Amazon Personalize Update: This release adds support for includedDatasetColumns and performIncrementalUpdate in solution APIs, and rankingInfluence in campaign and batch inference APIs.

Author: AWS

.changes/next-release/feature-AmazonPersonalize-6c3922d.json

@@ -0,0 +1,6 @@
+{
+    "type": "feature",
+    "category": "Amazon Personalize",
+    "contributor": "",
+    "description": "This release adds support for includedDatasetColumns and performIncrementalUpdate in solution APIs, and rankingInfluence in campaign and batch inference APIs."
+}

services/personalize/src/main/resources/codegen-resources/service-2.json

@@ -1319,6 +1319,10 @@
         "itemExplorationConfig":{
           "shape":"HyperParameters",
           "documentation":"<p>A string to string map specifying the exploration configuration hyperparameters, including <code>explorationWeight</code> and <code>explorationItemAgeCutOff</code>, you want to use to configure the amount of item exploration Amazon Personalize uses when recommending items. See <a href=\"https://docs.aws.amazon.com/personalize/latest/dg/native-recipe-new-item-USER_PERSONALIZATION.html\">User-Personalization</a>.</p>"
+        },
+        "rankingInfluence":{
+          "shape":"RankingInfluence",
+          "documentation":"<p>A map of ranking influence values for POPULARITY and FRESHNESS. For each key, specify a numerical value between 0.0 and 1.0 that determines how much influence that ranking factor has on the final recommendations. A value closer to 1.0 gives more weight to the factor, while a value closer to 0.0 reduces its influence.</p>"
         }
       },
       "documentation":"<p>The configuration details of a batch inference job.</p>"
@@ -1544,7 +1548,10 @@
           "shape":"Date",
           "documentation":"<p>The date and time (in Unix format) that the campaign was last updated.</p>"
         },
-        "latestCampaignUpdate":{"shape":"CampaignUpdateSummary"}
+        "latestCampaignUpdate":{
+          "shape":"CampaignUpdateSummary",
+          "documentation":"<p>Provides a summary of the properties of a campaign update. For a complete listing, call the <a href=\"https://docs.aws.amazon.com/personalize/latest/dg/API_DescribeCampaign.html\">DescribeCampaign</a> API.</p> <note> <p>The <code>latestCampaignUpdate</code> field is only returned when the campaign has had at least one <code>UpdateCampaign</code> call. </p> </note>"
+        }
       },
       "documentation":"<p>An object that describes the deployment of a solution version. For more information on campaigns, see <a href=\"https://docs.aws.amazon.com/personalize/latest/dg/API_CreateCampaign.html\">CreateCampaign</a>.</p>"
     },
@@ -1562,6 +1569,10 @@
         "syncWithLatestSolutionVersion":{
           "shape":"Boolean",
           "documentation":"<p>Whether the campaign automatically updates to use the latest solution version (trained model) of a solution. If you specify <code>True</code>, you must specify the ARN of your <i>solution</i> for the <code>SolutionVersionArn</code> parameter. It must be in <code>SolutionArn/$LATEST</code> format. The default is <code>False</code> and you must manually update the campaign to deploy the latest solution version. </p> <p> For more information about automatic campaign updates, see <a href=\"https://docs.aws.amazon.com/personalize/latest/dg/campaigns.html#create-campaign-automatic-latest-sv-update\">Enabling automatic campaign updates</a>. </p>"
+        },
+        "rankingInfluence":{
+          "shape":"RankingInfluence",
+          "documentation":"<p>A map of ranking influence values for POPULARITY and FRESHNESS. For each key, specify a numerical value between 0.0 and 1.0 that determines how much influence that ranking factor has on the final recommendations. A value closer to 1.0 gives more weight to the factor, while a value closer to 0.0 reduces its influence. </p>"
         }
       },
       "documentation":"<p>The configuration details of a campaign.</p>"
@@ -1985,8 +1996,7 @@
       "required":[
         "jobName",
         "datasetArn",
-        "dataSource",
-        "roleArn"
+        "dataSource"
       ],
       "members":{
         "jobName":{
@@ -2265,6 +2275,10 @@
           "shape":"PerformAutoTraining",
