eis chat completion and unified cc request refactor

Author: l-trotta

output/openapi/elasticsearch-openapi.json

@@ -56,6 +56,12 @@
       ],
       "response": []
     },
+    "inference.post_eis_chat_completion": {
+      "request": [
+        "Request: url path '/_inference/{task_type}/{eis_inference_id}/_stream' not found in the json spec"
+      ],
+      "response": []
+    },
     "ingest.get_ip_location_database": {
       "request": [
         "Request: query parameter 'master_timeout' does not exist in the json spec"

output/openapi/elasticsearch-serverless-openapi.json

@@ -1,5 +1,5 @@
 {
-  "inference.post.eis_chat_completion": {
+  "inference.post_eis_chat_completion": {
     "documentation": {
       "url": "https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html",
       "description": "Perform a chat completion task via the Elastic Inference Service (EIS)"

output/schema/schema-serverless.json

@@ -0,0 +1,61 @@
+/*
+ * 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 {
+  CompletionTool,
+  CompletionToolType,
+  Message
+} from '@inference/chat_completion_unified/UnifiedRequest'
+import { RequestBase } from '@_types/Base'
+import { float, long } from '@_types/Numeric'
+
+export interface RequestChatCompletionBase extends RequestBase {
+  /**
+   * A list of objects representing the conversation.
+   */
+  messages: Array<Message>
+  /**
+   * The ID of the model to use.
+   */
+  model?: string
+  /**
+   * The upper bound limit for the number of tokens that can be generated for a completion request.
+   */
+  max_completion_tokens?: long
+  /**
+   * A sequence of strings to control when the model should stop generating additional tokens.
+   */
+  stop?: Array<string>
+  /**
+   * The sampling temperature to use.
+   */
+  temperature?: float
+  /**
+   * Controls which tool is called by the model.
+   */
+  tool_choice?: CompletionToolType
+  /**
+   * A list of tools that the model can call.
+   */
+  tools?: Array<CompletionTool>
+  /**
+   * Nucleus sampling, an alternative to sampling with temperature.
+   */
+  top_p?: float
+}

output/schema/schema.json

@@ -17,10 +17,9 @@
  * under the License.
  */
 
+import { RequestChatCompletionBase } from '@inference/_types/CommonTypes'
 import { UserDefinedValue } from '@spec_utils/UserDefinedValue'
-import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
-import { float, long } from '@_types/Numeric'
 import { Duration } from '@_types/Time'
 
 /**
@@ -30,7 +29,7 @@ import { Duration } from '@_types/Time'
  * @availability serverless stability=stable visibility=public
  * @doc_id inference-api-chat-completion
  */
-export interface Request extends RequestBase {
+export interface Request extends RequestChatCompletionBase {
   urls: [
     {
       path: '/_inference/chat_completion/{inference_id}/_stream'
@@ -50,40 +49,6 @@ export interface Request extends RequestBase {
      */
     timeout?: Duration
   }
-  body: {
-    /**
-     * A list of objects representing the conversation.
-     */
-    messages: Array<Message>
-    /**
-     * The ID of the model to use.
-     */
-    model?: string
-    /**
-     * The upper bound limit for the number of tokens that can be generated for a completion request.
-     */
-    max_completion_tokens?: long
-    /**
-     * A sequence of strings to control when the model should stop generating additional tokens.
-     */
-    stop?: Array<string>
-    /**
-     * The sampling temperature to use.
-     */
-    temperature?: float
-    /**
-     * Controls which tool is called by the model.
-     */
-    tool_choice?: CompletionToolType
-    /**
-     * A list of tools that the model can call.
-     */
-    tools?: Array<CompletionTool>
-    /**
-     * Nucleus sampling, an alternative to sampling with temperature.
-     */
-    top_p?: float
-  }
 }
 
 /**

output/schema/validation-errors.json

@@ -17,42 +17,30 @@
  * under the License.
  */
 
-import type { Request as RequestChatCompletion } from '../chat_completion_unified/UnifiedRequest'
+import { RequestChatCompletionBase } from '@inference/_types/CommonTypes'
 import { Id } from '@_types/common'
 
-
-export type OmittedChatCompletion = Omit<RequestChatCompletion, 'urls' | 'path_parts'>;
-
 /**
  * Perform a chat completion task through the Elastic Inference Service (EIS).
  *
  * Perform a chat completion inference task with the `elastic` service.
- * @rest_spec_name inference.post.eis_chat_completion
+ * @rest_spec_name inference.post_eis_chat_completion
  * @availability stack since=9.0.0 stability=stable visibility=public
  * @availability serverless stability=stable visibility=public
  * @cluster_privileges manage_inference
  * @doc_id inference-api-post-eis-chat-completion
  */
-export interface Request extends OmittedChatCompletion {
+export interface Request extends RequestChatCompletionBase {
   urls: [
     {
-      path: '/_inference/{task_type}/{eis_inference_id}/_stream'
+      path: '/_inference/chat_completion/{eis_inference_id}/_stream'
       methods: ['POST']
     }
   ]
   path_parts: {
-    /**
-     * The type of the inference task that the model will perform.
-     */
-    task_type: EisTaskType
     /**
      * The unique identifier of the inference endpoint.
      */
     eis_inference_id: Id
   }
 }
-
-export enum EisTaskType {
-  chat_completion
-}
-