feat: add more configurability to feature_group.proto (#5656)

* feat: returns usage metadata for context caching

PiperOrigin-RevId: 670830441

Source-Link: googleapis/googleapis@95a1490

Source-Link: googleapis/googleapis-gen@7bffbbc
Copy-Tag: eyJwIjoicGFja2FnZXMvZ29vZ2xlLWNsb3VkLWFpcGxhdGZvcm0vLk93bEJvdC55YW1sIiwiaCI6IjdiZmZiYmM2ODdhNzc2OGNkMTZkNjk2MzUzMzJjOGY4MTQwNDgxYTkifQ==

* feat: add FLEX_START to Scheduling.strategy

PiperOrigin-RevId: 670984417

Source-Link: googleapis/googleapis@fa23e30

Source-Link: googleapis/googleapis-gen@474efb3
Copy-Tag: eyJwIjoicGFja2FnZXMvZ29vZ2xlLWNsb3VkLWFpcGxhdGZvcm0vLk93bEJvdC55YW1sIiwiaCI6IjQ3NGVmYjNjMjY5ZmMxMDQ0NTdkYjJkM2RiNGUxMWQ3YzdjMGEwNjMifQ==

* 🦉 Updates from OwlBot post-processor

See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md

* feat: add FLEX_START to Scheduling.strategy

PiperOrigin-RevId: 670985191

Source-Link: googleapis/googleapis@cb6264a

Source-Link: googleapis/googleapis-gen@9d3a1d7
Copy-Tag: eyJwIjoicGFja2FnZXMvZ29vZ2xlLWNsb3VkLWFpcGxhdGZvcm0vLk93bEJvdC55YW1sIiwiaCI6IjlkM2ExZDc4ZjVlZmY0ZWQxNjM0NGJlNGFlMWE3OTE0NWU5MDA3YmMifQ==

* feat: add more configurability to feature_group.proto
feat: add ragSource to feature_view.proto
feat: add sync watermark to feature_view_sync.proto
docs: fix typo in feature_online_store_admin_service.proto

PiperOrigin-RevId: 671111091

Source-Link: googleapis/googleapis@cb6a8ee

Source-Link: googleapis/googleapis-gen@f38a35f
Copy-Tag: eyJwIjoicGFja2FnZXMvZ29vZ2xlLWNsb3VkLWFpcGxhdGZvcm0vLk93bEJvdC55YW1sIiwiaCI6ImYzOGEzNWZmYzgzN2E5ZmRkZmM1OTI4OTAxNjYzZTlkMzJlZWVjMzQifQ==

* feat: add more configurability to feature_group.proto
feat: add ragSource to feature_view.proto
feat: add sync watermark to feature_view_sync.proto
docs: fix typo in feature_online_store_admin_service.proto

PiperOrigin-RevId: 671113897

Source-Link: googleapis/googleapis@68f6c7f

Source-Link: googleapis/googleapis-gen@03aeb16
Copy-Tag: eyJwIjoicGFja2FnZXMvZ29vZ2xlLWNsb3VkLWFpcGxhdGZvcm0vLk93bEJvdC55YW1sIiwiaCI6IjAzYWViMTY5ZTQyN2RmMDI1ZjU1NzYwM2RhZDhkZGNmZjU5YTQ2MmIifQ==

* 🦉 Updates from OwlBot post-processor

See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md

---------

Co-authored-by: Owl Bot <gcf-owl-bot[bot]@users.noreply.github.com>
Co-authored-by: sofisl <55454395+sofisl@users.noreply.github.com>

Author: gcf-owl-bot[bot]

packages/google-cloud-aiplatform/protos/google/cloud/aiplatform/v1/custom_job.proto

@@ -366,17 +366,20 @@ message Scheduling {
     // Strategy will default to STANDARD.
     STRATEGY_UNSPECIFIED = 0;
 
-    // Regular on-demand provisioning strategy.
+    // Deprecated. Regular on-demand provisioning strategy.
     ON_DEMAND = 1 [deprecated = true];
 
-    // Low cost by making potential use of spot resources.
+    // Deprecated. Low cost by making potential use of spot resources.
     LOW_COST = 2 [deprecated = true];
 
     // Standard provisioning strategy uses regular on-demand resources.
     STANDARD = 3;
 
     // Spot provisioning strategy uses spot resources.
     SPOT = 4;
+
+    // Flex Start strategy uses DWS to queue for resources.
+    FLEX_START = 6;
   }
 
   // The maximum job running time. The default is 7 days.

packages/google-cloud-aiplatform/protos/google/cloud/aiplatform/v1/feature_group.proto

@@ -60,12 +60,28 @@ message FeatureGroup {
     repeated string entity_id_columns = 2
         [(google.api.field_behavior) = OPTIONAL];
 
