feat: A new message RoutingConfig is added

feat: A new field `seed` is added to message `.google.cloud.aiplatform.v1beta1.GenerationConfig`
feat: A new field `routing_config` is added to message `.google.cloud.aiplatform.v1beta1.GenerationConfig`
feat: A new field `avg_logprobs` is added to message `.google.cloud.aiplatform.v1beta1.Candidate`
feat: A new field `satisfies_pzs` is added to message `.google.cloud.aiplatform.v1beta1.CustomJob`
feat: A new field `satisfies_pzi` is added to message `.google.cloud.aiplatform.v1beta1.CustomJob`
feat: A new field `satisfies_pzs` is added to message `.google.cloud.aiplatform.v1beta1.EntityType`
feat: A new field `satisfies_pzi` is added to message `.google.cloud.aiplatform.v1beta1.EntityType`
feat: A new message `TimeSeries` is added
feat: A new field `time_series` is added to message `.google.cloud.aiplatform.v1beta1.FeatureGroup`
feat: A new field `satisfies_pzs` is added to message `.google.cloud.aiplatform.v1beta1.FeatureOnlineStore`
feat: A new field `satisfies_pzi` is added to message `.google.cloud.aiplatform.v1beta1.FeatureOnlineStore`
feat: A new field `satisfies_pzs` is added to message `.google.cloud.aiplatform.v1beta1.FeatureView`
feat: A new field `satisfies_pzi` is added to message `.google.cloud.aiplatform.v1beta1.FeatureView`
feat: A new field `satisfies_pzs` is added to message `.google.cloud.aiplatform.v1beta1.FeatureViewSync`
feat: A new field `satisfies_pzi` is added to message `.google.cloud.aiplatform.v1beta1.FeatureViewSync`
feat: A new field `satisfies_pzs` is added to message `.google.cloud.aiplatform.v1beta1.Featurestore`
feat: A new field `satisfies_pzi` is added to message `.google.cloud.aiplatform.v1beta1.Featurestore`
feat: A new field `satisfies_pzs` is added to message `.google.cloud.aiplatform.v1beta1.HyperparameterTuningJob`
feat: A new field `satisfies_pzi` is added to message `.google.cloud.aiplatform.v1beta1.HyperparameterTuningJob`
feat: A new field `satisfies_pzs` is added to message `.google.cloud.aiplatform.v1beta1.Index`
feat: A new field `satisfies_pzi` is added to message `.google.cloud.aiplatform.v1beta1.Index`
feat: A new field `satisfies_pzs` is added to message `.google.cloud.aiplatform.v1beta1.IndexEndpoint`
feat: A new field `satisfies_pzi` is added to message `.google.cloud.aiplatform.v1beta1.IndexEndpoint`
feat: A new field `satisfies_pzs` is added to message `.google.cloud.aiplatform.v1beta1.ModelDeploymentMonitoringJob`
feat: A new field `satisfies_pzi` is added to message `.google.cloud.aiplatform.v1beta1.ModelDeploymentMonitoringJob`
feat: A new field `hugging_face_token` is added to message `.google.cloud.aiplatform.v1beta1.GetPublisherModelRequest`
feat: A new field `satisfies_pzs` is added to message `.google.cloud.aiplatform.v1beta1.NasJob`
feat: A new field `satisfies_pzi` is added to message `.google.cloud.aiplatform.v1beta1.NasJob`
feat: A new field `encryption_spec` is added to message `.google.cloud.aiplatform.v1beta1.NotebookExecutionJob`
feat: A new field `sample_request` is added to message `.google.cloud.aiplatform.v1beta1.PublisherModel`
feat: A new field `service_attachment` is added to message `.google.cloud.aiplatform.v1beta1.PrivateServiceConnectConfig`
feat: A new field `total_truncated_example_count` is added to message `.google.cloud.aiplatform.v1beta1.SupervisedTuningDataStats`
feat: A new field `truncated_example_indices` is added to message `.google.cloud.aiplatform.v1beta1.SupervisedTuningDataStats`
fix!: An existing message `GroundingAttribution` is removed
fix!: An existing field `grounding_attributions` is removed from message `.google.cloud.aiplatform.v1beta1.GroundingMetadata`
fix!: An existing field `disable_attribution` is removed from message `.google.cloud.aiplatform.v1beta1.GoogleSearchRetrieval`
docs: A comment for enum value `STOP` in enum `FinishReason` is changed
docs: A comment for enum value `MAX_TOKENS` in enum `FinishReason` is changed
docs: A comment for enum value `SAFETY` in enum `FinishReason` is changed
docs: A comment for enum value `RECITATION` in enum `FinishReason` is changed
docs: A comment for enum value `OTHER` in enum `FinishReason` is changed
docs: A comment for enum value `BLOCKLIST` in enum `FinishReason` is changed
docs: A comment for enum value `PROHIBITED_CONTENT` in enum `FinishReason` is changed
docs: A comment for enum value `SPII` in enum `FinishReason` is changed
docs: A comment for enum `Strategy` is changed
docs: A comment for enum value `STRATEGY_UNSPECIFIED` in enum `Strategy` is changed
docs: A comment for enum value `AUTO` in enum `Mode` is changed
docs: A comment for field `distance` in message `.google.cloud.aiplatform.v1beta1.RagContexts` is changed

