1// Copyright 2023 Google LLC 2// 3// Licensed under the Apache License, Version 2.0 (the "License"); 4// you may not use this file except in compliance with the License. 5// You may obtain a copy of the License at 6// 7// http://www.apache.org/licenses/LICENSE-2.0 8// 9// Unless required by applicable law or agreed to in writing, software 10// distributed under the License is distributed on an "AS IS" BASIS, 11// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12// See the License for the specific language governing permissions and 13// limitations under the License. 14 15syntax = "proto3"; 16 17package google.cloud.aiplatform.v1beta1; 18 19import "google/api/field_behavior.proto"; 20import "google/api/resource.proto"; 21import "google/cloud/aiplatform/v1beta1/io.proto"; 22import "google/protobuf/timestamp.proto"; 23 24option csharp_namespace = "Google.Cloud.AIPlatform.V1Beta1"; 25option go_package = "cloud.google.com/go/aiplatform/apiv1beta1/aiplatformpb;aiplatformpb"; 26option java_multiple_files = true; 27option java_outer_classname = "VertexRagDataProto"; 28option java_package = "com.google.cloud.aiplatform.v1beta1"; 29option php_namespace = "Google\\Cloud\\AIPlatform\\V1beta1"; 30option ruby_package = "Google::Cloud::AIPlatform::V1beta1"; 31 32// A RagCorpus is a RagFile container and a project can have multiple 33// RagCorpora. 34message RagCorpus { 35 option (google.api.resource) = { 36 type: "aiplatform.googleapis.com/RagCorpus" 37 pattern: "projects/{project}/locations/{location}/ragCorpora/{rag_corpus}" 38 plural: "ragCorpora" 39 singular: "ragCorpus" 40 }; 41 42 // Output only. The resource name of the RagCorpus. 43 string name = 1 [(google.api.field_behavior) = OUTPUT_ONLY]; 44 45 // Required. The display name of the RagCorpus. 46 // The name can be up to 128 characters long and can consist of any UTF-8 47 // characters. 48 string display_name = 2 [(google.api.field_behavior) = REQUIRED]; 49 50 // Optional. The description of the RagCorpus. 51 string description = 3 [(google.api.field_behavior) = OPTIONAL]; 52 53 // Output only. Timestamp when this RagCorpus was created. 54 google.protobuf.Timestamp create_time = 4 55 [(google.api.field_behavior) = OUTPUT_ONLY]; 56 57 // Output only. Timestamp when this RagCorpus was last updated. 58 google.protobuf.Timestamp update_time = 5 59 [(google.api.field_behavior) = OUTPUT_ONLY]; 60} 61 62// A RagFile contains user data for chunking, embedding and indexing. 63message RagFile { 64 option (google.api.resource) = { 65 type: "aiplatform.googleapis.com/RagFile" 66 pattern: "projects/{project}/locations/{location}/ragCorpora/{rag_corpus}/ragFiles/{rag_file}" 67 plural: "ragFiles" 68 singular: "ragFile" 69 }; 70 71 // The type of the RagFile. 72 enum RagFileType { 73 // RagFile type is unspecified. 74 RAG_FILE_TYPE_UNSPECIFIED = 0; 75 76 // RagFile type is TXT. 77 RAG_FILE_TYPE_TXT = 1; 78 79 // RagFile type is PDF. 80 RAG_FILE_TYPE_PDF = 2; 81 } 82 83 // The origin location of the RagFile if it is imported from Google Cloud 84 // Storage or Google Drive. 85 oneof rag_file_source { 86 // Output only. Google Cloud Storage location of the RagFile. 87 // It does not support wildcards in the GCS uri for now. 88 GcsSource gcs_source = 8 [(google.api.field_behavior) = OUTPUT_ONLY]; 89 90 // Output only. Google Drive location. Supports importing individual files 91 // as well as Google Drive folders. 92 GoogleDriveSource google_drive_source = 9 93 [(google.api.field_behavior) = OUTPUT_ONLY]; 94 95 // Output only. The RagFile is encapsulated and uploaded in the 96 // UploadRagFile request. 97 DirectUploadSource direct_upload_source = 10 98 [(google.api.field_behavior) = OUTPUT_ONLY]; 99 } 100 101 // Output only. The resource name of the RagFile. 102 string name = 1 [(google.api.field_behavior) = OUTPUT_ONLY]; 103 104 // Required. The display name of the RagFile. 105 // The name can be up to 128 characters long and can consist of any UTF-8 106 // characters. 107 string display_name = 2 [(google.api.field_behavior) = REQUIRED]; 108 109 // Optional. The description of the RagFile. 110 string description = 3 [(google.api.field_behavior) = OPTIONAL]; 111 112 // Output only. The size of the RagFile in bytes. 113 int64 size_bytes = 4 [(google.api.field_behavior) = OUTPUT_ONLY]; 114 115 // Output only. The type of the RagFile. 116 RagFileType rag_file_type = 5 [(google.api.field_behavior) = OUTPUT_ONLY]; 117 118 // Output only. Timestamp when this RagFile was created. 119 google.protobuf.Timestamp create_time = 6 120 [(google.api.field_behavior) = OUTPUT_ONLY]; 121 122 // Output only. Timestamp when this RagFile was last updated. 123 google.protobuf.Timestamp update_time = 7 124 [(google.api.field_behavior) = OUTPUT_ONLY]; 125} 126 127// Specifies the size and overlap of chunks for RagFiles. 128message RagFileChunkingConfig { 129 // The size of the chunks. 130 int32 chunk_size = 1; 131 132 // The overlap between chunks. 133 int32 chunk_overlap = 2; 134} 135 136// Config for uploading RagFile. 137message UploadRagFileConfig { 138 // Specifies the size and overlap of chunks after uploading RagFile. 139 RagFileChunkingConfig rag_file_chunking_config = 1; 140} 141 142// Config for importing RagFiles. 143message ImportRagFilesConfig { 144 oneof import_source { 145 // Google Cloud Storage location. Supports importing individual files as 146 // well as entire Google Cloud Storage directories. Sample formats: 147 // - `gs://bucket_name/my_directory/object_name/my_file.txt` 148 // - `gs://bucket_name/my_directory` 149 GcsSource gcs_source = 2; 150 151 // Google Drive location. Supports importing individual files as 152 // well as Google Drive folders. 153 GoogleDriveSource google_drive_source = 3; 154 } 155 156 // Specifies the size and overlap of chunks after importing RagFiles. 157 RagFileChunkingConfig rag_file_chunking_config = 4; 158} 159