+    // Optional. Set if the data source is not a time-series.
+    bool static_data_source = 3 [(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.v1.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];
+
+    // Optional. If set, all feature values will be fetched
+    // from a single row per unique entityId including nulls.
+    // If not set, will collapse all rows for each unique entityId into a singe
+    // row with any non-null values if present, if no non-null values are
+    // present will sync null.
+    // ex: If source has schema
+    // `(entity_id, feature_timestamp, f0, f1)` and the following rows:
+    // `(e1, 2020-01-01T10:00:00.123Z, 10, 15)`
+    // `(e1, 2020-02-01T10:00:00.123Z, 20, null)`
+    // If dense is set, `(e1, 20, null)` is synced to online stores. If dense is
+    // not set, `(e1, 20, 15)` is synced to online stores.
+    bool dense = 5 [(google.api.field_behavior) = OPTIONAL];
   }
 
   oneof source {

packages/google-cloud-aiplatform/protos/google/cloud/aiplatform/v1/feature_online_store_admin_service.proto

@@ -543,7 +543,7 @@ message SyncFeatureViewRequest {
   ];
 }
 
-// Respose message for
+// Response message for
 // [FeatureOnlineStoreAdminService.SyncFeatureView][google.cloud.aiplatform.v1.FeatureOnlineStoreAdminService.SyncFeatureView].
 message SyncFeatureViewResponse {
   // Format:

packages/google-cloud-aiplatform/protos/google/cloud/aiplatform/v1/feature_view.proto

@@ -157,6 +157,25 @@ message FeatureView {
     optional int64 project_number = 2 [(google.api.field_behavior) = OPTIONAL];
   }
 
+  // A Vertex Rag source for features that need to be synced to Online
+  // Store.
+  message VertexRagSource {
+    // Required. The BigQuery view/table URI that will be materialized on each
+    // manual sync trigger. The table/view is expected to have the following
+    // columns and types at least:
+    //  - `corpus_id` (STRING, NULLABLE/REQUIRED)
+    //  - `file_id` (STRING, NULLABLE/REQUIRED)
+    //  - `chunk_id` (STRING, NULLABLE/REQUIRED)
+    //  - `chunk_data_type` (STRING, NULLABLE/REQUIRED)
+    //  - `chunk_data` (STRING, NULLABLE/REQUIRED)
+    //  - `embeddings` (FLOAT, REPEATED)
+    //  - `file_original_uri` (STRING, NULLABLE/REQUIRED)
+    string uri = 1 [(google.api.field_behavior) = REQUIRED];
+
+    // Optional. The RAG corpus id corresponding to this FeatureView.
+    int64 rag_corpus_id = 2 [(google.api.field_behavior) = OPTIONAL];
+  }
+
   oneof source {
     // Optional. Configures how data is supposed to be extracted from a BigQuery
     // source to be loaded onto the FeatureOnlineStore.
@@ -167,6 +186,10 @@ message FeatureView {
     // need to be loaded onto the FeatureOnlineStore.
     FeatureRegistrySource feature_registry_source = 9
         [(google.api.field_behavior) = OPTIONAL];
+
+    // Optional. The Vertex RAG Source that the FeatureView is linked to.
+    VertexRagSource vertex_rag_source = 18
+        [(google.api.field_behavior) = OPTIONAL];
   }
 
   // Identifier. Name of the FeatureView. Format:

packages/google-cloud-aiplatform/protos/google/cloud/aiplatform/v1/feature_view_sync.proto

@@ -46,6 +46,10 @@ message FeatureViewSync {
 
     // Output only. BigQuery slot milliseconds consumed for the sync job.
     int64 total_slot = 2 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+    // Lower bound of the system time watermark for the sync job. This is only
+    // set for continuously syncing feature views.
+    google.protobuf.Timestamp system_watermark_time = 5;
   }
 
   // Identifier. Name of the FeatureViewSync. Format:

packages/google-cloud-aiplatform/protos/google/cloud/aiplatform/v1beta1/cached_content.proto

@@ -41,6 +41,24 @@ message CachedContent {
     singular: "cachedContent"
   };
 
+  // Metadata on the usage of the cached content.
+  message UsageMetadata {
+    // Total number of tokens that the cached content consumes.
+    int32 total_token_count = 1;
+
+    // Number of text characters.
+    int32 text_count = 2;
+
+    // Number of images.
+    int32 image_count = 3;
+
+    // Duration of video in seconds.
+    int32 video_duration_seconds = 4;
+
+    // Duration of audio in seconds.
+    int32 audio_duration_seconds = 5;
+  }
+
   // Expiration time of the cached content.
   oneof expiration {
     // Timestamp of when this resource is considered expired.
@@ -112,4 +130,7 @@ message CachedContent {
   // Output only. When the cache entry was last updated in UTC time.
   google.protobuf.Timestamp update_time = 8
       [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Metadata on the usage of the cached content.
+  UsageMetadata usage_metadata = 12 [(google.api.field_behavior) = OUTPUT_ONLY];
 }

packages/google-cloud-aiplatform/protos/google/cloud/aiplatform/v1beta1/custom_job.proto

