From 8fd08a0603680513fa80043984681f2c77569445 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Istv=C3=A1n=20Zolt=C3=A1n=20Szab=C3=B3?=
<szabosteve@gmail.com>
Date: Tue, 18 Mar 2025 15:16:47 +0100
Subject: [PATCH 1/2] Adds PUT EIS inference details (#3987)
* Adds EIS inference details.
Co-authored-by: Jonathan Buttner <56361221+jonathan-buttner@users.noreply.github.com>
---
output/openapi/elasticsearch-openapi.json | 113 +++++++-
.../elasticsearch-serverless-openapi.json | 113 +++++++-
output/schema/schema-serverless.json | 241 ++++++++++++++++--
output/schema/schema.json | 197 ++++++++++++++
output/typescript/types.ts | 20 ++
specification/_doc_ids/table.csv | 1 +
.../_json_spec/inference.put.eis.json | 35 +++
.../inference/put_eis/PutEisRequest.ts | 82 ++++++
.../inference/put_eis/PutEisResponse.ts | 24 ++
.../example/request/PutEisRequestExample.yaml | 11 +
10 files changed, 797 insertions(+), 40 deletions(-)
create mode 100644 specification/_json_spec/inference.put.eis.json
create mode 100644 specification/inference/put_eis/PutEisRequest.ts
create mode 100644 specification/inference/put_eis/PutEisResponse.ts
create mode 100644 specification/inference/put_eis/example/request/PutEisRequestExample.yaml
diff --git a/output/openapi/elasticsearch-openapi.json b/output/openapi/elasticsearch-openapi.json
index 6aece9a723..5d3f2d8a5c 100644
--- a/output/openapi/elasticsearch-openapi.json
+++ b/output/openapi/elasticsearch-openapi.json
@@ -17748,6 +17748,74 @@
"x-state": "Added in 8.11.0"
}
},
+ "/_inference/{task_type}/{eis_inference_id}": {
+ "put": {
+ "tags": [
+ "inference"
+ ],
+ "summary": "Create an Elastic Inference Service (EIS) inference endpoint",
+ "description": "Create an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).",
+ "operationId": "inference-put-eis",
+ "parameters": [
+ {
+ "in": "path",
+ "name": "task_type",
+ "description": "The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.",
+ "required": true,
+ "deprecated": false,
+ "schema": {
+ "$ref": "#/components/schemas/inference.put_eis:EisTaskType"
+ },
+ "style": "simple"
+ },
+ {
+ "in": "path",
+ "name": "eis_inference_id",
+ "description": "The unique identifier of the inference endpoint.",
+ "required": true,
+ "deprecated": false,
+ "schema": {
+ "$ref": "#/components/schemas/_types:Id"
+ },
+ "style": "simple"
+ }
+ ],
+ "requestBody": {
+ "content": {
+ "application/json": {
+ "schema": {
+ "type": "object",
+ "properties": {
+ "service": {
+ "$ref": "#/components/schemas/inference.put_eis:ServiceType"
+ },
+ "service_settings": {
+ "$ref": "#/components/schemas/inference.put_eis:EisServiceSettings"
+ }
+ },
+ "required": [
+ "service",
+ "service_settings"
+ ]
+ }
+ }
+ }
+ },
+ "responses": {
+ "200": {
+ "description": "",
+ "content": {
+ "application/json": {
+ "schema": {
+ "$ref": "#/components/schemas/inference._types:InferenceEndpointInfo"
+ }
+ }
+ }
+ }
+ },
+ "x-state": "Added in 8.12.0"
+ }
+ },
"/_inference/{task_type}/{openai_inference_id}": {
"put": {
"tags": [
@@ -76860,6 +76928,42 @@
"inference._types:ServiceSettings": {
"type": "object"
},
+ "inference.put_eis:EisTaskType": {
+ "type": "string",
+ "enum": [
+ "chat_completion"
+ ]
+ },
+ "inference.put_eis:ServiceType": {
+ "type": "string",
+ "enum": [
+ "elastic"
+ ]
+ },
+ "inference.put_eis:EisServiceSettings": {
+ "type": "object",
+ "properties": {
+ "model_id": {
+ "description": "The name of the model to use for the inference task.",
+ "type": "string"
+ },
+ "rate_limit": {
+ "$ref": "#/components/schemas/inference._types:RateLimitSetting"