PiperOrigin-RevId: 661167484

google/cloud/aiplatform/v1beta1/content.proto

@@ -137,6 +137,48 @@ message VideoMetadata {
 
 // Generation config.
 message GenerationConfig {
+  // The configuration for routing the request to a specific model.
+  message RoutingConfig {
+    // When automated routing is specified, the routing will be determined by
+    // the pretrained routing model and customer provided model routing
+    // preference.
+    message AutoRoutingMode {
+      // The model routing preference.
+      enum ModelRoutingPreference {
+        // Unspecified model routing preference.
+        UNKNOWN = 0;
+
+        // Prefer higher quality over low cost.
+        PRIORITIZE_QUALITY = 1;
+
+        // Balanced model routing preference.
+        BALANCED = 2;
+
+        // Prefer lower cost over higher quality.
+        PRIORITIZE_COST = 3;
+      }
+
+      // The model routing preference.
+      optional ModelRoutingPreference model_routing_preference = 1;
+    }
+
+    // When manual routing is set, the specified model will be used directly.
+    message ManualRoutingMode {
+      // The model name to use. Only the public LLM models are accepted. e.g.
+      // 'gemini-1.5-pro-001'.
+      optional string model_name = 1;
+    }
+
+    // Routing mode.
+    oneof routing_config {
+      // Automated routing.
+      AutoRoutingMode auto_mode = 1;
+
+      // Manual routing.
+      ManualRoutingMode manual_mode = 2;
+    }
+  }
+
   // Optional. Controls the randomness of predictions.
   optional float temperature = 1 [(google.api.field_behavior) = OPTIONAL];
 
@@ -161,6 +203,9 @@ message GenerationConfig {
   // Optional. Frequency penalties.
   optional float frequency_penalty = 9 [(google.api.field_behavior) = OPTIONAL];
 
+  // Optional. Seed.
+  optional int32 seed = 12 [(google.api.field_behavior) = OPTIONAL];
+
   // Optional. Output response mimetype of the generated candidate text.
   // Supported mimetype:
   // - `text/plain`: (default) Text output.
@@ -178,6 +223,10 @@ message GenerationConfig {
   // Compatible mimetypes:
   // `application/json`: Schema for JSON response.
   optional Schema response_schema = 16 [(google.api.field_behavior) = OPTIONAL];
+
+  // Optional. Routing configuration.
+  optional RoutingConfig routing_config = 17
+      [(google.api.field_behavior) = OPTIONAL];
 }
 
 // Safety settings.
@@ -317,34 +366,34 @@ message Candidate {
     // The finish reason is unspecified.
     FINISH_REASON_UNSPECIFIED = 0;
 
-    // Natural stop point of the model or provided stop sequence.
+    // Token generation reached a natural stopping point or a configured stop
+    // sequence.
     STOP = 1;
 
-    // The maximum number of tokens as specified in the request was reached.
+    // Token generation reached the configured maximum output tokens.
     MAX_TOKENS = 2;
 
