeout?: Duration
   }
   body: {
-    /**
-     * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
-     * @ext_doc_id inference-chunking
-     */
-    chunking_settings?: InferenceChunkingSettings
     /**
      * The type of service supported for the specified task type. In this case, `anthropic`.
      */
diff --git a/specification/inference/put_azureaistudio/PutAzureAiStudioRequest.ts b/specification/inference/put_azureaistudio/PutAzureAiStudioRequest.ts
index af5a05605f..8b152cd190 100644
--- a/specification/inference/put_azureaistudio/PutAzureAiStudioRequest.ts
+++ b/specification/inference/put_azureaistudio/PutAzureAiStudioRequest.ts
@@ -65,8 +65,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
+     * Applies only to the `text_embedding` task type.
+     * Not applicable to the `rerank` or `completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_azureopenai/PutAzureOpenAiRequest.ts b/specification/inference/put_azureopenai/PutAzureOpenAiRequest.ts
index a6f7c67657..dd72ba63d8 100644
--- a/specification/inference/put_azureopenai/PutAzureOpenAiRequest.ts
+++ b/specification/inference/put_azureopenai/PutAzureOpenAiRequest.ts
@@ -73,8 +73,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
+     * Applies only to the `text_embedding` task type.
+     * Not applicable to the `completion` task type.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_cohere/PutCohereRequest.ts b/specification/inference/put_cohere/PutCohereRequest.ts
index 66e893cb2f..ef267defa5 100644
--- a/specification/inference/put_cohere/PutCohereRequest.ts
+++ b/specification/inference/put_cohere/PutCohereRequest.ts
@@ -65,8 +65,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
+     * Applies only to the `text_embedding` task type.
+     * Not applicable to the `rerank` or `completion` task type.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_contextualai/PutContextualAiRequest.ts b/specification/inference/put_contextualai/PutContextualAiRequest.ts
index 51145847b0..0002b6ef8b 100644
--- a/specification/inference/put_contextualai/PutContextualAiRequest.ts
+++ b/specification/inference/put_contextualai/PutContextualAiRequest.ts
@@ -65,13 +65,6 @@ export interface Request extends RequestBase {
     timeout?: Duration
   }
   body: {
-    /**
-     * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
-     * @ext_doc_id inference-chunking
-     */
-    chunking_settings?: InferenceChunkingSettings
     /**
      * The type of service supported for the specified task type. In this case, `contextualai`.
      */
diff --git a/specification/inference/put_custom/PutCustomRequest.ts b/specification/inference/put_custom/PutCustomRequest.ts
index 22314d7c11..2365f2bbf6 100644
--- a/specification/inference/put_custom/PutCustomRequest.ts
+++ b/specification/inference/put_custom/PutCustomRequest.ts
@@ -97,7 +97,7 @@ export interface Request extends RequestBase {
     /**
      * The chunking configuration object.
      * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
+     * Not applicable to the `rerank` or `completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_deepseek/PutDeepSeekRequest.ts b/specification/inference/put_deepseek/PutDeepSeekRequest.ts
index b3d29fe86e..4085648003 100644
--- a/specification/inference/put_deepseek/PutDeepSeekRequest.ts
+++ b/specification/inference/put_deepseek/PutDeepSeekRequest.ts
@@ -62,13 +62,6 @@ export interface Request extends RequestBase {
     timeout?: Duration
   }
   body: {
-    /**
-     * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
-     * @ext_doc_id inference-chunking
-     */
-    chunking_settings?: InferenceChunkingSettings
     /**
      * The type of service supported for the specified task type. In this case, `deepseek`.
      */
diff --git a/specification/inference/put_elasticsearch/PutElasticsearchRequest.ts b/specification/inference/put_elasticsearch/PutElasticsearchRequest.ts
index b35720d1c7..74d51feb19 100644
--- a/specification/inference/put_elasticsearch/PutElasticsearchRequest.ts
+++ b/specification/inference/put_elasticsearch/PutElasticsearchRequest.ts
@@ -80,7 +80,7 @@ export interface Request extends RequestBase {
     /**
      * The chunking configuration object.
      * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
+     * Not applicable to the `rerank` task type.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_elser/PutElserRequest.ts b/specification/inference/put_elser/PutElserRequest.ts
index 66aa08d513..e5a21e2cdd 100644
--- a/specification/inference/put_elser/PutElserRequest.ts
+++ b/specification/inference/put_elser/PutElserRequest.ts
