Fix ingest schemas

CHANGELOG.md

@@ -88,6 +88,7 @@ Inspired from [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 - Fixed cluster API schemas ([#754](https://github.com/opensearch-project/opensearch-api-specification/pull/754))
 - Fixed schema validation for invalid properties in `retry` configuration ([#758](https://github.com/opensearch-project/opensearch-api-specification/pull/758))
 - Fixed nodes API schemas ([#761](https://github.com/opensearch-project/opensearch-api-specification/pull/761))
+- Fixed ingest API schemas ([#766](https://github.com/opensearch-project/opensearch-api-specification/pull/766))
 
 ### Changed
 - Changed `tasks._common:TaskInfo` and `tasks._common:TaskGroup` to be composed of a `tasks._common:TaskInfoBase` ([#683](https://github.com/opensearch-project/opensearch-api-specification/pull/683))

spec/schemas/ingest._common.yaml

@@ -45,8 +45,6 @@ components:
           $ref: '#/components/schemas/DateIndexNameProcessor'
         dot_expander:
           $ref: '#/components/schemas/DotExpanderProcessor'
-        enrich:
-          $ref: '#/components/schemas/EnrichProcessor'
         fail:
           $ref: '#/components/schemas/FailProcessor'
         foreach:
@@ -97,8 +95,6 @@ components:
           $ref: '#/components/schemas/DropProcessor'
         circle:
           $ref: '#/components/schemas/CircleProcessor'
-        inference:
-          $ref: '#/components/schemas/InferenceProcessor'
         text_embedding:
           $ref: '#/components/schemas/TextEmbeddingProcessor'
       minProperties: 1
@@ -117,7 +113,8 @@ components:
               description: |-
                 The number of chars being used for extraction to prevent huge fields.
                 Use `-1` for no limit.
-              type: number
+              type: integer
+              format: int64
             indexed_chars_field:
               $ref: '_common.yaml#/components/schemas/Field'
             properties:
@@ -170,8 +167,7 @@ components:
             value:
               description: The value to be appended. Supports template snippets.
               type: array
-              items:
-                type: object
+              items: {}
             allow_duplicates:
               description: If `false`, the processor does not append values already present in the field.
               type: boolean
@@ -188,7 +184,6 @@ components:
                 Value used to fill empty fields.
                 Empty fields are skipped if this is not provided.
                 An empty field is one with no value (2 consecutive separators) or empty quotes (`""`).
-              type: object
             field:
               $ref: '_common.yaml#/components/schemas/Field'
             ignore_missing:
@@ -319,38 +314,6 @@ components:
               type: string
           required:
             - field
-    EnrichProcessor:
-      allOf:
-        - $ref: '#/components/schemas/ProcessorBase'
-        - type: object
-          properties:
-            field:
-              $ref: '_common.yaml#/components/schemas/Field'
-            ignore_missing:
-              description: If `true` and `field` does not exist, the processor quietly exits without modifying the document.
-              type: boolean
-            max_matches:
-              description: |-
-                The maximum number of matched documents to include under the configured target field.
-                The `target_field` will be turned into a JSON array if `max_matches` is higher than 1, otherwise `target_field` will become a JSON object.
-                In order to avoid documents getting too large, the maximum allowed value is 128.
-              type: number
-            override:
-              description: |-
-                If processor will update fields with pre-existing non-null-valued field.
-                When set to `false`, such fields will not be touched.
-              type: boolean
-            policy_name:
-              description: The name of the enrich policy to use.
-              type: string
-            shape_relation:
-              $ref: '_common.yaml#/components/schemas/GeoShapeRelation'
-            target_field:
-              $ref: '_common.yaml#/components/schemas/Field'
-          required:
-            - field
-            - policy_name
-            - target_field
     FailProcessor:
       allOf:
         - $ref: '#/components/schemas/ProcessorBase'
@@ -647,7 +610,6 @@ components:
                 The value to be set for the field.
                 Supports template snippets.
                 May specify only one of `value` or `copy_from`.
-              type: object
           required:
             - field
     SortProcessor:
@@ -797,6 +759,7 @@ components:
             error_distance:
               description: The difference between the resulting inscribed distance from center to side and the circle's radius (measured in meters for `geo_shape`, unit-less for `shape`).
               type: number
+              format: double
             field:
               $ref: '_common.yaml#/components/schemas/Field'
             ignore_missing:
@@ -814,62 +777,7 @@ components:
       type: string
       enum:
         - geo_shape
-        - shape
-    InferenceProcessor:
-      allOf:
-        - $ref: '#/components/schemas/ProcessorBase'
-        - type: object
-          properties:
-            model_id:
-              $ref: '_common.yaml#/components/schemas/Id'
-            target_field:
-              $ref: '_common.yaml#/components/schemas/Field'
-            field_map:
-              description: |-
-                Maps the document field names to the known field names of the model.
-                This mapping takes precedence over any default mappings provided in the model configuration.
-              type: object
-              additionalProperties:
-                type: object
-            inference_config:
-              $ref: '#/components/schemas/InferenceConfig'
-          required:
-            - model_id
-    InferenceConfig:
-      type: object
-      properties:
-        regression:
-          $ref: '#/components/schemas/InferenceConfigRegression'
-        classification:
-          $ref: '#/components/schemas/InferenceConfigClassification'
-      minProperties: 1
-      maxProperties: 1
-    InferenceConfigRegression:
-      type: object
-      properties:
-        results_field:
-          $ref: '_common.yaml#/components/schemas/Field'
-        num_top_feature_importance_values:
-          description: Specifies the maximum number of feature importance values per document.
-          type: number
-    InferenceConfigClassification:
-      type: object
-      properties:
-        num_top_classes:
-          description: Specifies the number of top class predictions to return.
-          type: number
-        num_top_feature_importance_values:
-          description: Specifies the maximum number of feature importance values per document.
-          type: number
-        results_field:
-          $ref: '_common.yaml#/components/schemas/Field'
-        top_classes_results_field:
-          $ref: '_common.yaml#/components/schemas/Field'
-        prediction_field_type:
-          description: |-
-            Specifies the type of the predicted field to write.
-            Valid values are: `string`, `number`, `boolean`.
-          type: string
+        - xy_shape
     TextEmbeddingProcessor:
       allOf:
         - $ref: '#/components/schemas/ProcessorBase'
@@ -883,9 +791,9 @@ components:
               type: object
               additionalProperties:
                 type: string
-            description:
-              type: string
-              description: A brief description of the processor.
+            batch_size:
+              type: integer
+              format: int32
           required:
             - field_map
             - model_id

spec/schemas/ingest.simulate.yaml

@@ -15,7 +15,6 @@ components:
           $ref: '_common.yaml#/components/schemas/IndexName'
         _source:
           description: JSON body for the document.
-          type: object
       required:
         - _source
     PipelineSimulation:

spec/schemas/nodes.info.yaml

@@ -384,7 +384,6 @@ components:
         max_local_storage_nodes:
           type: string
       required:
-        - attr
         - name
     NodeInfoPath:
       type: object
@@ -443,7 +442,7 @@ components:
       type: object
       properties:
         type:
-          type: string
+          $ref: '#/components/schemas/NodeInfoSettingsHttpType'
         type.default:
           type: string
         compression:
@@ -452,6 +451,17 @@ components:
           $ref: '_common.yaml#/components/schemas/StringifiedInteger'
       required:
         - type
+    NodeInfoSettingsHttpType:
+      oneOf:
+        - title: type
+          type: string
+        - title: config
+          $ref: '#/components/schemas/NodeInfoSettingsHttpTypeConfig'
+    NodeInfoSettingsHttpTypeConfig:
+      type: object
+      properties:
+        default:
+          type: string
     NodeInfoBootstrap:
       type: object
       properties:
@@ -463,11 +473,22 @@ components:
       type: object
       properties:
         type:
-          type: string
+          $ref: '#/components/schemas/NodeInfoSettingsTransportType'
         type.default:
           type: string
       required:
         - type
+    NodeInfoSettingsTransportType:
+      oneOf:
+        - title: type
+          type: string
+        - title: config
+          $ref: '#/components/schemas/NodeInfoSettingsTransportTypeConfig'
+    NodeInfoSettingsTransportTypeConfig:
+      type: object
+      properties:
+        default:
+          type: string
     NodeInfoSettingsNetwork:
       type: object
       properties:
@@ -684,6 +705,3 @@ components:
           type: array
           items:
             $ref: '#/components/schemas/NodeInfoIngestProcessor'
-      required:
-        - request_processors
-        - response_processors