[8.0] Add more doc_ids for ML URLs (#1305) (#1307)

Author: lcawl

output/schema/schema.json

@@ -141,12 +141,12 @@ logstash-api-put-pipeline,/guide/en/elasticsearch/reference/current/logstash-api
 docs-multi-get,/guide/en/elasticsearch/reference/8.0/docs-multi-get.html
 migration-api-deprecation,/guide/en/elasticsearch/reference/current/migration-api-deprecation.html
 migration-api-feature-upgrade,/guide/en/elasticsearch/reference/current/migration-api-feature-upgrade.html
-ml-close-job,/guide/en/elasticsearch/reference/current/ml-close-job.html
-ml-delete-calendar,/guide/en/elasticsearch/reference/current/ml-delete-calendar.html
-ml-delete-calendar-event,/guide/en/elasticsearch/reference/current/ml-delete-calendar-event.html
-ml-delete-calendar-job,/guide/en/elasticsearch/reference/current/ml-delete-calendar-job.html
-delete-dfanalytics,/guide/en/elasticsearch/reference/current/delete-dfanalytics.html
-ml-delete-datafeed,/guide/en/elasticsearch/reference/current/ml-delete-datafeed.html
+ml-close-job,https://www.elastic.co/guide/en/elasticsearch/reference/8.0/ml-close-job.html
+ml-delete-calendar,https://www.elastic.co/guide/en/elasticsearch/reference/8.0/ml-delete-calendar.html
+ml-delete-calendar-event,https://www.elastic.co/guide/en/elasticsearch/reference/8.0/ml-delete-calendar-event.html
+ml-delete-calendar-job,https://www.elastic.co/guide/en/elasticsearch/reference/8.0/ml-delete-calendar-job.html
+ml-delete-dfanalytics,https://www.elastic.co/guide/en/elasticsearch/reference/8.0/delete-dfanalytics.html
+ml-delete-datafeed,https://www.elastic.co/guide/en/elasticsearch/reference/8.0/ml-delete-datafeed.html
 ml-delete-expired-data,/guide/en/elasticsearch/reference/current/ml-delete-expired-data.html
 ml-delete-filter,/guide/en/elasticsearch/reference/current/ml-delete-filter.html
 ml-delete-forecast,/guide/en/elasticsearch/reference/current/ml-delete-forecast.html
@@ -186,7 +186,7 @@ preview-dfanalytics,/guide/en/elasticsearch/reference/current/preview-dfanalytic
 ml-preview-datafeed,/guide/en/elasticsearch/reference/current/ml-preview-datafeed.html
 ml-put-calendar,/guide/en/elasticsearch/reference/current/ml-put-calendar.html
 ml-put-calendar-job,/guide/en/elasticsearch/reference/current/ml-put-calendar-job.html
-put-dfanalytics,/guide/en/elasticsearch/reference/current/put-dfanalytics.html
+put-dfanalytics,https://www.elastic.co/guide/en/elasticsearch/reference/8.0/put-dfanalytics.html
 ml-put-datafeed,/guide/en/elasticsearch/reference/current/ml-put-datafeed.html
 ml-put-filter,/guide/en/elasticsearch/reference/current/ml-put-filter.html
 ml-put-job,/guide/en/elasticsearch/reference/current/ml-put-job.html
@@ -336,7 +336,7 @@ search-rank-eval,/guide/en/elasticsearch/reference/current/search-rank-eval.html
 paginate-search-results,/guide/en/elasticsearch/reference/current/paginate-search-results.html
 sort-search-results,/guide/en/elasticsearch/reference/current/sort-search-results.html
 query-dsl-mlt-query,/guide/en/elasticsearch/reference/current/query-dsl-mlt-query.html
-query-dsl,/guide/en/elasticsearch/reference/current/query-dsl.html
+query-dsl,https://www.elastic.co/guide/en/elasticsearch/reference/8.0/query-dsl.html
 common-options,/guide/en/elasticsearch/reference/current/common-options.html
 indices-create-data-stream,/guide/en/elasticsearch/reference/current/indices-create-data-stream.html
 mapping-date-format,/guide/en/elasticsearch/reference/7.x/mapping-date-format.html
@@ -346,7 +346,8 @@ modules-node,/guide/en/elasticsearch/reference/current/modules-node.html
 search-aggregations-bucket-count-ks-test-aggregation,/guide/en/elasticsearch/reference/current/search-aggregations-bucket-count-ks-test-aggregation.html
 search-aggregations-bucket-correlation-aggregation,/guide/en/elasticsearch/reference/current/search-aggregations-bucket-correlation-aggregation.html
 search-aggregations-bucket-categorize-text-aggregation,/guide/en/elasticsearch/reference/current/search-aggregations-bucket-categorize-text-aggregation.html
-ml-feature-importance,/guide/en/machine-learning/7.12/ml-feature-importance.html
+search-aggregations-pipeline-bucket-path,https://www.elastic.co/guide/en/elasticsearch/reference/8.0/search-aggregations-pipeline.html#buckets-path-syntax
+ml-feature-importance,https://www.elastic.co/guide/en/machine-learning/8.0/ml-feature-importance.html
 analysis-normalizers,/guide/en/elasticsearch/reference/current/analysis-normalizers.html
 geo-shape,/guide/en/elasticsearch/reference/current/geo-shape.html
 shape,/guide/en/elasticsearch/reference/current/shape.html
@@ -364,13 +365,11 @@ cluster,/guide/en/elasticsearch/reference/current/cluster.html
 eql-syntax,/guide/en/elasticsearch/reference/current/eql-syntax.html
 eql,/guide/en/elasticsearch/reference/current/eql.html
 index-modules,/guide/en/elasticsearch/reference/7.8/index-modules.html
-ml-classification,/guide/en/machine-learning/current/dfa-classification.html
-ml-regression,/guide/en/machine-learning/current/dfa-regression.html
-ml-job-resource,/guide/en/elasticsearch/reference/current/ml-job-resource.html
-ml-settings,/guide/en/elasticsearch/reference/current/ml-settings.html
-cluster-nodes-stats,/guide/en/elasticsearch/reference/current/cluster-nodes-stats.html
-ml-settings,/guide/en/elasticsearch/reference/8.0/ml-settings.html
-ml-finding-anomalies,/guide/en/machine-learning/8.0/ml-ad-finding-anomalies.html
+ml-classification,https://www.elastic.co/guide/en/machine-learning/8.0/ml-dfa-classification.html
+ml-regression,https://www.elastic.co/guide/en/machine-learning/8.0/ml-dfa-regression.html
+ml-regression-loss,https://www.elastic.co/guide/en/machine-learning/8.0/dfa-regression-lossfunction.html
+ml-settings,https://www.elastic.co/guide/en/elasticsearch/reference/8.0/ml-settings.html
+ml-model-snapshots,https://www.elastic.co/guide/en/machine-learning/8.0/ml-ad-run-jobs.html#ml-ad-model-snapshots
 indexing-buffer,/guide/en/elasticsearch/reference/8.0/indexing-buffer.html
 field-and-document-access-control,/guide/en/elasticsearch/reference/current/field-and-document-access-control.html
 run-as-privilege,/guide/en/elasticsearch/reference/current/run-as-privilege.html

