Agents for Amazon Bedrock Update: Add support of new model types for Bedrock Agents, Adding inference profile support for Flows and Prompt Management, Adding new field to configure additional inference configurations for Flows and Prompt Management

Author: AWS

.changes/next-release/feature-AgentsforAmazonBedrock-80b4ad1.json

@@ -0,0 +1,6 @@
+{
+    "type": "feature",
+    "category": "Agents for Amazon Bedrock",
+    "contributor": "",
+    "description": "Add support of new model types for Bedrock Agents, Adding inference profile support for Flows and Prompt Management, Adding new field to configure additional inference configurations for Flows and Prompt Management"
+}

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

@@ -2333,7 +2333,7 @@
         },
         "foundationModel":{
           "shape":"ModelIdentifier",
-          "documentation":"<p>The Amazon Resource Name (ARN) of the foundation model to be used for orchestration by the agent you create.</p>"
+          "documentation":"<p>The identifier for the model that you want to be used for orchestration by the agent you create.</p> <p>The <code>modelId</code> to provide depends on the type of model or throughput that you use:</p> <ul> <li> <p>If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns\">Amazon Bedrock base model IDs (on-demand throughput)</a> in the Amazon Bedrock User Guide.</p> </li> <li> <p>If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html\">Supported Regions and models for cross-region inference</a> in the Amazon Bedrock User Guide.</p> </li> <li> <p>If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html\">Run inference using a Provisioned Throughput</a> in the Amazon Bedrock User Guide.</p> </li> <li> <p>If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html\">Use a custom model in Amazon Bedrock</a> in the Amazon Bedrock User Guide.</p> </li> <li> <p>If you use an <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html\">imported model</a>, specify the ARN of the imported model. You can get the model ARN from a successful call to <a href=\"https://docs.aws.amazon.com/bedrock/latest/APIReference/API_CreateModelImportJob.html\">CreateModelImportJob</a> or from the Imported models page in the Amazon Bedrock console.</p> </li> </ul>"
         },
         "guardrailConfiguration":{
           "shape":"GuardrailConfiguration",
@@ -3514,6 +3514,12 @@
       "members":{
       }
     },
+    "Document":{
+      "type":"structure",
+      "members":{
+      },
+      "document":true
+    },
     "DraftVersion":{
       "type":"string",
       "max":5,
@@ -3699,8 +3705,7 @@
           "documentation":"<p>A name for the condition that you can reference.</p>"
         }
       },
-      "documentation":"<p>Defines a condition in the condition node.</p>",
-      "sensitive":true
+      "documentation":"<p>Defines a condition in the condition node.</p>"
     },
     "FlowConditionExpression":{
       "type":"string",
@@ -3727,8 +3732,7 @@
       "type":"list",
       "member":{"shape":"FlowCondition"},
       "max":5,
-      "min":1,
-      "sensitive":true
+      "min":1
     },
     "FlowConnection":{
       "type":"structure",
@@ -3824,7 +3828,8 @@
           "documentation":"<p>An array of node definitions in the flow.</p>"
         }
       },
-      "documentation":"<p>The definition of the nodes and connections between nodes in the flow.</p>"
+      "documentation":"<p>The definition of the nodes and connections between nodes in the flow.</p>",
+      "sensitive":true
     },
     "FlowDescription":{
       "type":"string",
@@ -4036,8 +4041,7 @@
       "type":"list",
       "member":{"shape":"FlowNode"},
       "max":20,
-      "min":0,
-      "sensitive":true
+      "min":0
     },
     "FlowStatus":{
       "type":"string",
@@ -5226,9 +5230,10 @@
     },
     "KnowledgeBaseModelIdentifier":{
       "type":"string",
+      "documentation":"<p>ARN or Id of a Bedrock Foundational Model or Inference Profile, or the ARN of a jumpstart model or imported model, or a provisioned throughput ARN for custom models.</p>",
       "max":2048,
       "min":1,
-      "pattern":"^(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}/[a-z0-9]{12})|(:foundation-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|([0-9]{12}:provisioned-model/[a-z0-9]{12})))|([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|(([0-9a-zA-Z][_-]?)+)|(arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{1,20}):(|[0-9]{12}):(model-gateway|inference-profile)/[a-zA-Z0-9-:.]+)|([a-zA-Z0-9-:.]+)$"
+      "pattern":"^(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}/[a-z0-9]{12})|(:foundation-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|([0-9]{12}:imported-model/[a-z0-9]{12})|([0-9]{12}:provisioned-model/[a-z0-9]{12})))|([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|(([0-9a-zA-Z][_-]?)+)|(arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{1,20}):(|[0-9]{12}):(inference-profile|application-inference-profile)/[a-zA-Z0-9-:.]+)|([a-zA-Z0-9-:.]+)$"
     },
     "KnowledgeBaseRoleArn":{
       "type":"string",
@@ -5847,9 +5852,10 @@
     },
