feat: add rag_embedding_model_config to RagCorpus

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

@@ -29,6 +29,48 @@ option java_package = "com.google.cloud.aiplatform.v1beta1";
 option php_namespace = "Google\\Cloud\\AIPlatform\\V1beta1";
 option ruby_package = "Google::Cloud::AIPlatform::V1beta1";
 
+// Config for the embedding model to use for RAG.
+message RagEmbeddingModelConfig {
+  // Config representing a model hosted on Vertex Prediction Endpoint.
+  message VertexPredictionEndpoint {
+    // Required. The endpoint resource name.
+    // Format:
+    // `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}`
+    // or
+    // `projects/{project}/locations/{location}/endpoints/{endpoint}`
+    string endpoint = 1 [
+      (google.api.field_behavior) = REQUIRED,
+      (google.api.resource_reference) = {
+        type: "aiplatform.googleapis.com/Endpoint"
+      }
+    ];
+
+    // Output only. The resource name of the model that is deployed on the
+    // endpoint. Present only when the endpoint is not a publisher model.
+    // Pattern:
+    // `projects/{project}/locations/{location}/models/{model}`
+    string model = 2 [
+      (google.api.field_behavior) = OUTPUT_ONLY,
+      (google.api.resource_reference) = {
+        type: "aiplatform.googleapis.com/Model"
+      }
+    ];
+
+    // Output only. Version ID of the model that is deployed on the endpoint.
+    // Present only when the endpoint is not a publisher model.
+    string model_version_id = 3 [(google.api.field_behavior) = OUTPUT_ONLY];
+  }
+
+  // The model config to use.
+  oneof model_config {
+    // The Vertex AI Prediction Endpoint that either refers to a publisher model
+    // or an endpoint that is hosting a 1P fine-tuned text embedding model.
+    // Endpoints hosting non-1P fine-tuned text embedding models are
+    // currently not supported.
+    VertexPredictionEndpoint vertex_prediction_endpoint = 1;
+  }
+}
+
 // A RagCorpus is a RagFile container and a project can have multiple
 // RagCorpora.
 message RagCorpus {
@@ -50,6 +92,12 @@ message RagCorpus {
   // Optional. The description of the RagCorpus.
   string description = 3 [(google.api.field_behavior) = OPTIONAL];
 
+  // Optional. Immutable. The embedding model config of the RagCorpus.
+  RagEmbeddingModelConfig rag_embedding_model_config = 6 [
+    (google.api.field_behavior) = OPTIONAL,
+    (google.api.field_behavior) = IMMUTABLE
+  ];
+
   // Output only. Timestamp when this RagCorpus was created.
   google.protobuf.Timestamp create_time = 4
       [(google.api.field_behavior) = OUTPUT_ONLY];
@@ -155,4 +203,12 @@ message ImportRagFilesConfig {
 
   // Specifies the size and overlap of chunks after importing RagFiles.
   RagFileChunkingConfig rag_file_chunking_config = 4;
+
+  // Optional. The max number of queries per minute that this job is allowed to
+  // make to the embedding model specified on the corpus. This value is specific
+  // to this job and not shared across other import jobs. Consult the Quotas
+  // page on the project to set an appropriate value here.
+  // If unspecified, a default value of 1,000 QPM would be used.
+  int32 max_embedding_requests_per_min = 5
+      [(google.api.field_behavior) = OPTIONAL];
 }