@@ -366,17 +366,20 @@ message Scheduling {
     // Strategy will default to STANDARD.
     STRATEGY_UNSPECIFIED = 0;
 
-    // Regular on-demand provisioning strategy.
+    // Deprecated. Regular on-demand provisioning strategy.
     ON_DEMAND = 1 [deprecated = true];
 
-    // Low cost by making potential use of spot resources.
+    // Deprecated. Low cost by making potential use of spot resources.
     LOW_COST = 2 [deprecated = true];
 
     // Standard provisioning strategy uses regular on-demand resources.
     STANDARD = 3;
 
     // Spot provisioning strategy uses spot resources.
     SPOT = 4;
+
+    // Flex Start strategy uses DWS to queue for resources.
+    FLEX_START = 6;
   }
 
   // The maximum job running time. The default is 7 days.

packages/google-cloud-aiplatform/protos/google/cloud/aiplatform/v1beta1/feature_group.proto

@@ -60,12 +60,28 @@ message FeatureGroup {
     repeated string entity_id_columns = 2
         [(google.api.field_behavior) = OPTIONAL];
 
+    // Optional. Set if the data source is not a time-series.
+    bool static_data_source = 3 [(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];
+
+    // Optional. If set, all feature values will be fetched
+    // from a single row per unique entityId including nulls.
+    // If not set, will collapse all rows for each unique entityId into a singe
+    // row with any non-null values if present, if no non-null values are
+    // present will sync null.
+    // ex: If source has schema
+    // `(entity_id, feature_timestamp, f0, f1)` and the following rows:
+    // `(e1, 2020-01-01T10:00:00.123Z, 10, 15)`
+    // `(e1, 2020-02-01T10:00:00.123Z, 20, null)`
+    // If dense is set, `(e1, 20, null)` is synced to online stores. If dense is
+    // not set, `(e1, 20, 15)` is synced to online stores.
+    bool dense = 5 [(google.api.field_behavior) = OPTIONAL];
   }
 
   oneof source {

packages/google-cloud-aiplatform/protos/google/cloud/aiplatform/v1beta1/feature_online_store_admin_service.proto

@@ -543,7 +543,7 @@ message SyncFeatureViewRequest {
   ];
 }
 
-// Respose message for
+// Response message for
 // [FeatureOnlineStoreAdminService.SyncFeatureView][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.SyncFeatureView].
 message SyncFeatureViewResponse {
   // Format:

packages/google-cloud-aiplatform/protos/google/cloud/aiplatform/v1beta1/feature_view.proto

@@ -237,6 +237,25 @@ message FeatureView {
     optional int64 project_number = 2 [(google.api.field_behavior) = OPTIONAL];
   }
 
+  // A Vertex Rag source for features that need to be synced to Online
+  // Store.
+  message VertexRagSource {
+    // Required. The BigQuery view/table URI that will be materialized on each
+    // manual sync trigger. The table/view is expected to have the following
+    // columns and types at least:
+    //  - `corpus_id` (STRING, NULLABLE/REQUIRED)
+    //  - `file_id` (STRING, NULLABLE/REQUIRED)
+    //  - `chunk_id` (STRING, NULLABLE/REQUIRED)
+    //  - `chunk_data_type` (STRING, NULLABLE/REQUIRED)
+    //  - `chunk_data` (STRING, NULLABLE/REQUIRED)
+    //  - `embeddings` (FLOAT, REPEATED)
+    //  - `file_original_uri` (STRING, NULLABLE/REQUIRED)
+    string uri = 1 [(google.api.field_behavior) = REQUIRED];
+
+    // Optional. The RAG corpus id corresponding to this FeatureView.
+    int64 rag_corpus_id = 2 [(google.api.field_behavior) = OPTIONAL];
+  }
+
   // Service agent type used during data sync.
   enum ServiceAgentType {
     // By default, the project-level Vertex AI Service Agent is enabled.
@@ -263,6 +282,10 @@ message FeatureView {
     // need to be loaded onto the FeatureOnlineStore.
     FeatureRegistrySource feature_registry_source = 9
         [(google.api.field_behavior) = OPTIONAL];
+
+    // Optional. The Vertex RAG Source that the FeatureView is linked to.
+    VertexRagSource vertex_rag_source = 18
+        [(google.api.field_behavior) = OPTIONAL];
   }
 
   // Identifier. Name of the FeatureView. Format: