Inference task type endpoints (#3545)

* Refactoring inference endpoints

* Fixing stream completion url and removing the old url and class

* generating spec

* Adding doc id

* Renaming to match filename

* Switching to stream and regenerating files

* Using variant and adding _stream

* Removing variant

* Adding chat_completion and fixing update api

* Resolving conflicts

Author: jonathan-buttner

output/schema/schema.json

@@ -156,13 +156,6 @@
       ],
       "response": []
     },
-    "inference.update": {
-      "request": [
-        "/_inference/{inference_id}/_update: different http methods in the json spec",
-        "/_inference/{task_type}/{inference_id}/_update: different http methods in the json spec"
-      ],
-      "response": []
-    },
     "ingest.get_ip_location_database": {
       "request": [
         "Request: query parameter 'master_timeout' does not exist in the json spec"

output/schema/validation-errors.json

@@ -319,6 +319,7 @@ inference-api-post,https://www.elastic.co/docs/api/doc/elasticsearch/operation/o
 inference-api-put,https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put
 inference-api-put-watsonx,https://www.elastic.co/guide/en/elasticsearch/reference/current/infer-service-watsonx-ai.html
 inference-api-stream,https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-stream-inference
+inference-api-chat-completion,https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-unified-inference
 inference-api-update,https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-update
 inference-processor,https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-processor.html
 info-api,https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-info

output/typescript/types.ts

@@ -0,0 +1,31 @@
+{
+  "inference.chat_completion_unified": {
+    "documentation": {
+      "url": "https://www.elastic.co/guide/en/elasticsearch/reference/master/chat-completion-inference.html",
+      "description": "Perform chat completion inference"
+    },
+    "stability": "stable",
+    "visibility": "public",
+    "headers": {
+      "accept": ["text/event-stream"],
+      "content_type": ["application/json"]
+    },
+    "url": {
+      "paths": [
+        {
+          "path": "/_inference/chat_completion/{inference_id}/_stream",
+          "methods": ["POST"],
+          "parts": {
+            "inference_id": {
+              "type": "string",
+              "description": "The inference Id"
+            }
+          }
+        }
+      ]
+    },
+    "body": {
+      "description": "The inference payload"
+    }
+  }
+}

specification/_doc_ids/table.csv

@@ -1,8 +1,8 @@
 {
-  "inference.inference": {
+  "inference.completion": {
     "documentation": {
       "url": "https://www.elastic.co/guide/en/elasticsearch/reference/master/post-inference-api.html",
-      "description": "Perform inference"
+      "description": "Perform completion inference"
     },
     "stability": "stable",
     "visibility": "public",
@@ -13,28 +13,14 @@
     "url": {
       "paths": [
         {
-          "path": "/_inference/{inference_id}",
+          "path": "/_inference/completion/{inference_id}",
           "methods": ["POST"],
           "parts": {
             "inference_id": {
               "type": "string",
               "description": "The inference Id"
             }
           }
-        },
-        {
-          "path": "/_inference/{task_type}/{inference_id}",
-          "methods": ["POST"],
-          "parts": {
-            "task_type": {
-              "type": "string",
-              "description": "The task type"
-            },
-            "inference_id": {
-              "type": "string",
-              "description": "The inference Id"
-            }
-          }
         }
       ]
     },

specification/_json_spec/inference.chat_completion_unified.json

@@ -0,0 +1,31 @@
+{
+  "inference.rerank": {
+    "documentation": {
+      "url": "https://www.elastic.co/guide/en/elasticsearch/reference/master/post-inference-api.html",
+      "description": "Perform reranking inference"
+    },
+    "stability": "stable",
+    "visibility": "public",
+    "headers": {
+      "accept": ["application/json"],
+      "content_type": ["application/json"]
+    },
+    "url": {
+      "paths": [
+        {
+          "path": "/_inference/rerank/{inference_id}",
+          "methods": ["POST"],
+          "parts": {
+            "inference_id": {
+              "type": "string",
+              "description": "The inference Id"
+            }
+          }
+        }
+      ]
+    },
+    "body": {
+      "description": "The inference payload"
+    }
+  }
+}