           "documentation":"<p>Whether the solution uses automatic training to create new solution versions (trained models). The default is <code>True</code> and the solution automatically creates new solution versions every 7 days. You can change the training frequency by specifying a <code>schedulingExpression</code> in the <code>AutoTrainingConfig</code> as part of solution configuration. For more information about automatic training, see <a href=\"https://docs.aws.amazon.com/personalize/latest/dg/solution-config-auto-training.html\">Configuring automatic training</a>.</p> <p> Automatic solution version creation starts within one hour after the solution is ACTIVE. If you manually create a solution version within the hour, the solution skips the first automatic training. </p> <p> After training starts, you can get the solution version's Amazon Resource Name (ARN) with the <a href=\"https://docs.aws.amazon.com/personalize/latest/dg/API_ListSolutionVersions.html\">ListSolutionVersions</a> API operation. To get its status, use the <a href=\"https://docs.aws.amazon.com/personalize/latest/dg/API_DescribeSolutionVersion.html\">DescribeSolutionVersion</a>. </p>"
         },
+        "performIncrementalUpdate":{
+          "shape":"PerformIncrementalUpdate",
+          "documentation":"<p>Whether to perform incremental training updates on your model. When enabled, this allows the model to learn from new data more frequently without requiring full retraining, which enables near real-time personalization. This parameter is supported only for solutions that use the semantic-similarity recipe.</p>"
+        },
         "recipeArn":{
           "shape":"Arn",
           "documentation":"<p>The Amazon Resource Name (ARN) of the recipe to use for model training. This is required when <code>performAutoML</code> is false. For information about different Amazon Personalize recipes and their ARNs, see <a href=\"https://docs.aws.amazon.com/personalize/latest/dg/working-with-predefined-recipes.html\">Choosing a recipe</a>. </p>"
@@ -2812,7 +2826,8 @@
     },
     "DatasetType":{
       "type":"string",
-      "max":256
+      "max":256,
+      "pattern":"^[A-Za-z_]+$"
     },
     "DatasetUpdateSummary":{
       "type":"structure",
@@ -3103,7 +3118,7 @@
       "members":{
         "campaign":{
           "shape":"Campaign",
-          "documentation":"<p>The properties of the campaign.</p>"
+          "documentation":"<note> <p>The <code>latestCampaignUpdate</code> field is only returned when the campaign has had at least one <code>UpdateCampaign</code> call. </p> </note> <p>The properties of the campaign.</p> <note> <p>The <code>latestCampaignUpdate</code> field is only returned when the campaign has had at least one <code>UpdateCampaign</code> call.</p> </note>"
         }
       }
     },
@@ -3757,6 +3772,12 @@
         "INCREMENTAL"
       ]
     },
+    "IncludedDatasetColumns":{
+      "type":"map",
+      "key":{"shape":"DatasetType"},
+      "value":{"shape":"ColumnNamesList"},
+      "max":3
+    },
     "IngestionMode":{
       "type":"string",
       "enum":[
@@ -4547,6 +4568,27 @@
       "box":true
     },
     "PerformHPO":{"type":"boolean"},
+    "PerformIncrementalUpdate":{
+      "type":"boolean",
+      "box":true
+    },
+    "RankingInfluence":{
+      "type":"map",
+      "key":{"shape":"RankingInfluenceType"},
+      "value":{"shape":"RankingInfluenceWeight"}
+    },
+    "RankingInfluenceType":{
+      "type":"string",
+      "enum":[
+        "POPULARITY",
+        "FRESHNESS"
+      ]
+    },
+    "RankingInfluenceWeight":{
+      "type":"double",
+      "max":1,
+      "min":0
+    },
     "Recipe":{
       "type":"structure",
       "members":{
@@ -4862,6 +4904,10 @@
           "shape":"PerformAutoTraining",
           "documentation":"<p>Specifies whether the solution automatically creates solution versions. The default is <code>True</code> and the solution automatically creates new solution versions every 7 days.</p> <p>For more information about auto training, see <a href=\"https://docs.aws.amazon.com/personalize/latest/dg/customizing-solution-config.html\">Creating and configuring a solution</a>.</p>"
         },
+        "performIncrementalUpdate":{
+          "shape":"PerformIncrementalUpdate",
+          "documentation":"<p>A Boolean value that indicates whether incremental training updates are performed on the model. When enabled, this allows the model to learn from new data more frequently without requiring full retraining, which enables near real-time personalization. This parameter is supported only for solutions that use the semantic-similarity recipe</p>"
+        },
         "recipeArn":{
           "shape":"Arn",
           "documentation":"<p>The ARN of the recipe used to create the solution. This is required when <code>performAutoML</code> is false.</p>"
@@ -5003,6 +5049,10 @@
           "shape":"PerformAutoTraining",
