Add and correct response definitions for liveness and readiness

specification/protocol/inference_rest.md

@@ -55,7 +55,6 @@ The model ready endpoint returns the readiness probe response for the server alo
 
     $ready_model_response =
     {
-      "name" : $string,
       "ready": $bool
     }
 
@@ -68,7 +67,7 @@ The server ready endpoint returns the readiness probe response for the server.
 
     $ready_server_response =
     {
-      "live" : $bool,
+      "ready" : $bool
     }
 
 ---
@@ -81,7 +80,7 @@ The server live endpoint returns the liveness probe response for the server.
 
     $live_server_response =
     {
-      "live" : $bool,
+      "live" : $bool
     }
 
 ---

specification/protocol/open_inference_rest.yaml

@@ -28,6 +28,10 @@ paths:
       responses:
         '200':
           description: OK
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/live_server_response'
       operationId: get-v2-health-live
       description: The “server live” API indicates if the inference server is able to receive and respond to metadata and inference requests. The “server live” API can be used directly to implement the Kubernetes livenessProbe.
   /v2/health/ready:
@@ -37,6 +41,10 @@ paths:
       responses:
         '200':
           description: OK
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ready_server_response'
       operationId: get-v2-health-ready
       description: The “server ready” health API indicates if all the models are ready for inferencing. The “server ready” health API can be used directly to implement the Kubernetes readinessProbe.
   '/v2/models/${MODEL_NAME}/versions/${MODEL_VERSION}/ready':
@@ -57,6 +65,10 @@ paths:
       responses:
         '200':
           description: OK
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ready_model_response'
       operationId: get-v2-models-$-modelName-versions-$-modelVersion-ready
       description: The “model ready” health API indicates if a specific model is ready for inferencing. The model name and (optionally) version must be available in the URL. If a version is not provided the server may choose a version based on its own policies.
   /v2/:
@@ -100,6 +112,12 @@ paths:
             application/json:
               schema:
                 $ref: '#/components/schemas/metadata_model_response'
+        '400':
+          description: Bad Request
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/metadata_model_error_response'
       operationId: get-v2-models-$-modelName-versions-$-modelVersion
       description: 'The per-model metadata endpoint provides information about a model. A model metadata request is made with an HTTP GET to a model metadata endpoint. In the corresponding response the HTTP body contains the [Model Metadata Response JSON Object](#model-metadata-response-json-object) or the [Model Metadata Response JSON Error Object](#model-metadata-response-json-error-object). The model name and (optionally) version must be available in the URL. If a version is not provided the server may choose a version based on its own policies or return an error.'
   '/v2/models/${MODEL_NAME}/versions/${MODEL_VERSION}/infer':
@@ -138,6 +156,33 @@ paths:
       description: 'An inference request is made with an HTTP POST to an inference endpoint. In the request the HTTP body contains the [Inference Request JSON Object](#inference-request-json-object). In the corresponding response the HTTP body contains the [Inference Response JSON Object](#inference-response-json-object) or [Inference Response JSON Error Object](#inference-response-json-error-object). See [Inference Request Examples](#inference-request-examples) for some example HTTP/REST requests and responses.'
 components:
   schemas:
+    live_server_response:
+      title: live_server_response
+      type: object
+      description: ''
+      properties:
+        live:
+          type: boolean
+      required:
+        - live
+    ready_server_response:
+      title: ready_server_response
+      type: object
+      description: ''
+      properties:
+        ready:
+          type: boolean
+      required:
+        - ready
+    ready_model_response:
+      title: ready_model_response
+      type: object
+      description: ''
+      properties:
+        ready:
+          type: boolean
+      required:
+        - ready
     metadata_server_response:
       title: metadata_server_response
       type: object