Package google.cloud.discoveryengine.v1beta

Index

CompletionService

Service for Auto-Completion.

AdvancedCompleteQuery

rpc AdvancedCompleteQuery(AdvancedCompleteQueryRequest) returns (AdvancedCompleteQueryResponse)

Completes the user input with advanced keyword suggestions.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the completionConfig resource:

  • discoveryengine.completionConfigs.completeQuery

For more information, see the IAM documentation.

CompleteQuery

rpc CompleteQuery(CompleteQueryRequest) returns (CompleteQueryResponse)

Completes the specified user input with keyword suggestions.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the dataStore resource:

  • discoveryengine.dataStores.completeQuery

For more information, see the IAM documentation.

ImportCompletionSuggestions

rpc ImportCompletionSuggestions(ImportCompletionSuggestionsRequest) returns (Operation)

Imports CompletionSuggestions for a DataStore.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

ImportSuggestionDenyListEntries

rpc ImportSuggestionDenyListEntries(ImportSuggestionDenyListEntriesRequest) returns (Operation)

Imports all SuggestionDenyListEntry for a DataStore.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.suggestionDenyListEntries.import

For more information, see the IAM documentation.

PurgeCompletionSuggestions

rpc PurgeCompletionSuggestions(PurgeCompletionSuggestionsRequest) returns (Operation)

Permanently deletes all CompletionSuggestions for a DataStore.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

PurgeSuggestionDenyListEntries

rpc PurgeSuggestionDenyListEntries(PurgeSuggestionDenyListEntriesRequest) returns (Operation)

Permanently deletes all SuggestionDenyListEntry for a DataStore.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.suggestionDenyListEntries.purge

For more information, see the IAM documentation.

ControlService

Service for performing CRUD operations on Controls. Controls allow for custom logic to be implemented in the serving path. Controls need to be attached to a Serving Config to be considered during a request.

CreateControl

rpc CreateControl(CreateControlRequest) returns (Control)

Creates a Control.

By default 1000 controls are allowed for a data store. A request can be submitted to adjust this limit. If the Control to create already exists, an ALREADY_EXISTS error is returned.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.controls.create

For more information, see the IAM documentation.

DeleteControl

rpc DeleteControl(DeleteControlRequest) returns (Empty)

Deletes a Control.

If the Control to delete does not exist, a NOT_FOUND error is returned.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.controls.delete

For more information, see the IAM documentation.

GetControl

rpc GetControl(GetControlRequest) returns (Control)

Gets a Control.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.controls.get

For more information, see the IAM documentation.

ListControls

rpc ListControls(ListControlsRequest) returns (ListControlsResponse)

Lists all Controls by their parent DataStore.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.controls.list

For more information, see the IAM documentation.

UpdateControl

rpc UpdateControl(UpdateControlRequest) returns (Control)

Updates a Control.

Control action type cannot be changed. If the Control to update does not exist, a NOT_FOUND error is returned.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.controls.update

For more information, see the IAM documentation.

ConversationalSearchService

Service for conversational search.

AnswerQuery

rpc AnswerQuery(AnswerQueryRequest) returns (AnswerQueryResponse)

Answer query method.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the servingConfig resource:

  • discoveryengine.servingConfigs.answer

For more information, see the IAM documentation.

ConverseConversation

rpc ConverseConversation(ConverseConversationRequest) returns (ConverseConversationResponse)

Converses a conversation.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.conversations.converse

For more information, see the IAM documentation.

CreateConversation

rpc CreateConversation(CreateConversationRequest) returns (Conversation)

Creates a Conversation.

If the Conversation to create already exists, an ALREADY_EXISTS error is returned.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.conversations.create

For more information, see the IAM documentation.

CreateSession

rpc CreateSession(CreateSessionRequest) returns (Session)

Creates a Session.

If the Session to create already exists, an ALREADY_EXISTS error is returned.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.sessions.create

For more information, see the IAM documentation.

DeleteConversation

rpc DeleteConversation(DeleteConversationRequest) returns (Empty)

Deletes a Conversation.

If the Conversation to delete does not exist, a NOT_FOUND error is returned.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.conversations.delete

For more information, see the IAM documentation.

DeleteSession

rpc DeleteSession(DeleteSessionRequest) returns (Empty)

Deletes a Session.

If the Session to delete does not exist, a NOT_FOUND error is returned.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.sessions.delete

For more information, see the IAM documentation.

GetAnswer

rpc GetAnswer(GetAnswerRequest) returns (Answer)

Gets a Answer.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.answers.get

For more information, see the IAM documentation.

GetConversation

rpc GetConversation(GetConversationRequest) returns (Conversation)

Gets a Conversation.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.conversations.get

For more information, see the IAM documentation.

GetSession

rpc GetSession(GetSessionRequest) returns (Session)

Gets a Session.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.sessions.get

For more information, see the IAM documentation.

ListConversations

rpc ListConversations(ListConversationsRequest) returns (ListConversationsResponse)

Lists all Conversations by their parent DataStore.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.conversations.list

For more information, see the IAM documentation.

ListSessions

rpc ListSessions(ListSessionsRequest) returns (ListSessionsResponse)

Lists all Sessions by their parent DataStore.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.sessions.list

For more information, see the IAM documentation.

UpdateConversation

rpc UpdateConversation(UpdateConversationRequest) returns (Conversation)

Updates a Conversation.

Conversation action type cannot be changed. If the Conversation to update does not exist, a NOT_FOUND error is returned.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.conversations.update

For more information, see the IAM documentation.

UpdateSession

rpc UpdateSession(UpdateSessionRequest) returns (Session)

Updates a Session.

Session action type cannot be changed. If the Session to update does not exist, a NOT_FOUND error is returned.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.sessions.update

For more information, see the IAM documentation.

DataStoreService

Service for managing DataStore configuration.

CreateDataStore

rpc CreateDataStore(CreateDataStoreRequest) returns (Operation)

Creates a DataStore.

DataStore is for storing Documents. To serve these documents for Search, or Recommendation use case, an Engine needs to be created separately.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.dataStores.create

For more information, see the IAM documentation.

DeleteDataStore

rpc DeleteDataStore(DeleteDataStoreRequest) returns (Operation)

Deletes a DataStore.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.dataStores.delete

For more information, see the IAM documentation.

GetDataStore

rpc GetDataStore(GetDataStoreRequest) returns (DataStore)

Gets a DataStore.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.dataStores.get

For more information, see the IAM documentation.

ListDataStores

rpc ListDataStores(ListDataStoresRequest) returns (ListDataStoresResponse)

Lists all the DataStores associated with the project.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.dataStores.list

For more information, see the IAM documentation.

UpdateDataStore

rpc UpdateDataStore(UpdateDataStoreRequest) returns (DataStore)

Updates a DataStore

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.dataStores.update

For more information, see the IAM documentation.

DocumentService

Service for ingesting Document information of the customer's website.

BatchGetDocumentsMetadata

rpc BatchGetDocumentsMetadata(BatchGetDocumentsMetadataRequest) returns (BatchGetDocumentsMetadataResponse)

Gets index freshness metadata for Documents. Supported for website search only.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.documents.batchGetDocumentsMetadata

For more information, see the IAM documentation.

CreateDocument

rpc CreateDocument(CreateDocumentRequest) returns (Document)

Creates a Document.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.documents.create

For more information, see the IAM documentation.

DeleteDocument

rpc DeleteDocument(DeleteDocumentRequest) returns (Empty)

Deletes a Document.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.documents.delete

For more information, see the IAM documentation.

GetDocument

rpc GetDocument(GetDocumentRequest) returns (Document)

Gets a Document.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.documents.get

For more information, see the IAM documentation.

ImportDocuments

rpc ImportDocuments(ImportDocumentsRequest) returns (Operation)

Bulk import of multiple Documents. Request processing may be synchronous. Non-existing items are created.

Note: It is possible for a subset of the Documents to be successfully updated.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.documents.import

For more information, see the IAM documentation.

ListDocuments

rpc ListDocuments(ListDocumentsRequest) returns (ListDocumentsResponse)

Gets a list of Documents.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.documents.list

For more information, see the IAM documentation.

PurgeDocuments

rpc PurgeDocuments(PurgeDocumentsRequest) returns (Operation)

Permanently deletes all selected Documents in a branch.

This process is asynchronous. Depending on the number of Documents to be deleted, this operation can take hours to complete. Before the delete operation completes, some Documents might still be returned by DocumentService.GetDocument or DocumentService.ListDocuments.

To get a list of the Documents to be deleted, set PurgeDocumentsRequest.force to false.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.documents.purge

For more information, see the IAM documentation.

UpdateDocument

rpc UpdateDocument(UpdateDocumentRequest) returns (Document)

Updates a Document.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.documents.update

For more information, see the IAM documentation.

EngineService

Service for managing Engine configuration.

CreateEngine

rpc CreateEngine(CreateEngineRequest) returns (Operation)

Creates a Engine.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.engines.create

For more information, see the IAM documentation.

DeleteEngine

rpc DeleteEngine(DeleteEngineRequest) returns (Operation)

Deletes a Engine.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.engines.delete

For more information, see the IAM documentation.

GetEngine

rpc GetEngine(GetEngineRequest) returns (Engine)

Gets a Engine.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.engines.get

For more information, see the IAM documentation.

ListEngines

rpc ListEngines(ListEnginesRequest) returns (ListEnginesResponse)

Lists all the Engines associated with the project.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.engines.list

For more information, see the IAM documentation.

PauseEngine

rpc PauseEngine(PauseEngineRequest) returns (Engine)

Pauses the training of an existing engine. Only applicable if SolutionType is SOLUTION_TYPE_RECOMMENDATION.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.engines.pause

For more information, see the IAM documentation.

ResumeEngine

rpc ResumeEngine(ResumeEngineRequest) returns (Engine)

Resumes the training of an existing engine. Only applicable if SolutionType is SOLUTION_TYPE_RECOMMENDATION.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.engines.resume

For more information, see the IAM documentation.

TuneEngine

rpc TuneEngine(TuneEngineRequest) returns (Operation)

Tunes an existing engine. Only applicable if SolutionType is SOLUTION_TYPE_RECOMMENDATION.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.engines.tune

For more information, see the IAM documentation.

UpdateEngine

rpc UpdateEngine(UpdateEngineRequest) returns (Engine)

Updates an Engine

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.engines.update

For more information, see the IAM documentation.

EvaluationService

Service for managing Evaluations,

CreateEvaluation

rpc CreateEvaluation(CreateEvaluationRequest) returns (Operation)

Creates a Evaluation.

Upon creation, the evaluation will be automatically triggered and begin execution.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.evaluations.create

For more information, see the IAM documentation.

GetEvaluation

rpc GetEvaluation(GetEvaluationRequest) returns (Evaluation)

Gets a Evaluation.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.evaluations.get

For more information, see the IAM documentation.

ListEvaluationResults

rpc ListEvaluationResults(ListEvaluationResultsRequest) returns (ListEvaluationResultsResponse)

Gets a list of results for a given a Evaluation.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the evaluation resource:

  • discoveryengine.evaluations.get

For more information, see the IAM documentation.

ListEvaluations

rpc ListEvaluations(ListEvaluationsRequest) returns (ListEvaluationsResponse)

Gets a list of Evaluations.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.evaluations.list

For more information, see the IAM documentation.

GroundedGenerationService

Service for grounded generation.

CheckGrounding

rpc CheckGrounding(CheckGroundingRequest) returns (CheckGroundingResponse)

Performs a grounding check.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the groundingConfig resource:

  • discoveryengine.groundingConfigs.check

For more information, see the IAM documentation.

ProjectService

Service for operations on the Project.

ProvisionProject

rpc ProvisionProject(ProvisionProjectRequest) returns (Operation)

Provisions the project resource. During the process, related systems will get prepared and initialized.

Caller must read the Terms for data use, and optionally specify in request to provide consent to that service terms.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.projects.provision

For more information, see the IAM documentation.

RankService

Service for ranking text records.

Rank

rpc Rank(RankRequest) returns (RankResponse)

Ranks a list of text records based on the given input query.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the rankingConfig resource:

  • discoveryengine.rankingConfigs.rank

For more information, see the IAM documentation.

RecommendationService

Service for making recommendations.

Recommend

rpc Recommend(RecommendRequest) returns (RecommendResponse)

Makes a recommendation, which requires a contextual user event.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the servingConfig resource:

  • discoveryengine.servingConfigs.recommend

For more information, see the IAM documentation.

SampleQueryService

Service for managing SampleQuerys,

CreateSampleQuery

rpc CreateSampleQuery(CreateSampleQueryRequest) returns (SampleQuery)

Creates a SampleQuery

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.sampleQueries.create

For more information, see the IAM documentation.

DeleteSampleQuery

rpc DeleteSampleQuery(DeleteSampleQueryRequest) returns (Empty)

Deletes a SampleQuery.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.sampleQueries.delete

For more information, see the IAM documentation.

GetSampleQuery

rpc GetSampleQuery(GetSampleQueryRequest) returns (SampleQuery)

Gets a SampleQuery.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.sampleQueries.get

For more information, see the IAM documentation.

ImportSampleQueries

rpc ImportSampleQueries(ImportSampleQueriesRequest) returns (Operation)

Bulk import of multiple SampleQuerys. Sample queries that already exist may be deleted.

Note: It is possible for a subset of the SampleQuerys to be successfully imported.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.sampleQueries.import

For more information, see the IAM documentation.

ListSampleQueries

rpc ListSampleQueries(ListSampleQueriesRequest) returns (ListSampleQueriesResponse)

Gets a list of SampleQuerys.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.sampleQueries.list

For more information, see the IAM documentation.

UpdateSampleQuery

rpc UpdateSampleQuery(UpdateSampleQueryRequest) returns (SampleQuery)

Updates a SampleQuery.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.sampleQueries.update

For more information, see the IAM documentation.

SampleQuerySetService

Service for managing SampleQuerySets,

CreateSampleQuerySet

rpc CreateSampleQuerySet(CreateSampleQuerySetRequest) returns (SampleQuerySet)

Creates a SampleQuerySet

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.sampleQuerySets.create

For more information, see the IAM documentation.

DeleteSampleQuerySet

rpc DeleteSampleQuerySet(DeleteSampleQuerySetRequest) returns (Empty)

Deletes a SampleQuerySet.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.sampleQuerySets.delete

For more information, see the IAM documentation.

GetSampleQuerySet

rpc GetSampleQuerySet(GetSampleQuerySetRequest) returns (SampleQuerySet)

Gets a SampleQuerySet.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.sampleQuerySets.get

For more information, see the IAM documentation.

ListSampleQuerySets

rpc ListSampleQuerySets(ListSampleQuerySetsRequest) returns (ListSampleQuerySetsResponse)

Gets a list of SampleQuerySets.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.sampleQuerySets.list

For more information, see the IAM documentation.

UpdateSampleQuerySet

rpc UpdateSampleQuerySet(UpdateSampleQuerySetRequest) returns (SampleQuerySet)

Updates a SampleQuerySet.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.sampleQuerySets.update

For more information, see the IAM documentation.

SchemaService

Service for managing Schemas.

CreateSchema

rpc CreateSchema(CreateSchemaRequest) returns (Operation)

Creates a Schema.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.schemas.create

For more information, see the IAM documentation.

DeleteSchema

rpc DeleteSchema(DeleteSchemaRequest) returns (Operation)

Deletes a Schema.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.schemas.delete

For more information, see the IAM documentation.

GetSchema

rpc GetSchema(GetSchemaRequest) returns (Schema)

Gets a Schema.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.schemas.get

For more information, see the IAM documentation.

ListSchemas

rpc ListSchemas(ListSchemasRequest) returns (ListSchemasResponse)

Gets a list of Schemas.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.schemas.list

For more information, see the IAM documentation.

UpdateSchema

rpc UpdateSchema(UpdateSchemaRequest) returns (Operation)

Updates a Schema.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.schemas.update

For more information, see the IAM documentation.

SearchService

Service for search.

Search

rpc Search(SearchRequest) returns (SearchResponse)

Performs a search.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the servingConfig resource:

  • discoveryengine.servingConfigs.search

For more information, see the IAM documentation.

SearchLite

rpc SearchLite(SearchRequest) returns (SearchResponse)

Performs a search. Similar to the SearchService.Search method, but a lite version that allows API key for authentication, where OAuth and IAM checks are not required.

Only public website search is supported by this method. If data stores and engines not associated with public website search are specified, a FAILED_PRECONDITION error is returned.

This method can be used for easy onboarding without having to implement an authentication backend. However, it is strongly recommended to use SearchService.Search instead with required OAuth and IAM checks to provide better data security.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

SearchTuningService

Service for search tuning.

ListCustomModels

rpc ListCustomModels(ListCustomModelsRequest) returns (ListCustomModelsResponse)

Gets a list of all the custom models.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

TrainCustomModel

rpc TrainCustomModel(TrainCustomModelRequest) returns (Operation)

Trains a custom model.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the dataStore resource:

  • discoveryengine.dataStores.trainCustomModel

For more information, see the IAM documentation.

ServingConfigService

Service for operations related to ServingConfig.

GetServingConfig

rpc GetServingConfig(GetServingConfigRequest) returns (ServingConfig)

Gets a ServingConfig.

Returns a NotFound error if the ServingConfig does not exist.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.servingConfigs.get

For more information, see the IAM documentation.

ListServingConfigs

rpc ListServingConfigs(ListServingConfigsRequest) returns (ListServingConfigsResponse)

Lists all ServingConfigs linked to this dataStore.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.servingConfigs.list

For more information, see the IAM documentation.

UpdateServingConfig

rpc UpdateServingConfig(UpdateServingConfigRequest) returns (ServingConfig)

Updates a ServingConfig.

Returns a NOT_FOUND error if the ServingConfig does not exist.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.servingConfigs.update

For more information, see the IAM documentation.

SiteSearchEngineService

Service for managing site search related resources.

BatchCreateTargetSites

rpc BatchCreateTargetSites(BatchCreateTargetSitesRequest) returns (Operation)

Creates TargetSite in a batch.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.targetSites.batchCreate

For more information, see the IAM documentation.

BatchVerifyTargetSites

rpc BatchVerifyTargetSites(BatchVerifyTargetSitesRequest) returns (Operation)

Verify target sites' ownership and validity. This API sends all the target sites under site search engine for verification.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.siteSearchEngines.batchVerifyTargetSites

For more information, see the IAM documentation.

CreateTargetSite

rpc CreateTargetSite(CreateTargetSiteRequest) returns (Operation)

Creates a TargetSite.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.targetSites.create

For more information, see the IAM documentation.

DeleteTargetSite

rpc DeleteTargetSite(DeleteTargetSiteRequest) returns (Operation)

Deletes a TargetSite.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.targetSites.delete

For more information, see the IAM documentation.

DisableAdvancedSiteSearch

rpc DisableAdvancedSiteSearch(DisableAdvancedSiteSearchRequest) returns (Operation)

Downgrade from advanced site search to basic site search.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the siteSearchEngine resource:

  • discoveryengine.siteSearchEngines.disableAdvancedSiteSearch

For more information, see the IAM documentation.

EnableAdvancedSiteSearch

rpc EnableAdvancedSiteSearch(EnableAdvancedSiteSearchRequest) returns (Operation)

Upgrade from basic site search to advanced site search.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the siteSearchEngine resource:

  • discoveryengine.siteSearchEngines.enableAdvancedSiteSearch

For more information, see the IAM documentation.

FetchDomainVerificationStatus

rpc FetchDomainVerificationStatus(FetchDomainVerificationStatusRequest) returns (FetchDomainVerificationStatusResponse)

Returns list of target sites with its domain verification status. This method can only be called under data store with BASIC_SITE_SEARCH state at the moment.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the siteSearchEngine resource:

  • discoveryengine.siteSearchEngines.fetchDomainVerificationStatus

For more information, see the IAM documentation.

GetSiteSearchEngine

rpc GetSiteSearchEngine(GetSiteSearchEngineRequest) returns (SiteSearchEngine)

Gets the SiteSearchEngine.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.siteSearchEngines.get

For more information, see the IAM documentation.

GetTargetSite

rpc GetTargetSite(GetTargetSiteRequest) returns (TargetSite)

Gets a TargetSite.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.targetSites.get

For more information, see the IAM documentation.

ListTargetSites

rpc ListTargetSites(ListTargetSitesRequest) returns (ListTargetSitesResponse)

Gets a list of TargetSites.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.targetSites.list

For more information, see the IAM documentation.

RecrawlUris

rpc RecrawlUris(RecrawlUrisRequest) returns (Operation)

Request on-demand recrawl for a list of URIs.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the siteSearchEngine resource:

  • discoveryengine.siteSearchEngines.recrawlUris

For more information, see the IAM documentation.

UpdateTargetSite

rpc UpdateTargetSite(UpdateTargetSiteRequest) returns (Operation)

Updates a TargetSite.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.targetSites.update

For more information, see the IAM documentation.

UserEventService

Service for ingesting end user actions on a website to Discovery Engine API.

CollectUserEvent

rpc CollectUserEvent(CollectUserEventRequest) returns (HttpBody)

Writes a single user event from the browser. This uses a GET request to due to browser restriction of POST-ing to a third-party domain.

This method is used only by the Discovery Engine API JavaScript pixel and Google Tag Manager. Users should not call this method directly.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

ImportUserEvents

rpc ImportUserEvents(ImportUserEventsRequest) returns (Operation)

Bulk import of user events. Request processing might be synchronous. Events that already exist are skipped. Use this method for backfilling historical user events.

Operation.response is of type ImportResponse. Note that it is possible for a subset of the items to be successfully inserted. Operation.metadata is of type ImportMetadata.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.userEvents.import

For more information, see the IAM documentation.

PurgeUserEvents

rpc PurgeUserEvents(PurgeUserEventsRequest) returns (Operation)

Deletes permanently all user events specified by the filter provided. Depending on the number of events specified by the filter, this operation could take hours or days to complete. To test a filter, use the list command first.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.userEvents.purge

For more information, see the IAM documentation.

WriteUserEvent

rpc WriteUserEvent(WriteUserEventRequest) returns (UserEvent)

Writes a single user event.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the parent resource:

  • discoveryengine.userEvents.create

For more information, see the IAM documentation.

AdvancedCompleteQueryRequest

Request message for CompletionService.AdvancedCompleteQuery method. .

Fields
completion_config

string

Required. The completion_config of the parent dataStore or engine resource name for which the completion is performed, such as projects/*/locations/global/collections/default_collection/dataStores/*/completionConfig projects/*/locations/global/collections/default_collection/engines/*/completionConfig.

query

string

Required. The typeahead input used to fetch suggestions. Maximum length is 128 characters.

The query can not be empty for most of the suggestion types. If it is empty, an INVALID_ARGUMENT error is returned. The exception is when the suggestion_types contains only the type RECENT_SEARCH, the query can be an empty string. The is called "zero prefix" feature, which returns user's recently searched queries given the empty query.

query_model

string

Specifies the autocomplete data model. This overrides any model specified in the Configuration > Autocomplete section of the Cloud console. Currently supported values:

  • document - Using suggestions generated from user-imported documents.
  • search-history - Using suggestions generated from the past history of SearchService.Search API calls. Do not use it when there is no traffic for Search API.
  • user-event - Using suggestions generated from user-imported search events.
  • document-completable - Using suggestions taken directly from user-imported document fields marked as completable.

Default values:

  • document is the default model for regular dataStores.
  • search-history is the default model for site search dataStores.
user_pseudo_id

string

A unique identifier for tracking visitors. For example, this could be implemented with an HTTP cookie, which should be able to uniquely identify a visitor on a single device. This unique identifier should not change if the visitor logs in or out of the website.

This field should NOT have a fixed value such as unknown_visitor.

This should be the same identifier as UserEvent.user_pseudo_id and SearchRequest.user_pseudo_id.

The field must be a UTF-8 encoded string with a length limit of 128

user_info

UserInfo

Optional. Information about the end user.

This should be the same identifier information as UserEvent.user_info and SearchRequest.user_info.

include_tail_suggestions

bool

Indicates if tail suggestions should be returned if there are no suggestions that match the full query. Even if set to true, if there are suggestions that match the full query, those are returned and no tail suggestions are returned.

boost_spec

BoostSpec

Optional. Specification to boost suggestions matching the condition.

suggestion_types[]

SuggestionType

Optional. Suggestion types to return. If empty or unspecified, query suggestions are returned. Only one suggestion type is supported at the moment.

BoostSpec

Specification to boost suggestions based on the condtion of the suggestion.

Fields
condition_boost_specs[]

ConditionBoostSpec

Condition boost specifications. If a suggestion matches multiple conditions in the specifictions, boost values from these specifications are all applied and combined in a non-linear way. Maximum number of specifications is 20.

Note: Currently only support language condition boost.

ConditionBoostSpec

Boost applies to suggestions which match a condition.

Fields
condition

string

An expression which specifies a boost condition. The syntax is the same as filter expression syntax. Currently, the only supported condition is a list of BCP-47 lang codes.

Example:

  • To boost suggestions in languages en or fr: (lang_code: ANY("en", "fr"))
boost

float

Strength of the boost, which should be in [-1, 1]. Negative boost means demotion. Default is 0.0.

Setting to 1.0 gives the suggestions a big promotion. However, it does not necessarily mean that the top result will be a boosted suggestion.

Setting to -1.0 gives the suggestions a big demotion. However, other suggestions that are relevant might still be shown.

Setting to 0.0 means no boost applied. The boosting condition is ignored.

SuggestionType

Suggestion type to return.

Enums
SUGGESTION_TYPE_UNSPECIFIED Default value.
QUERY Returns query suggestions.
PEOPLE Returns people suggestions.
CONTENT Returns content suggestions.
GOOGLE_WORKSPACE Returns Google Workspace suggestions.

AdvancedCompleteQueryResponse

Response message for CompletionService.AdvancedCompleteQuery method.

Fields
query_suggestions[]

QuerySuggestion

Results of the matched query suggestions. The result list is ordered and the first result is a top suggestion.

tail_match_triggered

bool

True if the returned suggestions are all tail suggestions.

For tail matching to be triggered, include_tail_suggestions in the request must be true and there must be no suggestions that match the full query.

people_suggestions[]

PersonSuggestion

Results of the matched people suggestions. The result list is ordered and the first result is the top suggestion.

content_suggestions[]

ContentSuggestion

Results of the matched content suggestions. The result list is ordered and the first result is the top suggestion.

recent_search_suggestions[]

RecentSearchSuggestion

Results of the matched "recent search" suggestions. The result list is ordered and the first result is the top suggestion.

ContentSuggestion

Suggestions as content.

Fields
suggestion

string

The suggestion for the query.

content_type

ContentType

The type of the content suggestion.

document

Document

The document data snippet in the suggestion. Only a subset of fields will be populated.

data_store

string

The name of the dataStore that this suggestion belongs to.

ContentType

The type of the content returned for content suggestions.

Enums
CONTENT_TYPE_UNSPECIFIED Default value.
GOOGLE_WORKSPACE The suggestion is from a Google Workspace source.
THIRD_PARTY The suggestion is from a third party source.

PersonSuggestion

Suggestions as people.

Fields
suggestion

string

The suggestion for the query.

person_type

PersonType

The type of the person.

document

Document

The document data snippet in the suggestion. Only a subset of fields is populated.

data_store

string

The name of the dataStore that this suggestion belongs to.

PersonType

The type of the person based on the source.

Enums
PERSON_TYPE_UNSPECIFIED Default value.
CLOUD_IDENTITY The suggestion is from a GOOGLE_IDENTITY source.
THIRD_PARTY_IDENTITY The suggestion is from a THIRD_PARTY_IDENTITY source.

QuerySuggestion

Suggestions as search queries.

Fields
suggestion

string

The suggestion for the query.

completable_field_paths[]

string

The unique document field paths that serve as the source of this suggestion if it was generated from completable fields.

This field is only populated for the document-completable model.

data_store[]

string

The name of the dataStore that this suggestion belongs to.

RecentSearchSuggestion

Suggestions from recent search history.

Fields
suggestion

string

The suggestion for the query.

recent_search_time

Timestamp

The time when this recent rearch happened.

AdvancedSiteSearchConfig

This type has no fields.

Configuration data for advance site search.

AlloyDbSource

AlloyDB source import data from.

Fields
project_id

string

The project ID that contains the AlloyDB source. Has a length limit of 128 characters. If not specified, inherits the project ID from the parent request.

location_id

string

Required. The AlloyDB location to copy the data from with a length limit of 256 characters.

cluster_id

string

Required. The AlloyDB cluster to copy the data from with a length limit of 256 characters.

database_id

string

Required. The AlloyDB database to copy the data from with a length limit of 256 characters.

table_id

string

Required. The AlloyDB table to copy the data from with a length limit of 256 characters.

gcs_staging_dir

string

Intermediate Cloud Storage directory used for the import with a length limit of 2,000 characters. Can be specified if one wants to have the AlloyDB export to a specific Cloud Storage directory.

Ensure that the AlloyDB service account has the necessary Cloud Storage Admin permissions to access the specified Cloud Storage directory.

Answer

Defines an answer.

Fields
name

string

Immutable. Fully qualified name projects/{project}/locations/global/collections/{collection}/engines/{engine}/sessions/*/answers/*

state

State

The state of the answer generation.

answer_text

string

The textual answer.

citations[]

Citation

Citations.

references[]

Reference

References.

related_questions[]

string

Suggested related questions.

steps[]

Step

Answer generation steps.

query_understanding_info

QueryUnderstandingInfo

Query understanding information.

answer_skipped_reasons[]

AnswerSkippedReason

Additional answer-skipped reasons. This provides the reason for ignored cases. If nothing is skipped, this field is not set.

create_time

Timestamp

Output only. Answer creation timestamp.

complete_time

Timestamp

Output only. Answer completed timestamp.

AnswerSkippedReason

An enum for answer skipped reasons.

Enums
ANSWER_SKIPPED_REASON_UNSPECIFIED Default value. The answer skipped reason is not specified.
ADVERSARIAL_QUERY_IGNORED The adversarial query ignored case.
NON_ANSWER_SEEKING_QUERY_IGNORED

The non-answer seeking query ignored case

Google skips the answer if the query is chit chat.

OUT_OF_DOMAIN_QUERY_IGNORED

The out-of-domain query ignored case.

Google skips the answer if there are no high-relevance search results.

POTENTIAL_POLICY_VIOLATION

The potential policy violation case.

Google skips the answer if there is a potential policy violation detected. This includes content that may be violent or toxic.

NO_RELEVANT_CONTENT

The no relevant content case.

Google skips the answer if there is no relevant content in the retrieved search results.

JAIL_BREAKING_QUERY_IGNORED

The jail-breaking query ignored case.

For example, "Reply in the tone of a competing company's CEO". Google skips the answer if the query is classified as a jail-breaking query.

CUSTOMER_POLICY_VIOLATION

The customer policy violation case.

Google skips the summary if there is a customer policy violation detected. The policy is defined by the customer.

NON_ANSWER_SEEKING_QUERY_IGNORED_V2

The non-answer seeking query ignored case.

Google skips the answer if the query doesn't have clear intent.

LOW_GROUNDED_ANSWER

The low-grounded answer case.

Google skips the answer if a well grounded answer was unable to be generated.

Citation

Citation info for a segment.

Fields
start_index

int64

Index indicates the start of the segment, measured in bytes (UTF-8 unicode).

end_index

int64

End of the attributed segment, exclusive.

sources[]

CitationSource

Citation sources for the attributed segment.

CitationSource

Citation source.

Fields
reference_id

string

ID of the citation source.

QueryUnderstandingInfo

Query understanding information.

Fields
query_classification_info[]

QueryClassificationInfo

Query classification information.

QueryClassificationInfo

Query classification information.

Fields
type

Type

Query classification type.

positive

bool

Classification output.

Type

Query classification types.

Enums
TYPE_UNSPECIFIED Unspecified query classification type.
ADVERSARIAL_QUERY Adversarial query classification type.
NON_ANSWER_SEEKING_QUERY Non-answer-seeking query classification type, for chit chat.
JAIL_BREAKING_QUERY Jail-breaking query classification type.
NON_ANSWER_SEEKING_QUERY_V2 Non-answer-seeking query classification type, for no clear intent.

Reference

Reference.

Fields
Union field content. Search result content. content can be only one of the following:
unstructured_document_info

UnstructuredDocumentInfo

Unstructured document information.

chunk_info

ChunkInfo

Chunk information.

structured_document_info

StructuredDocumentInfo

Structured document information.

ChunkInfo

Chunk information.

Fields
chunk

string

Chunk resource name.

content

string

Chunk textual content.

document_metadata

DocumentMetadata

Document metadata.

relevance_score

float

The relevance of the chunk for a given query. Values range from 0.0 (completely irrelevant) to 1.0 (completely relevant). This value is for informational purpose only. It may change for the same query and chunk at any time due to a model retraining or change in implementation.

DocumentMetadata

Document metadata.

Fields
document

string

Document resource name.

uri

string

URI for the document.

title

string

Title.

page_identifier

string

Page identifier.

struct_data

Struct

The structured JSON metadata for the document. It is populated from the struct data from the Chunk in search result.

StructuredDocumentInfo

Structured search information.

Fields
document

string

Document resource name.

struct_data

Struct

Structured search data.

UnstructuredDocumentInfo

Unstructured document information.

Fields
document

string

Document resource name.

uri

string

URI for the document.

title

string

Title.

chunk_contents[]

ChunkContent

List of cited chunk contents derived from document content.

struct_data

Struct

The structured JSON metadata for the document. It is populated from the struct data from the Chunk in search result.

ChunkContent

Chunk content.

Fields
content

string

Chunk textual content.

page_identifier

string

Page identifier.

relevance_score

float

The relevance of the chunk for a given query. Values range from 0.0 (completely irrelevant) to 1.0 (completely relevant). This value is for informational purpose only. It may change for the same query and chunk at any time due to a model retraining or change in implementation.

State

Enumeration of the state of the answer generation.

Enums
STATE_UNSPECIFIED Unknown.
IN_PROGRESS Answer generation is currently in progress.
FAILED Answer generation currently failed.
SUCCEEDED Answer generation has succeeded.

Step

Step information.

Fields
state

State

The state of the step.

description

string

The description of the step.

thought

string

The thought of the step.

actions[]

Action

Actions.

Action

Action.

Fields
observation

Observation

Observation.

Union field action. The action. action can be only one of the following:
search_action

SearchAction

Search action.

Observation

Observation.

Fields
search_results[]

SearchResult

Search results observed by the search action, it can be snippets info or chunk info, depending on the citation type set by the user.

SearchResult

Fields
document

string

Document resource name.

uri

string

URI for the document.

title

string

Title.

snippet_info[]

SnippetInfo

If citation_type is DOCUMENT_LEVEL_CITATION, populate document level snippets.

chunk_info[]

ChunkInfo

If citation_type is CHUNK_LEVEL_CITATION and chunk mode is on, populate chunk info.

struct_data

Struct

Data representation. The structured JSON data for the document. It's populated from the struct data from the Document, or the Chunk in search result.

ChunkInfo

Chunk information.

Fields
chunk

string

Chunk resource name.

content

string

Chunk textual content.

relevance_score

float

The relevance of the chunk for a given query. Values range from 0.0 (completely irrelevant) to 1.0 (completely relevant). This value is for informational purpose only. It may change for the same query and chunk at any time due to a model retraining or change in implementation.

SnippetInfo

Snippet information.

Fields
snippet

string

Snippet content.

snippet_status

string

Status of the snippet defined by the search team.

SearchAction

Search action.

Fields
query

string

The query to search.

State

Enumeration of the state of the step.

Enums
STATE_UNSPECIFIED Unknown.
IN_PROGRESS Step is currently in progress.
FAILED Step currently failed.
SUCCEEDED Step has succeeded.

AnswerQueryRequest

Request message for ConversationalSearchService.AnswerQuery method.

Fields
serving_config

string

Required. The resource name of the Search serving config, such as projects/*/locations/global/collections/default_collection/engines/*/servingConfigs/default_serving_config, or projects/*/locations/global/collections/default_collection/dataStores/*/servingConfigs/default_serving_config. This field is used to identify the serving configuration name, set of models used to make the search.

query

Query

Required. Current user query.

session

string

The session resource name. Not required.

When session field is not set, the API is in sessionless mode.

We support auto session mode: users can use the wildcard symbol - as session ID. A new ID will be automatically generated and assigned.

safety_spec

SafetySpec

Model specification.

related_questions_spec

RelatedQuestionsSpec

Related questions specification.

grounding_spec

GroundingSpec

Optional. Grounding specification.

answer_generation_spec

AnswerGenerationSpec

Answer generation specification.

search_spec

SearchSpec

Search specification.

query_understanding_spec

QueryUnderstandingSpec

Query understanding specification.

asynchronous_mode
(deprecated)

bool

Deprecated: This field is deprecated. Streaming Answer API will be supported.

Asynchronous mode control.

If enabled, the response will be returned with answer/session resource name without final answer. The API users need to do the polling to get the latest status of answer/session by calling ConversationalSearchService.GetAnswer or ConversationalSearchService.GetSession method.

user_pseudo_id

string

A unique identifier for tracking visitors. For example, this could be implemented with an HTTP cookie, which should be able to uniquely identify a visitor on a single device. This unique identifier should not change if the visitor logs in or out of the website.

This field should NOT have a fixed value such as unknown_visitor.

The field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an INVALID_ARGUMENT error is returned.

user_labels

map<string, string>

The user labels applied to a resource must meet the following requirements:

  • Each resource can have multiple labels, up to a maximum of 64.
  • Each label must be a key-value pair.
  • Keys have a minimum length of 1 character and a maximum length of 63 characters and cannot be empty. Values can be empty and have a maximum length of 63 characters.
  • Keys and values can contain only lowercase letters, numeric characters, underscores, and dashes. All characters must use UTF-8 encoding, and international characters are allowed.
  • The key portion of a label must be unique. However, you can use the same key with multiple resources.
  • Keys must start with a lowercase letter or international character.

See Google Cloud Document for more details.

AnswerGenerationSpec

Answer generation specification.

Fields
model_spec

ModelSpec

Answer generation model specification.

prompt_spec

PromptSpec

Answer generation prompt specification.

include_citations

bool

Specifies whether to include citation metadata in the answer. The default value is false.

answer_language_code

string

Language code for Answer. Use language tags defined by BCP47. Note: This is an experimental feature.

ignore_adversarial_query

bool

Specifies whether to filter out adversarial queries. The default value is false.

Google employs search-query classification to detect adversarial queries. No answer is returned if the search query is classified as an adversarial query. For example, a user might ask a question regarding negative comments about the company or submit a query designed to generate unsafe, policy-violating output. If this field is set to true, we skip generating answers for adversarial queries and return fallback messages instead.

ignore_non_answer_seeking_query

bool

Specifies whether to filter out queries that are not answer-seeking. The default value is false.

Google employs search-query classification to detect answer-seeking queries. No answer is returned if the search query is classified as a non-answer seeking query. If this field is set to true, we skip generating answers for non-answer seeking queries and return fallback messages instead.

ignore_jail_breaking_query

bool

Optional. Specifies whether to filter out jail-breaking queries. The default value is false.

Google employs search-query classification to detect jail-breaking queries. No summary is returned if the search query is classified as a jail-breaking query. A user might add instructions to the query to change the tone, style, language, content of the answer, or ask the model to act as a different entity, e.g. "Reply in the tone of a competing company's CEO". If this field is set to true, we skip generating summaries for jail-breaking queries and return fallback messages instead.

ignore_low_relevant_content

bool

Specifies whether to filter out queries that have low relevance.

If this field is set to false, all search results are used regardless of relevance to generate answers. If set to true or unset, the behavior will be determined automatically by the service.

ModelSpec

Answer Generation Model specification.

Fields
model_version

string

Model version. If not set, it will use the default stable model. Allowed values are: stable, preview.

PromptSpec

Answer generation prompt specification.

Fields
preamble

string

Customized preamble.

GroundingSpec

Grounding specification.

Fields
include_grounding_supports

bool

Optional. Specifies whether to include grounding_supports in the answer. The default value is false.

When this field is set to true, returned answer will have grounding_score and will contain GroundingSupports for each claim.

filtering_level

FilteringLevel

Optional. Specifies whether to enable the filtering based on grounding score and at what level.

FilteringLevel

Level to filter based on answer grounding.

Enums
FILTERING_LEVEL_UNSPECIFIED Default is no filter
FILTERING_LEVEL_LOW Filter answers based on a low threshold.
FILTERING_LEVEL_HIGH Filter answers based on a high threshold.

QueryUnderstandingSpec

Query understanding specification.

Fields
query_classification_spec

QueryClassificationSpec

Query classification specification.

query_rephraser_spec

QueryRephraserSpec

Query rephraser specification.

QueryClassificationSpec

Query classification specification.

Fields
types[]

Type

Enabled query classification types.

Type

Query classification types.

Enums
TYPE_UNSPECIFIED Unspecified query classification type.
ADVERSARIAL_QUERY Adversarial query classification type.
NON_ANSWER_SEEKING_QUERY Non-answer-seeking query classification type, for chit chat.
JAIL_BREAKING_QUERY Jail-breaking query classification type.
NON_ANSWER_SEEKING_QUERY_V2 Non-answer-seeking query classification type, for no clear intent.

QueryRephraserSpec

Query rephraser specification.

Fields
disable

bool

Disable query rephraser.

max_rephrase_steps

int32

Max rephrase steps. The max number is 5 steps. If not set or set to < 1, it will be set to 1 by default.

RelatedQuestionsSpec

Related questions specification.

Fields
enable

bool

Enable related questions feature if true.

SafetySpec

Safety specification.

Fields
enable

bool

Enable the safety filtering on the answer response. It is false by default.

SearchSpec

Search specification.

Fields
Union field input. Search parameters to control the search behavior. Or provide search result list to generate answer. input can be only one of the following:
search_params

SearchParams

Search parameters.

search_result_list

SearchResultList

Search result list.

SearchParams

Search parameters.

Fields
max_return_results

int32

Number of search results to return. The default value is 10.

filter

string

The filter syntax consists of an expression language for constructing a predicate from one or more fields of the documents being filtered. Filter expression is case-sensitive. This will be used to filter search results which may affect the Answer response.

If this field is unrecognizable, an INVALID_ARGUMENT is returned.

Filtering in Vertex AI Search is done by mapping the LHS filter key to a key property defined in the Vertex AI Search backend -- this mapping is defined by the customer in their schema. For example a media customers might have a field 'name' in their schema. In this case the filter would look like this: filter --> name:'ANY("king kong")'

For more information about filtering including syntax and filter operators, see Filter

boost_spec

BoostSpec

Boost specification to boost certain documents in search results which may affect the answer query response. For more information on boosting, see Boosting

order_by

string

The order in which documents are returned. Documents can be ordered by a field in an Document object. Leave it unset if ordered by relevance. order_by expression is case-sensitive. For more information on ordering, see Ordering

If this field is unrecognizable, an INVALID_ARGUMENT is returned.

search_result_mode

SearchResultMode

Specifies the search result mode. If unspecified, the search result mode defaults to DOCUMENTS. See parse and chunk documents

data_store_specs[]

DataStoreSpec

Specs defining dataStores to filter on in a search call and configurations for those dataStores. This is only considered for engines with multiple dataStores use case. For single dataStore within an engine, they should use the specs at the top level.

natural_language_query_understanding_spec

NaturalLanguageQueryUnderstandingSpec

Optional. Specification to enable natural language understanding capabilities for search requests.

SearchResultList

Search result list.

Fields
search_results[]

SearchResult

Search results.

SearchResult

Search result.

Fields
Union field content. Search result content. content can be only one of the following:
unstructured_document_info

UnstructuredDocumentInfo

Unstructured document information.

chunk_info

ChunkInfo

Chunk information.

ChunkInfo

Chunk information.

Fields
chunk

string

Chunk resource name.

content

string

Chunk textual content.

document_metadata

DocumentMetadata

Metadata of the document from the current chunk.

DocumentMetadata

Document metadata contains the information of the document of the current chunk.

Fields
uri

string

Uri of the document.

title

string

Title of the document.

UnstructuredDocumentInfo

Unstructured document information.

Fields
document

string

Document resource name.

uri

string

URI for the document.

title

string

Title.

document_contexts[]

DocumentContext

List of document contexts. The content will be used for Answer Generation. This is supposed to be the main content of the document that can be long and comprehensive.

extractive_segments[]

ExtractiveSegment

List of extractive segments.

extractive_answers[]
(deprecated)

ExtractiveAnswer

Deprecated: This field is deprecated and will have no effect on the Answer generation. Please use document_contexts and extractive_segments fields. List of extractive answers.

DocumentContext

Document context.

Fields
page_identifier

string

Page identifier.

content

string

Document content to be used for answer generation.

ExtractiveAnswer

Extractive answer. Guide

Fields
page_identifier

string

Page identifier.

content

string

Extractive answer content.

ExtractiveSegment

Extractive segment. Guide Answer generation will only use it if document_contexts is empty. This is supposed to be shorter snippets.

Fields
page_identifier

string

Page identifier.

content

string

Extractive segment content.

AnswerQueryResponse

Response message for ConversationalSearchService.AnswerQuery method.

Fields
answer

Answer

Answer resource object. If AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec.max_rephrase_steps is greater than 1, use Answer.name to fetch answer information using ConversationalSearchService.GetAnswer API.

session

Session

Session resource object. It will be only available when session field is set and valid in the AnswerQueryRequest request.

answer_query_token

string

A global unique ID used for logging.

BatchCreateTargetSiteMetadata

Metadata related to the progress of the SiteSearchEngineService.BatchCreateTargetSites operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

BatchCreateTargetSitesRequest

Request message for SiteSearchEngineService.BatchCreateTargetSites method.

Fields
parent

string

Required. The parent resource shared by all TargetSites being created. projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/siteSearchEngine. The parent field in the CreateBookRequest messages must either be empty or match this field.

requests[]

CreateTargetSiteRequest

Required. The request message specifying the resources to create. A maximum of 20 TargetSites can be created in a batch.

BatchCreateTargetSitesResponse

Response message for SiteSearchEngineService.BatchCreateTargetSites method.

Fields
target_sites[]

TargetSite

TargetSites created.

BatchGetDocumentsMetadataRequest

Request message for DocumentService.BatchGetDocumentsMetadata method.

Fields
parent

string

Required. The parent branch resource name, such as projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}.

matcher

Matcher

Required. Matcher for the Documents.

FhirMatcher

Matcher for the Documents by FHIR resource names.

Fields
fhir_resources[]

string

Required. The FHIR resources to match by. Format: projects/{project}/locations/{location}/datasets/{dataset}/fhirStores/{fhir_store}/fhir/{resource_type}/{fhir_resource_id}

Matcher

Matcher for the Documents. Currently supports matching by exact URIs.

Fields
Union field matcher. Matcher for the Documents. matcher can be only one of the following:
uris_matcher

UrisMatcher

Matcher by exact URIs.

fhir_matcher

FhirMatcher

Matcher by FHIR resource names.

UrisMatcher

Matcher for the Documents by exact uris.

Fields
uris[]

string

The exact URIs to match by.

BatchGetDocumentsMetadataResponse

Response message for DocumentService.BatchGetDocumentsMetadata method.

Fields
documents_metadata[]

DocumentMetadata

The metadata of the Documents.

DocumentMetadata

The metadata of a Document.

Fields
matcher_value

MatcherValue

The value of the matcher that was used to match the Document.

state

State

The state of the document.

last_refreshed_time

Timestamp

The timestamp of the last time the Document was last indexed.

data_ingestion_source

string

The data ingestion source of the Document.

Allowed values are:

  • batch: Data ingested via Batch API, e.g., ImportDocuments.
  • streaming Data ingested via Streaming API, e.g., FHIR streaming.

MatcherValue

The value of the matcher that was used to match the Document.

Fields
Union field matcher_value. The value of the matcher that was used to match the Document. matcher_value can be only one of the following:
uri

string

If match by URI, the URI of the Document.

fhir_resource

string

Format: projects/{project}/locations/{location}/datasets/{dataset}/fhirStores/{fhir_store}/fhir/{resource_type}/{fhir_resource_id}

State

The state of the Document.

Enums
STATE_UNSPECIFIED Should never be set.
INDEXED The Document is indexed.
NOT_IN_TARGET_SITE The Document is not indexed because its URI is not in the TargetSite.
NOT_IN_INDEX The Document is not indexed.

BatchVerifyTargetSitesMetadata

Metadata related to the progress of the SiteSearchEngineService.BatchVerifyTargetSites operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

BatchVerifyTargetSitesRequest

Request message for SiteSearchEngineService.BatchVerifyTargetSites method.

Fields
parent

string

Required. The parent resource shared by all TargetSites being verified. projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/siteSearchEngine.

BatchVerifyTargetSitesResponse

This type has no fields.

Response message for SiteSearchEngineService.BatchVerifyTargetSites method.

BigQuerySource

BigQuery source import data from.

Fields
project_id

string

The project ID or the project number that contains the BigQuery source. Has a length limit of 128 characters. If not specified, inherits the project ID from the parent request.

dataset_id

string

Required. The BigQuery data set to copy the data from with a length limit of 1,024 characters.

table_id

string

Required. The BigQuery table to copy the data from with a length limit of 1,024 characters.

gcs_staging_dir

string

Intermediate Cloud Storage directory used for the import with a length limit of 2,000 characters. Can be specified if one wants to have the BigQuery export to a specific Cloud Storage directory.

data_schema

string

The schema to use when parsing the data from the source.

Supported values for user event imports:

  • user_event (default): One UserEvent per row.

Supported values for document imports:

Union field partition. BigQuery table partition info. Leave this empty if the BigQuery table is not partitioned. partition can be only one of the following:
partition_date

Date

BigQuery time partitioned table's _PARTITIONDATE in YYYY-MM-DD format.

BigtableOptions

The Bigtable Options object that contains information to support the import.

Fields
key_field_name

string

The field name used for saving row key value in the document. The name has to match the pattern [a-zA-Z0-9][a-zA-Z0-9-_]*.

families

map<string, BigtableColumnFamily>

The mapping from family names to an object that contains column families level information for the given column family. If a family is not present in this map it will be ignored.

BigtableColumn

The column of the Bigtable.

Fields
qualifier

bytes

Required. Qualifier of the column. If it cannot be decoded with utf-8, use a base-64 encoded string instead.

field_name

string

The field name to use for this column in the document. The name has to match the pattern [a-zA-Z0-9][a-zA-Z0-9-_]*. If not set, it is parsed from the qualifier bytes with best effort. However, due to different naming patterns, field name collisions could happen, where parsing behavior is undefined.

encoding

Encoding

The encoding mode of the values when the type is not STRING. Acceptable encoding values are:

  • TEXT: indicates values are alphanumeric text strings.
  • BINARY: indicates values are encoded using HBase Bytes.toBytes family of functions. This can be overridden for a specific column by listing that column in columns and specifying an encoding for it.
type

Type

The type of values in this column family. The values are expected to be encoded using HBase Bytes.toBytes function when the encoding value is set to BINARY.

BigtableColumnFamily

The column family of the Bigtable.

Fields
field_name

string

The field name to use for this column family in the document. The name has to match the pattern [a-zA-Z0-9][a-zA-Z0-9-_]*. If not set, it is parsed from the family name with best effort. However, due to different naming patterns, field name collisions could happen, where parsing behavior is undefined.

encoding

Encoding

The encoding mode of the values when the type is not STRING. Acceptable encoding values are:

  • TEXT: indicates values are alphanumeric text strings.
  • BINARY: indicates values are encoded using HBase Bytes.toBytes family of functions. This can be overridden for a specific column by listing that column in columns and specifying an encoding for it.
type

Type

The type of values in this column family. The values are expected to be encoded using HBase Bytes.toBytes function when the encoding value is set to BINARY.

columns[]

BigtableColumn

The list of objects that contains column level information for each column. If a column is not present in this list it will be ignored.

Encoding

The encoding mode of a Bigtable column or column family.

Enums
ENCODING_UNSPECIFIED The encoding is unspecified.
TEXT Text encoding.
BINARY Binary encoding.

Type

The type of values in a Bigtable column or column family. The values are expected to be encoded using HBase Bytes.toBytes function when the encoding value is set to BINARY.

Enums
TYPE_UNSPECIFIED The type is unspecified.
STRING String type.
NUMBER Numerical type.
INTEGER Integer type.
VAR_INTEGER Variable length integer type.
BIG_NUMERIC BigDecimal type.
BOOLEAN Boolean type.
JSON JSON type.

BigtableSource

The Cloud Bigtable source for importing data.

Fields
project_id

string

The project ID that contains the Bigtable source. Has a length limit of 128 characters. If not specified, inherits the project ID from the parent request.

instance_id

string

Required. The instance ID of the Cloud Bigtable that needs to be imported.

table_id

string

Required. The table ID of the Cloud Bigtable that needs to be imported.

bigtable_options

BigtableOptions

Required. Bigtable options that contains information needed when parsing data into typed structures. For example, column type annotations.

CheckGroundingRequest

Request message for GroundedGenerationService.CheckGrounding method.

Fields
grounding_config

string

Required. The resource name of the grounding config, such as projects/*/locations/global/groundingConfigs/default_grounding_config.

answer_candidate

string

Answer candidate to check. It can have a maximum length of 4096 tokens.

facts[]

GroundingFact

List of facts for the grounding check. We support up to 200 facts.

grounding_spec

CheckGroundingSpec

Configuration of the grounding check.

user_labels

map<string, string>

The user labels applied to a resource must meet the following requirements:

  • Each resource can have multiple labels, up to a maximum of 64.
  • Each label must be a key-value pair.
  • Keys have a minimum length of 1 character and a maximum length of 63 characters and cannot be empty. Values can be empty and have a maximum length of 63 characters.
  • Keys and values can contain only lowercase letters, numeric characters, underscores, and dashes. All characters must use UTF-8 encoding, and international characters are allowed.
  • The key portion of a label must be unique. However, you can use the same key with multiple resources.
  • Keys must start with a lowercase letter or international character.

See Google Cloud Document for more details.

CheckGroundingResponse

Response message for the GroundedGenerationService.CheckGrounding method.

Fields
cited_chunks[]

FactChunk

List of facts cited across all claims in the answer candidate. These are derived from the facts supplied in the request.

claims[]

Claim

Claim texts and citation info across all claims in the answer candidate.

support_score

float

The support score for the input answer candidate. Higher the score, higher is the fraction of claims that are supported by the provided facts. This is always set when a response is returned.

Claim

Text and citation info for a claim in the answer candidate.

Fields
claim_text

string

Text for the claim in the answer candidate. Always provided regardless of whether citations or anti-citations are found.

citation_indices[]

int32

A list of indices (into 'cited_chunks') specifying the citations associated with the claim. For instance [1,3,4] means that cited_chunks[1], cited_chunks[3], cited_chunks[4] are the facts cited supporting for the claim. A citation to a fact indicates that the claim is supported by the fact.

start_pos

int32

Position indicating the start of the claim in the answer candidate, measured in bytes.

end_pos

int32

Position indicating the end of the claim in the answer candidate, exclusive.

grounding_check_required

bool

Indicates that this claim required grounding check. When the system decided this claim doesn't require attribution/grounding check, this field will be set to false. In that case, no grounding check was done for the claim and therefore citation_indices, anti_citation_indices, and score should not be returned.

FactChunk

Fact chunk for grounding check.

Fields
chunk_text

string

Text content of the fact chunk. Can be at most 10K characters long.

source

string

Source from which this fact chunk was retrieved. For a fact chunk retrieved from inline facts, this field will contain the index of the specific fact from which this chunk was retrieved.

CheckGroundingSpec

Specification for the grounding check.

Fields
citation_threshold

double

The threshold (in [0,1]) used for determining whether a fact must be cited for a claim in the answer candidate. Choosing a higher threshold will lead to fewer but very strong citations, while choosing a lower threshold may lead to more but somewhat weaker citations. If unset, the threshold will default to 0.6.

Chunk

Chunk captures all raw metadata information of items to be recommended or searched in the chunk mode.

Fields
name

string

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.

id

string

Unique chunk ID of the current chunk.

content

string

Content is a string from a document (parsed content).

document_metadata

DocumentMetadata

Metadata of the document from the current chunk.

derived_struct_data

Struct

Output only. This field is OUTPUT_ONLY. It contains derived data that are not in the original input document.

page_span

PageSpan

Page span of the chunk.

chunk_metadata

ChunkMetadata

Output only. Metadata of the current chunk.

relevance_score

double

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 [SearchService.SearchResponse][].

ChunkMetadata

Metadata of the current chunk. This field is only populated on SearchService.Search API.

Fields
previous_chunks[]

Chunk

The previous chunks of the current chunk. The number is controlled by SearchRequest.ContentSearchSpec.ChunkSpec.num_previous_chunks. This field is only populated on SearchService.Search API.

next_chunks[]

Chunk

The next chunks of the current chunk. The number is controlled by SearchRequest.ContentSearchSpec.ChunkSpec.num_next_chunks. This field is only populated on SearchService.Search API.

DocumentMetadata

Document metadata contains the information of the document of the current chunk.

Fields
uri

string

Uri of the document.

title

string

Title of the document.

struct_data

Struct

Data representation. The structured JSON data for the document. It should conform to the registered Schema or an INVALID_ARGUMENT error is thrown.

PageSpan

Page span of the chunk.

Fields
page_start

int32

The start page of the chunk.

page_end

int32

The end page of the chunk.

CloudSqlSource

Cloud SQL source import data from.

Fields
project_id

string

The project ID that contains the Cloud SQL source. Has a length limit of 128 characters. If not specified, inherits the project ID from the parent request.

instance_id

string

Required. The Cloud SQL instance to copy the data from with a length limit of 256 characters.

database_id

string

Required. The Cloud SQL database to copy the data from with a length limit of 256 characters.

table_id

string

Required. The Cloud SQL table to copy the data from with a length limit of 256 characters.

gcs_staging_dir

string

Intermediate Cloud Storage directory used for the import with a length limit of 2,000 characters. Can be specified if one wants to have the Cloud SQL export to a specific Cloud Storage directory.

Ensure that the Cloud SQL service account has the necessary Cloud Storage Admin permissions to access the specified Cloud Storage directory.

offload

bool

Option for serverless export. Enabling this option will incur additional cost. More info can be found here.

CmekConfig

Configurations used to enable CMEK data encryption with Cloud KMS keys.

Fields
name

string

Required. Name of the CmekConfig, of the form projects/{project}/locations/{location}/cmekConfig or projects/{project}/locations/{location}/cmekConfigs/{cmekConfig}.

kms_key

string

Kms key resource name which will be used to encrypt resources projects/{project}/locations/{location}/keyRings/{keyRing}/cryptoKeys/{keyId}.

kms_key_version

string

Kms key version resource name which will be used to encrypt resources <kms_key>/cryptoKeyVersions/{keyVersion}.

state

State

Output only. State of the CmekConfig.

is_default

bool

Output only. The default CmekConfig for the Customer.

last_rotation_timestamp_micros

int64

Output only. The timestamp of the last key rotation.

State

States of the CmekConfig.

Enums
STATE_UNSPECIFIED The CmekConfig state is unknown.
CREATING The CmekConfig is creating.
ACTIVE The CmekConfig can be used with DataStores.
KEY_ISSUE The CmekConfig is unavailable, most likely due to the KMS Key being revoked.
DELETING The CmekConfig is deleting.
UNUSABLE The CmekConfig is not usable, most likely due to some internal issue.
ACTIVE_ROTATING The KMS key version is being rotated.

CollectUserEventRequest

Request message for CollectUserEvent method.

Fields
parent

string

Required. The parent DataStore resource name, such as projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}.

user_event

string

Required. URL encoded UserEvent proto with a length limit of 2,000,000 characters.

uri

string

The URL including cgi-parameters but excluding the hash fragment with a length limit of 5,000 characters. This is often more useful than the referer URL, because many browsers only send the domain for third-party requests.

ets

int64

The event timestamp in milliseconds. This prevents browser caching of otherwise identical get requests. The name is abbreviated to reduce the payload bytes.

CompleteQueryRequest

Request message for CompletionService.CompleteQuery method.

Fields
data_store

string

Required. The parent data store resource name for which the completion is performed, such as projects/*/locations/global/collections/default_collection/dataStores/default_data_store.

query

string

Required. The typeahead input used to fetch suggestions. Maximum length is 128 characters.

query_model

string

Specifies the autocomplete data model. This overrides any model specified in the Configuration > Autocomplete section of the Cloud console. Currently supported values:

  • document - Using suggestions generated from user-imported documents.
  • search-history - Using suggestions generated from the past history of SearchService.Search API calls. Do not use it when there is no traffic for Search API.
  • user-event - Using suggestions generated from user-imported search events.
  • document-completable - Using suggestions taken directly from user-imported document fields marked as completable.

Default values:

  • document is the default model for regular dataStores.
  • search-history is the default model for site search dataStores.
user_pseudo_id

string

A unique identifier for tracking visitors. For example, this could be implemented with an HTTP cookie, which should be able to uniquely identify a visitor on a single device. This unique identifier should not change if the visitor logs in or out of the website.

This field should NOT have a fixed value such as unknown_visitor.

This should be the same identifier as UserEvent.user_pseudo_id and SearchRequest.user_pseudo_id.

The field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an INVALID_ARGUMENT error is returned.

include_tail_suggestions

bool

Indicates if tail suggestions should be returned if there are no suggestions that match the full query. Even if set to true, if there are suggestions that match the full query, those are returned and no tail suggestions are returned.

CompleteQueryResponse

Response message for CompletionService.CompleteQuery method.

Fields
query_suggestions[]

QuerySuggestion

Results of the matched query suggestions. The result list is ordered and the first result is a top suggestion.

tail_match_triggered

bool

True if the returned suggestions are all tail suggestions.

For tail matching to be triggered, include_tail_suggestions in the request must be true and there must be no suggestions that match the full query.

QuerySuggestion

Suggestions as search queries.

Fields
suggestion

string

The suggestion for the query.

completable_field_paths[]

string

The unique document field paths that serve as the source of this suggestion if it was generated from completable fields.

This field is only populated for the document-completable model.

CompletionInfo

Detailed completion information including completion attribution token and clicked completion info.

Fields
selected_suggestion

string

End user selected CompleteQueryResponse.QuerySuggestion.suggestion.

selected_position

int32

End user selected CompleteQueryResponse.QuerySuggestion.suggestion position, starting from 0.

CompletionSuggestion

Autocomplete suggestions that are imported from Customer.

Fields
suggestion

string

Required. The suggestion text.

language_code

string

BCP-47 language code of this suggestion.

group_id

string

If two suggestions have the same groupId, they will not be returned together. Instead the one ranked higher will be returned. This can be used to deduplicate semantically identical suggestions.

group_score

double

The score of this suggestion within its group.

alternative_phrases[]

string

Alternative matching phrases for this suggestion.

Union field ranking_info. Ranking metrics of this suggestion. ranking_info can be only one of the following:
global_score

double

Global score of this suggestion. Control how this suggestion would be scored / ranked.

frequency

int64

Frequency of this suggestion. Will be used to rank suggestions when score is not available.

Condition

Defines circumstances to be checked before allowing a behavior

Fields
query_terms[]

QueryTerm

Search only A list of terms to match the query on. Cannot be set when Condition.query_regex is set.

Maximum of 10 query terms.

active_time_range[]

TimeRange

Range of time(s) specifying when condition is active.

Maximum of 10 time ranges.

query_regex

string

Optional. Query regex to match the whole search query. Cannot be set when Condition.query_terms is set. This is currently supporting promotion use case.

QueryTerm

Matcher for search request query

Fields
value

string

The specific query value to match against

Must be lowercase, must be UTF-8. Can have at most 3 space separated terms if full_match is true. Cannot be an empty string. Maximum length of 5000 characters.

full_match

bool

Whether the search query needs to exactly match the query term.

TimeRange

Used for time-dependent conditions.

Fields
start_time

Timestamp

Start of time range.

Range is inclusive.

end_time

Timestamp

End of time range.

Range is inclusive. Must be in the future.

Control

Defines a conditioned behavior to employ during serving. Must be attached to a ServingConfig to be considered at serving time. Permitted actions dependent on SolutionType.

Fields
name

string

Immutable. Fully qualified name projects/*/locations/global/dataStore/*/controls/*

display_name

string

Required. Human readable name. The identifier used in UI views.

Must be UTF-8 encoded string. Length limit is 128 characters. Otherwise an INVALID ARGUMENT error is thrown.

associated_serving_config_ids[]

string

Output only. List of all ServingConfig IDs this control is attached to. May take up to 10 minutes to update after changes.

solution_type

SolutionType

Required. Immutable. What solution the control belongs to.

Must be compatible with vertical of resource. Otherwise an INVALID ARGUMENT error is thrown.

use_cases[]

SearchUseCase

Specifies the use case for the control. Affects what condition fields can be set. Only applies to SOLUTION_TYPE_SEARCH. Currently only allow one use case per control. Must be set when solution_type is SolutionType.SOLUTION_TYPE_SEARCH.

conditions[]

Condition

Determines when the associated action will trigger.

Omit to always apply the action. Currently only a single condition may be specified. Otherwise an INVALID ARGUMENT error is thrown.

Union field action. Actions are restricted by Vertical and Solution

Required. action can be only one of the following:

boost_action

BoostAction

Defines a boost-type control

filter_action

FilterAction

Defines a filter-type control Currently not supported by Recommendation

redirect_action

RedirectAction

Defines a redirect-type control.

synonyms_action

SynonymsAction

Treats a group of terms as synonyms of one another.

BoostAction

Adjusts order of products in returned list.

Fields
boost

float

Required. Strength of the boost, which should be in [-1, 1]. Negative boost means demotion. Default is 0.0 (No-op).

filter

string

Required. Specifies which products to apply the boost to.

If no filter is provided all products will be boosted (No-op). Syntax documentation: https://cloud.google.com/retail/docs/filter-and-order Maximum length is 5000 characters. Otherwise an INVALID ARGUMENT error is thrown.

data_store

string

Required. Specifies which data store's documents can be boosted by this control. Full data store name e.g. projects/123/locations/global/collections/default_collection/dataStores/default_data_store

FilterAction

Specified which products may be included in results. Uses same filter as boost.

Fields
filter

string

Required. A filter to apply on the matching condition results.

Required Syntax documentation: https://cloud.google.com/retail/docs/filter-and-order Maximum length is 5000 characters. Otherwise an INVALID ARGUMENT error is thrown.

data_store

string

Required. Specifies which data store's documents can be filtered by this control. Full data store name e.g. projects/123/locations/global/collections/default_collection/dataStores/default_data_store

RedirectAction

Redirects a shopper to the provided URI.

Fields
redirect_uri

string

Required. The URI to which the shopper will be redirected.

Required. URI must have length equal or less than 2000 characters. Otherwise an INVALID ARGUMENT error is thrown.

SynonymsAction

Creates a set of terms that will act as synonyms of one another.

Example: "happy" will also be considered as "glad", "glad" will also be considered as "happy".

Fields
synonyms[]

string

Defines a set of synonyms. Can specify up to 100 synonyms. Must specify at least 2 synonyms. Otherwise an INVALID ARGUMENT error is thrown.

Conversation

External conversation proto definition.

Fields
name

string

Immutable. Fully qualified name projects/{project}/locations/global/collections/{collection}/dataStore/*/conversations/* or projects/{project}/locations/global/collections/{collection}/engines/*/conversations/*.

state

State

The state of the Conversation.

user_pseudo_id

string

A unique identifier for tracking users.

messages[]

ConversationMessage

Conversation messages.

start_time

Timestamp

Output only. The time the conversation started.

end_time

Timestamp

Output only. The time the conversation finished.

State

Enumeration of the state of the conversation.

Enums
STATE_UNSPECIFIED Unknown.
IN_PROGRESS Conversation is currently open.
COMPLETED Conversation has been completed.

ConversationContext

Defines context of the conversation

Fields
context_documents[]

string

The current list of documents the user is seeing. It contains the document resource references.

active_document

string

The current active document the user opened. It contains the document resource reference.

ConversationMessage

Defines a conversation message.

Fields
create_time

Timestamp

Output only. Message creation timestamp.

Union field message.

message can be only one of the following:

user_input

TextInput

User text input.

reply

Reply

Search reply.

ConverseConversationRequest

Request message for ConversationalSearchService.ConverseConversation method.

Fields
name

string

Required. The resource name of the Conversation to get. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store_id}/conversations/{conversation_id}. Use projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store_id}/conversations/- to activate auto session mode, which automatically creates a new conversation inside a ConverseConversation session.

query

TextInput

Required. Current user input.

serving_config

string

The resource name of the Serving Config to use. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store_id}/servingConfigs/{serving_config_id} If this is not set, the default serving config will be used.

conversation

Conversation

The conversation to be used by auto session only. The name field will be ignored as we automatically assign new name for the conversation in auto session.

user_labels

map<string, string>

The user labels applied to a resource must meet the following requirements:

  • Each resource can have multiple labels, up to a maximum of 64.
  • Each label must be a key-value pair.
  • Keys have a minimum length of 1 character and a maximum length of 63 characters and cannot be empty. Values can be empty and have a maximum length of 63 characters.
  • Keys and values can contain only lowercase letters, numeric characters, underscores, and dashes. All characters must use UTF-8 encoding, and international characters are allowed.
  • The key portion of a label must be unique. However, you can use the same key with multiple resources.
  • Keys must start with a lowercase letter or international character.

See Google Cloud Document for more details.

summary_spec

SummarySpec

A specification for configuring the summary returned in the response.

filter

string

The filter syntax consists of an expression language for constructing a predicate from one or more fields of the documents being filtered. Filter expression is case-sensitive. This will be used to filter search results which may affect the summary response.

If this field is unrecognizable, an INVALID_ARGUMENT is returned.

Filtering in Vertex AI Search is done by mapping the LHS filter key to a key property defined in the Vertex AI Search backend -- this mapping is defined by the customer in their schema. For example a media customer might have a field 'name' in their schema. In this case the filter would look like this: filter --> name:'ANY("king kong")'

For more information about filtering including syntax and filter operators, see Filter

boost_spec

BoostSpec

Boost specification to boost certain documents in search results which may affect the converse response. For more information on boosting, see Boosting

ConverseConversationResponse

Response message for ConversationalSearchService.ConverseConversation method.

Fields
reply

Reply

Answer to the current query.

conversation

Conversation

Updated conversation including the answer.

related_questions[]

string

Suggested related questions.

search_results[]

SearchResult

Search Results.

CreateControlRequest

Request for CreateControl method.

Fields
parent

string

Required. Full resource name of parent data store. Format: projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id} or projects/{project}/locations/{location}/collections/{collection_id}/engines/{engine_id}.

control

Control

Required. The Control to create.

control_id

string

Required. The ID to use for the Control, which will become the final component of the Control's resource name.

This value must be within 1-63 characters. Valid characters are /[a-z][0-9]-_/.

CreateConversationRequest

Request for CreateConversation method.

Fields
parent

string

Required. Full resource name of parent data store. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store_id}

conversation

Conversation

Required. The conversation to create.

CreateDataStoreMetadata

Metadata related to the progress of the DataStoreService.CreateDataStore operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

CreateDataStoreRequest

Request for DataStoreService.CreateDataStore method.

Fields
parent

string

Required. The parent resource name, such as projects/{project}/locations/{location}/collections/{collection}.

data_store

DataStore

Required. The DataStore to create.

data_store_id

string

Required. The ID to use for the DataStore, which will become the final component of the DataStore's resource name.

This field must conform to RFC-1034 standard with a length limit of 63 characters. Otherwise, an INVALID_ARGUMENT error is returned.

skip_default_schema_creation

bool

A boolean flag indicating whether to skip the default schema creation for the data store. Only enable this flag if you are certain that the default schema is incompatible with your use case.

If set to true, you must manually create a schema for the data store before any documents can be ingested.

This flag cannot be specified if data_store.starting_schema is specified.

Union field cmek_options. CMEK options for the DataStore. Setting this field will override the default CmekConfig if one is set for the project. cmek_options can be only one of the following:
cmek_config_name

string

Resource name of the CmekConfig to use for protecting this DataStore.

disable_cmek

bool

DataStore without CMEK protections. If a default CmekConfig is set for the project, setting this field will override the default CmekConfig as well.

CreateDocumentRequest

Request message for DocumentService.CreateDocument method.

Fields
parent

string

Required. The parent resource name, such as projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}.

document

Document

Required. The Document to create.

document_id

string

Required. The ID to use for the Document, which becomes the final component of the Document.name.

If the caller does not have permission to create the Document, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

This field must be unique among all Documents with the same parent. Otherwise, an ALREADY_EXISTS error is returned.

This field must conform to RFC-1034 standard with a length limit of 63 characters. Otherwise, an INVALID_ARGUMENT error is returned.

CreateEngineMetadata

Metadata related to the progress of the EngineService.CreateEngine operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

CreateEngineRequest

Request for EngineService.CreateEngine method.

Fields
parent

string

Required. The parent resource name, such as projects/{project}/locations/{location}/collections/{collection}.

engine

Engine

Required. The Engine to create.

engine_id

string

Required. The ID to use for the Engine, which will become the final component of the Engine's resource name.

This field must conform to RFC-1034 standard with a length limit of 63 characters. Otherwise, an INVALID_ARGUMENT error is returned.

CreateEvaluationMetadata

This type has no fields.

Metadata for EvaluationService.CreateEvaluation method.

CreateEvaluationRequest

Request message for EvaluationService.CreateEvaluation method.

Fields
parent

string

Required. The parent resource name, such as projects/{project}/locations/{location}.

evaluation

Evaluation

Required. The Evaluation to create.

CreateSampleQueryRequest

Request message for SampleQueryService.CreateSampleQuery method.

Fields
parent

string

Required. The parent resource name, such as projects/{project}/locations/{location}/sampleQuerySets/{sampleQuerySet}.

sample_query

SampleQuery

Required. The SampleQuery to create.

sample_query_id

string

Required. The ID to use for the SampleQuery, which will become the final component of the SampleQuery.name.

If the caller does not have permission to create the SampleQuery, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

This field must be unique among all SampleQuerys with the same parent. Otherwise, an ALREADY_EXISTS error is returned.

This field must conform to RFC-1034 standard with a length limit of 63 characters. Otherwise, an INVALID_ARGUMENT error is returned.

CreateSampleQuerySetRequest

Request message for SampleQuerySetService.CreateSampleQuerySet method.

Fields
parent

string

Required. The parent resource name, such as projects/{project}/locations/{location}.

sample_query_set

SampleQuerySet

Required. The SampleQuerySet to create.

sample_query_set_id

string

Required. The ID to use for the SampleQuerySet, which will become the final component of the SampleQuerySet.name.

If the caller does not have permission to create the SampleQuerySet, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

This field must be unique among all SampleQuerySets with the same parent. Otherwise, an ALREADY_EXISTS error is returned.

This field must conform to RFC-1034 standard with a length limit of 63 characters. Otherwise, an INVALID_ARGUMENT error is returned.

CreateSchemaMetadata

Metadata for Create Schema LRO.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

CreateSchemaRequest

Request message for SchemaService.CreateSchema method.

Fields
parent

string

Required. The parent data store resource name, in the format of projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}.

schema

Schema

Required. The Schema to create.

schema_id

string

Required. The ID to use for the Schema, which becomes the final component of the Schema.name.

This field should conform to RFC-1034 standard with a length limit of 63 characters.

CreateSessionRequest

Request for CreateSession method.

Fields
parent

string

Required. Full resource name of parent data store. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store_id}

session

Session

Required. The session to create.

CreateTargetSiteMetadata

Metadata related to the progress of the SiteSearchEngineService.CreateTargetSite operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

CreateTargetSiteRequest

Request message for SiteSearchEngineService.CreateTargetSite method.

Fields
parent

string

Required. Parent resource name of TargetSite, such as projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/siteSearchEngine.

target_site

TargetSite

Required. The TargetSite to create.

CustomAttribute

A custom attribute that is not explicitly modeled in a resource, e.g. UserEvent.

Fields
text[]

string

The textual values of this custom attribute. For example, ["yellow", "green"] when the key is "color".

Empty string is not allowed. Otherwise, an INVALID_ARGUMENT error is returned.

Exactly one of CustomAttribute.text or CustomAttribute.numbers should be set. Otherwise, an INVALID_ARGUMENT error is returned.

numbers[]

double

The numerical values of this custom attribute. For example, [2.3, 15.4] when the key is "lengths_cm".

Exactly one of CustomAttribute.text or CustomAttribute.numbers should be set. Otherwise, an INVALID_ARGUMENT error is returned.

CustomTuningModel

Metadata that describes a custom tuned model.

Fields
name

string

Required. The fully qualified resource name of the model.

Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/customTuningModels/{custom_tuning_model}.

Model must be an alpha-numerical string with limit of 40 characters.

display_name

string

The display name of the model.

model_version

int64

The version of the model.

model_state

ModelState

The state that the model is in (e.g.TRAINING or TRAINING_FAILED).

create_time
(deprecated)

Timestamp

Deprecated: Timestamp the Model was created at.

training_start_time

Timestamp

Timestamp the model training was initiated.

metrics

map<string, double>

The metrics of the trained model.

error_message

string

Currently this is only populated if the model state is INPUT_VALIDATION_FAILED.

ModelState

The state of the model.

Enums
MODEL_STATE_UNSPECIFIED Default value.
TRAINING_PAUSED The model is in a paused training state.
TRAINING The model is currently training.
TRAINING_COMPLETE The model has successfully completed training.
READY_FOR_SERVING The model is ready for serving.
TRAINING_FAILED The model training failed.
NO_IMPROVEMENT The model training finished successfully but metrics did not improve.
INPUT_VALIDATION_FAILED Input data validation failed. Model training didn't start.

DataStore

DataStore captures global settings and configs at the DataStore level.

Fields
name

string

Immutable. The full resource name of the data store. Format: projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}.

This field must be a UTF-8 encoded string with a length limit of 1024 characters.

display_name

string

Required. The data store display name.

This field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an INVALID_ARGUMENT error is returned.

industry_vertical

IndustryVertical

Immutable. The industry vertical that the data store registers.

solution_types[]

SolutionType

The solutions that the data store enrolls. Available solutions for each industry_vertical:

  • MEDIA: SOLUTION_TYPE_RECOMMENDATION and SOLUTION_TYPE_SEARCH.
  • SITE_SEARCH: SOLUTION_TYPE_SEARCH is automatically enrolled. Other solutions cannot be enrolled.
default_schema_id

string

Output only. The id of the default Schema asscociated to this data store.

content_config

ContentConfig

Immutable. The content config of the data store. If this field is unset, the server behavior defaults to ContentConfig.NO_CONTENT.

create_time

Timestamp

Output only. Timestamp the DataStore was created at.

advanced_site_search_config

AdvancedSiteSearchConfig

Optional. Configuration for advanced site search.

language_info

LanguageInfo

Language info for DataStore.

natural_language_query_understanding_config

NaturalLanguageQueryUnderstandingConfig

Optional. Configuration for Natural Language Query Understanding.

kms_key_name

string

Input only. The KMS key to be used to protect this DataStore at creation time.

Must be set for requests that need to comply with CMEK Org Policy protections.

If this field is set and processed successfully, the DataStore will be protected by the KMS key, as indicated in the cmek_config field.

cmek_config

CmekConfig

Output only. CMEK-related information for the DataStore.

billing_estimation

BillingEstimation

Output only. Data size estimation for billing.

workspace_config

WorkspaceConfig

Config to store data store type configuration for workspace data. This must be set when DataStore.content_config is set as DataStore.ContentConfig.GOOGLE_WORKSPACE.

document_processing_config

DocumentProcessingConfig

Configuration for Document understanding and enrichment.

starting_schema

Schema

The start schema to use for this DataStore when provisioning it. If unset, a default vertical specialized schema will be used.

This field is only used by [CreateDataStore][] API, and will be ignored if used in other APIs. This field will be omitted from all API responses including [CreateDataStore][] API. To retrieve a schema of a DataStore, use SchemaService.GetSchema API instead.

The provided schema will be validated against certain rules on schema. Learn more from this doc.

serving_config_data_store

ServingConfigDataStore

Optional. Stores serving config at DataStore level.

BillingEstimation

Estimation of data size per data store.

Fields
structured_data_size

int64

Data size for structured data in terms of bytes.

unstructured_data_size

int64

Data size for unstructured data in terms of bytes.

website_data_size

int64

Data size for websites in terms of bytes.

structured_data_update_time

Timestamp

Last updated timestamp for structured data.

unstructured_data_update_time

Timestamp

Last updated timestamp for unstructured data.

website_data_update_time

Timestamp

Last updated timestamp for websites.

ContentConfig

Content config of the data store.

Enums
CONTENT_CONFIG_UNSPECIFIED Default value.
NO_CONTENT Only contains documents without any Document.content.
CONTENT_REQUIRED Only contains documents with Document.content.
PUBLIC_WEBSITE The data store is used for public website search.
GOOGLE_WORKSPACE The data store is used for workspace search. Details of workspace data store are specified in the WorkspaceConfig.

ServingConfigDataStore

Stores information regarding the serving configurations at DataStore level.

Fields
disabled_for_serving

bool

If set true, the DataStore will not be available for serving search requests.

DeleteControlRequest

Request for DeleteControl method.

Fields
name

string

Required. The resource name of the Control to delete. Format: projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}/controls/{control_id}

DeleteConversationRequest

Request for DeleteConversation method.

Fields
name

string

Required. The resource name of the Conversation to delete. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store_id}/conversations/{conversation_id}

DeleteDataStoreMetadata

Metadata related to the progress of the DataStoreService.DeleteDataStore operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

DeleteDataStoreRequest

Request message for DataStoreService.DeleteDataStore method.

Fields
name

string

Required. Full resource name of DataStore, such as projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}.

If the caller does not have permission to delete the DataStore, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the DataStore to delete does not exist, a NOT_FOUND error is returned.

DeleteDocumentRequest

Request message for DocumentService.DeleteDocument method.

Fields
name

string

Required. Full resource name of Document, such as projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document}.

If the caller does not have permission to delete the Document, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the Document to delete does not exist, a NOT_FOUND error is returned.

DeleteEngineMetadata

Metadata related to the progress of the EngineService.DeleteEngine operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

DeleteEngineRequest

Request message for EngineService.DeleteEngine method.

Fields
name

string

Required. Full resource name of Engine, such as projects/{project}/locations/{location}/collections/{collection_id}/engines/{engine_id}.

If the caller does not have permission to delete the Engine, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the Engine to delete does not exist, a NOT_FOUND error is returned.

DeleteSampleQueryRequest

Request message for SampleQueryService.DeleteSampleQuery method.

Fields
name

string

Required. Full resource name of SampleQuery, such as projects/{project}/locations/{location}/sampleQuerySets/{sample_query_set}/sampleQueries/{sample_query}.

If the caller does not have permission to delete the SampleQuery, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the SampleQuery to delete does not exist, a NOT_FOUND error is returned.

DeleteSampleQuerySetRequest

Request message for SampleQuerySetService.DeleteSampleQuerySet method.

Fields
name

string

Required. Full resource name of SampleQuerySet, such as projects/{project}/locations/{location}/sampleQuerySets/{sample_query_set}.

If the caller does not have permission to delete the SampleQuerySet, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the SampleQuerySet to delete does not exist, a NOT_FOUND error is returned.

DeleteSchemaMetadata

Metadata for DeleteSchema LRO.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

DeleteSchemaRequest

Request message for SchemaService.DeleteSchema method.

Fields
name

string

Required. The full resource name of the schema, in the format of projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/schemas/{schema}.

DeleteSessionRequest

Request for DeleteSession method.

Fields
name

string

Required. The resource name of the Session to delete. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store_id}/sessions/{session_id}

DeleteTargetSiteMetadata

Metadata related to the progress of the SiteSearchEngineService.DeleteTargetSite operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

DeleteTargetSiteRequest

Request message for SiteSearchEngineService.DeleteTargetSite method.

Fields
name

string

Required. Full resource name of TargetSite, such as projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/siteSearchEngine/targetSites/{target_site}.

If the caller does not have permission to access the TargetSite, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the requested TargetSite does not exist, a NOT_FOUND error is returned.

DisableAdvancedSiteSearchMetadata

Metadata related to the progress of the SiteSearchEngineService.DisableAdvancedSiteSearch operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

DisableAdvancedSiteSearchRequest

Request message for SiteSearchEngineService.DisableAdvancedSiteSearch method.

Fields
site_search_engine

string

Required. Full resource name of the SiteSearchEngine, such as projects/{project}/locations/{location}/dataStores/{data_store_id}/siteSearchEngine.

DisableAdvancedSiteSearchResponse

This type has no fields.

Response message for SiteSearchEngineService.DisableAdvancedSiteSearch method.

Document

Document captures all raw metadata information of items to be recommended or searched.

Fields
name

string

Immutable. The full resource name of the document. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document_id}.

This field must be a UTF-8 encoded string with a length limit of 1024 characters.

id

string

Immutable. The identifier of the document.

Id should conform to RFC-1034 standard with a length limit of 63 characters.

schema_id

string

The identifier of the schema located in the same data store.

content

Content

The unstructured data linked to this document. Content must be set if this document is under a CONTENT_REQUIRED data store.

parent_document_id

string

The identifier of the parent document. Currently supports at most two level document hierarchy.

Id should conform to RFC-1034 standard with a length limit of 63 characters.

derived_struct_data

Struct

Output only. This field is OUTPUT_ONLY. It contains derived data that are not in the original input document.

index_time

Timestamp

Output only. The last time the document was indexed. If this field is set, the document could be returned in search results.

This field is OUTPUT_ONLY. If this field is not populated, it means the document has never been indexed.

index_status

IndexStatus

Output only. The index status of the document.

  • If document is indexed successfully, the index_time field is populated.
  • Otherwise, if document is not indexed due to errors, the error_samples field is populated.
  • Otherwise, index_status is unset.
Union field data. Data representation. One of struct_data or json_data should be provided otherwise an INVALID_ARGUMENT error is thrown. data can be only one of the following:
struct_data

Struct

The structured JSON data for the document. It should conform to the registered Schema or an INVALID_ARGUMENT error is thrown.

json_data

string

The JSON string representation of the document. It should conform to the registered Schema or an INVALID_ARGUMENT error is thrown.

Content

Unstructured data linked to this document.

Fields
mime_type

string

The MIME type of the content. Supported types:

  • application/pdf (PDF, only native PDFs are supported for now)
  • text/html (HTML)
  • application/vnd.openxmlformats-officedocument.wordprocessingml.document (DOCX)
  • application/vnd.openxmlformats-officedocument.presentationml.presentation (PPTX)
  • text/plain (TXT)

See https://www.iana.org/assignments/media-types/media-types.xhtml.

Union field content.

content can be only one of the following:

raw_bytes

bytes

The content represented as a stream of bytes. The maximum length is 1,000,000 bytes (1 MB / ~0.95 MiB).

Note: As with all bytes fields, this field is represented as pure binary in Protocol Buffers and base64-encoded string in JSON. For example, abc123!?$*&()'-=@~ should be represented as YWJjMTIzIT8kKiYoKSctPUB+ in JSON. See https://developers.google.com/protocol-buffers/docs/proto3#json.

uri

string

The URI of the content. Only Cloud Storage URIs (e.g. gs://bucket-name/path/to/file) are supported. The maximum file size is 2.5 MB for text-based formats, 200 MB for other formats.

IndexStatus

Index status of the document.

Fields
index_time

Timestamp

The time when the document was indexed. If this field is populated, it means the document has been indexed.

error_samples[]

Status

A sample of errors encountered while indexing the document. If this field is populated, the document is not indexed due to errors.

DocumentInfo

Detailed document information associated with a user event.

Fields
promotion_ids[]

string

The promotion IDs associated with this Document. Currently, this field is restricted to at most one ID.

joined

bool

Output only. Whether the referenced Document can be found in the data store.

Union field document_descriptor. A required descriptor of the associated Document.

  • If id is specified, then the default values for {location}, {collection_id}, {data_store_id}, and {branch_id} are used when annotating with the stored Document.

  • If name is specified, then the provided values (default values allowed) for {location}, {collection_id}, {data_store_id}, and {branch_id} are used when annotating with the stored Document. document_descriptor can be only one of the following:

id

string

The Document resource ID.

name

string

The Document resource full name, of the form: projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}/branches/{branch_id}/documents/{document_id}

uri

string

The Document URI - only allowed for website data stores.

quantity

int32

Quantity of the Document associated with the user event. Defaults to 1.

For example, this field is 2 if two quantities of the same Document are involved in a add-to-cart event.

Required for events of the following event types:

  • add-to-cart
  • purchase

DocumentProcessingConfig

A singleton resource of DataStore. If it's empty when DataStore is created and DataStore is set to DataStore.ContentConfig.CONTENT_REQUIRED, the default parser will default to digital parser.

Fields
name

string

The full resource name of the Document Processing Config. Format: projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig.

chunking_config

ChunkingConfig

Whether chunking mode is enabled.

default_parsing_config

ParsingConfig

Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.

parsing_config_overrides

map<string, ParsingConfig>

Map from file type to override the default parsing configuration based on the file type. Supported keys:

  • pdf: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported.
  • html: Override parsing config for HTML files, only digital parsing and layout parsing are supported.
  • docx: Override parsing config for DOCX files, only digital parsing and layout parsing are supported.
  • pptx: Override parsing config for PPTX files, only digital parsing and layout parsing are supported.
  • xlsm: Override parsing config for XLSM files, only digital parsing and layout parsing are supported.
  • xlsx: Override parsing config for XLSX files, only digital parsing and layout parsing are supported.

ChunkingConfig

Configuration for chunking config.

Fields
Union field chunk_mode. Additional configs that defines the behavior of the chunking. chunk_mode can be only one of the following:
layout_based_chunking_config

LayoutBasedChunkingConfig

Configuration for the layout based chunking.

LayoutBasedChunkingConfig

Configuration for the layout based chunking.

Fields
chunk_size

int32

The token size limit for each chunk.

Supported values: 100-500 (inclusive). Default value: 500.

include_ancestor_headings

bool

Whether to include appending different levels of headings to chunks from the middle of the document to prevent context loss.

Default value: False.

ParsingConfig

Related configurations applied to a specific type of document parser.

Fields
Union field type_dedicated_config. Configs for document processing types. type_dedicated_config can be only one of the following:
digital_parsing_config

DigitalParsingConfig

Configurations applied to digital parser.

ocr_parsing_config

OcrParsingConfig

Configurations applied to OCR parser. Currently it only applies to PDFs.

layout_parsing_config

LayoutParsingConfig

Configurations applied to layout parser.

DigitalParsingConfig

This type has no fields.

The digital parsing configurations for documents.

LayoutParsingConfig

This type has no fields.

The layout parsing configurations for documents.

OcrParsingConfig

The OCR parsing configurations for documents.

Fields
enhanced_document_elements[]
(deprecated)

string

[DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to layout_parsing_config.

use_native_text

bool

If true, will use native text instead of OCR text on pages containing native text.

DoubleList

Double list.

Fields
values[]

double

Double values.

EmbeddingConfig

Defines embedding config, used for bring your own embeddings feature.

Fields
field_path

string

Full field path in the schema mapped as embedding field.

EnableAdvancedSiteSearchMetadata

Metadata related to the progress of the SiteSearchEngineService.EnableAdvancedSiteSearch operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

EnableAdvancedSiteSearchRequest

Request message for SiteSearchEngineService.EnableAdvancedSiteSearch method.

Fields
site_search_engine

string

Required. Full resource name of the SiteSearchEngine, such as projects/{project}/locations/{location}/dataStores/{data_store_id}/siteSearchEngine.

EnableAdvancedSiteSearchResponse

This type has no fields.

Response message for SiteSearchEngineService.EnableAdvancedSiteSearch method.

Engine

Metadata that describes the training and serving parameters of an Engine.

Fields
name

string

Immutable. The fully qualified resource name of the engine.

This field must be a UTF-8 encoded string with a length limit of 1024 characters.

Format: projects/{project}/locations/{location}/collections/{collection}/engines/{engine} engine should be 1-63 characters, and valid characters are /[a-z0-9][a-z0-9-_]*/. Otherwise, an INVALID_ARGUMENT error is returned.

display_name

string

Required. The display name of the engine. Should be human readable. UTF-8 encoded string with limit of 1024 characters.

create_time

Timestamp

Output only. Timestamp the Recommendation Engine was created at.

update_time

Timestamp

Output only. Timestamp the Recommendation Engine was last updated.

data_store_ids[]

string

The data stores associated with this engine.

For SOLUTION_TYPE_SEARCH and SOLUTION_TYPE_RECOMMENDATION type of engines, they can only associate with at most one data store.

If solution_type is SOLUTION_TYPE_CHAT, multiple DataStores in the same Collection can be associated here.

Note that when used in CreateEngineRequest, one DataStore id must be provided as the system will use it for necessary initializations.

solution_type

SolutionType

Required. The solutions of the engine.

industry_vertical

IndustryVertical

The industry vertical that the engine registers. The restriction of the Engine industry vertical is based on DataStore: If unspecified, default to GENERIC. Vertical on Engine has to match vertical of the DataStore linked to the engine.

common_config

CommonConfig

Common config spec that specifies the metadata of the engine.

disable_analytics

bool

Optional. Whether to disable analytics for searches performed on this engine.

Union field engine_config. Additional config specs that defines the behavior of the engine. engine_config can be only one of the following:
chat_engine_config

ChatEngineConfig

Configurations for the Chat Engine. Only applicable if solution_type is SOLUTION_TYPE_CHAT.

search_engine_config

SearchEngineConfig

Configurations for the Search Engine. Only applicable if solution_type is SOLUTION_TYPE_SEARCH.

Union field engine_metadata. Engine metadata to monitor the status of the engine. engine_metadata can be only one of the following:
chat_engine_metadata

ChatEngineMetadata

Output only. Additional information of the Chat Engine. Only applicable if solution_type is SOLUTION_TYPE_CHAT.

ChatEngineConfig

Configurations for a Chat Engine.

Fields
agent_creation_config

AgentCreationConfig

The configurationt generate the Dialogflow agent that is associated to this Engine.

Note that these configurations are one-time consumed by and passed to Dialogflow service. It means they cannot be retrieved using EngineService.GetEngine or EngineService.ListEngines API after engine creation.

AgentCreationConfig

Configurations for generating a Dialogflow agent.

Note that these configurations are one-time consumed by and passed to Dialogflow service. It means they cannot be retrieved using EngineService.GetEngine or EngineService.ListEngines API after engine creation.

Fields
business

string

Name of the company, organization or other entity that the agent represents. Used for knowledge connector LLM prompt and for knowledge search.

default_language_code

string

Required. The default language of the agent as a language tag. See Language Support for a list of the currently supported language codes.

time_zone

string

Required. The time zone of the agent from the time zone database, e.g., America/New_York, Europe/Paris.

location

string

Agent location for Agent creation, supported values: global/us/eu. If not provided, us Engine will create Agent using us-central-1 by default; eu Engine will create Agent using eu-west-1 by default.

ChatEngineMetadata

Additional information of a Chat Engine. Fields in this message are output only.

Fields
dialogflow_agent

string

The resource name of a Dialogflow agent, that this Chat Engine refers to.

Format: projects/<Project ID>/locations/<Location ID>/agents/<Agent ID>.

CommonConfig

Common configurations for an Engine.

Fields
company_name

string

The name of the company, business or entity that is associated with the engine. Setting this may help improve LLM related features.

SearchEngineConfig

Configurations for a Search Engine.

Fields
search_tier

SearchTier

The search feature tier of this engine.

Different tiers might have different pricing. To learn more, check the pricing documentation.

Defaults to SearchTier.SEARCH_TIER_STANDARD if not specified.

search_add_ons[]

SearchAddOn

The add-on that this search engine enables.

Evaluation

An evaluation is a single execution (or run) of an evaluation process. It encapsulates the state of the evaluation and the resulting data.

Fields
name

string

Identifier. The full resource name of the Evaluation, in the format of projects/{project}/locations/{location}/evaluations/{evaluation}.

This field must be a UTF-8 encoded string with a length limit of 1024 characters.

evaluation_spec

EvaluationSpec

Required. The specification of the evaluation.

quality_metrics

QualityMetrics

Output only. The metrics produced by the evaluation, averaged across all SampleQuerys in the SampleQuerySet.

Only populated when the evaluation's state is SUCCEEDED.

state

State

Output only. The state of the evaluation.

error

Status

Output only. The error that occurred during evaluation. Only populated when the evaluation's state is FAILED.

create_time

Timestamp

Output only. Timestamp the Evaluation was created at.

end_time

Timestamp

Output only. Timestamp the Evaluation was completed at.

error_samples[]

Status

Output only. A sample of errors encountered while processing the request.

EvaluationSpec

Describes the specification of the evaluation.

Fields
query_set_spec

QuerySetSpec

Required. The specification of the query set.

Union field search_spec. The search specification. search_spec can be only one of the following:
search_request

SearchRequest

Required. The search request that is used to perform the evaluation.

Only the following fields within SearchRequest are supported; if any other fields are provided, an UNSUPPORTED error will be returned:

QuerySetSpec

Describes the specification of the query set.

Fields
sample_query_set

string

Required. The full resource name of the SampleQuerySet used for the evaluation, in the format of projects/{project}/locations/{location}/sampleQuerySets/{sampleQuerySet}.

State

Describes the state of an evaluation.

Enums
STATE_UNSPECIFIED The evaluation is unspecified.
PENDING The service is preparing to run the evaluation.
RUNNING The evaluation is in progress.
SUCCEEDED The evaluation completed successfully.
FAILED The evaluation failed.

FetchDomainVerificationStatusRequest

Request message for SiteSearchEngineService.FetchDomainVerificationStatus method.

Fields
site_search_engine

string

Required. The site search engine resource under which we fetch all the domain verification status. projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/siteSearchEngine.

page_size

int32

Requested page size. Server may return fewer items than requested. If unspecified, server will pick an appropriate default. The maximum value is 1000; values above 1000 will be coerced to 1000.

If this field is negative, an INVALID_ARGUMENT error is returned.

page_token

string

A page token, received from a previous FetchDomainVerificationStatus call. Provide this to retrieve the subsequent page.

When paginating, all other parameters provided to FetchDomainVerificationStatus must match the call that provided the page token.

FetchDomainVerificationStatusResponse

Response message for SiteSearchEngineService.FetchDomainVerificationStatus method.

Fields
target_sites[]

TargetSite

List of TargetSites containing the site verification status.

next_page_token

string

A token that can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.

total_size

int32

The total number of items matching the request. This will always be populated in the response.

FhirStoreSource

Cloud FhirStore source import data from.

Fields
fhir_store

string

Required. The full resource name of the FHIR store to import data from, in the format of projects/{project}/locations/{location}/datasets/{dataset}/fhirStores/{fhir_store}.

gcs_staging_dir

string

Intermediate Cloud Storage directory used for the import with a length limit of 2,000 characters. Can be specified if one wants to have the FhirStore export to a specific Cloud Storage directory.

resource_types[]

string

The FHIR resource types to import. The resource types should be a subset of all supported FHIR resource types. Default to all supported FHIR resource types if empty.

FirestoreSource

Firestore source import data from.

Fields
project_id

string

The project ID that the Cloud SQL source is in with a length limit of 128 characters. If not specified, inherits the project ID from the parent request.

database_id

string

Required. The Firestore database to copy the data from with a length limit of 256 characters.

collection_id

string

Required. The Firestore collection (or entity) to copy the data from with a length limit of 1,500 characters.

gcs_staging_dir

string

Intermediate Cloud Storage directory used for the import with a length limit of 2,000 characters. Can be specified if one wants to have the Firestore export to a specific Cloud Storage directory.

Ensure that the Firestore service account has the necessary Cloud Storage Admin permissions to access the specified Cloud Storage directory.

GcsSource

Cloud Storage location for input content.

Fields
input_uris[]

string

Required. Cloud Storage URIs to input files. Each URI can be up to 2000 characters long. URIs can match the full object path (for example, gs://bucket/directory/object.json) or a pattern matching one or more files, such as gs://bucket/directory/*.json.

A request can contain at most 100 files (or 100,000 files if data_schema is content). Each file can be up to 2 GB (or 100 MB if data_schema is content).

data_schema

string

The schema to use when parsing the data from the source.

Supported values for document imports:

  • document (default): One JSON Document per line. Each document must have a valid Document.id.
  • content: Unstructured data (e.g. PDF, HTML). Each file matched by input_uris becomes a document, with the ID set to the first 128 bits of SHA256(URI) encoded as a hex string.
  • custom: One custom data JSON per row in arbitrary format that conforms to the defined Schema of the data store. This can only be used by the GENERIC Data Store vertical.
  • csv: A CSV file with header conforming to the defined Schema of the data store. Each entry after the header is imported as a Document. This can only be used by the GENERIC Data Store vertical.

Supported values for user event imports:

  • user_event (default): One JSON UserEvent per line.

GetAnswerRequest

Request for GetAnswer method.

Fields
name

string

Required. The resource name of the Answer to get. Format: projects/{project}/locations/{location}/collections/{collection}/engines/{engine_id}/sessions/{session_id}/answers/{answer_id}

GetControlRequest

Request for GetControl method.

Fields
name

string

Required. The resource name of the Control to get. Format: projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}/controls/{control_id}

GetConversationRequest

Request for GetConversation method.

Fields
name

string

Required. The resource name of the Conversation to get. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store_id}/conversations/{conversation_id}

GetDataStoreRequest

Request message for DataStoreService.GetDataStore method.

Fields
name

string

Required. Full resource name of DataStore, such as projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}.

If the caller does not have permission to access the DataStore, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the requested DataStore does not exist, a NOT_FOUND error is returned.

GetDocumentRequest

Request message for DocumentService.GetDocument method.

Fields
name

string

Required. Full resource name of Document, such as projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document}.

If the caller does not have permission to access the Document, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the requested Document does not exist, a NOT_FOUND error is returned.

GetEngineRequest

Request message for EngineService.GetEngine method.

Fields
name

string

Required. Full resource name of Engine, such as projects/{project}/locations/{location}/collections/{collection_id}/engines/{engine_id}.

GetEvaluationRequest

Request message for EvaluationService.GetEvaluation method.

Fields
name

string

Required. Full resource name of Evaluation, such as projects/{project}/locations/{location}/evaluations/{evaluation}.

If the caller does not have permission to access the Evaluation, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the requested Evaluation does not exist, a NOT_FOUND error is returned.

GetSampleQueryRequest

Request message for SampleQueryService.GetSampleQuery method.

Fields
name

string

Required. Full resource name of SampleQuery, such as projects/{project}/locations/{location}/sampleQuerySets/{sample_query_set}/sampleQueries/{sample_query}.

If the caller does not have permission to access the SampleQuery, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the requested SampleQuery does not exist, a NOT_FOUND error is returned.

GetSampleQuerySetRequest

Request message for SampleQuerySetService.GetSampleQuerySet method.

Fields
name

string

Required. Full resource name of SampleQuerySet, such as projects/{project}/locations/{location}/sampleQuerySets/{sample_query_set}.

If the caller does not have permission to access the SampleQuerySet, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the requested SampleQuerySet does not exist, a NOT_FOUND error is returned.

GetSchemaRequest

Request message for SchemaService.GetSchema method.

Fields
name

string

Required. The full resource name of the schema, in the format of projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/schemas/{schema}.

GetServingConfigRequest

Request for GetServingConfig method.

Fields
name

string

Required. The resource name of the ServingConfig to get. Format: projects/{project}/locations/{location}/collections/{collection}/engines/{engine}/servingConfigs/{serving_config_id}

GetSessionRequest

Request for GetSession method.

Fields
name

string

Required. The resource name of the Session to get. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store_id}/sessions/{session_id}

GetSiteSearchEngineRequest

Request message for SiteSearchEngineService.GetSiteSearchEngine method.

Fields
name

string

Required. Resource name of SiteSearchEngine, such as projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/siteSearchEngine.

If the caller does not have permission to access the [SiteSearchEngine], regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

GetTargetSiteRequest

Request message for SiteSearchEngineService.GetTargetSite method.

Fields
name

string

Required. Full resource name of TargetSite, such as projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/siteSearchEngine/targetSites/{target_site}.

If the caller does not have permission to access the TargetSite, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the requested TargetSite does not exist, a NOT_FOUND error is returned.

GroundingFact

Grounding Fact.

Fields
fact_text

string

Text content of the fact. Can be at most 10K characters long.

attributes

map<string, string>

Attributes associated with the fact. Common attributes include source (indicating where the fact was sourced from), author (indicating the author of the fact), and so on.

ImportCompletionSuggestionsMetadata

Metadata related to the progress of the ImportCompletionSuggestions operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

success_count

int64

Count of CompletionSuggestions successfully imported.

failure_count

int64

Count of CompletionSuggestions that failed to be imported.

ImportCompletionSuggestionsRequest

Request message for CompletionService.ImportCompletionSuggestions method.

Fields
parent

string

Required. The parent data store resource name for which to import customer autocomplete suggestions.

Follows pattern projects/*/locations/*/collections/*/dataStores/*

error_config

ImportErrorConfig

The desired location of errors incurred during the Import.

Union field source. The source of the autocomplete suggestions. source can be only one of the following:
inline_source

InlineSource

The Inline source for suggestion entries.

gcs_source

GcsSource

Cloud Storage location for the input content.

bigquery_source

BigQuerySource

BigQuery input source.

InlineSource

The inline source for CompletionSuggestions.

Fields
suggestions[]

CompletionSuggestion

Required. A list of all denylist entries to import. Max of 1000 items.

ImportCompletionSuggestionsResponse

Response of the CompletionService.ImportCompletionSuggestions method. If the long running operation is done, this message is returned by the google.longrunning.Operations.response field if the operation is successful.

Fields
error_samples[]

Status

A sample of errors encountered while processing the request.

error_config

ImportErrorConfig

The desired location of errors incurred during the Import.

ImportDocumentsMetadata

Metadata related to the progress of the ImportDocuments operation. This is returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

success_count

int64

Count of entries that were processed successfully.

failure_count

int64

Count of entries that encountered errors while processing.

total_count

int64

Total count of entries that were processed.

ImportDocumentsRequest

Request message for Import methods.

Fields
parent

string

Required. The parent branch resource name, such as projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}. Requires create/update permission.

error_config

ImportErrorConfig

The desired location of errors incurred during the Import.

reconciliation_mode

ReconciliationMode

The mode of reconciliation between existing documents and the documents to be imported. Defaults to ReconciliationMode.INCREMENTAL.

update_mask

FieldMask

Indicates which fields in the provided imported documents to update. If not set, the default is to update all fields.

auto_generate_ids

bool

Whether to automatically generate IDs for the documents if absent.

If set to true, Document.ids are automatically generated based on the hash of the payload, where IDs may not be consistent during multiple imports. In which case ReconciliationMode.FULL is highly recommended to avoid duplicate contents. If unset or set to false, Document.ids have to be specified using id_field, otherwise, documents without IDs fail to be imported.

Supported data sources:

id_field

string

The field indicates the ID field or column to be used as unique IDs of the documents.

For GcsSource it is the key of the JSON field. For instance, my_id for JSON {"my_id": "some_uuid"}. For others, it may be the column name of the table where the unique ids are stored.

The values of the JSON field or the table column are used as the Document.ids. The JSON field or the table column must be of string type, and the values must be set as valid strings conform to RFC-1034 with 1-63 characters. Otherwise, documents without valid IDs fail to be imported.

Only set this field when auto_generate_ids is unset or set as false. Otherwise, an INVALID_ARGUMENT error is thrown.

If it is unset, a default value _id is used when importing from the allowed data sources.

Supported data sources:

Union field source. Required. The source of the input. source can be only one of the following:
inline_source

InlineSource

The Inline source for the input content for documents.

gcs_source

GcsSource

Cloud Storage location for the input content.

bigquery_source

BigQuerySource

BigQuery input source.

fhir_store_source

FhirStoreSource

FhirStore input source.

spanner_source

SpannerSource

Spanner input source.

cloud_sql_source

CloudSqlSource

Cloud SQL input source.

firestore_source

FirestoreSource

Firestore input source.

alloy_db_source

AlloyDbSource

AlloyDB input source.

bigtable_source

BigtableSource

Cloud Bigtable input source.

InlineSource

The inline source for the input config for ImportDocuments method.

Fields
documents[]

Document

Required. A list of documents to update/create. Each document must have a valid Document.id. Recommended max of 100 items.

ReconciliationMode

Indicates how imported documents are reconciled with the existing documents created or imported before.

Enums
RECONCILIATION_MODE_UNSPECIFIED Defaults to INCREMENTAL.
INCREMENTAL Inserts new documents or updates existing documents.
FULL Calculates diff and replaces the entire document dataset. Existing documents may be deleted if they are not present in the source location.

ImportDocumentsResponse

Response of the ImportDocumentsRequest. If the long running operation is done, then this message is returned by the google.longrunning.Operations.response field if the operation was successful.

Fields
error_samples[]

Status

A sample of errors encountered while processing the request.

error_config

ImportErrorConfig

Echoes the destination for the complete errors in the request if set.

ImportErrorConfig

Configuration of destination for Import related errors.

Fields
Union field destination. Required. Errors destination. destination can be only one of the following:
gcs_prefix

string

Cloud Storage prefix for import errors. This must be an empty, existing Cloud Storage directory. Import errors are written to sharded files in this directory, one per line, as a JSON-encoded google.rpc.Status message.

ImportSampleQueriesMetadata

Metadata related to the progress of the ImportSampleQueries operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

ImportSampleQueries operation create time.

update_time

Timestamp

ImportSampleQueries operation last update time. If the operation is done, this is also the finish time.

success_count

int64

Count of SampleQuerys successfully imported.

failure_count

int64

Count of SampleQuerys that failed to be imported.

total_count

int64

Total count of SampleQuerys that were processed.

ImportSampleQueriesRequest

Request message for SampleQueryService.ImportSampleQueries method.

Fields
parent

string

Required. The parent sample query set resource name, such as projects/{project}/locations/{location}/sampleQuerySets/{sampleQuerySet}.

If the caller does not have permission to list SampleQuerys under this sample query set, regardless of whether or not this sample query set exists, a PERMISSION_DENIED error is returned.

error_config

ImportErrorConfig

The desired location of errors incurred during the Import.

Union field source. The source of the sample queries. source can be only one of the following:
inline_source

InlineSource

The Inline source for sample query entries.

gcs_source

GcsSource

Cloud Storage location for the input content.

bigquery_source

BigQuerySource

BigQuery input source.

InlineSource

The inline source for SampleQuerys.

Fields
sample_queries[]

SampleQuery

Required. A list of SampleQuerys to import. Max of 1000 items.

ImportSampleQueriesResponse

Response of the SampleQueryService.ImportSampleQueries method. If the long running operation is done, this message is returned by the google.longrunning.Operations.response field if the operation is successful.

Fields
error_samples[]

Status

A sample of errors encountered while processing the request.

error_config

ImportErrorConfig

The desired location of errors incurred during the Import.

ImportSuggestionDenyListEntriesMetadata

Metadata related to the progress of the ImportSuggestionDenyListEntries operation. This is returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

ImportSuggestionDenyListEntriesRequest

Request message for CompletionService.ImportSuggestionDenyListEntries method.

Fields
parent

string

Required. The parent data store resource name for which to import denylist entries. Follows pattern projects/*/locations/*/collections/*/dataStores/*.

Union field source. The source of the updated SuggestionDenyList. source can be only one of the following:
inline_source

InlineSource

The Inline source for the input content for suggestion deny list entries.

gcs_source

GcsSource

Cloud Storage location for the input content.

Only 1 file can be specified that contains all entries to import. Supported values gcs_source.schema for autocomplete suggestion deny list entry imports:

  • suggestion_deny_list (default): One JSON [SuggestionDenyListEntry] per line.

InlineSource

The inline source for SuggestionDenyListEntry.

Fields
entries[]

SuggestionDenyListEntry

Required. A list of all denylist entries to import. Max of 1000 items.

ImportSuggestionDenyListEntriesResponse

Response message for CompletionService.ImportSuggestionDenyListEntries method.

Fields
error_samples[]

Status

A sample of errors encountered while processing the request.

imported_entries_count

int64

Count of deny list entries successfully imported.

failed_entries_count

int64

Count of deny list entries that failed to be imported.

ImportUserEventsMetadata

Metadata related to the progress of the Import operation. This is returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

success_count

int64

Count of entries that were processed successfully.

failure_count

int64

Count of entries that encountered errors while processing.

ImportUserEventsRequest

Request message for the ImportUserEvents request.

Fields
parent

string

Required. Parent DataStore resource name, of the form projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}

error_config

ImportErrorConfig

The desired location of errors incurred during the Import. Cannot be set for inline user event imports.

Union field source. Required - The desired input source of the user event data. source can be only one of the following:
inline_source

InlineSource

The Inline source for the input content for UserEvents.

gcs_source

GcsSource

Cloud Storage location for the input content.

bigquery_source

BigQuerySource

BigQuery input source.

InlineSource

The inline source for the input config for ImportUserEvents method.

Fields
user_events[]

UserEvent

Required. A list of user events to import. Recommended max of 10k items.

ImportUserEventsResponse

Response of the ImportUserEventsRequest. If the long running operation was successful, then this message is returned by the google.longrunning.Operations.response field if the operation was successful.

Fields
error_samples[]

Status

A sample of errors encountered while processing the request.

error_config

ImportErrorConfig

Echoes the destination for the complete errors if this field was set in the request.

joined_events_count

int64

Count of user events imported with complete existing Documents.

unjoined_events_count

int64

Count of user events imported, but with Document information not found in the existing Branch.

IndustryVertical

The industry vertical associated with the DataStore.

Enums
INDUSTRY_VERTICAL_UNSPECIFIED Value used when unset.
GENERIC The generic vertical for documents that are not specific to any industry vertical.
MEDIA The media industry vertical.
HEALTHCARE_FHIR The healthcare FHIR vertical.

Interval

A floating point interval.

Fields

Union field min. The lower bound of the interval. If neither of the min fields are set, then the lower bound is negative infinity.

This field must be not larger than max. Otherwise, an INVALID_ARGUMENT error is returned. min can be only one of the following:

minimum

double

Inclusive lower bound.

exclusive_minimum

double

Exclusive lower bound.

Union field max. The upper bound of the interval. If neither of the max fields are set, then the upper bound is positive infinity.

This field must be not smaller than min. Otherwise, an INVALID_ARGUMENT error is returned. max can be only one of the following:

maximum

double

Inclusive upper bound.

exclusive_maximum

double

Exclusive upper bound.

LanguageInfo

Language info for DataStore.

Fields
language_code

string

The language code for the DataStore.

normalized_language_code

string

Output only. This is the normalized form of language_code. E.g.: language_code of en-GB, en_GB, en-UK or en-gb will have normalized_language_code of en-GB.

language

string

Output only. Language part of normalized_language_code. E.g.: en-US -> en, zh-Hans-HK -> zh, en -> en.

region

string

Output only. Region part of normalized_language_code, if present. E.g.: en-US -> US, zh-Hans-HK -> HK, en -> ``.

ListControlsRequest

Request for ListControls method.

Fields
parent

string

Required. The data store resource name. Format: projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id} or projects/{project}/locations/{location}/collections/{collection_id}/engines/{engine_id}.

page_size

int32

Optional. Maximum number of results to return. If unspecified, defaults to 50. Max allowed value is 1000.

page_token

string

Optional. A page token, received from a previous ListControls call. Provide this to retrieve the subsequent page.

filter

string

Optional. A filter to apply on the list results. Supported features:

  • List all the products under the parent branch if filter is unset. Currently this field is unsupported.

ListControlsResponse

Response for ListControls method.

Fields
controls[]

Control

All the Controls for a given data store.

next_page_token

string

Pagination token, if not returned indicates the last page.

ListConversationsRequest

Request for ListConversations method.

Fields
parent

string

Required. The data store resource name. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store_id}

page_size

int32

Maximum number of results to return. If unspecified, defaults to 50. Max allowed value is 1000.

page_token

string

A page token, received from a previous ListConversations call. Provide this to retrieve the subsequent page.

filter

string

A filter to apply on the list results. The supported features are: user_pseudo_id, state.

Example: "user_pseudo_id = some_id"

order_by

string

A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields: * update_time * create_time * conversation_name

Example: "update_time desc" "create_time"

ListConversationsResponse

Response for ListConversations method.

Fields
conversations[]

Conversation

All the Conversations for a given data store.

next_page_token

string

Pagination token, if not returned indicates the last page.

ListCustomModelsRequest

Request message for SearchTuningService.ListCustomModels method.

Fields
data_store

string

Required. The resource name of the parent Data Store, such as projects/*/locations/global/collections/default_collection/dataStores/default_data_store. This field is used to identify the data store where to fetch the models from.

ListCustomModelsResponse

Response message for SearchTuningService.ListCustomModels method.

Fields
models[]

CustomTuningModel

List of custom tuning models.

ListDataStoresRequest

Request message for DataStoreService.ListDataStores method.

Fields
parent

string

Required. The parent branch resource name, such as projects/{project}/locations/{location}/collections/{collection_id}.

If the caller does not have permission to list DataStores under this location, regardless of whether or not this data store exists, a PERMISSION_DENIED error is returned.

page_size

int32

Maximum number of DataStores to return. If unspecified, defaults to 10. The maximum allowed value is 50. Values above 50 will be coerced to 50.

If this field is negative, an INVALID_ARGUMENT is returned.

page_token

string

A page token ListDataStoresResponse.next_page_token, received from a previous DataStoreService.ListDataStores call. Provide this to retrieve the subsequent page.

When paginating, all other parameters provided to DataStoreService.ListDataStores must match the call that provided the page token. Otherwise, an INVALID_ARGUMENT error is returned.

filter

string

Filter by solution type . For example: filter = 'solution_type:SOLUTION_TYPE_SEARCH'

ListDataStoresResponse

Response message for DataStoreService.ListDataStores method.

Fields
data_stores[]

DataStore

All the customer's DataStores.

next_page_token

string

A token that can be sent as ListDataStoresRequest.page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.

ListDocumentsRequest

Request message for DocumentService.ListDocuments method.

Fields
parent

string

Required. The parent branch resource name, such as projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}. Use default_branch as the branch ID, to list documents under the default branch.

If the caller does not have permission to list Documents under this branch, regardless of whether or not this branch exists, a PERMISSION_DENIED error is returned.

page_size

int32

Maximum number of Documents to return. If unspecified, defaults to 100. The maximum allowed value is 1000. Values above 1000 are set to 1000.

If this field is negative, an INVALID_ARGUMENT error is returned.

page_token

string

A page token ListDocumentsResponse.next_page_token, received from a previous DocumentService.ListDocuments call. Provide this to retrieve the subsequent page.

When paginating, all other parameters provided to DocumentService.ListDocuments must match the call that provided the page token. Otherwise, an INVALID_ARGUMENT error is returned.

ListDocumentsResponse

Response message for DocumentService.ListDocuments method.

Fields
documents[]

Document

The Documents.

next_page_token

string

A token that can be sent as ListDocumentsRequest.page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.

ListEnginesRequest

Request message for EngineService.ListEngines method.

Fields
parent

string

Required. The parent resource name, such as projects/{project}/locations/{location}/collections/{collection_id}.

page_size

int32

Optional. Not supported.

page_token

string

Optional. Not supported.

filter

string

Optional. Filter by solution type. For example: solution_type=SOLUTION_TYPE_SEARCH

ListEnginesResponse

Response message for EngineService.ListEngines method.

Fields
engines[]

Engine

All the customer's Engines.

next_page_token

string

Not supported.

ListEvaluationResultsRequest

Request message for EvaluationService.ListEvaluationResults method.

Fields
evaluation

string

Required. The evaluation resource name, such as projects/{project}/locations/{location}/evaluations/{evaluation}.

If the caller does not have permission to list [EvaluationResult][] under this evaluation, regardless of whether or not this evaluation set exists, a PERMISSION_DENIED error is returned.

page_size

int32

Maximum number of [EvaluationResult][] to return. If unspecified, defaults to 100. The maximum allowed value is 1000. Values above 1000 will be coerced to 1000.

If this field is negative, an INVALID_ARGUMENT error is returned.

page_token

string

A page token ListEvaluationResultsResponse.next_page_token, received from a previous EvaluationService.ListEvaluationResults call. Provide this to retrieve the subsequent page.

When paginating, all other parameters provided to EvaluationService.ListEvaluationResults must match the call that provided the page token. Otherwise, an INVALID_ARGUMENT error is returned.

ListEvaluationResultsResponse

Response message for EvaluationService.ListEvaluationResults method.

Fields
evaluation_results[]

EvaluationResult

The EvaluationResults.

next_page_token

string

A token that can be sent as ListEvaluationResultsRequest.page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.

EvaluationResult

Represents the results of an evaluation for a single SampleQuery.

Fields
sample_query

SampleQuery

Output only. The SampleQuery that was evaluated.

quality_metrics

QualityMetrics

Output only. The metrics produced by the evaluation, for a given SampleQuery.

ListEvaluationsRequest

Request message for EvaluationService.ListEvaluations method.

Fields
parent

string

Required. The parent location resource name, such as projects/{project}/locations/{location}.

If the caller does not have permission to list Evaluations under this location, regardless of whether or not this location exists, a PERMISSION_DENIED error is returned.

page_size

int32

Maximum number of Evaluations to return. If unspecified, defaults to 100. The maximum allowed value is 1000. Values above 1000 will be coerced to 1000.

If this field is negative, an INVALID_ARGUMENT error is returned.

page_token

string

A page token ListEvaluationsResponse.next_page_token, received from a previous EvaluationService.ListEvaluations call. Provide this to retrieve the subsequent page.

When paginating, all other parameters provided to EvaluationService.ListEvaluations must match the call that provided the page token. Otherwise, an INVALID_ARGUMENT error is returned.

ListEvaluationsResponse

Response message for EvaluationService.ListEvaluations method.

Fields
evaluations[]

Evaluation

The Evaluations.

next_page_token

string

A token that can be sent as ListEvaluationsRequest.page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.

ListSampleQueriesRequest

Request message for SampleQueryService.ListSampleQueries method.

Fields
parent

string

Required. The parent sample query set resource name, such as projects/{project}/locations/{location}/sampleQuerySets/{sampleQuerySet}.

If the caller does not have permission to list SampleQuerys under this sample query set, regardless of whether or not this sample query set exists, a PERMISSION_DENIED error is returned.

page_size

int32

Maximum number of SampleQuerys to return. If unspecified, defaults to 100. The maximum allowed value is 1000. Values above 1000 will be coerced to 1000.

If this field is negative, an INVALID_ARGUMENT error is returned.

page_token

string

A page token ListSampleQueriesResponse.next_page_token, received from a previous SampleQueryService.ListSampleQueries call. Provide this to retrieve the subsequent page.

When paginating, all other parameters provided to SampleQueryService.ListSampleQueries must match the call that provided the page token. Otherwise, an INVALID_ARGUMENT error is returned.

ListSampleQueriesResponse

Response message for SampleQueryService.ListSampleQueries method.

Fields
sample_queries[]

SampleQuery

The SampleQuerys.

next_page_token

string

A token that can be sent as ListSampleQueriesRequest.page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.

ListSampleQuerySetsRequest

Request message for SampleQuerySetService.ListSampleQuerySets method.

Fields
parent

string

Required. The parent location resource name, such as projects/{project}/locations/{location}.

If the caller does not have permission to list SampleQuerySets under this location, regardless of whether or not this location exists, a PERMISSION_DENIED error is returned.

page_size

int32

Maximum number of SampleQuerySets to return. If unspecified, defaults to 100. The maximum allowed value is 1000. Values above 1000 will be coerced to 1000.

If this field is negative, an INVALID_ARGUMENT error is returned.

page_token

string

A page token ListSampleQuerySetsResponse.next_page_token, received from a previous SampleQuerySetService.ListSampleQuerySets call. Provide this to retrieve the subsequent page.

When paginating, all other parameters provided to SampleQuerySetService.ListSampleQuerySets must match the call that provided the page token. Otherwise, an INVALID_ARGUMENT error is returned.

ListSampleQuerySetsResponse

Response message for SampleQuerySetService.ListSampleQuerySets method.

Fields
sample_query_sets[]

SampleQuerySet

The SampleQuerySets.

next_page_token

string

A token that can be sent as ListSampleQuerySetsRequest.page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.

ListSchemasRequest

Request message for SchemaService.ListSchemas method.

Fields
parent

string

Required. The parent data store resource name, in the format of projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}.

page_size

int32

The maximum number of Schemas to return. The service may return fewer than this value.

If unspecified, at most 100 Schemas are returned.

The maximum value is 1000; values above 1000 are set to 1000.

page_token

string

A page token, received from a previous SchemaService.ListSchemas call. Provide this to retrieve the subsequent page.

When paginating, all other parameters provided to SchemaService.ListSchemas must match the call that provided the page token.

ListSchemasResponse

Response message for SchemaService.ListSchemas method.

Fields
schemas[]

Schema

The Schemas.

next_page_token

string

A token that can be sent as ListSchemasRequest.page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.

ListServingConfigsRequest

Request for ListServingConfigs method.

Fields
parent

string

Required. Full resource name of the parent resource. Format: projects/{project}/locations/{location}/collections/{collection}/engines/{engine}

page_size

int32

Optional. Maximum number of results to return. If unspecified, defaults to 100. If a value greater than 100 is provided, at most 100 results are returned.

page_token

string

Optional. A page token, received from a previous ListServingConfigs call. Provide this to retrieve the subsequent page.

ListServingConfigsResponse

Response for ListServingConfigs method.

Fields
serving_configs[]

ServingConfig

All the ServingConfigs for a given dataStore.

next_page_token

string

Pagination token, if not returned indicates the last page.

ListSessionsRequest

Request for ListSessions method.

Fields
parent

string

Required. The data store resource name. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store_id}

page_size

int32

Maximum number of results to return. If unspecified, defaults to 50. Max allowed value is 1000.

page_token

string

A page token, received from a previous ListSessions call. Provide this to retrieve the subsequent page.

filter

string

A filter to apply on the list results. The supported features are: user_pseudo_id, state.

Example: "user_pseudo_id = some_id"

order_by

string

A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields: * update_time * create_time * session_name

Example: "update_time desc" "create_time"

ListSessionsResponse

Response for ListSessions method.

Fields
sessions[]

Session

All the Sessions for a given data store.

next_page_token

string

Pagination token, if not returned indicates the last page.

ListTargetSitesRequest

Request message for SiteSearchEngineService.ListTargetSites method.

Fields
parent

string

Required. The parent site search engine resource name, such as projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/siteSearchEngine.

If the caller does not have permission to list TargetSites under this site search engine, regardless of whether or not this branch exists, a PERMISSION_DENIED error is returned.

page_size

int32

Requested page size. Server may return fewer items than requested. If unspecified, server will pick an appropriate default. The maximum value is 1000; values above 1000 will be coerced to 1000.

If this field is negative, an INVALID_ARGUMENT error is returned.

page_token

string

A page token, received from a previous ListTargetSites call. Provide this to retrieve the subsequent page.

When paginating, all other parameters provided to ListTargetSites must match the call that provided the page token.

ListTargetSitesResponse

Response message for SiteSearchEngineService.ListTargetSites method.

Fields
target_sites[]

TargetSite

List of TargetSites.

next_page_token

string

A token that can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.

total_size

int32

The total number of items matching the request. This will always be populated in the response.

MediaInfo

Media-specific user event information.

Fields
media_progress_duration

Duration

The media progress time in seconds, if applicable. For example, if the end user has finished 90 seconds of a playback video, then MediaInfo.media_progress_duration.seconds should be set to 90.

media_progress_percentage

float

Media progress should be computed using only the media_progress_duration relative to the media total length.

This value must be between [0, 1.0] inclusive.

If this is not a playback or the progress cannot be computed (e.g. ongoing livestream), this field should be unset.

NaturalLanguageQueryUnderstandingConfig

Configuration for Natural Language Query Understanding.

Fields
mode

Mode

Mode of Natural Language Query Understanding. If this field is unset, the behavior defaults to NaturalLanguageQueryUnderstandingConfig.Mode.DISABLED.

Mode

Mode of Natural Language Query Understanding. When the NaturalLanguageQueryUnderstandingConfig.Mode is ENABLED, the natural language understanding capabilities will be enabled for a search request if the NaturalLanguageQueryUnderstandingSpec.FilterExtractionCondition in the SearchRequest is ENABLED.

Enums
MODE_UNSPECIFIED Default value.
DISABLED Natural Language Query Understanding is disabled.
ENABLED Natural Language Query Understanding is enabled.

PageInfo

Detailed page information.

Fields
pageview_id

string

A unique ID of a web page view.

This should be kept the same for all user events triggered from the same pageview. For example, an item detail page view could trigger multiple events as the user is browsing the page. The pageview_id property should be kept the same for all these events so that they can be grouped together properly.

When using the client side event reporting with JavaScript pixel and Google Tag Manager, this value is filled in automatically.

page_category

string

The most specific category associated with a category page.

To represent full path of category, use '>' sign to separate different hierarchies. If '>' is part of the category name, replace it with other character(s).

Category pages include special pages such as sales or promotions. For instance, a special sale page may have the category hierarchy: "pageCategory" : "Sales > 2017 Black Friday Deals".

Required for view-category-page events. Other event types should not set this field. Otherwise, an INVALID_ARGUMENT error is returned.

uri

string

Complete URL (window.location.href) of the user's current page.

When using the client side event reporting with JavaScript pixel and Google Tag Manager, this value is filled in automatically. Maximum length 5,000 characters.

referrer_uri

string

The referrer URL of the current page.

When using the client side event reporting with JavaScript pixel and Google Tag Manager, this value is filled in automatically. However, some browser privacy restrictions may cause this field to be empty.

PanelInfo

Detailed panel information associated with a user event.

Fields
panel_id

string

Required. The panel ID.

display_name

string

The display name of the panel.

panel_position

int32

The ordered position of the panel, if shown to the user with other panels. If set, then total_panels must also be set.

total_panels

int32

The total number of panels, including this one, shown to the user. Must be set if panel_position is set.

PauseEngineRequest

Request for pausing training of an engine.

Fields
name

string

Required. The name of the engine to pause. Format: projects/{project}/locations/{location}/collections/{collection_id}/engines/{engine_id}

Project

Metadata and configurations for a Google Cloud project in the service.

Fields
name

string

Output only. Full resource name of the project, for example projects/{project}. Note that when making requests, project number and project id are both acceptable, but the server will always respond in project number.

create_time

Timestamp

Output only. The timestamp when this project is created.

provision_completion_time

Timestamp

Output only. The timestamp when this project is successfully provisioned. Empty value means this project is still provisioning and is not ready for use.

service_terms_map

map<string, ServiceTerms>

Output only. A map of terms of services. The key is the id of ServiceTerms.

ServiceTerms

Metadata about the terms of service.

Fields
id

string

The unique identifier of this terms of service. Available terms:

version

string

The version string of the terms of service. For acceptable values, see the comments for id above.

state

State

Whether the project has accepted/rejected the service terms or it is still pending.

accept_time

Timestamp

The last time when the project agreed to the terms of service.

decline_time

Timestamp

The last time when the project declined or revoked the agreement to terms of service.

State

The agreement states this terms of service.

Enums
STATE_UNSPECIFIED The default value of the enum. This value is not actually used.
TERMS_ACCEPTED The project has given consent to the terms of service.
TERMS_PENDING The project is pending to review and accept the terms of service.
TERMS_DECLINED The project has declined or revoked the agreement to terms of service.

ProvisionProjectMetadata

This type has no fields.

Metadata associated with a project provision operation.

ProvisionProjectRequest

Request for ProjectService.ProvisionProject method.

Fields
name

string

Required. Full resource name of a Project, such as projects/{project_id_or_number}.

accept_data_use_terms

bool

Required. Set to true to specify that caller has read and would like to give consent to the Terms for data use.

data_use_terms_version

string

Required. The version of the Terms for data use that caller has read and would like to give consent to.

Acceptable version is 2022-11-23, and this may change over time.

PurgeCompletionSuggestionsMetadata

Metadata related to the progress of the PurgeCompletionSuggestions operation. This is returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

PurgeCompletionSuggestionsRequest

Request message for CompletionService.PurgeCompletionSuggestions method.

Fields
parent

string

Required. The parent data store resource name for which to purge completion suggestions. Follows pattern projects/*/locations/*/collections/*/dataStores/*.

PurgeCompletionSuggestionsResponse

Response message for CompletionService.PurgeCompletionSuggestions method.

Fields
purge_succeeded

bool

Whether the completion suggestions were successfully purged.

error_samples[]

Status

A sample of errors encountered while processing the request.

PurgeDocumentsMetadata

Metadata related to the progress of the PurgeDocuments operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

success_count

int64

Count of entries that were deleted successfully.

failure_count

int64

Count of entries that encountered errors while processing.

ignored_count

int64

Count of entries that were ignored as entries were not found.

PurgeDocumentsRequest

Request message for DocumentService.PurgeDocuments method.

Fields
parent

string

Required. The parent resource name, such as projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}.

filter

string

Required. Filter matching documents to purge. Only currently supported value is * (all items).

error_config

PurgeErrorConfig

The desired location of errors incurred during the purge.

force

bool

Actually performs the purge. If force is set to false, return the expected purge count without deleting any documents.

Union field source. The desired input source for the purging documents based on document IDs. source can be only one of the following:
gcs_source

GcsSource

Cloud Storage location for the input content. Supported data_schema: * document_id: One valid Document.id per line.

inline_source

InlineSource

Inline source for the input content for purge.

InlineSource

The inline source for the input config for DocumentService.PurgeDocuments method.

Fields
documents[]

string

Required. A list of full resource name of documents to purge. In the format projects/*/locations/*/collections/*/dataStores/*/branches/*/documents/*. Recommended max of 100 items.

PurgeDocumentsResponse

Response message for DocumentService.PurgeDocuments method. If the long running operation is successfully done, then this message is returned by the google.longrunning.Operations.response field.

Fields
purge_count

int64

The total count of documents purged as a result of the operation.

purge_sample[]

string

A sample of document names that will be deleted. Only populated if force is set to false. A max of 100 names will be returned and the names are chosen at random.

PurgeErrorConfig

Configuration of destination for Purge related errors.

Fields
Union field destination. Required. Errors destination. destination can be only one of the following:
gcs_prefix

string

Cloud Storage prefix for purge errors. This must be an empty, existing Cloud Storage directory. Purge errors are written to sharded files in this directory, one per line, as a JSON-encoded google.rpc.Status message.

PurgeSuggestionDenyListEntriesMetadata

Metadata related to the progress of the PurgeSuggestionDenyListEntries operation. This is returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

PurgeSuggestionDenyListEntriesRequest

Request message for CompletionService.PurgeSuggestionDenyListEntries method.

Fields
parent

string

Required. The parent data store resource name for which to import denylist entries. Follows pattern projects/*/locations/*/collections/*/dataStores/*.

PurgeSuggestionDenyListEntriesResponse

Response message for CompletionService.PurgeSuggestionDenyListEntries method.

Fields
purge_count

int64

Number of suggestion deny list entries purged.

error_samples[]

Status

A sample of errors encountered while processing the request.

PurgeUserEventsMetadata

Metadata related to the progress of the PurgeUserEvents operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

success_count

int64

Count of entries that were deleted successfully.

failure_count

int64

Count of entries that encountered errors while processing.

PurgeUserEventsRequest

Request message for PurgeUserEvents method.

Fields
parent

string

Required. The resource name of the catalog under which the events are created. The format is projects/{project}/locations/global/collections/{collection}/dataStores/{dataStore}.

filter

string

Required. The filter string to specify the events to be deleted with a length limit of 5,000 characters. The eligible fields for filtering are:

  • eventType: Double quoted UserEvent.event_type string.
  • eventTime: in ISO 8601 "zulu" format.
  • userPseudoId: Double quoted string. Specifying this will delete all events associated with a visitor.
  • userId: Double quoted string. Specifying this will delete all events associated with a user.

Examples:

  • Deleting all events in a time range: eventTime > "2012-04-23T18:25:43.511Z" eventTime < "2012-04-23T18:30:43.511Z"
  • Deleting specific eventType: eventType = "search"
  • Deleting all events for a specific visitor: userPseudoId = "visitor1024"
  • Deleting all events inside a DataStore: *

The filtering fields are assumed to have an implicit AND.

force

bool

The force field is currently not supported. Purge user event requests will permanently delete all purgeable events. Once the development is complete: If force is set to false, the method will return the expected purge count without deleting any user events. This field will default to false if not included in the request.

PurgeUserEventsResponse

Response of the PurgeUserEventsRequest. If the long running operation is successfully done, then this message is returned by the google.longrunning.Operations.response field.

Fields
purge_count

int64

The total count of events purged as a result of the operation.

QualityMetrics

Describes the metrics produced by the evaluation.

Fields
doc_recall

TopkMetrics

Recall per document, at various top-k cutoff levels.

Recall is the fraction of relevant documents retrieved out of all relevant documents.

Example (top-5): * For a single SampleQuery, If 3 out of 5 relevant documents are retrieved in the top-5, recall@5 = 3/5 = 0.6

doc_precision

TopkMetrics

Precision per document, at various top-k cutoff levels.

Precision is the fraction of retrieved documents that are relevant.

Example (top-5): * For a single SampleQuery, If 4 out of 5 retrieved documents in the top-5 are relevant, precision@5 = 4/5 = 0.8

doc_ndcg

TopkMetrics

Normalized discounted cumulative gain (NDCG) per document, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved documents (D1, D2, D3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [D3 (0), D1 (1), D2 (1)] Ideal: [D1 (1), D2 (1), D3 (0)]

Calculate NDCG@3 for each SampleQuery: * DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13 * Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63 * NDCG@3: 1.13/1.63 = 0.693

page_recall

TopkMetrics

Recall per page, at various top-k cutoff levels.

Recall is the fraction of relevant pages retrieved out of all relevant pages.

Example (top-5): * For a single SampleQuery, if 3 out of 5 relevant pages are retrieved in the top-5, recall@5 = 3/5 = 0.6

page_ndcg

TopkMetrics

Normalized discounted cumulative gain (NDCG) per page, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved pages (P1, P2, P3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [P3 (0), P1 (1), P2 (1)] Ideal: [P1 (1), P2 (1), P3 (0)]

Calculate NDCG@3 for SampleQuery: * DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13 * Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63 * NDCG@3: 1.13/1.63 = 0.693

TopkMetrics

Stores the metric values at specific top-k levels.

Fields
top_1

double

The top-1 value.

top_3

double

The top-3 value.

top_5

double

The top-5 value.

top_10

double

The top-10 value.

Query

Defines a user inputed query.

Fields
query_id

string

Unique Id for the query.

Union field content. Query content. content can be only one of the following:
text

string

Plain text.

RankRequest

Request message for RankService.Rank method.

Fields
ranking_config

string

Required. The resource name of the rank service config, such as projects/{project_num}/locations/{location}/rankingConfigs/default_ranking_config.

model

string

The identifier of the model to use. It is one of:

  • semantic-ranker-512@latest: Semantic ranking model with maxiumn input token size 512.

It is set to semantic-ranker-512@latest by default if unspecified.

top_n

int32

The number of results to return. If this is unset or no bigger than zero, returns all results.

query

string

The query to use.

records[]

RankingRecord

Required. A list of records to rank. At most 200 records to rank.

ignore_record_details_in_response

bool

If true, the response will contain only record ID and score. By default, it is false, the response will contain record details.

user_labels

map<string, string>

The user labels applied to a resource must meet the following requirements:

  • Each resource can have multiple labels, up to a maximum of 64.
  • Each label must be a key-value pair.
  • Keys have a minimum length of 1 character and a maximum length of 63 characters and cannot be empty. Values can be empty and have a maximum length of 63 characters.
  • Keys and values can contain only lowercase letters, numeric characters, underscores, and dashes. All characters must use UTF-8 encoding, and international characters are allowed.
  • The key portion of a label must be unique. However, you can use the same key with multiple resources.
  • Keys must start with a lowercase letter or international character.

See Google Cloud Document for more details.

RankResponse

Response message for RankService.Rank method.

Fields
records[]

RankingRecord

A list of records sorted by descending score.

RankingRecord

Record message for RankService.Rank method.

Fields
id

string

The unique ID to represent the record.

title

string

The title of the record. Empty by default. At least one of title or content should be set otherwise an INVALID_ARGUMENT error is thrown.

content

string

The content of the record. Empty by default. At least one of title or content should be set otherwise an INVALID_ARGUMENT error is thrown.

score

float

The score of this record based on the given query and selected model.

RecommendRequest

Request message for Recommend method.

Fields
serving_config

string

Required. Full resource name of a ServingConfig: projects/*/locations/global/collections/*/engines/*/servingConfigs/*, or projects/*/locations/global/collections/*/dataStores/*/servingConfigs/*

One default serving config is created along with your recommendation engine creation. The engine ID is used as the ID of the default serving config. For example, for Engine projects/*/locations/global/collections/*/engines/my-engine, you can use projects/*/locations/global/collections/*/engines/my-engine/servingConfigs/my-engine for your RecommendationService.Recommend requests.

user_event

UserEvent

Required. Context about the user, what they are looking at and what action they took to trigger the Recommend request. Note that this user event detail won't be ingested to userEvent logs. Thus, a separate userEvent write request is required for event logging.

Don't set UserEvent.user_pseudo_id or UserEvent.user_info.user_id to the same fixed ID for different users. If you are trying to receive non-personalized recommendations (not recommended; this can negatively impact model performance), instead set UserEvent.user_pseudo_id to a random unique ID and leave UserEvent.user_info.user_id unset.

page_size

int32

Maximum number of results to return. Set this property to the number of recommendation results needed. If zero, the service chooses a reasonable default. The maximum allowed value is 100. Values above 100 are set to 100.

filter

string

Filter for restricting recommendation results with a length limit of 5,000 characters. Currently, only filter expressions on the filter_tags attribute is supported.

Examples:

  • (filter_tags: ANY("Red", "Blue") OR filter_tags: ANY("Hot", "Cold"))
  • (filter_tags: ANY("Red", "Blue")) AND NOT (filter_tags: ANY("Green"))

If attributeFilteringSyntax is set to true under the params field, then attribute-based expressions are expected instead of the above described tag-based syntax. Examples:

  • (launguage: ANY("en", "es")) AND NOT (categories: ANY("Movie"))
  • (available: true) AND (launguage: ANY("en", "es")) OR (categories: ANY("Movie"))

If your filter blocks all results, the API returns generic (unfiltered) popular Documents. If you only want results strictly matching the filters, set strictFiltering to true in RecommendRequest.params to receive empty results instead.

Note that the API never returns Documents with storageStatus as EXPIRED or DELETED regardless of filter choices.

validate_only

bool

Use validate only mode for this recommendation query. If set to true, a fake model is used that returns arbitrary Document IDs. Note that the validate only mode should only be used for testing the API, or if the model is not ready.

params

map<string, Value>

Additional domain specific parameters for the recommendations.

Allowed values:

  • returnDocument: Boolean. If set to true, the associated Document object is returned in RecommendResponse.RecommendationResult.document.
  • returnScore: Boolean. If set to true, the recommendation score corresponding to each returned Document is set in RecommendResponse.RecommendationResult.metadata. The given score indicates the probability of a Document conversion given the user's context and history.
  • strictFiltering: Boolean. True by default. If set to false, the service returns generic (unfiltered) popular Documents instead of empty if your filter blocks all recommendation results.
  • diversityLevel: String. Default empty. If set to be non-empty, then it needs to be one of:
    • no-diversity
    • low-diversity
    • medium-diversity
    • high-diversity
    • auto-diversity This gives request-level control and adjusts recommendation results based on Document category.
  • attributeFilteringSyntax: Boolean. False by default. If set to true, the filter field is interpreted according to the new, attribute-based syntax.
user_labels

map<string, string>

The user labels applied to a resource must meet the following requirements:

  • Each resource can have multiple labels, up to a maximum of 64.
  • Each label must be a key-value pair.
  • Keys have a minimum length of 1 character and a maximum length of 63 characters and cannot be empty. Values can be empty and have a maximum length of 63 characters.
  • Keys and values can contain only lowercase letters, numeric characters, underscores, and dashes. All characters must use UTF-8 encoding, and international characters are allowed.
  • The key portion of a label must be unique. However, you can use the same key with multiple resources.
  • Keys must start with a lowercase letter or international character.

See Requirements for labels for more details.

RecommendResponse

Response message for Recommend method.

Fields
results[]

RecommendationResult

A list of recommended Documents. The order represents the ranking (from the most relevant Document to the least).

attribution_token

string

A unique attribution token. This should be included in the UserEvent logs resulting from this recommendation, which enables accurate attribution of recommendation model performance.

missing_ids[]

string

IDs of documents in the request that were missing from the default Branch associated with the requested ServingConfig.

validate_only

bool

True if RecommendRequest.validate_only was set.

RecommendationResult

RecommendationResult represents a generic recommendation result with associated metadata.

Fields
id

string

Resource ID of the recommended Document.

document

Document

Set if returnDocument is set to true in RecommendRequest.params.

metadata

map<string, Value>

Additional Document metadata or annotations.

Possible values:

RecrawlUrisMetadata

Metadata related to the progress of the SiteSearchEngineService.RecrawlUris operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

invalid_uris[]

string

Unique URIs in the request that have invalid format. Sample limited to 1000.

invalid_uris_count

int32

Total number of unique URIs in the request that have invalid format.

uris_not_matching_target_sites[]

string

Unique URIs in the request that don't match any TargetSite in the DataStore, only match TargetSites that haven't been fully indexed, or match a TargetSite with type EXCLUDE. Sample limited to 1000.

uris_not_matching_target_sites_count

int32

Total number of URIs that don't match any TargetSites.

valid_uris_count

int32

Total number of unique URIs in the request that are not in invalid_uris.

success_count

int32

Total number of URIs that have been crawled so far.

pending_count

int32

Total number of URIs that have yet to be crawled.

quota_exceeded_count

int32

Total number of URIs that were rejected due to insufficient indexing resources.

RecrawlUrisRequest

Request message for SiteSearchEngineService.RecrawlUris method.

Fields
site_search_engine

string

Required. Full resource name of the SiteSearchEngine, such as projects/*/locations/*/collections/*/dataStores/*/siteSearchEngine.

uris[]

string

Required. List of URIs to crawl. At most 10K URIs are supported, otherwise an INVALID_ARGUMENT error is thrown. Each URI should match at least one TargetSite in site_search_engine.

site_credential

string

Optional. Full resource name of the [SiteCredential][], such as projects/*/locations/*/collections/*/dataStores/*/siteSearchEngine/siteCredentials/*. Only set to crawl private URIs.

RecrawlUrisResponse

Response message for SiteSearchEngineService.RecrawlUris method.

Fields
failure_samples[]

FailureInfo

Details for a sample of up to 10 failed_uris.

failed_uris[]

string

URIs that were not crawled before the LRO terminated.

FailureInfo

Details about why a particular URI failed to be crawled. Each FailureInfo contains one FailureReason per CorpusType.

Fields
uri

string

URI that failed to be crawled.

failure_reasons[]

FailureReason

List of failure reasons by corpus type (e.g. desktop, mobile).

FailureReason

Details about why crawling failed for a particular CorpusType, e.g., DESKTOP and MOBILE crawling may fail for different reasons.

Fields
corpus_type

CorpusType

DESKTOP, MOBILE, or CORPUS_TYPE_UNSPECIFIED.

error_message

string

Reason why the URI was not crawled.

CorpusType

CorpusType for the failed crawling operation.

Enums
CORPUS_TYPE_UNSPECIFIED Default value.
DESKTOP Denotes a crawling attempt for the desktop version of a page.
MOBILE Denotes a crawling attempt for the mobile version of a page.

Reply

Defines a reply message to user.

Fields
reply
(deprecated)

string

DEPRECATED: use summary instead. Text reply.

references[]
(deprecated)

Reference

References in the reply.

summary

Summary

Summary based on search results.

Reference

Defines reference in reply.

Fields
uri

string

URI link reference.

anchor_text

string

Anchor text.

start

int32

Anchor text start index.

end

int32

Anchor text end index.

ResumeEngineRequest

Request for resuming training of an engine.

Fields
name

string

Required. The name of the engine to resume. Format: projects/{project}/locations/{location}/collections/{collection_id}/engines/{engine_id}

SampleQuery

Sample Query captures metadata to be used for evaluation.

Fields
name

string

Identifier. The full resource name of the sample query, in the format of projects/{project}/locations/{location}/sampleQuerySets/{sample_query_set}/sampleQueries/{sample_query}.

This field must be a UTF-8 encoded string with a length limit of 1024 characters.

create_time

Timestamp

Output only. Timestamp the SampleQuery was created at.

Union field content. The content of the sample query. content can be only one of the following:
query_entry

QueryEntry

The query entry.

QueryEntry

Query Entry captures metadata to be used for search evaluation.

Fields
query

string

Required. The query.

targets[]

Target

List of targets for the query.

Target

Defines the parameters of the query's expected outcome.

Fields
uri

string

Expected uri of the target.

This field must be a UTF-8 encoded string with a length limit of 2048 characters.

Example of valid uris: https://example.com/abc, gcs://example/example.pdf.

page_numbers[]

int32

Expected page numbers of the target.

Each page number must be non negative.

score

double

Relevance score of the target.

SampleQuerySet

A SampleQuerySet is the parent resource of SampleQuery, and contains the configurations shared by all SampleQuery under it.

Fields
name

string

Identifier. The full resource name of the SampleQuerySet, in the format of projects/{project}/locations/{location}/sampleQuerySets/{sample_query_set}.

This field must be a UTF-8 encoded string with a length limit of 1024 characters.

display_name

string

Required. The sample query set display name.

This field must be a UTF-8 encoded string with a length limit of 128 characters.

create_time

Timestamp

Output only. Timestamp the SampleQuerySet was created at.

description

string

The description of the SampleQuerySet.

Schema

Defines the structure and layout of a type of document data.

Fields
name

string

Immutable. The full resource name of the schema, in the format of projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/schemas/{schema}.

This field must be a UTF-8 encoded string with a length limit of 1024 characters.

Union field schema. Schema representation. One of struct_schema or json_schema should be provided otherwise an INVALID_ARGUMENT error is thrown. schema can be only one of the following:
struct_schema

Struct

The structured representation of the schema.

json_schema

string

The JSON representation of the schema.

SearchAddOn

Add-on that provides additional functionality for search.

Enums
SEARCH_ADD_ON_UNSPECIFIED Default value when the enum is unspecified. This is invalid to use.
SEARCH_ADD_ON_LLM Large language model add-on.

SearchInfo

Detailed search information.

Fields
search_query

string

The user's search query.

See SearchRequest.query for definition.

The value must be a UTF-8 encoded string with a length limit of 5,000 characters. Otherwise, an INVALID_ARGUMENT error is returned.

At least one of search_query or PageInfo.page_category is required for search events. Other event types should not set this field. Otherwise, an INVALID_ARGUMENT error is returned.

order_by

string

The order in which products are returned, if applicable.

See SearchRequest.order_by for definition and syntax.

The value must be a UTF-8 encoded string with a length limit of 1,000 characters. Otherwise, an INVALID_ARGUMENT error is returned.

This can only be set for search events. Other event types should not set this field. Otherwise, an INVALID_ARGUMENT error is returned.

offset

int32

An integer that specifies the current offset for pagination (the 0-indexed starting location, amongst the products deemed by the API as relevant).

See SearchRequest.offset for definition.

If this field is negative, an INVALID_ARGUMENT is returned.

This can only be set for search events. Other event types should not set this field. Otherwise, an INVALID_ARGUMENT error is returned.

SearchRequest

Request message for SearchService.Search method.

Fields
serving_config

string

Required. The resource name of the Search serving config, such as projects/*/locations/global/collections/default_collection/engines/*/servingConfigs/default_serving_config, or projects/*/locations/global/collections/default_collection/dataStores/default_data_store/servingConfigs/default_serving_config. This field is used to identify the serving configuration name, set of models used to make the search.

branch

string

The branch resource name, such as projects/*/locations/global/collections/default_collection/dataStores/default_data_store/branches/0.

Use default_branch as the branch ID or leave this field empty, to search documents under the default branch.

query

string

Raw search query.

image_query

ImageQuery

Raw image query.

page_size

int32

Maximum number of Documents to return. The maximum allowed value depends on the data type. Values above the maximum value are coerced to the maximum value.

  • Websites with basic indexing: Default 10, Maximum 25.
  • Websites with advanced indexing: Default 25, Maximum 50.
  • Other: Default 50, Maximum 100.

If this field is negative, an INVALID_ARGUMENT is returned.

page_token

string

A page token received from a previous SearchService.Search call. Provide this to retrieve the subsequent page.

When paginating, all other parameters provided to SearchService.Search must match the call that provided the page token. Otherwise, an INVALID_ARGUMENT error is returned.

offset

int32

A 0-indexed integer that specifies the current offset (that is, starting result location, amongst the Documents deemed by the API as relevant) in search results. This field is only considered if page_token is unset.

If this field is negative, an INVALID_ARGUMENT is returned.

one_box_page_size

int32

The maximum number of results to return for OneBox. This applies to each OneBox type individually. Default number is 10.

data_store_specs[]

DataStoreSpec

Specs defining dataStores to filter on in a search call and configurations for those dataStores. This is only considered for engines with multiple dataStores use case. For single dataStore within an engine, they should use the specs at the top level.

filter

string

The filter syntax consists of an expression language for constructing a predicate from one or more fields of the documents being filtered. Filter expression is case-sensitive.

If this field is unrecognizable, an INVALID_ARGUMENT is returned.

Filtering in Vertex AI Search is done by mapping the LHS filter key to a key property defined in the Vertex AI Search backend -- this mapping is defined by the customer in their schema. For example a media customer might have a field 'name' in their schema. In this case the filter would look like this: filter --> name:'ANY("king kong")'

For more information about filtering including syntax and filter operators, see Filter

canonical_filter

string

The default filter that is applied when a user performs a search without checking any filters on the search page.

The filter applied to every search request when quality improvement such as query expansion is needed. In the case a query does not have a sufficient amount of results this filter will be used to determine whether or not to enable the query expansion flow. The original filter will still be used for the query expanded search. This field is strongly recommended to achieve high search quality.

For more information about filter syntax, see SearchRequest.filter.

order_by

string

The order in which documents are returned. Documents can be ordered by a field in an Document object. Leave it unset if ordered by relevance. order_by expression is case-sensitive.

For more information on ordering the website search results, see Order web search results. For more information on ordering the healthcare search results, see Order healthcare search results. If this field is unrecognizable, an INVALID_ARGUMENT is returned.

user_info

UserInfo

Information about the end user. Highly recommended for analytics. UserInfo.user_agent is used to deduce device_type for analytics.

language_code

string

The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see Standard fields. This field helps to better interpret the query. If a value isn't specified, the query language code is automatically detected, which may not be accurate.

region_code

string

The Unicode country/region code (CLDR) of a location, such as "US" and "419". For more information, see Standard fields. If set, then results will be boosted based on the region_code provided.

facet_specs[]

FacetSpec

Facet specifications for faceted search. If empty, no facets are returned.

A maximum of 100 values are allowed. Otherwise, an INVALID_ARGUMENT error is returned.

boost_spec

BoostSpec

Boost specification to boost certain documents. For more information on boosting, see Boosting

params

map<string, Value>

Additional search parameters.

For public website search only, supported values are:

  • user_country_code: string. Default empty. If set to non-empty, results are restricted or boosted based on the location provided. For example, user_country_code: "au"

For available codes see Country Codes

  • search_type: double. Default empty. Enables non-webpage searching depending on the value. The only valid non-default value is 1, which enables image searching. For example, search_type: 1
query_expansion_spec

QueryExpansionSpec

The query expansion specification that specifies the conditions under which query expansion occurs.

spell_correction_spec

SpellCorrectionSpec

The spell correction specification that specifies the mode under which spell correction takes effect.

user_pseudo_id

string

A unique identifier for tracking visitors. For example, this could be implemented with an HTTP cookie, which should be able to uniquely identify a visitor on a single device. This unique identifier should not change if the visitor logs in or out of the website.

This field should NOT have a fixed value such as unknown_visitor.

This should be the same identifier as UserEvent.user_pseudo_id and CompleteQueryRequest.user_pseudo_id

The field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an INVALID_ARGUMENT error is returned.

content_search_spec

ContentSearchSpec

A specification for configuring the behavior of content search.

embedding_spec

EmbeddingSpec

Uses the provided embedding to do additional semantic document retrieval. The retrieval is based on the dot product of SearchRequest.EmbeddingSpec.EmbeddingVector.vector and the document embedding that is provided in SearchRequest.EmbeddingSpec.EmbeddingVector.field_path.

If SearchRequest.EmbeddingSpec.EmbeddingVector.field_path is not provided, it will use ServingConfig.EmbeddingConfig.field_path.

ranking_expression

string

The ranking expression controls the customized ranking on retrieval documents. This overrides ServingConfig.ranking_expression. The ranking expression is a single function or multiple functions that are joined by "+".

  • ranking_expression = function, { " + ", function };

Supported functions:

  • double * relevance_score
  • double * dotProduct(embedding_field_path)

Function variables:

  • relevance_score: pre-defined keywords, used for measure relevance between query and document.
  • embedding_field_path: the document embedding field used with query embedding vector.
  • dotProduct: embedding function between embedding_field_path and query embedding vector.

Example ranking expression:

If document has an embedding field doc_embedding, the ranking expression could be 0.5 * relevance_score + 0.3 * dotProduct(doc_embedding).

user_labels

map<string, string>

The user labels applied to a resource must meet the following requirements:

  • Each resource can have multiple labels, up to a maximum of 64.
  • Each label must be a key-value pair.
  • Keys have a minimum length of 1 character and a maximum length of 63 characters and cannot be empty. Values can be empty and have a maximum length of 63 characters.
  • Keys and values can contain only lowercase letters, numeric characters, underscores, and dashes. All characters must use UTF-8 encoding, and international characters are allowed.
  • The key portion of a label must be unique. However, you can use the same key with multiple resources.
  • Keys must start with a lowercase letter or international character.

See Google Cloud Document for more details.

natural_language_query_understanding_spec

NaturalLanguageQueryUnderstandingSpec

If naturalLanguageQueryUnderstandingSpec is not specified, no additional natural language query understanding will be done.

search_as_you_type_spec

SearchAsYouTypeSpec

Search as you type configuration. Only supported for the IndustryVertical.MEDIA vertical.

session

string

The session resource name. Optional.

Session allows users to do multi-turn /search API calls or coordination between /search API calls and /answer API calls.

Example #1 (multi-turn /search API calls): 1. Call /search API with the auto-session mode (see below). 2. Call /search API with the session ID generated in the first call. Here, the previous search query gets considered in query standing. I.e., if the first query is "How did Alphabet do in 2022?" and the current query is "How about 2023?", the current query will be interpreted as "How did Alphabet do in 2023?".

Example #2 (coordination between /search API calls and /answer API calls): 1. Call /search API with the auto-session mode (see below). 2. Call /answer API with the session ID generated in the first call. Here, the answer generation happens in the context of the search results from the first search call.

Auto-session mode: when projects/.../sessions/- is used, a new session gets automatically created. Otherwise, users can use the create-session API to create a session manually.

Multi-turn Search feature is currently at private GA stage. Please use v1alpha or v1beta version instead before we launch this feature to public GA. Or ask for allowlisting through Google Support team.

session_spec

SessionSpec

Session specification.

Can be used only when session is set.

relevance_threshold

RelevanceThreshold

The relevance threshold of the search results.

Default to Google defined threshold, leveraging a balance of precision and recall to deliver both highly accurate results and comprehensive coverage of relevant information.

personalization_spec

PersonalizationSpec

The specification for personalization.

Notice that if both ServingConfig.personalization_spec and SearchRequest.personalization_spec are set, SearchRequest.personalization_spec overrides ServingConfig.personalization_spec.

BoostSpec

Boost specification to boost certain documents.

Fields
condition_boost_specs[]

ConditionBoostSpec

Condition boost specifications. If a document matches multiple conditions in the specifictions, boost scores from these specifications are all applied and combined in a non-linear way. Maximum number of specifications is 20.

ConditionBoostSpec

Boost applies to documents which match a condition.

Fields
condition

string

An expression which specifies a boost condition. The syntax and supported fields are the same as a filter expression. See SearchRequest.filter for detail syntax and limitations.

Examples:

  • To boost documents with document ID "doc_1" or "doc_2", and color "Red" or "Blue": (document_id: ANY("doc_1", "doc_2")) AND (color: ANY("Red", "Blue"))
boost

float

Strength of the condition boost, which should be in [-1, 1]. Negative boost means demotion. Default is 0.0.

Setting to 1.0 gives the document a big promotion. However, it does not necessarily mean that the boosted document will be the top result at all times, nor that other documents will be excluded. Results could still be shown even when none of them matches the condition. And results that are significantly more relevant to the search query can still trump your heavily favored but irrelevant documents.

Setting to -1.0 gives the document a big demotion. However, results that are deeply relevant might still be shown. The document will have an upstream battle to get a fairly high ranking, but it is not blocked out completely.

Setting to 0.0 means no boost applied. The boosting condition is ignored. Only one of the (condition, boost) combination or the boost_control_spec below are set. If both are set then the global boost is ignored and the more fine-grained boost_control_spec is applied.

boost_control_spec

BoostControlSpec

Complex specification for custom ranking based on customer defined attribute value.

BoostControlSpec

Specification for custom ranking based on customer specified attribute value. It provides more controls for customized ranking than the simple (condition, boost) combination above.

Fields
field_name

string

The name of the field whose value will be used to determine the boost amount.

attribute_type

AttributeType

The attribute type to be used to determine the boost amount. The attribute value can be derived from the field value of the specified field_name. In the case of numerical it is straightforward i.e. attribute_value = numerical_field_value. In the case of freshness however, attribute_value = (time.now() - datetime_field_value).

interpolation_type

InterpolationType

The interpolation type to be applied to connect the control points listed below.

control_points[]

ControlPoint

The control points used to define the curve. The monotonic function (defined through the interpolation_type above) passes through the control points listed here.

AttributeType

The attribute(or function) for which the custom ranking is to be applied.

Enums
ATTRIBUTE_TYPE_UNSPECIFIED Unspecified AttributeType.
NUMERICAL The value of the numerical field will be used to dynamically update the boost amount. In this case, the attribute_value (the x value) of the control point will be the actual value of the numerical field for which the boost_amount is specified.
FRESHNESS For the freshness use case the attribute value will be the duration between the current time and the date in the datetime field specified. The value must be formatted as an XSD dayTimeDuration value (a restricted subset of an ISO 8601 duration value). The pattern for this is: [nD][T[nH][nM][nS]]. For example, 5D, 3DT12H30M, T24H.

ControlPoint

The control points used to define the curve. The curve defined through these control points can only be monotonically increasing or decreasing(constant values are acceptable).

Fields
attribute_value

string

Can be one of: 1. The numerical field value. 2. The duration spec for freshness: The value must be formatted as an XSD dayTimeDuration value (a restricted subset of an ISO 8601 duration value). The pattern for this is: [nD][T[nH][nM][nS]].

boost_amount

float

The value between -1 to 1 by which to boost the score if the attribute_value evaluates to the value specified above.

InterpolationType

The interpolation type to be applied. Default will be linear (Piecewise Linear).

Enums
INTERPOLATION_TYPE_UNSPECIFIED Interpolation type is unspecified. In this case, it defaults to Linear.
LINEAR Piecewise linear interpolation will be applied.

ContentSearchSpec

A specification for configuring the behavior of content search.

Fields
snippet_spec

SnippetSpec

If snippetSpec is not specified, snippets are not included in the search response.

summary_spec

SummarySpec

If summarySpec is not specified, summaries are not included in the search response.

extractive_content_spec

ExtractiveContentSpec

If there is no extractive_content_spec provided, there will be no extractive answer in the search response.

search_result_mode

SearchResultMode

Specifies the search result mode. If unspecified, the search result mode defaults to DOCUMENTS.

chunk_spec

ChunkSpec

Specifies the chunk spec to be returned from the search response. Only available if the SearchRequest.ContentSearchSpec.search_result_mode is set to CHUNKS

ChunkSpec

Specifies the chunk spec to be returned from the search response. Only available if the SearchRequest.ContentSearchSpec.search_result_mode is set to CHUNKS

Fields
num_previous_chunks

int32

The number of previous chunks to be returned of the current chunk. The maximum allowed value is 3. If not specified, no previous chunks will be returned.

num_next_chunks

int32

The number of next chunks to be returned of the current chunk. The maximum allowed value is 3. If not specified, no next chunks will be returned.

ExtractiveContentSpec

A specification for configuring the extractive content in a search response.

Fields
max_extractive_answer_count

int32

The maximum number of extractive answers returned in each search result.

An extractive answer is a verbatim answer extracted from the original document, which provides a precise and contextually relevant answer to the search query.

If the number of matching answers is less than the max_extractive_answer_count, return all of the answers. Otherwise, return the max_extractive_answer_count.

At most five answers are returned for each SearchResult.

max_extractive_segment_count

int32

The max number of extractive segments returned in each search result. Only applied if the DataStore is set to DataStore.ContentConfig.CONTENT_REQUIRED or DataStore.solution_types is SOLUTION_TYPE_CHAT.

An extractive segment is a text segment extracted from the original document that is relevant to the search query, and, in general, more verbose than an extractive answer. The segment could then be used as input for LLMs to generate summaries and answers.

If the number of matching segments is less than max_extractive_segment_count, return all of the segments. Otherwise, return the max_extractive_segment_count.

return_extractive_segment_score

bool

Specifies whether to return the confidence score from the extractive segments in each search result. This feature is available only for new or allowlisted data stores. To allowlist your data store, contact your Customer Engineer. The default value is false.

num_previous_segments

int32

Specifies whether to also include the adjacent from each selected segments. Return at most num_previous_segments segments before each selected segments.

num_next_segments

int32

Return at most num_next_segments segments after each selected segments.

SearchResultMode

Specifies the search result mode. If unspecified, the search result mode defaults to DOCUMENTS.

Enums
SEARCH_RESULT_MODE_UNSPECIFIED Default value.
DOCUMENTS Returns documents in the search result.
CHUNKS Returns chunks in the search result. Only available if the [DataStore.DocumentProcessingConfig.chunking_config][] is specified.

SnippetSpec

A specification for configuring snippets in a search response.

Fields
max_snippet_count
(deprecated)

int32

[DEPRECATED] This field is deprecated. To control snippet return, use return_snippet field. For backwards compatibility, we will return snippet if max_snippet_count > 0.

reference_only
(deprecated)

bool

[DEPRECATED] This field is deprecated and will have no affect on the snippet.

return_snippet

bool

If true, then return snippet. If no snippet can be generated, we return "No snippet is available for this page." A snippet_status with SUCCESS or NO_SNIPPET_AVAILABLE will also be returned.

SummarySpec

A specification for configuring a summary returned in a search response.

Fields
summary_result_count

int32

The number of top results to generate the summary from. If the number of results returned is less than summaryResultCount, the summary is generated from all of the results.

At most 10 results for documents mode, or 50 for chunks mode, can be used to generate a summary. The chunks mode is used when SearchRequest.ContentSearchSpec.search_result_mode is set to CHUNKS.

include_citations

bool

Specifies whether to include citations in the summary. The default value is false.

When this field is set to true, summaries include in-line citation numbers.

Example summary including citations:

BigQuery is Google Cloud's fully managed and completely serverless enterprise data warehouse [1]. BigQuery supports all data types, works across clouds, and has built-in machine learning and business intelligence, all within a unified platform [2, 3].

The citation numbers refer to the returned search results and are 1-indexed. For example, [1] means that the sentence is attributed to the first search result. [2, 3] means that the sentence is attributed to both the second and third search results.

ignore_adversarial_query

bool

Specifies whether to filter out adversarial queries. The default value is false.

Google employs search-query classification to detect adversarial queries. No summary is returned if the search query is classified as an adversarial query. For example, a user might ask a question regarding negative comments about the company or submit a query designed to generate unsafe, policy-violating output. If this field is set to true, we skip generating summaries for adversarial queries and return fallback messages instead.

ignore_non_summary_seeking_query

bool

Specifies whether to filter out queries that are not summary-seeking. The default value is false.

Google employs search-query classification to detect summary-seeking queries. No summary is returned if the search query is classified as a non-summary seeking query. For example, why is the sky blue and Who is the best soccer player in the world? are summary-seeking queries, but SFO airport and world cup 2026 are not. They are most likely navigational queries. If this field is set to true, we skip generating summaries for non-summary seeking queries and return fallback messages instead.

ignore_low_relevant_content

bool

Specifies whether to filter out queries that have low relevance. The default value is false.

If this field is set to false, all search results are used regardless of relevance to generate answers. If set to true, only queries with high relevance search results will generate answers.

ignore_jail_breaking_query

bool

Optional. Specifies whether to filter out jail-breaking queries. The default value is false.

Google employs search-query classification to detect jail-breaking queries. No summary is returned if the search query is classified as a jail-breaking query. A user might add instructions to the query to change the tone, style, language, content of the answer, or ask the model to act as a different entity, e.g. "Reply in the tone of a competing company's CEO". If this field is set to true, we skip generating summaries for jail-breaking queries and return fallback messages instead.

model_prompt_spec

ModelPromptSpec

If specified, the spec will be used to modify the prompt provided to the LLM.

language_code

string

Language code for Summary. Use language tags defined by BCP47. Note: This is an experimental feature.

model_spec

ModelSpec

If specified, the spec will be used to modify the model specification provided to the LLM.

use_semantic_chunks

bool

If true, answer will be generated from most relevant chunks from top search results. This feature will improve summary quality. Note that with this feature enabled, not all top search results will be referenced and included in the reference list, so the citation source index only points to the search results listed in the reference list.

ModelPromptSpec

Specification of the prompt to use with the model.

Fields
preamble

string

Text at the beginning of the prompt that instructs the assistant. Examples are available in the user guide.

ModelSpec

Specification of the model.

Fields
version

string

The model version used to generate the summary.

Supported values are:

DataStoreSpec

A struct to define data stores to filter on in a search call and configurations for those data stores. Otherwise, an INVALID_ARGUMENT error is returned.

Fields
data_store

string

Required. Full resource name of DataStore, such as projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}.

filter

string

Optional. Filter specification to filter documents in the data store specified by data_store field. For more information on filtering, see Filtering

EmbeddingSpec

The specification that uses customized query embedding vector to do semantic document retrieval.

Fields
embedding_vectors[]

EmbeddingVector

The embedding vector used for retrieval. Limit to 1.

EmbeddingVector

Embedding vector.

Fields
field_path

string

Embedding field path in schema.

vector[]

float

Query embedding vector.

FacetSpec

A facet specification to perform faceted search.

Fields
facet_key

FacetKey

Required. The facet key specification.

limit

int32

Maximum facet values that are returned for this facet. If unspecified, defaults to 20. The maximum allowed value is 300. Values above 300 are coerced to 300. For aggregation in healthcare search, when the [FacetKey.key] is "healthcare_aggregation_key", the limit will be overridden to 10,000 internally, regardless of the value set here.

If this field is negative, an INVALID_ARGUMENT is returned.

excluded_filter_keys[]

string

List of keys to exclude when faceting.

By default, FacetKey.key is not excluded from the filter unless it is listed in this field.

Listing a facet key in this field allows its values to appear as facet results, even when they are filtered out of search results. Using this field does not affect what search results are returned.

For example, suppose there are 100 documents with the color facet "Red" and 200 documents with the color facet "Blue". A query containing the filter "color:ANY("Red")" and having "color" as FacetKey.key would by default return only "Red" documents in the search results, and also return "Red" with count 100 as the only color facet. Although there are also blue documents available, "Blue" would not be shown as an available facet value.

If "color" is listed in "excludedFilterKeys", then the query returns the facet values "Red" with count 100 and "Blue" with count 200, because the "color" key is now excluded from the filter. Because this field doesn't affect search results, the search results are still correctly filtered to return only "Red" documents.

A maximum of 100 values are allowed. Otherwise, an INVALID_ARGUMENT error is returned.

enable_dynamic_position

bool

Enables dynamic position for this facet. If set to true, the position of this facet among all facets in the response is determined automatically. If dynamic facets are enabled, it is ordered together. If set to false, the position of this facet in the response is the same as in the request, and it is ranked before the facets with dynamic position enable and all dynamic facets.

For example, you may always want to have rating facet returned in the response, but it's not necessarily to always display the rating facet at the top. In that case, you can set enable_dynamic_position to true so that the position of rating facet in response is determined automatically.

Another example, assuming you have the following facets in the request:

  • "rating", enable_dynamic_position = true

  • "price", enable_dynamic_position = false

  • "brands", enable_dynamic_position = false

And also you have a dynamic facets enabled, which generates a facet gender. Then the final order of the facets in the response can be ("price", "brands", "rating", "gender") or ("price", "brands", "gender", "rating") depends on how API orders "gender" and "rating" facets. However, notice that "price" and "brands" are always ranked at first and second position because their enable_dynamic_position is false.

FacetKey

Specifies how a facet is computed.

Fields
key

string

Required. Supported textual and numerical facet keys in Document object, over which the facet values are computed. Facet key is case-sensitive.

intervals[]

Interval

Set only if values should be bucketed into intervals. Must be set for facets with numerical values. Must not be set for facet with text values. Maximum number of intervals is 30.

restricted_values[]

string

Only get facet for the given restricted values. Only supported on textual fields. For example, suppose "category" has three values "Action > 2022", "Action > 2021" and "Sci-Fi > 2022". If set "restricted_values" to "Action > 2022", the "category" facet only contains "Action > 2022". Only supported on textual fields. Maximum is 10.

prefixes[]

string

Only get facet values that start with the given string prefix. For example, suppose "category" has three values "Action > 2022", "Action > 2021" and "Sci-Fi > 2022". If set "prefixes" to "Action", the "category" facet only contains "Action > 2022" and "Action > 2021". Only supported on textual fields. Maximum is 10.

contains[]

string

Only get facet values that contain the given strings. For example, suppose "category" has three values "Action > 2022", "Action > 2021" and "Sci-Fi > 2022". If set "contains" to "2022", the "category" facet only contains "Action > 2022" and "Sci-Fi > 2022". Only supported on textual fields. Maximum is 10.

case_insensitive

bool

True to make facet keys case insensitive when getting faceting values with prefixes or contains; false otherwise.

order_by

string

The order in which documents are returned.

Allowed values are:

If not set, textual values are sorted in natural order; numerical intervals are sorted in the order given by FacetSpec.FacetKey.intervals.

ImageQuery

Specifies the image query input.

Fields

Union field image.

image can be only one of the following:

image_bytes

string

Base64 encoded image bytes. Supported image formats: JPEG, PNG, and BMP.

NaturalLanguageQueryUnderstandingSpec

Specification to enable natural language understanding capabilities for search requests.

Fields
filter_extraction_condition

FilterExtractionCondition

The condition under which filter extraction should occur. Default to [Condition.DISABLED][].

geo_search_query_detection_field_names[]

string

Field names used for location-based filtering, where geolocation filters are detected in natural language search queries. Only valid when the FilterExtractionCondition is set to ENABLED.

If this field is set, it overrides the field names set in ServingConfig.geo_search_query_detection_field_names.

FilterExtractionCondition

Enum describing under which condition filter extraction should occur.

Enums
CONDITION_UNSPECIFIED Server behavior defaults to [Condition.DISABLED][].
DISABLED Disables NL filter extraction.
ENABLED Enables NL filter extraction.

PersonalizationSpec

The specification for personalization.

Fields
mode

Mode

The personalization mode of the search request. Defaults to Mode.AUTO.

Mode

The personalization mode of each search request.

Enums
MODE_UNSPECIFIED Default value. In this case, server behavior defaults to Mode.AUTO.
AUTO Personalization is enabled if data quality requirements are met.
DISABLED Disable personalization.

QueryExpansionSpec

Specification to determine under which conditions query expansion should occur.

Fields
condition

Condition

The condition under which query expansion should occur. Default to Condition.DISABLED.

pin_unexpanded_results

bool

Whether to pin unexpanded results. If this field is set to true, unexpanded products are always at the top of the search results, followed by the expanded results.

Condition

Enum describing under which condition query expansion should occur.

Enums
CONDITION_UNSPECIFIED Unspecified query expansion condition. In this case, server behavior defaults to Condition.DISABLED.
DISABLED Disabled query expansion. Only the exact search query is used, even if SearchResponse.total_size is zero.
AUTO Automatic query expansion built by the Search API.

RelevanceThreshold

The relevance threshold of the search results. The higher relevance threshold is, the higher relevant results are shown and the less number of results are returned.

Enums
RELEVANCE_THRESHOLD_UNSPECIFIED Default value. In this case, server behavior defaults to Google defined threshold.
LOWEST Lowest relevance threshold.
LOW Low relevance threshold.
MEDIUM Medium relevance threshold.
HIGH High relevance threshold.

SearchAsYouTypeSpec

Specification for search as you type in search requests.

Fields
condition

Condition

The condition under which search as you type should occur. Default to Condition.DISABLED.

Condition

Enum describing under which condition search as you type should occur.

Enums
CONDITION_UNSPECIFIED Server behavior defaults to Condition.DISABLED.
DISABLED Disables Search As You Type.
ENABLED Enables Search As You Type.

SessionSpec

Session specification.

Multi-turn Search feature is currently at private GA stage. Please use v1alpha or v1beta version instead before we launch this feature to public GA. Or ask for allowlisting through Google Support team.

Fields
query_id

string

If set, the search result gets stored to the "turn" specified by this query ID.

Example: Let's say the session looks like this: session { name: ".../sessions/xxx" turns { query { text: "What is foo?" query_id: ".../questions/yyy" } answer: "Foo is ..." } turns { query { text: "How about bar then?" query_id: ".../questions/zzz" } } }

The user can call /search API with a request like this:

session: ".../sessions/xxx" session_spec { query_id: ".../questions/zzz" }

Then, the API stores the search result, associated with the last turn. The stored search result can be used by a subsequent /answer API call (with the session ID and the query ID specified). Also, it is possible to call /search and /answer in parallel with the same session ID & query ID.

search_result_persistence_count

int32

The number of top search results to persist. The persisted search results can be used for the subsequent /answer api call.

This field is simliar to the summary_result_count field in SearchRequest.ContentSearchSpec.SummarySpec.summary_result_count.

At most 10 results for documents mode, or 50 for chunks mode.

SpellCorrectionSpec

The specification for query spell correction.

Fields
mode

Mode

The mode under which spell correction replaces the original search query. Defaults to Mode.AUTO.

Mode

Enum describing under which mode spell correction should occur.

Enums
MODE_UNSPECIFIED Unspecified spell correction mode. In this case, server behavior defaults to Mode.AUTO.
SUGGESTION_ONLY Search API tries to find a spelling suggestion. If a suggestion is found, it is put in the SearchResponse.corrected_query. The spelling suggestion won't be used as the search query.
AUTO Automatic spell correction built by the Search API. Search will be based on the corrected query if found.

SearchResponse

Response message for SearchService.Search method.

Fields
results[]

SearchResult

A list of matched documents. The order represents the ranking.

facets[]

Facet

Results of facets requested by user.

guided_search_result

GuidedSearchResult

Guided search result.

total_size

int32

The estimated total count of matched items irrespective of pagination. The count of results returned by pagination may be less than the total_size that matches.

attribution_token

string

A unique search token. This should be included in the UserEvent logs resulting from this search, which enables accurate attribution of search model performance. This also helps to identify a request during the customer support scenarios.

redirect_uri

string

The URI of a customer-defined redirect page. If redirect action is triggered, no search is performed, and only redirect_uri and attribution_token are set in the response.

next_page_token

string

A token that can be sent as SearchRequest.page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.

corrected_query

string

Contains the spell corrected query, if found. If the spell correction type is AUTOMATIC, then the search results are based on corrected_query. Otherwise the original query is used for search.

summary

Summary

A summary as part of the search results. This field is only returned if SearchRequest.ContentSearchSpec.summary_spec is set.

applied_controls[]

string

Controls applied as part of the Control service.

geo_search_debug_info[]

GeoSearchDebugInfo

query_expansion_info

QueryExpansionInfo

Query expansion information for the returned results.

natural_language_query_understanding_info

NaturalLanguageQueryUnderstandingInfo

Natural language query understanding information for the returned results.

session_info

SessionInfo

Session information.

Only set if SearchRequest.session is provided. See its description for more details.

one_box_results[]

OneBoxResult

A list of One Box results. There can be multiple One Box results of different types.

Facet

A facet result.

Fields
key

string

The key for this facet. For example, "colors" or "price". It matches SearchRequest.FacetSpec.FacetKey.key.

values[]

FacetValue

The facet values for this field.

dynamic_facet

bool

Whether the facet is dynamically generated.

FacetValue

A facet value which contains value names and their count.

Fields
count

int64

Number of items that have this facet value.

Union field facet_value. A facet value which contains values. facet_value can be only one of the following:
value

string

Text value of a facet, such as "Black" for facet "colors".

interval

Interval

Interval value for a facet, such as [10, 20) for facet "price". It matches SearchRequest.FacetSpec.FacetKey.intervals.

GeoSearchDebugInfo

Debug information specifically related to forward geocoding issues arising from Geolocation Search.

Fields
original_address_query

string

The address from which forward geocoding ingestion produced issues.

error_message

string

The error produced.

GuidedSearchResult

Guided search result. The guided search helps user to refine the search results and narrow down to the real needs from a broaded search results.

Fields
refinement_attributes[]

RefinementAttribute

A list of ranked refinement attributes.

follow_up_questions[]

string

Suggested follow-up questions.

RefinementAttribute

Useful attribute for search result refinements.

Fields
attribute_key

string

Attribute key used to refine the results. For example, "movie_type".

attribute_value

string

Attribute value used to refine the results. For example, "drama".

NaturalLanguageQueryUnderstandingInfo

Information describing what natural language understanding was done on the input query.

Fields
extracted_filters

string

The filters that were extracted from the input query.

rewritten_query

string

Rewritten input query minus the extracted filters.

structured_extracted_filter

StructuredExtractedFilter

The filters that were extracted from the input query represented in a structured form.

StructuredExtractedFilter

The filters that were extracted from the input query represented in a structured form.

Fields
expression

Expression

The expression denoting the filter that was extracted from the input query in a structured form. It can be a simple expression denoting a single string, numerical or geolocation constraint or a compound expression which is a combination of multiple expressions connected using logical (OR and AND) operators.

AndExpression

Logical And operator.

Fields
expressions[]

Expression

The expressions that were ANDed together.

Expression

The expression denoting the filter that was extracted from the input query.

Fields
Union field expr. The expression type. expr can be only one of the following:
string_constraint

StringConstraint

String constraint expression.

number_constraint

NumberConstraint

Numerical constraint expression.

geolocation_constraint

GeolocationConstraint

Geolocation constraint expression.

and_expr

AndExpression

Logical "And" compound operator connecting multiple expressions.

or_expr

OrExpression

Logical "Or" compound operator connecting multiple expressions.

GeolocationConstraint

Constraint of a geolocation field. Name of the geolocation field as defined in the schema.

Fields
field_name

string

The name of the geolocation field as defined in the schema.

address

string

The reference address that was inferred from the input query. The proximity of the reference address to the geolocation field will be used to filter the results.

latitude

double

The latitude of the geolocation inferred from the input query.

longitude

double

The longitude of the geolocation inferred from the input query.

radius_in_meters

float

The radius in meters around the address. The record is returned if the location of the geolocation field is within the radius.

NumberConstraint

Constraint expression of a number field. Example: price < 100.

Fields
field_name

string

Name of the numerical field as defined in the schema.

comparison

Comparison

The comparison operation performed between the field value and the value specified in the constraint.

value

double

The value specified in the numerical constraint.

query_segment

string

Identifies the keywords within the search query that match a filter.

Comparison

The comparison operation that was performed.

Enums
COMPARISON_UNSPECIFIED Undefined comparison operator.
EQUALS Denotes equality = operator.
LESS_THAN_EQUALS Denotes less than or equal to <= operator.
LESS_THAN Denotes less than < operator.
GREATER_THAN_EQUALS Denotes greater than or equal to >= operator.
GREATER_THAN Denotes greater than > operator.

OrExpression

Logical Or operator.

Fields
expressions[]

Expression

The expressions that were ORed together.

StringConstraint

Constraint expression of a string field.

Fields
field_name

string

Name of the string field as defined in the schema.

values[]

string

Values of the string field. The record will only be returned if the field value matches one of the values specified here.

query_segment

string

Identifies the keywords within the search query that match a filter.

OneBoxResult

OneBoxResult is a holder for all results of specific type that we want to display in UI differently.

Fields
one_box_type

OneBoxType

The type of One Box result.

search_results[]

SearchResult

The search results for this One Box.

OneBoxType

The type of One Box result.

Enums
ONE_BOX_TYPE_UNSPECIFIED Default value. Should not be used.
PEOPLE One Box result contains people results.
ORGANIZATION One Box result contains organization results.
SLACK One Box result contains slack results.
KNOWLEDGE_GRAPH One Box result contains Knowledge Graph search responses.