-    // The token generation was stopped as the response was flagged for safety
-    // reasons. NOTE: When streaming the Candidate.content will be empty if
-    // content filters blocked the output.
+    // Token generation stopped because the content potentially contains safety
+    // violations. NOTE: When streaming,
+    // [content][google.cloud.aiplatform.v1beta1.Candidate.content] is empty if
+    // content filters blocks the output.
     SAFETY = 3;
 
-    // The token generation was stopped as the response was flagged for
-    // unauthorized citations.
+    // Token generation stopped because the content potentially contains
+    // copyright violations.
     RECITATION = 4;
 
-    // All other reasons that stopped the token generation
+    // All other reasons that stopped the token generation.
     OTHER = 5;
 
-    // The token generation was stopped as the response was flagged for the
-    // terms which are included from the terminology blocklist.
+    // Token generation stopped because the content contains forbidden terms.
     BLOCKLIST = 6;
 
-    // The token generation was stopped as the response was flagged for
-    // the prohibited contents.
+    // Token generation stopped for potentially containing prohibited content.
     PROHIBITED_CONTENT = 7;
 
-    // The token generation was stopped as the response was flagged for
-    // Sensitive Personally Identifiable Information (SPII) contents.
+    // Token generation stopped because the content potentially contains
+    // Sensitive Personally Identifiable Information (SPII).
     SPII = 8;
 
     // The function call generated by the model is invalid.
@@ -357,6 +406,9 @@ message Candidate {
   // Output only. Content parts of the candidate.
   Content content = 2 [(google.api.field_behavior) = OUTPUT_ONLY];
 
+  // Output only. Average log probability score of the candidate.
+  double avg_logprobs = 9 [(google.api.field_behavior) = OUTPUT_ONLY];
+
   // Output only. The reason why the model stopped generating tokens.
   // If empty, the model has not stopped generating the tokens.
   FinishReason finish_reason = 3 [(google.api.field_behavior) = OUTPUT_ONLY];
@@ -445,46 +497,6 @@ message GroundingSupport {
   repeated float confidence_scores = 3;
 }
 
-// Grounding attribution.
-message GroundingAttribution {
-  // Attribution from the web.
-  message Web {
-    // Output only. URI reference of the attribution.
-    string uri = 1 [(google.api.field_behavior) = OUTPUT_ONLY];
-
-    // Output only. Title of the attribution.
-    string title = 2 [(google.api.field_behavior) = OUTPUT_ONLY];
-  }
-
-  // Attribution from context retrieved by the retrieval tools.
-  message RetrievedContext {
-    // Output only. URI reference of the attribution.
-    string uri = 1 [(google.api.field_behavior) = OUTPUT_ONLY];
-
-    // Output only. Title of the attribution.
-    string title = 2 [(google.api.field_behavior) = OUTPUT_ONLY];
-  }
-
-  oneof reference {
-    // Optional. Attribution from the web.
-    Web web = 3 [(google.api.field_behavior) = OPTIONAL];
-
-    // Optional. Attribution from context retrieved by the retrieval tools.
-    RetrievedContext retrieved_context = 4
-        [(google.api.field_behavior) = OPTIONAL];
-  }
-
-  // Output only. Segment of the content this attribution belongs to.
-  Segment segment = 1 [(google.api.field_behavior) = OUTPUT_ONLY];
-
-  // Optional. Output only. Confidence score of the attribution. Ranges from 0
-  // to 1. 1 is the most confident.
-  optional float confidence_score = 2 [
-    (google.api.field_behavior) = OPTIONAL,
-    (google.api.field_behavior) = OUTPUT_ONLY
-  ];
-}
-
 // Metadata returned to client when grounding is enabled.
 message GroundingMetadata {
   // Optional. Web search queries for the following-up web search.
@@ -499,10 +511,6 @@ message GroundingMetadata {
   repeated string retrieval_queries = 3
       [(google.api.field_behavior) = OPTIONAL];
 
-  // Optional. List of grounding attributions.
-  repeated GroundingAttribution grounding_attributions = 2
-      [(google.api.field_behavior) = OPTIONAL];
-
   // List of supporting references retrieved from specified grounding source.
   repeated GroundingChunk grounding_chunks = 5;
 

google/cloud/aiplatform/v1beta1/custom_job.proto

@@ -109,6 +109,12 @@ message CustomJob {
   // The values are the URIs for each node's interactive shell.
   map<string, string> web_access_uris = 16
       [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzs = 18 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzi = 19 [(google.api.field_behavior) = OUTPUT_ONLY];
 }
 
