diff --git a/google/cloud/aiplatform/v1/feature_online_store.proto b/google/cloud/aiplatform/v1/feature_online_store.proto
index a6a2040ab0095..53469fc74e01f 100644
--- a/google/cloud/aiplatform/v1/feature_online_store.proto
+++ b/google/cloud/aiplatform/v1/feature_online_store.proto
@@ -60,6 +60,19 @@ message FeatureOnlineStore {
     AutoScaling auto_scaling = 1 [(google.api.field_behavior) = REQUIRED];
   }
 
+  // Optimized storage type
+  message Optimized {}
+
+  // The dedicated serving endpoint for this FeatureOnlineStore. Only need to
+  // set when you choose Optimized storage type. Public endpoint is provisioned
+  // by default.
+  message DedicatedServingEndpoint {
+    // Output only. This field will be populated with the domain name to use for
+    // this FeatureOnlineStore
+    string public_endpoint_domain_name = 2
+        [(google.api.field_behavior) = OUTPUT_ONLY];
+  }
+
   // Possible states a featureOnlineStore can have.
   enum State {
     // Default value. This value is unused.
@@ -82,6 +95,13 @@ message FeatureOnlineStore {
     // to serve featureValues for all FeatureViews under this
     // FeatureOnlineStore.
     Bigtable bigtable = 8;
+
+    // Contains settings for the Optimized store that will be created
+    // to serve featureValues for all FeatureViews under this
+    // FeatureOnlineStore. When choose Optimized storage type, need to set
+    // [PrivateServiceConnectConfig.enable_private_service_connect][google.cloud.aiplatform.v1.PrivateServiceConnectConfig.enable_private_service_connect]
+    // to use private endpoint. Otherwise will use public endpoint by default.
+    Optimized optimized = 12;
   }
 
   // Identifier. Name of the FeatureOnlineStore. Format:
@@ -115,4 +135,9 @@ message FeatureOnlineStore {
 
   // Output only. State of the featureOnlineStore.
   State state = 7 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Optional. The dedicated serving endpoint for this FeatureOnlineStore, which
+  // is different from common Vertex service endpoint.
+  DedicatedServingEndpoint dedicated_serving_endpoint = 10
+      [(google.api.field_behavior) = OPTIONAL];
 }
diff --git a/google/cloud/aiplatform/v1/feature_online_store_service.proto b/google/cloud/aiplatform/v1/feature_online_store_service.proto
index bb451126e2dee..82667c2434a2e 100644
--- a/google/cloud/aiplatform/v1/feature_online_store_service.proto
+++ b/google/cloud/aiplatform/v1/feature_online_store_service.proto
@@ -141,6 +141,11 @@ message FetchFeatureValuesResponse {
     // Feature values in proto Struct format.
     google.protobuf.Struct proto_struct = 2;
   }
+
+  // The data key associated with this response.
+  // Will only be populated for
+  // [FeatureOnlineStoreService.StreamingFetchFeatureValues][] RPCs.
+  FeatureViewDataKey data_key = 4;
 }
 
 // A query to find a number of similar entities.
diff --git a/google/cloud/aiplatform/v1/feature_view.proto b/google/cloud/aiplatform/v1/feature_view.proto
index 07b5b139d3cba..03f080f0db4e9 100644
--- a/google/cloud/aiplatform/v1/feature_view.proto
+++ b/google/cloud/aiplatform/v1/feature_view.proto
@@ -57,6 +57,85 @@ message FeatureView {
     string cron = 1;
   }
 