+ }
+ },
+ "required": [
+ "model_id"
+ ]
+ },
+ "inference._types:RateLimitSetting": {
+ "type": "object",
+ "properties": {
+ "requests_per_minute": {
+ "description": "The number of requests allowed per minute.",
+ "type": "number"
+ }
+ }
+ },
"inference.put_openai:OpenAITaskType": {
"type": "string",
"enum": [
@@ -76912,15 +77016,6 @@
"model_id"
]
},
- "inference._types:RateLimitSetting": {
- "type": "object",
- "properties": {
- "requests_per_minute": {
- "description": "The number of requests allowed per minute.",
- "type": "number"
- }
- }
- },
"inference.put_openai:OpenAITaskSettings": {
"type": "object",
"properties": {
diff --git a/output/openapi/elasticsearch-serverless-openapi.json b/output/openapi/elasticsearch-serverless-openapi.json
index 170d015a7c..124dae311d 100644
--- a/output/openapi/elasticsearch-serverless-openapi.json
+++ b/output/openapi/elasticsearch-serverless-openapi.json
@@ -9719,6 +9719,74 @@
"x-state": "Added in 8.11.0"
}
},
+ "/_inference/{task_type}/{eis_inference_id}": {
+ "put": {
+ "tags": [
+ "inference"
+ ],
+ "summary": "Create an Elastic Inference Service (EIS) inference endpoint",
+ "description": "Create an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).",
+ "operationId": "inference-put-eis",
+ "parameters": [
+ {
+ "in": "path",
+ "name": "task_type",
+ "description": "The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.",
+ "required": true,
+ "deprecated": false,
+ "schema": {
+ "$ref": "#/components/schemas/inference.put_eis:EisTaskType"
+ },
+ "style": "simple"
+ },
+ {
+ "in": "path",
+ "name": "eis_inference_id",
+ "description": "The unique identifier of the inference endpoint.",
+ "required": true,
+ "deprecated": false,
+ "schema": {
+ "$ref": "#/components/schemas/_types:Id"
+ },
+ "style": "simple"
+ }
+ ],
+ "requestBody": {
+ "content": {
+ "application/json": {
+ "schema": {
+ "type": "object",
+ "properties": {
+ "service": {
+ "$ref": "#/components/schemas/inference.put_eis:ServiceType"
+ },
+ "service_settings": {
+ "$ref": "#/components/schemas/inference.put_eis:EisServiceSettings"
+ }
+ },
+ "required": [
+ "service",
+ "service_settings"
+ ]
+ }
+ }
+ }
+ },
+ "responses": {
+ "200": {
+ "description": "",
+ "content": {
+ "application/json": {
+ "schema": {
+ "$ref": "#/components/schemas/inference._types:InferenceEndpointInfo"
+ }
+ }
+ }
+ }
+ },
+ "x-state": "Added in 8.12.0"
+ }
+ },
"/_inference/{task_type}/{openai_inference_id}": {
"put": {
"tags": [
@@ -48195,6 +48263,42 @@
"inference._types:ServiceSettings": {
"type": "object"
},
+ "inference.put_eis:EisTaskType": {
+ "type": "string",
+ "enum": [
+ "chat_completion"
+ ]
+ },
+ "inference.put_eis:ServiceType": {
+ "type": "string",
+ "enum": [
+ "elastic"
+ ]
+ },
+ "inference.put_eis:EisServiceSettings": {
+ "type": "object",
+ "properties": {
+ "model_id": {
+ "description": "The name of the model to use for the inference task.",
+ "type": "string"
+ },
+ "rate_limit": {
+ "$ref": "#/components/schemas/inference._types:RateLimitSetting"
+ }
+ },
+ "required": [
+ "model_id"
+ ]
+ },
+ "inference._types:RateLimitSetting": {
+ "type": "object",
+ "properties": {
+ "requests_per_minute": {
+ "description": "The number of requests allowed per minute.",
+ "type": "number"
+ }
+ }
+ },
"inference.put_openai:OpenAITaskType": {
"type": "string",
"enum": [
@@ -48247,15 +48351,6 @@
"model_id"
]
},
- "inference._types:RateLimitSetting": {
- "type": "object",
- "properties": {
- "requests_per_minute": {
- "description": "The number of requests allowed per minute.",