specification/_doc_ids/table.csv

@@ -26,7 +26,8 @@ import { Aggregation } from './Aggregation'
 
 export class BucketPathAggregation extends Aggregation {
   /**
-   * Path to the buckets that contain one set of values to correlate. For syntax, see [buckets_path Syntax](https://www.elastic.co/guide/en/elasticsearch/reference/current/search-aggregations-pipeline.html#buckets-path-syntax).
+   * Path to the buckets that contain one set of values to correlate.
+   * @doc_id search-aggregations-pipeline-bucket-path
    */
   buckets_path?: BucketsPath
 }
@@ -167,8 +168,9 @@ export class RegressionInferenceOptions {
   /** The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value. */
   results_field?: Field
   /**
-   * Specifies the maximum number of feature importance values per document. By default, it is zero and no feature importance calculation occurs.
-   * @doc_url https://www.elastic.co/guide/en/machine-learning/7.12/ml-feature-importance.html
+   * Specifies the maximum number of feature importance values per document.
+   * @doc_id ml-feature-importance
+   * @server_default 0
    */
   num_top_feature_importance_values?: integer
 }
@@ -177,8 +179,9 @@ export class ClassificationInferenceOptions {
   /** Specifies the number of top class predictions to return. Defaults to 0. */
   num_top_classes?: integer
   /**
-   * Specifies the maximum number of feature importance values per document. By default, it is zero and no feature importance calculation occurs.
-   * @doc_url https://www.elastic.co/guide/en/machine-learning/7.12/ml-feature-importance.html
+   * Specifies the maximum number of feature importance values per document.
+   * @server_default 0
+   * @doc_id ml-feature-importance
    */
   num_top_feature_importance_values?: integer
   /** Specifies the type of the predicted field to write. Acceptable values are: string, number, boolean. When boolean is provided 1.0 is transformed to true and 0.0 to false. */

specification/_types/aggregations/pipeline.ts

@@ -40,7 +40,7 @@ export class DataframeAnalyticsSource {
   index: Indices
   /**
    * The Elasticsearch query domain-specific language (DSL). This value corresponds to the query object in an Elasticsearch search POST body. All the options that are supported by Elasticsearch can be used, as this object is passed verbatim to Elasticsearch. By default, this property has the following value: {"match_all": {}}.
-   * @doc_url https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl.html
+   * @doc_id query-dsl
    */
   query?: QueryContainer
   /**
@@ -84,17 +84,17 @@ export class DataframeAnalyticsDestination {
 export class DataframeAnalysisContainer {
   /**
    * The configuration information necessary to perform classification.
-   * @doc_url https://www.elastic.co/guide/en/machine-learning/current/dfa-classification.html
+   * @doc_id ml-classification
    */
   classification?: DataframeAnalysisClassification
   /**
    * The configuration information necessary to perform outlier detection. NOTE: Advanced parameters are for fine-tuning classification analysis. They are set automatically by hyperparameter optimization to give the minimum validation error. It is highly recommended to use the default values unless you fully understand the function of these parameters.
-   * @doc_url https://www.elastic.co/guide/en/machine-learning/current/dfa-classification.html
+   * @doc_id ml-classification
    */
   outlier_detection?: DataframeAnalysisOutlierDetection
   /**
    * The configuration information necessary to perform regression. NOTE: Advanced parameters are for fine-tuning regression analysis. They are set automatically by hyperparameter optimization to give the minimum validation error. It is highly recommended to use the default values unless you fully understand the function of these parameters.
-   * @doc_url https://www.elastic.co/guide/en/machine-learning/current/dfa-regression.html
+   * @doc_id ml-regression
    */
   regression?: DataframeAnalysisRegression
 }

specification/ml/_types/DataframeAnalytics.ts

@@ -20,9 +20,6 @@
 import { OverloadOf } from '@spec_utils/behaviors'
 import { Field } from '@_types/common'
 
-/**
- * @doc_url https://www.elastic.co/guide/en/elasticsearch/reference/current/ml-job-resource.html#ml-apimodelplotconfig
- */
 export class ModelPlotConfig {
   /**
    * If true, enables calculation and storage of the model change annotations for each entity that is being analyzed.

specification/ml/_types/ModelPlot.ts

@@ -41,7 +41,7 @@ export class TrainedModelStats {
   inference_stats?: TrainedModelInferenceStats
   /**
    * A collection of ingest stats for the model across all nodes. The values are summations of the individual node statistics. The format matches the ingest section in Nodes stats.
-   * @doc_url https://www.elastic.co/guide/en/elasticsearch/reference/current/cluster-nodes-stats.html
+   * @doc_id cluster-nodes-stats
    */
   ingest?: Dictionary<string, UserDefinedValue> // TODO -- this is not complete
 }
@@ -53,7 +53,7 @@ export class TrainedModelInferenceStats {
   inference_count: long
   /**
    * The number of times the model was loaded for inference and was not retrieved from the cache. If this number is close to the inference_count, then the cache is not being appropriately used. This can be solved by increasing the cache size or its time-to-live (TTL). See General machine learning settings for the appropriate settings.
-   * @doc_url https://www.elastic.co/guide/en/elasticsearch/reference/current/ml-settings.html#general-ml-settings
+   * @doc_id ml-settings
    */
   cache_miss_count: long
   /** The number of inference calls where all the training features for the model were missing. */
@@ -114,7 +114,7 @@ export class TrainedModelConfigMetadata {
 export class Hyperparameter {
   /**
    * A positive number showing how much the parameter influences the variation of the loss function. For hyperparameters with values that are not specified by the user but tuned during hyperparameter optimization.
-   * @doc_url https://www.elastic.co/guide/en/machine-learning/7.12/dfa-regression.html#dfa-regression-lossfunction
+   * @doc_id ml-regression-loss
    */
   absolute_importance?: double
   /** Name of the hyperparameter. */

specification/ml/_types/TrainedModel.ts

@@ -31,6 +31,7 @@ import { Time } from '@_types/Time'
  * @since 5.4.0
  * @stability stable
  * @cluster_privileges manage_ml
+ * @doc_id ml-close-job
  */
 export interface Request extends RequestBase {
   path_parts: {

specification/ml/close_job/MlCloseJobRequest.ts

@@ -26,6 +26,7 @@ import { Id } from '@_types/common'
  * @since 6.2.0
  * @stability stable
  * @cluster_privileges manage_ml
+ * @doc_id ml-delete-calendar
  */
 export interface Request extends RequestBase {
   path_parts: {

specification/ml/delete_calendar/MlDeleteCalendarRequest.ts

@@ -25,6 +25,7 @@ import { Id } from '@_types/common'
  * @rest_spec_name ml.delete_calendar_event
  * @since 6.2.0
  * @stability stable
+ * @doc_id ml-delete-calendar-event
  */
 export interface Request extends RequestBase {
   path_parts: {

specification/ml/delete_calendar_event/MlDeleteCalendarEventRequest.ts

@@ -26,6 +26,7 @@ import { Id } from '@_types/common'
  * @since 6.2.0
  * @stability stable
  * @cluster_privileges manage_ml
+ * @doc_id ml-delete-calendar-job
  */
 export interface Request extends RequestBase {
   path_parts: {

specification/ml/delete_calendar_job/MlDeleteCalendarJobRequest.ts

@@ -27,6 +27,7 @@ import { Time } from '@_types/Time'
  * @since 7.3.0
  * @stability stable
  * @cluster_privileges manage_ml
+ * @doc_id ml-delete-dfanalytics
  */
 export interface Request extends RequestBase {
   path_parts: {

specification/ml/delete_data_frame_analytics/MlDeleteDataFrameAnalyticsRequest.ts

@@ -26,6 +26,7 @@ import { Id } from '@_types/common'
  * @since 5.4.0
  * @stability stable
  * @cluster_privileges manage_ml
+ * @doc_id ml-delete-datafeed
  */
 export interface Request extends RequestBase {
   path_parts: {

specification/ml/delete_datafeed/MlDeleteDatafeedRequest.ts

@@ -44,7 +44,8 @@ export interface Request extends RequestBase {
      */
     index: IndexName
     /**
-     * A query clause that retrieves a subset of data from the source index. See [QueryDSL](https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl.html).
+     * A query clause that retrieves a subset of data from the source index.
+     * @doc_id query-dsl
      */
     query?: QueryContainer
   }

specification/ml/evaluate_data_frame/MlEvaluateDataFrameRequest.ts

@@ -72,20 +72,20 @@ export interface Request extends RequestBase {
     description?: string
     /**
      * The approximate maximum amount of memory resources that are permitted for
-     * analytical processing. The default value for data frame analytics jobs is
-     * 1gb. If your elasticsearch.yml file contains an
-     * xpack.ml.max_model_memory_limit setting, an error occurs when you try to
-     * create data frame analytics jobs that have model_memory_limit values
+     * analytical processing. If your `elasticsearch.yml` file contains an
+     * `xpack.ml.max_model_memory_limit` setting, an error occurs when you try to
+     * create data frame analytics jobs that have `model_memory_limit` values
      * greater than that setting.
-     * @doc_url https://www.elastic.co/guide/en/elasticsearch/reference/current/ml-settings.html
+     * @server_default 1gb
+     * @doc_id ml-settings
      */
     model_memory_limit?: string
     /**
-     * The maximum number of threads to be used by the analysis. The default
-     * value is 1. Using more threads may decrease the time necessary to
-     * complete the analysis at the cost of using more CPU. Note that the
-     * process may use additional threads for operational functionality other
-     * than the analysis itself.
+     * The maximum number of threads to be used by the analysis. Using more
+     * threads may decrease the time necessary to complete the analysis at the
+     * cost of using more CPU. Note that the process may use additional threads
+     * for operational functionality other than the analysis itself.
+     * @server_default 1
      */
     max_num_threads?: integer
     /**
@@ -100,7 +100,7 @@ export interface Request extends RequestBase {
      * Specifies whether this job can start when there is insufficient machine
      * learning node capacity for it to be immediately assigned to a node.
      * @server_default false
-     * @doc_url https://www.elastic.co/guide/en/elasticsearch/reference/current/ml-settings.html#advanced-ml-settings
+     * @doc_id ml-settings
      */
     allow_lazy_start?: boolean
   }

specification/ml/explain_data_frame_analytics/MlExplainDataFrameAnalyticsRequest.ts