+  // Configuration for vector indexing.
+  message IndexConfig {
+    // Configuration options for using brute force search.
+    message BruteForceConfig {}
+
+    // Configuration options for the tree-AH algorithm.
+    message TreeAHConfig {
+      // Optional. Number of embeddings on each leaf node. The default value is
+      // 1000 if not set.
+      optional int64 leaf_node_embedding_count = 1
+          [(google.api.field_behavior) = OPTIONAL];
+    }
+
+    // The distance measure used in nearest neighbor search.
+    enum DistanceMeasureType {
+      // Should not be set.
+      DISTANCE_MEASURE_TYPE_UNSPECIFIED = 0;
+
+      // Euclidean (L_2) Distance.
+      SQUARED_L2_DISTANCE = 1;
+
+      // Cosine Distance. Defined as 1 - cosine similarity.
+      //
+      // We strongly suggest using DOT_PRODUCT_DISTANCE + UNIT_L2_NORM instead
+      // of COSINE distance. Our algorithms have been more optimized for
+      // DOT_PRODUCT distance which, when combined with UNIT_L2_NORM, is
+      // mathematically equivalent to COSINE distance and results in the same
+      // ranking.
+      COSINE_DISTANCE = 2;
+
+      // Dot Product Distance. Defined as a negative of the dot product.
+      DOT_PRODUCT_DISTANCE = 3;
+    }
+
+    // The configuration with regard to the algorithms used for efficient
+    // search.
+    oneof algorithm_config {
+      // Optional. Configuration options for the tree-AH algorithm (Shallow tree
+      // + Asymmetric Hashing). Please refer to this paper for more details:
+      // https://arxiv.org/abs/1908.10396
+      TreeAHConfig tree_ah_config = 6 [(google.api.field_behavior) = OPTIONAL];
+
+      // Optional. Configuration options for using brute force search, which
+      // simply implements the standard linear search in the database for each
+      // query. It is primarily meant for benchmarking and to generate the
+      // ground truth for approximate search.
+      BruteForceConfig brute_force_config = 7
+          [(google.api.field_behavior) = OPTIONAL];
+    }
+
+    // Optional. Column of embedding. This column contains the source data to
+    // create index for vector search. embedding_column must be set when using
+    // vector search.
+    string embedding_column = 1 [(google.api.field_behavior) = OPTIONAL];
+
+    // Optional. Columns of features that're used to filter vector search
+    // results.
+    repeated string filter_columns = 2 [(google.api.field_behavior) = OPTIONAL];
+
+    // Optional. Column of crowding. This column contains crowding attribute
+    // which is a constraint on a neighbor list produced by
+    // [FeatureOnlineStoreService.SearchNearestEntities][google.cloud.aiplatform.v1.FeatureOnlineStoreService.SearchNearestEntities]
+    // to diversify search results. If
+    // [NearestNeighborQuery.per_crowding_attribute_neighbor_count][google.cloud.aiplatform.v1.NearestNeighborQuery.per_crowding_attribute_neighbor_count]
+    // is set to K in
+    // [SearchNearestEntitiesRequest][google.cloud.aiplatform.v1.SearchNearestEntitiesRequest],
+    // it's guaranteed that no more than K entities of the same crowding
+    // attribute are returned in the response.
+    string crowding_column = 3 [(google.api.field_behavior) = OPTIONAL];
+
+    // Optional. The number of dimensions of the input embedding.
+    optional int32 embedding_dimension = 4
+        [(google.api.field_behavior) = OPTIONAL];
+
+    // Optional. The distance measure used in nearest neighbor search.
+    DistanceMeasureType distance_measure_type = 5
+        [(google.api.field_behavior) = OPTIONAL];
+  }
+
   // A Feature Registry source for features that need to be synced to Online
   // Store.
   message FeatureRegistrySource {
@@ -123,4 +202,10 @@ message FeatureView {
   // end of the sync the latest featureValues for each entityId of this
   // FeatureView are made ready for online serving.
   SyncConfig sync_config = 7;
+
+  // Optional. Configuration for index preparation for vector search. It
+  // contains the required configurations to create an index from source data,
+  // so that approximate nearest neighbor (a.k.a ANN) algorithms search can be
+  // performed during online serving.
+  IndexConfig index_config = 15 [(google.api.field_behavior) = OPTIONAL];
 }