     "ModelIdentifier":{
       "type":"string",
+      "documentation":"<p>ARN or Id of a Bedrock Foundational Model or Inference Profile, or the ARN of a jumpstart model or imported model, or a provisioned throughput ARN for custom models.</p>",
       "max":2048,
       "min":1,
-      "pattern":"^arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}(([:][a-z0-9-]{1,63}){0,2})?/[a-z0-9]{12})|(:foundation-model/([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.]?[a-z0-9-]{1,63})([:][a-z0-9-]{1,63}){0,2})))|(([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.]?[a-z0-9-]{1,63})([:][a-z0-9-]{1,63}){0,2}))|(([0-9a-zA-Z][_-]?)+)$"
+      "pattern":"^(arn:aws(-[^:]{1,12})?:(bedrock|sagemaker):[a-z0-9-]{1,20}:([0-9]{12})?:([a-z-]+/)?)?([a-zA-Z0-9.-]{1,63}){0,2}(([:][a-z0-9-]{1,63}){0,2})?(/[a-z0-9]{1,12})?$"
     },
     "MongoDbAtlasCollectionName":{
       "type":"string",
@@ -6323,6 +6329,10 @@
         "templateType"
       ],
       "members":{
+        "additionalModelRequestFields":{
+          "shape":"Document",
+          "documentation":"<p>Contains model-specific inference configurations that aren't in the <code>inferenceConfiguration</code> field. To see model-specific inference parameters, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html\">Inference request parameters and response fields for foundation models</a>.</p>"
+        },
         "inferenceConfiguration":{
           "shape":"PromptInferenceConfiguration",
           "documentation":"<p>Contains inference configurations for the prompt.</p>"
@@ -6450,9 +6460,10 @@
     },
     "PromptModelIdentifier":{
       "type":"string",
+      "documentation":"<p>ARN or Id of a Bedrock Foundational Model or Inference Profile, or the ARN of a jumpstart model or imported model, or a provisioned throughput ARN for custom models.</p>",
       "max":2048,
       "min":1,
-      "pattern":"^(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}/[a-z0-9]{12})|(:foundation-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|([0-9]{12}:provisioned-model/[a-z0-9]{12})))|([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|(([0-9a-zA-Z][_-]?)+)|(arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{1,20}):(|[0-9]{12}):(model-gateway|inference-profile)/[a-zA-Z0-9-:.]+)|([a-zA-Z0-9-:.]+)$"
+      "pattern":"^(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}/[a-z0-9]{12})|(:foundation-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|([0-9]{12}:imported-model/[a-z0-9]{12})|([0-9]{12}:provisioned-model/[a-z0-9]{12})))|([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|(([0-9a-zA-Z][_-]?)+)|(arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{1,20}):(|[0-9]{12}):(inference-profile|application-inference-profile)/[a-zA-Z0-9-:.]+)|([a-zA-Z0-9-:.]+)$"
     },
     "PromptModelInferenceConfiguration":{
       "type":"structure",
@@ -6583,6 +6594,10 @@
         "templateType"
       ],
       "members":{
+        "additionalModelRequestFields":{
+          "shape":"Document",
+          "documentation":"<p>Contains model-specific inference configurations that aren't in the <code>inferenceConfiguration</code> field. To see model-specific inference parameters, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html\">Inference request parameters and response fields for foundation models</a>.</p>"
+        },
         "inferenceConfiguration":{
           "shape":"PromptInferenceConfiguration",
           "documentation":"<p>Contains inference configurations for the prompt variant.</p>"
@@ -7676,7 +7691,7 @@
         },
         "foundationModel":{
           "shape":"ModelIdentifier",
-          "documentation":"<p>Specifies a new foundation model to be used for orchestration by the agent.</p>"
+          "documentation":"<p>The identifier for the model that you want to be used for orchestration by the agent you create.</p> <p>The <code>modelId</code> to provide depends on the type of model or throughput that you use:</p> <ul> <li> <p>If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns\">Amazon Bedrock base model IDs (on-demand throughput)</a> in the Amazon Bedrock User Guide.</p> </li> <li> <p>If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html\">Supported Regions and models for cross-region inference</a> in the Amazon Bedrock User Guide.</p> </li> <li> <p>If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html\">Run inference using a Provisioned Throughput</a> in the Amazon Bedrock User Guide.</p> </li> <li> <p>If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html\">Use a custom model in Amazon Bedrock</a> in the Amazon Bedrock User Guide.</p> </li> <li> <p>If you use an <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html\">imported model</a>, specify the ARN of the imported model. You can get the model ARN from a successful call to <a href=\"https://docs.aws.amazon.com/bedrock/latest/APIReference/API_CreateModelImportJob.html\">CreateModelImportJob</a> or from the Imported models page in the Amazon Bedrock console.</p> </li> </ul>"
         },
         "guardrailConfiguration":{
           "shape":"GuardrailConfiguration",