@@ -24,7 +24,6 @@ import { integer } from '@_types/Numeric'
  * Response codes
  * 400 - If include_model_definition is true, this code indicates that more than one models match the ID pattern.
  * 404 (Missing resources) - If allow_no_match is false, this code indicates that there are no resources that match the request or only partial matches for the request.
- * @doc_url https://www.elastic.co/guide/en/elasticsearch/reference/current/get-trained-models.html#ml-get-trained-models-results
  */
 export class Response {
   body: {

specification/ml/get_trained_models/MlGetTrainedModelResponse.ts

@@ -37,10 +37,10 @@ export interface Request extends RequestBase {
   }
   body: {
     /**
-     * A data frame analytics config as described in Create data frame analytics
-     * jobs. Note that id and dest don’t need to be provided in the context of
+     * A data frame analytics config as described in create data frame analytics
+     * jobs. Note that `id` and `dest` don’t need to be provided in the context of
      * this API.
-     * @doc_url https://www.elastic.co/guide/en/elasticsearch/reference/current/put-dfanalytics.html
+     * @doc_id put-dfanalytics
      */
     config?: DataframePreviewConfig
   }

specification/ml/preview_data_frame_analytics/MlPreviewDataFrameAnalyticsRequest.ts

@@ -36,6 +36,7 @@ import { integer } from '@_types/Numeric'
  * @stability stable
  * @cluster_privileges manage_ml
  * @index_privileges create_index, index, manage, read, view_index_metadata
+ * @doc_id put-dfanalytics
  */
 export interface Request extends RequestBase {
   path_parts: {
@@ -50,14 +51,14 @@ export interface Request extends RequestBase {
     /**
      * Specifies whether this job can start when there is insufficient machine
      * learning node capacity for it to be immediately assigned to a node. If
-     * set to false and a machine learning node with capacity to run the job
-     * cannot be immediately found, the API returns an error. If set to true,
+     * set to `false` and a machine learning node with capacity to run the job
+     * cannot be immediately found, the API returns an error. If set to `true`,
      * the API does not return an error; the job waits in the `starting` state
      * until sufficient machine learning node capacity is available. This
      * behavior is also affected by the cluster-wide
      * `xpack.ml.max_lazy_ml_nodes` setting.
      * @server_default false
-     * @doc_url https://www.elastic.co/guide/en/elasticsearch/reference/current/ml-settings.html#advanced-ml-settings
+     * @doc_id ml-settings
      */
     allow_lazy_start?: boolean
     /**

specification/ml/put_data_frame_analytics/MlPutDataFrameAnalyticsRequest.ts

@@ -45,12 +45,12 @@ export interface Request extends RequestBase {
     description?: string
     /**
      * The approximate maximum amount of memory resources that are permitted for
-     * analytical processing. The default value for data frame analytics jobs is
-     * 1gb. If your elasticsearch.yml file contains an
+     * analytical processing. If your `elasticsearch.yml` file contains an
      * `xpack.ml.max_model_memory_limit` setting, an error occurs when you try
-     * to create data frame analytics jobs that have model_memory_limit values
+     * to create data frame analytics jobs that have `model_memory_limit` values
      * greater than that setting.
-     * @doc_url https://www.elastic.co/guide/en/elasticsearch/reference/current/ml-settings.html
+     * @server_default 1gb
+     * @doc_id ml-settings
      */
     model_memory_limit?: string
     /**
@@ -65,7 +65,7 @@ export interface Request extends RequestBase {
      * Specifies whether this job can start when there is insufficient machine
      * learning node capacity for it to be immediately assigned to a node.
      * @server_default false
-     * @doc_url https://www.elastic.co/guide/en/elasticsearch/reference/current/ml-settings.html#advanced-ml-settings
+     * @doc_id ml-settings
      */
     allow_lazy_start?: boolean
   }