- "type": "number"
- }
- }
- },
"inference.put_openai:OpenAITaskSettings": {
"type": "object",
"properties": {
diff --git a/output/schema/schema-serverless.json b/output/schema/schema-serverless.json
index 26a51f2716..9c0960916c 100644
--- a/output/schema/schema-serverless.json
+++ b/output/schema/schema-serverless.json
@@ -4713,6 +4713,51 @@
}
]
},
+ {
+ "availability": {
+ "serverless": {
+ "stability": "stable",
+ "visibility": "public"
+ },
+ "stack": {
+ "since": "8.12.0",
+ "stability": "stable",
+ "visibility": "public"
+ }
+ },
+ "description": "Create an Elastic Inference Service (EIS) inference endpoint.\n\nCreate an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).",
+ "docId": "inference-api-put-eis",
+ "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/current/infer-service-eis.html",
+ "name": "inference.put_eis",
+ "privileges": {
+ "cluster": [
+ "manage_inference"
+ ]
+ },
+ "request": {
+ "name": "Request",
+ "namespace": "inference.put_eis"
+ },
+ "requestBodyRequired": false,
+ "requestMediaType": [
+ "application/json"
+ ],
+ "response": {
+ "name": "Response",
+ "namespace": "inference.put_eis"
+ },
+ "responseMediaType": [
+ "application/json"
+ ],
+ "urls": [
+ {
+ "methods": [
+ "PUT"
+ ],
+ "path": "/_inference/{task_type}/{eis_inference_id}"
+ }
+ ]
+ },
{
"availability": {
"serverless": {
@@ -27292,6 +27337,98 @@
},
"specLocation": "inference/put/PutResponse.ts#L22-L24"
},
+ {
+ "attachedBehaviors": [
+ "CommonQueryParameters"
+ ],
+ "body": {
+ "kind": "properties",
+ "properties": [
+ {
+ "description": "The type of service supported for the specified task type. In this case, `elastic`.",
+ "name": "service",
+ "required": true,
+ "type": {
+ "kind": "instance_of",
+ "type": {
+ "name": "ServiceType",
+ "namespace": "inference.put_eis"
+ }
+ }
+ },
+ {
+ "description": "Settings used to install the inference model. These settings are specific to the `elastic` service.",
+ "name": "service_settings",
+ "required": true,
+ "type": {
+ "kind": "instance_of",
+ "type": {
+ "name": "EisServiceSettings",
+ "namespace": "inference.put_eis"
+ }
+ }
+ }
+ ]
+ },
+ "description": "Create an Elastic Inference Service (EIS) inference endpoint.\n\nCreate an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).",
+ "inherits": {
+ "type": {
+ "name": "RequestBase",
+ "namespace": "_types"
+ }
+ },
+ "kind": "request",
+ "name": {
+ "name": "Request",
+ "namespace": "inference.put_eis"
+ },
+ "path": [
+ {
+ "description": "The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.",
+ "name": "task_type",
+ "required": true,
+ "type": {
+ "kind": "instance_of",
+ "type": {
+ "name": "EisTaskType",
+ "namespace": "inference.put_eis"
+ }
+ }
+ },
+ {
+ "description": "The unique identifier of the inference endpoint.",
+ "name": "eis_inference_id",
+ "required": true,
+ "type": {
+ "kind": "instance_of",
+ "type": {
+ "name": "Id",
+ "namespace": "_types"
+ }
+ }
+ }
+ ],
+ "query": [],
+ "specLocation": "inference/put_eis/PutEisRequest.ts#L24-L62"
+ },
+ {
+ "body": {
+ "kind": "value",
+ "value": {
+ "kind": "instance_of",
+ "type": {
+ "name": "InferenceEndpointInfo",
+ "namespace": "inference._types"
+ }
+ }
+ },
+ "kind": "response",
+ "name": {
+ "name": "Response",
+ "namespace": "inference.put_eis"
+ },
+ "specLocation": "inference/put_eis/PutEisResponse.ts#L22-L24"
+ },
{
"attachedBehaviors": [
"CommonQueryParameters"
@@ -99831,6 +99968,32 @@
],
"specLocation": "inference/chat_completion_unified/UnifiedRequest.ts#L94-L106"
},
+ {
+ "kind": "enum",
+ "members": [
+ {
+ "name": "chat_completion"
+ }
+ ],
+ "name": {
+ "name": "EisTaskType",
+ "namespace": "inference.put_eis"
+ },
+ "specLocation": "inference/put_eis/PutEisRequest.ts#L64-L66"
+ },
+ {
+ "kind": "enum",
+ "members": [
+ {
+ "name": "elastic"
+ }
+ ],
+ "name": {
+ "name": "ServiceType",
+ "namespace": "inference.put_eis"
+ },
+ "specLocation": "inference/put_eis/PutEisRequest.ts#L68-L70"
+ },
{
"kind": "enum",
"members": [
@@ -120199,6 +120362,62 @@
],
"specLocation": "inference/_types/Services.ts#L60-L89"
},
+ {
+ "kind": "interface",
+ "name": {
+ "name": "EisServiceSettings",
+ "namespace": "inference.put_eis"
+ },
+ "properties": [
+ {
+ "description": "The name of the model to use for the inference task.",
+ "name": "model_id",
+ "required": true,
+ "type": {
+ "kind": "instance_of",
+ "type": {
+ "name": "string",
+ "namespace": "_builtins"
+ }
+ }
+ },
+ {
+ "description": "This setting helps to minimize the number of rate limit errors returned.\nBy default, the `elastic` service sets the number of requests allowed per minute to `240` in case of `chat_completion`.",
+ "name": "rate_limit",
+ "required": false,
+ "type": {
+ "kind": "instance_of",
+ "type": {
+ "name": "RateLimitSetting",
+ "namespace": "inference._types"
+ }
+ }
+ }
+ ],
+ "specLocation": "inference/put_eis/PutEisRequest.ts#L72-L82"
+ },
+ {
+ "kind": "interface",
+ "name": {
+ "name": "RateLimitSetting",
+ "namespace": "inference._types"
+ },
+ "properties": [
+ {
+ "description": "The number of requests allowed per minute.",
+ "name": "requests_per_minute",
+ "required": false,
+ "type": {
+ "kind": "instance_of",
+ "type": {
+ "name": "integer",
+ "namespace": "_types"
+ }
+ }
+ }
+ ],
+ "specLocation": "inference/_types/Services.ts#L95-L100"
+ },
{
"kind": "interface",
"name": {
@@ -120286,28 +120505,6 @@
],
"specLocation": "inference/put_openai/PutOpenAiRequest.ts#L94-L136"
},
- {
- "kind": "interface",
- "name": {
- "name": "RateLimitSetting",
- "namespace": "inference._types"
- },
- "properties": [
- {
- "description": "The number of requests allowed per minute.",
- "name": "requests_per_minute",
- "required": false,
- "type": {
- "kind": "instance_of",
- "type": {
- "name": "integer",
- "namespace": "_types"
- }
- }
- }
- ],
- "specLocation": "inference/_types/Services.ts#L95-L100"
- },
{
"kind": "interface",
"name": {
diff --git a/output/schema/schema.json b/output/schema/schema.json
index 328e0564fe..72025c6792 100644
--- a/output/schema/schema.json
+++ b/output/schema/schema.json
@@ -9306,6 +9306,51 @@
}
]
},
+ {
+ "availability": {
+ "serverless": {
+ "stability": "stable",
+ "visibility": "public"
+ },
+ "stack": {
+ "since": "8.12.0",
+ "stability": "stable",
+ "visibility": "public"
+ }
+ },
+ "description": "Create an Elastic Inference Service (EIS) inference endpoint.\n\nCreate an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).",
+ "docId": "inference-api-put-eis",
+ "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/current/infer-service-eis.html",
+ "name": "inference.put_eis",
+ "privileges": {
+ "cluster": [
+ "manage_inference"
+ ]
+ },
+ "request": {
+ "name": "Request",
+ "namespace": "inference.put_eis"
+ },
+ "requestBodyRequired": false,
+ "requestMediaType": [
+ "application/json"
+ ],
+ "response": {
+ "name": "Response",
+ "namespace": "inference.put_eis"
+ },
+ "responseMediaType": [
+ "application/json"
+ ],
+ "urls": [
+ {
+ "methods": [
+ "PUT"
+ ],
+ "path": "/_inference/{task_type}/{eis_inference_id}"
+ }
+ ]
+ },
{
"availability": {
"serverless": {
@@ -149961,6 +150006,158 @@
},
"specLocation": "inference/put/PutResponse.ts#L22-L24"
},
+ {
+ "kind": "interface",
+ "name": {
+ "name": "EisServiceSettings",
+ "namespace": "inference.put_eis"
+ },
+ "properties": [
+ {
+ "description": "The name of the model to use for the inference task.",
+ "name": "model_id",
+ "required": true,
+ "type": {
+ "kind": "instance_of",
+ "type": {
+ "name": "string",
+ "namespace": "_builtins"
+ }
+ }
+ },
+ {
+ "description": "This setting helps to minimize the number of rate limit errors returned.\nBy default, the `elastic` service sets the number of requests allowed per minute to `240` in case of `chat_completion`.",
+ "name": "rate_limit",
+ "required": false,
+ "type": {
+ "kind": "instance_of",
+ "type": {
+ "name": "RateLimitSetting",
+ "namespace": "inference._types"
+ }
+ }
+ }
+ ],
+ "specLocation": "inference/put_eis/PutEisRequest.ts#L72-L82"
+ },
+ {
+ "kind": "enum",
+ "members": [
+ {
+ "name": "chat_completion"
+ }
+ ],
+ "name": {
+ "name": "EisTaskType",
+ "namespace": "inference.put_eis"
+ },
+ "specLocation": "inference/put_eis/PutEisRequest.ts#L64-L66"
+ },
+ {
+ "kind": "request",
+ "attachedBehaviors": [
+ "CommonQueryParameters"
+ ],
+ "body": {
+ "kind": "properties",
+ "properties": [
+ {
+ "description": "The type of service supported for the specified task type. In this case, `elastic`.",
+ "name": "service",
+ "required": true,
+ "type": {
+ "kind": "instance_of",
+ "type": {
+ "name": "ServiceType",
+ "namespace": "inference.put_eis"
+ }
+ }
+ },
+ {
+ "description": "Settings used to install the inference model. These settings are specific to the `elastic` service.",
+ "name": "service_settings",
+ "required": true,
+ "type": {
+ "kind": "instance_of",
+ "type": {
+ "name": "EisServiceSettings",
+ "namespace": "inference.put_eis"
+ }
+ }
+ }
+ ]
+ },
+ "description": "Create an Elastic Inference Service (EIS) inference endpoint.\n\nCreate an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).",
+ "inherits": {
+ "type": {
+ "name": "RequestBase",
+ "namespace": "_types"
+ }
+ },
+ "name": {
+ "name": "Request",
+ "namespace": "inference.put_eis"
+ },
+ "path": [
+ {
+ "description": "The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.",
+ "name": "task_type",
+ "required": true,
+ "type": {
+ "kind": "instance_of",
+ "type": {
+ "name": "EisTaskType",
+ "namespace": "inference.put_eis"
+ }
+ }
+ },
+ {
+ "description": "The unique identifier of the inference endpoint.",
+ "name": "eis_inference_id",
+ "required": true,
+ "type": {
+ "kind": "instance_of",
+ "type": {
+ "name": "Id",
+ "namespace": "_types"
+ }
+ }
+ }
+ ],
+ "query": [],
+ "specLocation": "inference/put_eis/PutEisRequest.ts#L24-L62"
+ },
+ {
+ "kind": "response",
+ "body": {
+ "kind": "value",
+ "value": {
+ "kind": "instance_of",
+ "type": {
+ "name": "InferenceEndpointInfo",
+ "namespace": "inference._types"
+ }
+ }
+ },
+ "name": {
+ "name": "Response",
+ "namespace": "inference.put_eis"
+ },
+ "specLocation": "inference/put_eis/PutEisResponse.ts#L22-L24"
+ },
+ {
+ "kind": "enum",
+ "members": [
+ {
+ "name": "elastic"
+ }
+ ],
+ "name": {
+ "name": "ServiceType",
+ "namespace": "inference.put_eis"
+ },
+ "specLocation": "inference/put_eis/PutEisRequest.ts#L68-L70"
+ },
{
"kind": "interface",
"name": {
diff --git a/output/typescript/types.ts b/output/typescript/types.ts
index 9bc05b0e33..8010d6e3ba 100644
--- a/output/typescript/types.ts
+++ b/output/typescript/types.ts
@@ -13225,6 +13225,26 @@ export interface InferencePutRequest extends RequestBase {
export type InferencePutResponse = InferenceInferenceEndpointInfo
+export interface InferencePutEisEisServiceSettings {
+ model_id: string
+ rate_limit?: InferenceRateLimitSetting
+}
+
+export type InferencePutEisEisTaskType = 'chat_completion'
+
+export interface InferencePutEisRequest extends RequestBase {
+ task_type: InferencePutEisEisTaskType
+ eis_inference_id: Id
+ body?: {
+ service: InferencePutEisServiceType
+ service_settings: InferencePutEisEisServiceSettings
+ }
+}
+
+export type InferencePutEisResponse = InferenceInferenceEndpointInfo
+
+export type InferencePutEisServiceType = 'elastic'
+
export interface InferencePutOpenaiOpenAIServiceSettings {
api_key: string
dimensions?: integer
diff --git a/specification/_doc_ids/table.csv b/specification/_doc_ids/table.csv
index b4ea1b4724..865d3b4e33 100644
--- a/specification/_doc_ids/table.csv
+++ b/specification/_doc_ids/table.csv
@@ -318,6 +318,7 @@ inference-api-delete,https://www.elastic.co/guide/en/elasticsearch/reference/{br
inference-api-get,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/get-inference-api.html
inference-api-post,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/post-inference-api.html
inference-api-put,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/put-inference-api.html
+inference-api-put-eis,https://www.elastic.co/guide/en/elasticsearch/reference/current/infer-service-elastic.html
inference-api-put-openai,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/infer-service-openai.html
inference-api-put-watsonx,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/infer-service-watsonx-ai.html
inference-api-stream,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/stream-inference-api.html
diff --git a/specification/_json_spec/inference.put.eis.json b/specification/_json_spec/inference.put.eis.json
new file mode 100644
index 0000000000..281758769e
--- /dev/null
+++ b/specification/_json_spec/inference.put.eis.json
@@ -0,0 +1,35 @@
+{
+ "inference.put_eis": {
+ "documentation": {
+ "url": "https://www.elastic.co/guide/en/elasticsearch/reference/current/infer-service-eis.html",
+ "description": "Configure an EIS inference endpoint"
+ },
+ "stability": "stable",
+ "visibility": "public",
+ "headers": {
+ "accept": ["application/json"],
+ "content_type": ["application/json"]
+ },
+ "url": {
+ "paths": [
+ {
+ "path": "/_inference/{task_type}/{eis_inference_id}",
+ "methods": ["PUT"],
+ "parts": {
+ "task_type": {
+ "type": "string",
+ "description": "The task type"
+ },
+ "eis_inference_id": {
+ "type": "string",
+ "description": "The inference ID"
+ }
+ }
+ }
+ ]
+ },
+ "body": {
+ "description": "The inference endpoint's service settings"
+ }
+ }
+}
diff --git a/specification/inference/put_eis/PutEisRequest.ts b/specification/inference/put_eis/PutEisRequest.ts
new file mode 100644
index 0000000000..c788009a32
--- /dev/null
+++ b/specification/inference/put_eis/PutEisRequest.ts
@@ -0,0 +1,82 @@
+/*
+ * Licensed to Elasticsearch B.V. under one or more contributor
+ * license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright
+ * ownership. Elasticsearch B.V. licenses this file to you under
+ * the Apache License, Version 2.0 (the "License"); you may
+ * not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+import { RateLimitSetting } from '@inference/_types/Services'
+import { RequestBase } from '@_types/Base'
+import { Id } from '@_types/common'
+
+/**
+ * Create an Elastic Inference Service (EIS) inference endpoint.
+ *
+ * Create an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).
+ * @rest_spec_name inference.put_eis
+ * @availability stack since=8.12.0 stability=stable visibility=public
+ * @availability serverless stability=stable visibility=public
+ * @cluster_privileges manage_inference
+ * @doc_id inference-api-put-eis
+ */
+export interface Request extends RequestBase {
+ urls: [
+ {
+ path: '/_inference/{task_type}/{eis_inference_id}'
+ methods: ['PUT']
+ }
+ ]
+ path_parts: {
+ /**
+ * The type of the inference task that the model will perform.
+ * NOTE: The `chat_completion` task type only supports streaming and only through the _stream API.
+ */
+ task_type: EisTaskType
+ /**
+ * The unique identifier of the inference endpoint.
+ */
+ eis_inference_id: Id
+ }
+ body: {
+ /**
+ * The type of service supported for the specified task type. In this case, `elastic`.
+ */
+ service: ServiceType
+ /**
+ * Settings used to install the inference model. These settings are specific to the `elastic` service.
+ */
+ service_settings: EisServiceSettings
+ }
+}
+
+export enum EisTaskType {
+ chat_completion
+}
+
+export enum ServiceType {
+ elastic
+}
+
+export class EisServiceSettings {
+ /**
+ * The name of the model to use for the inference task.
+ */
+ model_id: string
+ /**
+ * This setting helps to minimize the number of rate limit errors returned.
+ * By default, the `elastic` service sets the number of requests allowed per minute to `240` in case of `chat_completion`.
+ */
+ rate_limit?: RateLimitSetting
+}
diff --git a/specification/inference/put_eis/PutEisResponse.ts b/specification/inference/put_eis/PutEisResponse.ts
new file mode 100644
index 0000000000..d40639b031
--- /dev/null
+++ b/specification/inference/put_eis/PutEisResponse.ts
@@ -0,0 +1,24 @@
+/*
+ * Licensed to Elasticsearch B.V. under one or more contributor
+ * license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright
+ * ownership. Elasticsearch B.V. licenses this file to you under
+ * the Apache License, Version 2.0 (the "License"); you may
+ * not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+import { InferenceEndpointInfo } from '@inference/_types/Services'
+
+export class Response {
+ body: InferenceEndpointInfo
+}
diff --git a/specification/inference/put_eis/example/request/PutEisRequestExample.yaml b/specification/inference/put_eis/example/request/PutEisRequestExample.yaml
new file mode 100644
index 0000000000..573bc66d22
--- /dev/null
+++ b/specification/inference/put_eis/example/request/PutEisRequestExample.yaml
@@ -0,0 +1,11 @@
+summary: A chat completion task
+description: Run `PUT _inference/chat_completion/chat-completion-endpoint` to create an inference endpoint to perform a chat completion task type.
+# method_request: "PUT _inference/chat_completion/chat-completion-endpoint"
+# type: "request"
+value: |-
+ {
+ "service": "elastic",
+ "service_settings": {
+ "model_id": "rainbow-sprinkles"
+ }
+ }
From 2cdb0b654d8d445d49b178805d84d8f3d01b88d9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Istv=C3=A1n=20Zolt=C3=A1n=20Szab=C3=B3?=
<szabosteve@gmail.com>
Date: Tue, 18 Mar 2025 15:59:26 +0100
Subject: [PATCH 2/2] Update specification/_doc_ids/table.csv
---
specification/_doc_ids/table.csv | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/specification/_doc_ids/table.csv b/specification/_doc_ids/table.csv
index 865d3b4e33..d338333d1e 100644
--- a/specification/_doc_ids/table.csv
+++ b/specification/_doc_ids/table.csv
@@ -318,7 +318,7 @@ inference-api-delete,https://www.elastic.co/guide/en/elasticsearch/reference/{br
inference-api-get,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/get-inference-api.html
inference-api-post,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/post-inference-api.html
inference-api-put,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/put-inference-api.html
-inference-api-put-eis,https://www.elastic.co/guide/en/elasticsearch/reference/current/infer-service-elastic.html
+inference-api-put-eis,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/infer-service-elastic.html
inference-api-put-openai,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/infer-service-openai.html
inference-api-put-watsonx,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/infer-service-watsonx-ai.html
inference-api-stream,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/stream-inference-api.html