 // Represents the spec of a CustomJob.
@@ -352,16 +358,16 @@ message PythonPackageSpec {
 // All parameters related to queuing and scheduling of custom jobs.
 message Scheduling {
   // Optional. This determines which type of scheduling strategy to use. Right
-  // now users have two options such as ON_DEMAND which will use regular on
-  // demand resources to schedule the job, the other is LOW_COST which would
+  // now users have two options such as STANDARD which will use regular on
+  // demand resources to schedule the job, the other is SPOT which would
   // leverage spot resources alongwith regular resources to schedule
   // the job.
   enum Strategy {
-    // Strategy will default to ON_DEMAND.
+    // Strategy will default to STANDARD.
     STRATEGY_UNSPECIFIED = 0;
 
     // Regular on-demand provisioning strategy.
-    ON_DEMAND = 1;
+    ON_DEMAND = 1 [deprecated = true];
 
     // Low cost by making potential use of spot resources.
     LOW_COST = 2 [deprecated = true];

google/cloud/aiplatform/v1beta1/entity_type.proto

@@ -95,4 +95,10 @@ message EntityType {
   // values older than `offline_storage_ttl_days` since the feature generation
   // time. If unset (or explicitly set to 0), default to 4000 days TTL.
   int32 offline_storage_ttl_days = 10 [(google.api.field_behavior) = OPTIONAL];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzs = 11 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzi = 12 [(google.api.field_behavior) = OUTPUT_ONLY];
 }

google/cloud/aiplatform/v1beta1/feature_group.proto

@@ -40,6 +40,14 @@ message FeatureGroup {
 
   // Input source type for BigQuery Tables and Views.
   message BigQuery {
+    message TimeSeries {
+      // Optional. Column hosting timestamp values for a time-series source.
+      // Will be used to determine the latest `feature_values` for each entity.
+      // Optional. If not provided, column named `feature_timestamp` of
+      // type `TIMESTAMP` will be used.
+      string timestamp_column = 1 [(google.api.field_behavior) = OPTIONAL];
+    }
+
     // Required. Immutable. The BigQuery source URI that points to either a
     // BigQuery Table or View.
     BigQuerySource big_query_source = 1 [
@@ -51,6 +59,13 @@ message FeatureGroup {
     // If not provided defaults to `entity_id`.
     repeated string entity_id_columns = 2
         [(google.api.field_behavior) = OPTIONAL];
+
+    // Optional. If the source is a time-series source, this can be set to
+    // control how downstream sources (ex:
+    // [FeatureView][google.cloud.aiplatform.v1beta1.FeatureView] ) will treat
+    // time-series sources. If not set, will treat the source as a time-series
+    // source with `feature_timestamp` as timestamp column and no scan boundary.
+    TimeSeries time_series = 4 [(google.api.field_behavior) = OPTIONAL];
   }
 
   oneof source {

google/cloud/aiplatform/v1beta1/feature_online_store.proto

@@ -179,4 +179,10 @@ message FeatureOnlineStore {
   // Optional. Customer-managed encryption key spec for data storage. If set,
   // online store will be secured by this key.
   EncryptionSpec encryption_spec = 13 [(google.api.field_behavior) = OPTIONAL];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzs = 15 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzi = 16 [(google.api.field_behavior) = OUTPUT_ONLY];
 }

google/cloud/aiplatform/v1beta1/feature_view.proto

@@ -324,4 +324,10 @@ message FeatureView {
   // bigquery.dataViewer should be granted to this service account to allow
   // Vertex AI Feature Store to sync data to the online store.
   string service_account_email = 13 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzs = 19 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzi = 20 [(google.api.field_behavior) = OUTPUT_ONLY];
 }

google/cloud/aiplatform/v1beta1/feature_view_sync.proto

@@ -67,4 +67,10 @@ message FeatureViewSync {
 
   // Output only. Summary of the sync job.
   SyncSummary sync_summary = 6 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzs = 7 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzi = 8 [(google.api.field_behavior) = OUTPUT_ONLY];
 }

