googleapis/google/cloud/discoveryengine/v1/chunk.proto
Google APIs 9953dde4a2 feat: add CMEK config service
feat: add identity mapping service
feat: add user license config service
feat: add HealthcareFhirConfig to FHIR data store
feat: add ConnectorRunErrorContext to error log
feat: support structured content for chunk
feat: support ACL data store and document
feat: add more options for layout parser config
feat: support media recommendation engine
feat: enable claim level score for grounding
feat: add custom search operators for Workspace search
feat: add more indexing state for site search engine
docs: keep the API doc up-to-date with recent changes

PiperOrigin-RevId: 766759284
2025-06-03 11:51:52 -07:00

172 lines
6.5 KiB
Protocol Buffer

// Copyright 2025 Google LLC
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
syntax = "proto3";
package google.cloud.discoveryengine.v1;
import "google/api/field_behavior.proto";
import "google/api/resource.proto";
import "google/protobuf/struct.proto";
option csharp_namespace = "Google.Cloud.DiscoveryEngine.V1";
option go_package = "cloud.google.com/go/discoveryengine/apiv1/discoveryenginepb;discoveryenginepb";
option java_multiple_files = true;
option java_outer_classname = "ChunkProto";
option java_package = "com.google.cloud.discoveryengine.v1";
option objc_class_prefix = "DISCOVERYENGINE";
option php_namespace = "Google\\Cloud\\DiscoveryEngine\\V1";
option ruby_package = "Google::Cloud::DiscoveryEngine::V1";
// Chunk captures all raw metadata information of items to be recommended or
// searched in the chunk mode.
message Chunk {
option (google.api.resource) = {
type: "discoveryengine.googleapis.com/Chunk"
pattern: "projects/{project}/locations/{location}/dataStores/{data_store}/branches/{branch}/documents/{document}/chunks/{chunk}"
pattern: "projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document}/chunks/{chunk}"
};
// Document metadata contains the information of the document of the current
// chunk.
message DocumentMetadata {
// Uri of the document.
string uri = 1;
// Title of the document.
string title = 2;
// Data representation.
// The structured JSON data for the document. It should conform to the
// registered [Schema][google.cloud.discoveryengine.v1.Schema] or an
// `INVALID_ARGUMENT` error is thrown.
google.protobuf.Struct struct_data = 3;
}
// Page span of the chunk.
message PageSpan {
// The start page of the chunk.
int32 page_start = 1;
// The end page of the chunk.
int32 page_end = 2;
}
// Metadata of the current chunk. This field is only populated on
// [SearchService.Search][google.cloud.discoveryengine.v1.SearchService.Search]
// API.
message ChunkMetadata {
// The previous chunks of the current chunk. The number is controlled by
// [SearchRequest.ContentSearchSpec.ChunkSpec.num_previous_chunks][google.cloud.discoveryengine.v1.SearchRequest.ContentSearchSpec.ChunkSpec.num_previous_chunks].
// This field is only populated on
// [SearchService.Search][google.cloud.discoveryengine.v1.SearchService.Search]
// API.
repeated Chunk previous_chunks = 1;
// The next chunks of the current chunk. The number is controlled by
// [SearchRequest.ContentSearchSpec.ChunkSpec.num_next_chunks][google.cloud.discoveryengine.v1.SearchRequest.ContentSearchSpec.ChunkSpec.num_next_chunks].
// This field is only populated on
// [SearchService.Search][google.cloud.discoveryengine.v1.SearchService.Search]
// API.
repeated Chunk next_chunks = 2;
}
// The structured content information.
message StructuredContent {
// Output only. The structure type of the structured content.
StructureType structure_type = 1
[(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. The content of the structured content.
string content = 2 [(google.api.field_behavior) = OUTPUT_ONLY];
}
// The annotation metadata includes structured content in the current chunk.
message AnnotationMetadata {
// Output only. The structured content information.
StructuredContent structured_content = 1
[(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. Image id is provided if the structured content is based on
// an image.
string image_id = 2 [(google.api.field_behavior) = OUTPUT_ONLY];
}
// Defines the types of the structured content that can be extracted.
enum StructureType {
// Default value.
STRUCTURE_TYPE_UNSPECIFIED = 0;
// Shareholder structure.
SHAREHOLDER_STRUCTURE = 1;
// Signature structure.
SIGNATURE_STRUCTURE = 2;
// Checkbox structure.
CHECKBOX_STRUCTURE = 3;
}
// The full resource name of the chunk.
// Format:
// `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document_id}/chunks/{chunk_id}`.
//
// This field must be a UTF-8 encoded string with a length limit of 1024
// characters.
string name = 1;
// Unique chunk ID of the current chunk.
string id = 2;
// Content is a string from a document (parsed content).
string content = 3;
// Output only. Represents the relevance score based on similarity.
// Higher score indicates higher chunk relevance.
// The score is in range [-1.0, 1.0].
// Only populated on
// [SearchResponse][google.cloud.discoveryengine.v1.SearchResponse].
optional double relevance_score = 8
[(google.api.field_behavior) = OUTPUT_ONLY];
// Metadata of the document from the current chunk.
DocumentMetadata document_metadata = 5;
// Output only. This field is OUTPUT_ONLY.
// It contains derived data that are not in the original input document.
google.protobuf.Struct derived_struct_data = 4
[(google.api.field_behavior) = OUTPUT_ONLY];
// Page span of the chunk.
PageSpan page_span = 6;
// Output only. Metadata of the current chunk.
ChunkMetadata chunk_metadata = 7 [(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. Image Data URLs if the current chunk contains images.
// Data URLs are composed of four parts: a prefix (data:), a MIME type
// indicating the type of data, an optional base64 token if non-textual,
// and the data itself:
// data:[<mediatype>][;base64],<data>
repeated string data_urls = 9 [(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. Annotation contents if the current chunk contains annotations.
repeated string annotation_contents = 11
[(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. The annotation metadata includes structured content in the
// current chunk.
repeated AnnotationMetadata annotation_metadata = 12
[(google.api.field_behavior) = OUTPUT_ONLY];
}