           "documentation":"<p>Whether the solution automatically creates solution versions.</p>"
         },
+        "performIncrementalUpdate":{
+          "shape":"PerformIncrementalUpdate",
+          "documentation":"<p>A Boolean value that indicates whether incremental training updates are performed on the model. When enabled, this allows the model to learn from new data more frequently without requiring full retraining, which enables near real-time personalization. This parameter is supported only for solutions that use the semantic-similarity recipe.</p>"
+        },
         "creationDateTime":{
           "shape":"Date",
           "documentation":"<p>The date and time (in Unix format) that the solution update was created.</p>"
@@ -5041,6 +5091,10 @@
           "shape":"PerformAutoML",
           "documentation":"<p>When true, Amazon Personalize searches for the most optimal recipe according to the solution configuration. When false (the default), Amazon Personalize uses <code>recipeArn</code>.</p>"
         },
+        "performIncrementalUpdate":{
+          "shape":"PerformIncrementalUpdate",
+          "documentation":"<p>Whether the solution version should perform an incremental update. When set to true, the training will process only the data that has changed since the latest training, similar to when trainingMode is set to UPDATE. This can only be used with solution versions that use the User-Personalization recipe.</p>"
+        },
         "recipeArn":{
           "shape":"Arn",
           "documentation":"<p>The ARN of the recipe used in the solution.</p>"
@@ -5290,6 +5344,10 @@
         "excludedDatasetColumns":{
           "shape":"ExcludedDatasetColumns",
           "documentation":"<p>Specifies the columns to exclude from training. Each key is a dataset type, and each value is a list of columns. Exclude columns to control what data Amazon Personalize uses to generate recommendations.</p> <p> For example, you might have a column that you want to use only to filter recommendations. You can exclude this column from training and Amazon Personalize considers it only when filtering. </p>"
+        },
+        "includedDatasetColumns":{
+          "shape":"IncludedDatasetColumns",
+          "documentation":"<p>A map that specifies which columns to include from each dataset during training. The map can contain up to 3 entries, where each key is a dataset name (maximum length of 256 characters, must contain only letters and underscores) and each value is an array of up to 50 column names. Column names can be up to 150 characters long, must start with a letter or underscore, and can contain only letters, numbers, and underscores.</p>"
         }
       },
       "documentation":"<p>The training data configuration to use when creating a domain recommender or custom solution version (trained model).</p>"
@@ -5478,6 +5536,10 @@
           "shape":"PerformAutoTraining",
           "documentation":"<p>Whether the solution uses automatic training to create new solution versions (trained models). You can change the training frequency by specifying a <code>schedulingExpression</code> in the <code>AutoTrainingConfig</code> as part of solution configuration. </p> <p> If you turn on automatic training, the first automatic training starts within one hour after the solution update completes. If you manually create a solution version within the hour, the solution skips the first automatic training. For more information about automatic training, see <a href=\"https://docs.aws.amazon.com/personalize/latest/dg/solution-config-auto-training.html\">Configuring automatic training</a>. </p> <p> After training starts, you can get the solution version's Amazon Resource Name (ARN) with the <a href=\"https://docs.aws.amazon.com/personalize/latest/dg/API_ListSolutionVersions.html\">ListSolutionVersions</a> API operation. To get its status, use the <a href=\"https://docs.aws.amazon.com/personalize/latest/dg/API_DescribeSolutionVersion.html\">DescribeSolutionVersion</a>. </p>"
         },
+        "performIncrementalUpdate":{
+          "shape":"PerformIncrementalUpdate",
+          "documentation":"<p>Whether to perform incremental training updates on your model. When enabled, this allows the model to learn from new data more frequently without requiring full retraining, which enables near real-time personalization. This parameter is supported only for solutions that use the semantic-similarity recipe.</p>"
+        },
         "solutionUpdateConfig":{
           "shape":"SolutionUpdateConfig",
           "documentation":"<p>The new configuration details of the solution.</p>"