@@ -79,8 +79,6 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * Note that for ELSER endpoints, the max_chunk_size may not exceed `300`.
      * @ext_doc_id inference-chunking
      */
diff --git a/specification/inference/put_googleaistudio/PutGoogleAiStudioRequest.ts b/specification/inference/put_googleaistudio/PutGoogleAiStudioRequest.ts
index 943a53236c..c8c2f0f6a8 100644
--- a/specification/inference/put_googleaistudio/PutGoogleAiStudioRequest.ts
+++ b/specification/inference/put_googleaistudio/PutGoogleAiStudioRequest.ts
@@ -64,8 +64,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
+     * Applies only to the `text_embedding` task type.
+     * Not applicable to the `completion` task type.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_googlevertexai/PutGoogleVertexAiRequest.ts b/specification/inference/put_googlevertexai/PutGoogleVertexAiRequest.ts
index df9b02e6e5..943faaf1dc 100644
--- a/specification/inference/put_googlevertexai/PutGoogleVertexAiRequest.ts
+++ b/specification/inference/put_googlevertexai/PutGoogleVertexAiRequest.ts
@@ -65,7 +65,7 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Applies only to the `text_embedding` task type.
      * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
diff --git a/specification/inference/put_hugging_face/PutHuggingFaceRequest.ts b/specification/inference/put_hugging_face/PutHuggingFaceRequest.ts
index b9ddb24c2a..62f47a6846 100644
--- a/specification/inference/put_hugging_face/PutHuggingFaceRequest.ts
+++ b/specification/inference/put_hugging_face/PutHuggingFaceRequest.ts
@@ -101,7 +101,7 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Applies only to the `text_embedding` task type.
      * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
diff --git a/specification/inference/put_jinaai/PutJinaAiRequest.ts b/specification/inference/put_jinaai/PutJinaAiRequest.ts
index ae349183d0..a6f048ccfb 100644
--- a/specification/inference/put_jinaai/PutJinaAiRequest.ts
+++ b/specification/inference/put_jinaai/PutJinaAiRequest.ts
@@ -68,8 +68,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
+     * Applies only to the `text_embedding` task type.
+     * Not applicable to the `rerank` task type.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_llama/PutLlamaRequest.ts b/specification/inference/put_llama/PutLlamaRequest.ts
index e8549300fb..d1542382d6 100644
--- a/specification/inference/put_llama/PutLlamaRequest.ts
+++ b/specification/inference/put_llama/PutLlamaRequest.ts
@@ -64,8 +64,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
+     * Applies only to the `text_embedding` task type.
+     * Not applicable to the `completion` or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_mistral/PutMistralRequest.ts b/specification/inference/put_mistral/PutMistralRequest.ts
index 768b0b3b02..304351e87a 100644
--- a/specification/inference/put_mistral/PutMistralRequest.ts
+++ b/specification/inference/put_mistral/PutMistralRequest.ts
@@ -64,8 +64,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
+     * Applies only to the `text_embedding` task type.
+     * Not applicable to the `completion` or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_openai/PutOpenAiRequest.ts b/specification/inference/put_openai/PutOpenAiRequest.ts
index 9f642dacba..48ec00c1ad 100644
--- a/specification/inference/put_openai/PutOpenAiRequest.ts
+++ b/specification/inference/put_openai/PutOpenAiRequest.ts
@@ -66,8 +66,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
+     * Applies only to the `text_embedding` task type.
+     * Not applicable to the `completion` or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_voyageai/PutVoyageAIRequest.ts b/specification/inference/put_voyageai/PutVoyageAIRequest.ts
index 0bd62aaf31..99ec97c36b 100644
--- a/specification/inference/put_voyageai/PutVoyageAIRequest.ts
+++ b/specification/inference/put_voyageai/PutVoyageAIRequest.ts
@@ -67,8 +67,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
+     * Applies only to the `text_embedding` task type.
+     * Not applicable to the `rerank` task type.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_watsonx/PutWatsonxRequest.ts b/specification/inference/put_watsonx/PutWatsonxRequest.ts
index b48fb3aa4c..86837a2254 100644
--- a/specification/inference/put_watsonx/PutWatsonxRequest.ts
+++ b/specification/inference/put_watsonx/PutWatsonxRequest.ts
@@ -25,6 +25,7 @@ import {
   WatsonxServiceType,
   WatsonxTaskType
 } from '@inference/_types/CommonTypes'
+import { InferenceChunkingSettings } from '@inference/_types/Services'
 
 /**
  * Create a Watsonx inference endpoint.
@@ -63,6 +64,13 @@ export interface Request extends RequestBase {
     timeout?: Duration
   }
   body: {
+    /**
+     * The chunking configuration object.
+     * Applies only to the `text_embedding` task type.
+     * Not applicable to the `completion` or `chat_completion` task types.
+     * @ext_doc_id inference-chunking
+     */
+    chunking_settings?: InferenceChunkingSettings
     /**
      * The type of service supported for the specified task type. In this case, `watsonxai`.
      */

From eeb184788afb0e94bcd1d90cba5420323718c3fe Mon Sep 17 00:00:00 2001
From: kosabogi <boglarka.kosa@elastic.co>
Date: Fri, 31 Oct 2025 12:03:15 +0100
Subject: [PATCH 5/6] Fixes oxford comma

---
 .../inference/put_alibabacloud/PutAlibabaCloudRequest.ts      | 4 ++--
 .../put_amazonsagemaker/PutAmazonSageMakerRequest.ts          | 2 +-
 specification/inference/put_custom/PutCustomRequest.ts        | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts b/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts
index a75902890a..b2ce40073a 100644
--- a/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts
+++ b/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts
@@ -65,8 +65,8 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
-     * Not applicable to the `rerank`, or `completion` task types.
+     * Applies only to the `sparse_embedding` or `text_embedding` task types.
+     * Not applicable to the `rerank` or `completion` task types.
      * @ext_doc_id inference-chunking
      */
     chunking_settings?: InferenceChunkingSettings
diff --git a/specification/inference/put_amazonsagemaker/PutAmazonSageMakerRequest.ts b/specification/inference/put_amazonsagemaker/PutAmazonSageMakerRequest.ts
index a333fbbef5..b91ebdcf5a 100644
--- a/specification/inference/put_amazonsagemaker/PutAmazonSageMakerRequest.ts
+++ b/specification/inference/put_amazonsagemaker/PutAmazonSageMakerRequest.ts
@@ -65,7 +65,7 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Applies only to the `sparse_embedding` or `text_embedding` task types.
      * Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
      * @ext_doc_id inference-chunking
      */
diff --git a/specification/inference/put_custom/PutCustomRequest.ts b/specification/inference/put_custom/PutCustomRequest.ts
index 2365f2bbf6..9d7ef981c1 100644
--- a/specification/inference/put_custom/PutCustomRequest.ts
+++ b/specification/inference/put_custom/PutCustomRequest.ts
@@ -96,7 +96,7 @@ export interface Request extends RequestBase {
   body: {
     /**
      * The chunking configuration object.
-     * Applies only to the `sparse_embedding` and `text_embedding` task types.
+     * Applies only to the `sparse_embedding` or `text_embedding` task types.
      * Not applicable to the `rerank` or `completion` task types.
      * @ext_doc_id inference-chunking
      */

From 52f1aaf4e33dce82e1640021f903cf41f26c9ce5 Mon Sep 17 00:00:00 2001
From: kosabogi <boglarka.kosa@elastic.co>
Date: Fri, 31 Oct 2025 12:05:02 +0100
Subject: [PATCH 6/6] Formatting fix

---
 specification/inference/put_anthropic/PutAnthropicRequest.ts     | 1 -
 .../inference/put_contextualai/PutContextualAiRequest.ts         | 1 -
 specification/inference/put_deepseek/PutDeepSeekRequest.ts       | 1 -
 3 files changed, 3 deletions(-)

diff --git a/specification/inference/put_anthropic/PutAnthropicRequest.ts b/specification/inference/put_anthropic/PutAnthropicRequest.ts
index e30638ec43..501bf7a631 100644
--- a/specification/inference/put_anthropic/PutAnthropicRequest.ts
+++ b/specification/inference/put_anthropic/PutAnthropicRequest.ts
@@ -26,7 +26,6 @@ import {
   AnthropicTaskSettings,
   AnthropicTaskType
 } from '@inference/_types/CommonTypes'
-import { InferenceChunkingSettings } from '@inference/_types/Services'
 
 /**
  * Create an Anthropic inference endpoint.
diff --git a/specification/inference/put_contextualai/PutContextualAiRequest.ts b/specification/inference/put_contextualai/PutContextualAiRequest.ts
index 0002b6ef8b..d52ac070b8 100644
--- a/specification/inference/put_contextualai/PutContextualAiRequest.ts
+++ b/specification/inference/put_contextualai/PutContextualAiRequest.ts
@@ -25,7 +25,6 @@ import {
   ContextualAIServiceType,
   ContextualAITaskSettings
 } from '@inference/_types/CommonTypes'
-import { InferenceChunkingSettings } from '@inference/_types/Services'
 import { TaskTypeContextualAI } from '@inference/_types/TaskType'
 
 /**
diff --git a/specification/inference/put_deepseek/PutDeepSeekRequest.ts b/specification/inference/put_deepseek/PutDeepSeekRequest.ts
index 4085648003..7387aba59a 100644
--- a/specification/inference/put_deepseek/PutDeepSeekRequest.ts
+++ b/specification/inference/put_deepseek/PutDeepSeekRequest.ts
@@ -24,7 +24,6 @@ import {
   DeepSeekServiceSettings,
   DeepSeekServiceType
 } from '@inference/_types/CommonTypes'
-import { InferenceChunkingSettings } from '@inference/_types/Services'
 import { TaskTypeDeepSeek } from '@inference/_types/TaskType'
 
 /**