google/cloud/aiplatform/v1beta1/featurestore.proto

@@ -149,4 +149,10 @@ message Featurestore {
   // Optional. Customer-managed encryption key spec for data storage. If set,
   // both of the online and offline data storage will be secured by this key.
   EncryptionSpec encryption_spec = 10 [(google.api.field_behavior) = OPTIONAL];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzs = 14 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzi = 15 [(google.api.field_behavior) = OUTPUT_ONLY];
 }

google/cloud/aiplatform/v1beta1/hyperparameter_tuning_job.proto

@@ -113,4 +113,10 @@ message HyperparameterTuningJob {
   // If this is set, then all resources created by the HyperparameterTuningJob
   // will be encrypted with the provided encryption key.
   EncryptionSpec encryption_spec = 17;
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzs = 19 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzi = 20 [(google.api.field_behavior) = OUTPUT_ONLY];
 }

google/cloud/aiplatform/v1beta1/index.proto

@@ -125,6 +125,12 @@ message Index {
   // Immutable. Customer-managed encryption key spec for an Index. If set, this
   // Index and all sub-resources of this Index will be secured by this key.
   EncryptionSpec encryption_spec = 17 [(google.api.field_behavior) = IMMUTABLE];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzs = 18 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzi = 19 [(google.api.field_behavior) = OUTPUT_ONLY];
 }
 
 // A datapoint of Index.

google/cloud/aiplatform/v1beta1/index_endpoint.proto

@@ -128,6 +128,12 @@ message IndexEndpoint {
   // set, this IndexEndpoint and all sub-resources of this IndexEndpoint will be
   // secured by this key.
   EncryptionSpec encryption_spec = 15 [(google.api.field_behavior) = IMMUTABLE];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzs = 17 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzi = 18 [(google.api.field_behavior) = OUTPUT_ONLY];
 }
 
 // A deployment of an Index. IndexEndpoints contain one or more DeployedIndexes.

google/cloud/aiplatform/v1beta1/model_deployment_monitoring_job.proto

@@ -224,6 +224,12 @@ message ModelDeploymentMonitoringJob {
   // Output only. Only populated when the job's state is `JOB_STATE_FAILED` or
   // `JOB_STATE_CANCELLED`.
   google.rpc.Status error = 23 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzs = 26 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzi = 27 [(google.api.field_behavior) = OUTPUT_ONLY];
 }
 
 // ModelDeploymentMonitoringBigQueryTable specifies the BigQuery table name

google/cloud/aiplatform/v1beta1/model_garden_service.proto

@@ -93,6 +93,9 @@ message GetPublisherModelRequest {
   // Optional. Boolean indicates whether the requested model is a Hugging Face
   // model.
   bool is_hugging_face_model = 5 [(google.api.field_behavior) = OPTIONAL];
+
+  // Optional. Token used to access Hugging Face gated models.
+  string hugging_face_token = 6 [(google.api.field_behavior) = OPTIONAL];
 }
 
 // Request message for

google/cloud/aiplatform/v1beta1/nas_job.proto

@@ -97,6 +97,12 @@ message NasJob {
   // and restricted image training for tenant project.
   bool enable_restricted_image_training = 14
       [deprecated = true, (google.api.field_behavior) = OPTIONAL];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzs = 15 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzi = 16 [(google.api.field_behavior) = OUTPUT_ONLY];
 }
 
 // Represents a NasTrial details along with its parameters. If there is a

google/cloud/aiplatform/v1beta1/notebook_execution_job.proto

@@ -18,6 +18,7 @@ package google.cloud.aiplatform.v1beta1;
 
 import "google/api/field_behavior.proto";
 import "google/api/resource.proto";
+import "google/cloud/aiplatform/v1beta1/encryption_spec.proto";
 import "google/cloud/aiplatform/v1beta1/job_state.proto";
 import "google/protobuf/duration.proto";
 import "google/protobuf/timestamp.proto";
@@ -155,4 +156,9 @@ message NotebookExecutionJob {
   // System reserved label keys are prefixed with "aiplatform.googleapis.com/"
   // and are immutable.
   map<string, string> labels = 19;
+
+  // Customer-managed encryption key spec for the notebook execution job.
+  // This field is auto-populated if the
+  // [NotebookService.NotebookRuntimeTemplate][] has an encryption spec.
+  EncryptionSpec encryption_spec = 22;
 }