QueryExpansionInfo

Information describing query expansion including whether expansion has occurred.

Fields
expanded_query

bool

Bool describing whether query expansion has occurred.

pinned_result_count

int64

Number of pinned results. This field will only be set when expansion happens and SearchRequest.QueryExpansionSpec.pin_unexpanded_results is set to true.

SearchResult

Represents the search results.

Fields
id

string

Document.id of the searched Document.

document

Document

The document data snippet in the search response. Only fields that are marked as retrievable are populated.

chunk

Chunk

The chunk data in the search response if the SearchRequest.ContentSearchSpec.search_result_mode is set to CHUNKS.

model_scores

map<string, DoubleList>

Google provided available scores.

SessionInfo

Information about the session.

Fields
name

string

Name of the session. If the auto-session mode is used (when SearchRequest.session ends with "-"), this field holds the newly generated session name.

query_id

string

Query ID that corresponds to this search API call. One session can have multiple turns, each with a unique query ID.

By specifying the session name and this query ID in the Answer API call, the answer generation happens in the context of the search results from this search call.

Summary

Summary of the top N search results specified by the summary spec.

Fields
summary_text

string

The summary content.

summary_skipped_reasons[]

SummarySkippedReason

Additional summary-skipped reasons. This provides the reason for ignored cases. If nothing is skipped, this field is not set.

safety_attributes

SafetyAttributes

A collection of Safety Attribute categories and their associated confidence scores.

summary_with_metadata

SummaryWithMetadata

Summary with metadata information.

Citation

Citation info for a segment.

Fields
start_index

int64

Index indicates the start of the segment, measured in bytes/unicode.

end_index

int64

End of the attributed segment, exclusive.

sources[]

CitationSource

Citation sources for the attributed segment.

CitationMetadata

Citation metadata.

Fields
citations[]

Citation

Citations for segments.

CitationSource

Citation source.

Fields
reference_index

int64

Document reference index from SummaryWithMetadata.references. It is 0-indexed and the value will be zero if the reference_index is not set explicitly.

Reference

Document reference.

Fields
title

string

Title of the document.

document

string

Required. Document.name of the document. Full resource name of the referenced document, in the format projects/*/locations/*/collections/*/dataStores/*/branches/*/documents/*.

uri

string

Cloud Storage or HTTP uri for the document.

chunk_contents[]

ChunkContent

List of cited chunk contents derived from document content.

ChunkContent

Chunk content.

Fields
content

string

Chunk textual content.

page_identifier

string

Page identifier.

SafetyAttributes

Safety Attribute categories and their associated confidence scores.

Fields
categories[]

string

The display names of Safety Attribute categories associated with the generated content. Order matches the Scores.

scores[]

float

The confidence scores of the each category, higher value means higher confidence. Order matches the Categories.

SummarySkippedReason

An Enum for summary-skipped reasons.

Enums
SUMMARY_SKIPPED_REASON_UNSPECIFIED Default value. The summary skipped reason is not specified.
ADVERSARIAL_QUERY_IGNORED

The adversarial query ignored case.

Only used when SummarySpec.ignore_adversarial_query is set to true.

NON_SUMMARY_SEEKING_QUERY_IGNORED

The non-summary seeking query ignored case.

Google skips the summary if the query is chit chat. Only used when SummarySpec.ignore_non_summary_seeking_query is set to true.

OUT_OF_DOMAIN_QUERY_IGNORED

The out-of-domain query ignored case.

Google skips the summary if there are no high-relevance search results. For example, the data store contains facts about company A but the user query is asking questions about company B.

POTENTIAL_POLICY_VIOLATION

The potential policy violation case.

Google skips the summary if there is a potential policy violation detected. This includes content that may be violent or toxic.

LLM_ADDON_NOT_ENABLED

The LLM addon not enabled case.

Google skips the summary if the LLM addon is not enabled.

NO_RELEVANT_CONTENT

The no relevant content case.

Google skips the summary if there is no relevant content in the retrieved search results.

JAIL_BREAKING_QUERY_IGNORED

The jail-breaking query ignored case.

For example, "Reply in the tone of a competing company's CEO". Only used when [SearchRequest.ContentSearchSpec.SummarySpec.ignore_jail_breaking_query] is set to true.

CUSTOMER_POLICY_VIOLATION

The customer policy violation case.

Google skips the summary if there is a customer policy violation detected. The policy is defined by the customer.

NON_SUMMARY_SEEKING_QUERY_IGNORED_V2

The non-answer seeking query ignored case.

Google skips the summary if the query doesn't have clear intent. Only used when [SearchRequest.ContentSearchSpec.SummarySpec.ignore_non_answer_seeking_query] is set to true.

SummaryWithMetadata

Summary with metadata information.

Fields
summary

string

Summary text with no citation information.

citation_metadata

CitationMetadata

Citation metadata for given summary.

references[]

Reference

Document References.

SearchTier

Tiers of search features. Different tiers might have different pricing. To learn more, check the pricing documentation.

Enums
SEARCH_TIER_UNSPECIFIED Default value when the enum is unspecified. This is invalid to use.
SEARCH_TIER_STANDARD Standard tier.
SEARCH_TIER_ENTERPRISE Enterprise tier.

SearchUseCase

Defines a further subdivision of SolutionType. Specifically applies to SOLUTION_TYPE_SEARCH.

Enums
SEARCH_USE_CASE_UNSPECIFIED Value used when unset. Will not occur in CSS.
SEARCH_USE_CASE_BROWSE Browse use case. Expects the traffic has an empty query.

ServingConfig

Configures metadata that is used to generate serving time results (e.g. search results or recommendation predictions). The ServingConfig is passed in the search and predict request and generates results.

Fields
name

string

Immutable. Fully qualified name projects/{project}/locations/{location}/collections/{collection_id}/engines/{engine_id}/servingConfigs/{serving_config_id}

display_name

string

Required. The human readable serving config display name. Used in Discovery UI.

This field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an INVALID_ARGUMENT error is returned.

solution_type

SolutionType

Required. Immutable. Specifies the solution type that a serving config can be associated with.

model_id

string

The id of the model to use at serving time. Currently only RecommendationModels are supported. Can be changed but only to a compatible model (e.g. others-you-may-like CTR to others-you-may-like CVR).

Required when SolutionType is SOLUTION_TYPE_RECOMMENDATION.

diversity_level

string

How much diversity to use in recommendation model results e.g. medium-diversity or high-diversity. Currently supported values:

  • no-diversity
  • low-diversity
  • medium-diversity
  • high-diversity
  • auto-diversity

If not specified, we choose default based on recommendation model type. Default value: no-diversity.

Can only be set if SolutionType is SOLUTION_TYPE_RECOMMENDATION.

embedding_config

EmbeddingConfig

Bring your own embedding config. The config is used for search semantic retrieval. The retrieval is based on the dot product of SearchRequest.EmbeddingSpec.EmbeddingVector.vector and the document embeddings that are provided by this EmbeddingConfig. If SearchRequest.EmbeddingSpec.EmbeddingVector.vector is provided, it overrides this ServingConfig.embedding_config.

ranking_expression

string

The ranking expression controls the customized ranking on retrieval documents. To leverage this, document embedding is required. The ranking expression setting in ServingConfig applies to all search requests served by the serving config. However, if SearchRequest.ranking_expression is specified, it overrides the ServingConfig ranking expression.

The ranking expression is a single function or multiple functions that are joined by "+".

  • ranking_expression = function, { " + ", function };

Supported functions:

  • double * relevance_score
  • double * dotProduct(embedding_field_path)

Function variables:

  • relevance_score: pre-defined keywords, used for measure relevance between query and document.
  • embedding_field_path: the document embedding field used with query embedding vector.
  • dotProduct: embedding function between embedding_field_path and query embedding vector.

Example ranking expression:

If document has an embedding field doc_embedding, the ranking expression could be 0.5 * relevance_score + 0.3 * dotProduct(doc_embedding).

create_time

Timestamp

Output only. ServingConfig created timestamp.

update_time

Timestamp

Output only. ServingConfig updated timestamp.

filter_control_ids[]

string

Filter controls to use in serving path. All triggered filter controls will be applied. Filter controls must be in the same data store as the serving config. Maximum of 20 filter controls.

boost_control_ids[]

string

Boost controls to use in serving path. All triggered boost controls will be applied. Boost controls must be in the same data store as the serving config. Maximum of 20 boost controls.

redirect_control_ids[]

string

IDs of the redirect controls. Only the first triggered redirect action is applied, even if multiple apply. Maximum number of specifications is 100.

Can only be set if SolutionType is SOLUTION_TYPE_SEARCH.

synonyms_control_ids[]

string

Condition synonyms specifications. If multiple synonyms conditions match, all matching synonyms controls in the list will execute. Maximum number of specifications is 100.

Can only be set if SolutionType is SOLUTION_TYPE_SEARCH.

oneway_synonyms_control_ids[]

string

Condition oneway synonyms specifications. If multiple oneway synonyms conditions match, all matching oneway synonyms controls in the list will execute. Maximum number of specifications is 100.

Can only be set if SolutionType is SOLUTION_TYPE_SEARCH.

dissociate_control_ids[]

string

Condition do not associate specifications. If multiple do not associate conditions match, all matching do not associate controls in the list will execute. Order does not matter. Maximum number of specifications is 100.

Can only be set if SolutionType is SOLUTION_TYPE_SEARCH.

replacement_control_ids[]

string

Condition replacement specifications. Applied according to the order in the list. A previously replaced term can not be re-replaced. Maximum number of specifications is 100.

Can only be set if SolutionType is SOLUTION_TYPE_SEARCH.

ignore_control_ids[]

string

Condition ignore specifications. If multiple ignore conditions match, all matching ignore controls in the list will execute. Order does not matter. Maximum number of specifications is 100.

personalization_spec

PersonalizationSpec

The specification for personalization spec.

Notice that if both ServingConfig.personalization_spec and SearchRequest.personalization_spec are set, SearchRequest.personalization_spec overrides ServingConfig.personalization_spec.

Union field vertical_config. Industry vertical specific config. vertical_config can be only one of the following:
media_config

MediaConfig

The MediaConfig of the serving configuration.

generic_config

GenericConfig

The GenericConfig of the serving configuration.

GenericConfig

Specifies the configurations needed for Generic Discovery.Currently we support:

  • content_search_spec: configuration for generic content search.
Fields
content_search_spec

ContentSearchSpec

Specifies the expected behavior of content search. Only valid for content-search enabled data store.

MediaConfig

Specifies the configurations needed for Media Discovery. Currently we support:

  • demote_content_watched: Threshold for watched content demotion. Customers can specify if using watched content demotion or use viewed detail page. Using the content watched demotion, customers need to specify the watched minutes or percentage exceeds the threshold, the content will be demoted in the recommendation result.
  • promote_fresh_content: cutoff days for fresh content promotion. Customers can specify if using content freshness promotion. If the content was published within the cutoff days, the content will be promoted in the recommendation result. Can only be set if SolutionType is SOLUTION_TYPE_RECOMMENDATION.
Fields
demotion_event_type

string

Specifies the event type used for demoting recommendation result. Currently supported values:

  • view-item: Item viewed.
  • media-play: Start/resume watching a video, playing a song, etc.
  • media-complete: Finished or stopped midway through a video, song, etc.

If unset, watch history demotion will not be applied. Content freshness demotion will still be applied.

demote_content_watched_past_days

int32

Optional. Specifies the number of days to look back for demoting watched content. If set to zero or unset, defaults to the maximum of 365 days.

content_freshness_cutoff_days

int32

Specifies the content freshness used for recommendation result. Contents will be demoted if contents were published for more than content freshness cutoff days.

Union field demote_content_watched. Specify the threshold for demoting watched content, the threshold can be either percentage or minutes value. This must be set for media-complete event type. demote_content_watched can be only one of the following:
content_watched_percentage_threshold

float

Specifies the content watched percentage threshold for demotion. Threshold value must be between [0, 1.0] inclusive.

content_watched_seconds_threshold

float

Specifies the content watched minutes threshold for demotion.

Session

External session proto definition.

Fields
name

string

Immutable. Fully qualified name projects/{project}/locations/global/collections/{collection}/engines/{engine}/sessions/*

state

State

The state of the session.

user_pseudo_id

string

A unique identifier for tracking users.

turns[]

Turn

Turns.

start_time

Timestamp

Output only. The time the session started.

end_time

Timestamp

Output only. The time the session finished.

State

Enumeration of the state of the session.

Enums
STATE_UNSPECIFIED State is unspecified.
IN_PROGRESS The session is currently open.

Turn

Represents a turn, including a query from the user and a answer from service.

Fields
query

Query

The user query.

answer

string

The resource name of the answer to the user query.

Only set if the answer generation (/answer API call) happened in this turn.

SiteSearchEngine

SiteSearchEngine captures DataStore level site search persisting configurations. It is a singleton value per data store.

Fields
name

string

The fully qualified resource name of the site search engine. Format: projects/*/locations/*/dataStores/*/siteSearchEngine

SiteVerificationInfo

Verification information for target sites in advanced site search.

Fields
site_verification_state

SiteVerificationState

Site verification state indicating the ownership and validity.

verify_time

Timestamp

Latest site verification time.

SiteVerificationState

Site verification state.

Enums
SITE_VERIFICATION_STATE_UNSPECIFIED Defaults to VERIFIED.
VERIFIED Site ownership verified.
UNVERIFIED Site ownership pending verification or verification failed.
EXEMPTED Site exempt from verification, e.g., a public website that opens to all.

SolutionType

The type of solution.

Enums
SOLUTION_TYPE_UNSPECIFIED Default value.
SOLUTION_TYPE_RECOMMENDATION Used for Recommendations AI.
SOLUTION_TYPE_CHAT Used for use cases related to the Generative AI agent.
SOLUTION_TYPE_GENERATIVE_CHAT Used for use cases related to the Generative Chat agent. It's used for Generative chat engine only, the associated data stores must enrolled with SOLUTION_TYPE_CHAT solution.

SpannerSource

The Spanner source for importing data

Fields
project_id

string

The project ID that contains the Spanner source. Has a length limit of 128 characters. If not specified, inherits the project ID from the parent request.

instance_id

string

Required. The instance ID of the source Spanner table.

database_id

string

Required. The database ID of the source Spanner table.

table_id

string

Required. The table name of the Spanner database that needs to be imported.

enable_data_boost

bool

Whether to apply data boost on Spanner export. Enabling this option will incur additional cost. More info can be found here.

SuggestionDenyListEntry

Suggestion deny list entry identifying the phrase to block from suggestions and the applied operation for the phrase.

Fields
block_phrase

string

Required. Phrase to block from suggestions served. Can be maximum 125 characters.

match_operator

MatchOperator

Required. The match operator to apply for this phrase. Whether to block the exact phrase, or block any suggestions containing this phrase.

MatchOperator

Operator for matching with the generated suggestions.

Enums
MATCH_OPERATOR_UNSPECIFIED Default value. Should not be used
EXACT_MATCH If the suggestion is an exact match to the block_phrase, then block it.
CONTAINS If the suggestion contains the block_phrase, then block it.

TargetSite

A target site for the SiteSearchEngine.

Fields
name

string

Output only. The fully qualified resource name of the target site. projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/siteSearchEngine/targetSites/{target_site} The target_site_id is system-generated.

provided_uri_pattern

string

Required. Input only. The user provided URI pattern from which the generated_uri_pattern is generated.

type

Type

The type of the target site, e.g., whether the site is to be included or excluded.

exact_match

bool

Input only. If set to false, a uri_pattern is generated to include all pages whose address contains the provided_uri_pattern. If set to true, an uri_pattern is generated to try to be an exact match of the provided_uri_pattern or just the specific page if the provided_uri_pattern is a specific one. provided_uri_pattern is always normalized to generate the URI pattern to be used by the search engine.

generated_uri_pattern

string

Output only. This is system-generated based on the provided_uri_pattern.

root_domain_uri

string

Output only. Root domain of the provided_uri_pattern.

site_verification_info

SiteVerificationInfo

Output only. Site ownership and validity verification status.

indexing_status

IndexingStatus

Output only. Indexing status.

update_time

Timestamp

Output only. The target site's last updated time.

failure_reason

FailureReason

Output only. Failure reason.

FailureReason

Site search indexing failure reasons.

Fields
Union field failure. Failure reason. failure can be only one of the following:
quota_failure

QuotaFailure

Failed due to insufficient quota.

QuotaFailure

Failed due to insufficient quota.

Fields
total_required_quota

int64

This number is an estimation on how much total quota this project needs to successfully complete indexing.

IndexingStatus

Target site indexing status enumeration.

Enums
INDEXING_STATUS_UNSPECIFIED Defaults to SUCCEEDED.
PENDING The target site is in the update queue and will be picked up by indexing pipeline.
FAILED The target site fails to be indexed.
SUCCEEDED The target site has been indexed.
DELETING The previously indexed target site has been marked to be deleted. This is a transitioning state which will resulted in either: 1. target site deleted if unindexing is successful; 2. state reverts to SUCCEEDED if the unindexing fails.

Type

Possible target site types.

Enums
TYPE_UNSPECIFIED This value is unused. In this case, server behavior defaults to Type.INCLUDE.
INCLUDE Include the target site.
EXCLUDE Exclude the target site.

TextInput

Defines text input.

Fields
input

string

Text input.

context

ConversationContext

Conversation context of the input.

TrainCustomModelMetadata

Metadata related to the progress of the TrainCustomModel operation. This is returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

TrainCustomModelRequest

Request message for SearchTuningService.TrainCustomModel method.

Fields
data_store

string

Required. The resource name of the Data Store, such as projects/*/locations/global/collections/default_collection/dataStores/default_data_store. This field is used to identify the data store where to train the models.

model_type

string

Model to be trained. Supported values are:

  • search-tuning: Fine tuning the search system based on data provided.
error_config

ImportErrorConfig

The desired location of errors incurred during the data ingestion and training.

model_id

string

If not provided, a UUID will be generated.

Union field training_input. Model training input. training_input can be only one of the following:
gcs_training_input

GcsTrainingInput

Cloud Storage training input.

GcsTrainingInput

Cloud Storage training data input.

Fields
corpus_data_path

string

The Cloud Storage corpus data which could be associated in train data. The data path format is gs://<bucket_to_data>/<jsonl_file_name>. A newline delimited jsonl/ndjson file.

For search-tuning model, each line should have the _id, title and text. Example: {"_id": "doc1", title: "relevant doc", "text": "relevant text"}

query_data_path

string

The gcs query data which could be associated in train data. The data path format is gs://<bucket_to_data>/<jsonl_file_name>. A newline delimited jsonl/ndjson file.

For search-tuning model, each line should have the _id and text. Example: {"_id": "query1", "text": "example query"}

train_data_path

string

Cloud Storage training data path whose format should be gs://<bucket_to_data>/<tsv_file_name>. The file should be in tsv format. Each line should have the doc_id and query_id and score (number).

For search-tuning model, it should have the query-id corpus-id score as tsv file header. The score should be a number in [0, inf+). The larger the number is, the more relevant the pair is. Example:

  • query-id\tcorpus-id\tscore
  • query1\tdoc1\t1
test_data_path

string

Cloud Storage test data. Same format as train_data_path. If not provided, a random 80/20 train/test split will be performed on train_data_path.

TrainCustomModelResponse

Response of the TrainCustomModelRequest. This message is returned by the google.longrunning.Operations.response field.

Fields
error_samples[]

Status

A sample of errors encountered while processing the data.

error_config

ImportErrorConfig

Echoes the destination for the complete errors in the request if set.

model_status

string

The trained model status. Possible values are:

  • bad-data: The training data quality is bad.
  • no-improvement: Tuning didn't improve performance. Won't deploy.
  • in-progress: Model training job creation is in progress.
  • training: Model is actively training.
  • evaluating: The model is evaluating trained metrics.
  • indexing: The model trained metrics are indexing.
  • ready: The model is ready for serving.
metrics

map<string, double>

The metrics of the trained model.

model_name

string

Fully qualified name of the CustomTuningModel.

TransactionInfo

A transaction represents the entire purchase transaction.

Fields
currency

string

Required. Currency code. Use three-character ISO-4217 code.

transaction_id

string

The transaction ID with a length limit of 128 characters.

value

float

Required. Total non-zero value associated with the transaction. This value may include shipping, tax, or other adjustments to the total value that you want to include.

tax

float

All the taxes associated with the transaction.

cost

float

All the costs associated with the products. These can be manufacturing costs, shipping expenses not borne by the end user, or any other costs, such that:

discount_value

float

The total discount(s) value applied to this transaction. This figure should be excluded from TransactionInfo.value

For example, if a user paid TransactionInfo.value amount, then nominal (pre-discount) value of the transaction is the sum of TransactionInfo.value and TransactionInfo.discount_value

This means that profit is calculated the same way, regardless of the discount value, and that TransactionInfo.discount_value can be larger than TransactionInfo.value:

TuneEngineMetadata

Metadata associated with a tune operation.

Fields
engine

string

Required. The resource name of the engine that this tune applies to. Format: projects/{project}/locations/{location}/collections/{collection_id}/engines/{engine_id}

TuneEngineRequest

Request to manually start a tuning process now (instead of waiting for the periodically scheduled tuning to happen).

Fields
name

string

Required. The resource name of the engine to tune. Format: projects/{project}/locations/{location}/collections/{collection_id}/engines/{engine_id}

TuneEngineResponse

This type has no fields.

Response associated with a tune operation.

UpdateControlRequest

Request for UpdateControl method.

Fields
control

Control

Required. The Control to update.

update_mask

FieldMask

Optional. Indicates which fields in the provided Control to update. The following are NOT supported:

If not set or empty, all supported fields are updated.

UpdateConversationRequest

Request for UpdateConversation method.

Fields
conversation

Conversation

Required. The Conversation to update.

update_mask

FieldMask

Indicates which fields in the provided Conversation to update. The following are NOT supported:

If not set or empty, all supported fields are updated.

UpdateDataStoreRequest

Request message for DataStoreService.UpdateDataStore method.

Fields
data_store

DataStore

Required. The DataStore to update.

If the caller does not have permission to update the DataStore, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the DataStore to update does not exist, a NOT_FOUND error is returned.

update_mask

FieldMask

Indicates which fields in the provided DataStore to update.

If an unsupported or unknown field is provided, an INVALID_ARGUMENT error is returned.

UpdateDocumentRequest

Request message for DocumentService.UpdateDocument method.

Fields
document

Document

Required. The document to update/create.

If the caller does not have permission to update the Document, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the Document to update does not exist and allow_missing is not set, a NOT_FOUND error is returned.

allow_missing

bool

If set to true and the Document is not found, a new Document is be created.

update_mask

FieldMask

Indicates which fields in the provided imported 'document' to update. If not set, by default updates all fields.

UpdateEngineRequest

Request message for EngineService.UpdateEngine method.

Fields
engine

Engine

Required. The Engine to update.

If the caller does not have permission to update the Engine, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the Engine to update does not exist, a NOT_FOUND error is returned.

update_mask

FieldMask

Indicates which fields in the provided Engine to update.

If an unsupported or unknown field is provided, an INVALID_ARGUMENT error is returned.

UpdateSampleQueryRequest

Request message for SampleQueryService.UpdateSampleQuery method.

Fields
sample_query

SampleQuery

Required. The simple query to update.

If the caller does not have permission to update the SampleQuery, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the SampleQuery to update does not exist a NOT_FOUND error is returned.

update_mask

FieldMask

Indicates which fields in the provided imported 'simple query' to update. If not set, will by default update all fields.

UpdateSampleQuerySetRequest

Request message for SampleQuerySetService.UpdateSampleQuerySet method.

Fields
sample_query_set

SampleQuerySet

Required. The sample query set to update.

If the caller does not have permission to update the SampleQuerySet, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the SampleQuerySet to update does not exist a NOT_FOUND error is returned.

update_mask

FieldMask

Indicates which fields in the provided imported 'sample query set' to update. If not set, will by default update all fields.

UpdateSchemaMetadata

Metadata for UpdateSchema LRO.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

UpdateSchemaRequest

Request message for SchemaService.UpdateSchema method.

Fields
schema

Schema

Required. The Schema to update.

allow_missing

bool

If set to true, and the Schema is not found, a new Schema is created. In this situation, update_mask is ignored.

UpdateServingConfigRequest

Request for UpdateServingConfig method.

Fields
serving_config

ServingConfig

Required. The ServingConfig to update.

update_mask

FieldMask

Indicates which fields in the provided ServingConfig to update. The following are NOT supported:

If not set, all supported fields are updated.

UpdateSessionRequest

Request for UpdateSession method.

Fields
session

Session

Required. The Session to update.

update_mask

FieldMask

Indicates which fields in the provided Session to update. The following are NOT supported:

If not set or empty, all supported fields are updated.

UpdateTargetSiteMetadata

Metadata related to the progress of the SiteSearchEngineService.UpdateTargetSite operation. This will be returned by the google.longrunning.Operation.metadata field.

Fields
create_time

Timestamp

Operation create time.

update_time

Timestamp

Operation last update time. If the operation is done, this is also the finish time.

UpdateTargetSiteRequest

Request message for SiteSearchEngineService.UpdateTargetSite method.

Fields
target_site

TargetSite

Required. The target site to update. If the caller does not have permission to update the TargetSite, regardless of whether or not it exists, a PERMISSION_DENIED error is returned.

If the TargetSite to update does not exist, a NOT_FOUND error is returned.

UserEvent

UserEvent captures all metadata information Discovery Engine API needs to know about how end users interact with your website.

Fields
event_type

string

Required. User event type. Allowed values are:

Generic values:

  • search: Search for Documents.
  • view-item: Detailed page view of a Document.
  • view-item-list: View of a panel or ordered list of Documents.
  • view-home-page: View of the home page.
  • view-category-page: View of a category page, e.g. Home > Men > Jeans
  • add-feedback: Add a user feedback.

Retail-related values:

  • add-to-cart: Add an item(s) to cart, e.g. in Retail online shopping
  • purchase: Purchase an item(s)

Media-related values:

  • media-play: Start/resume watching a video, playing a song, etc.
  • media-complete: Finished or stopped midway through a video, song, etc.
user_pseudo_id

string

Required. A unique identifier for tracking visitors.

For example, this could be implemented with an HTTP cookie, which should be able to uniquely identify a visitor on a single device. This unique identifier should not change if the visitor log in/out of the website.

Do not set the field to the same fixed ID for different users. This mixes the event history of those users together, which results in degraded model quality.

The field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an INVALID_ARGUMENT error is returned.

The field should not contain PII or user-data. We recommend to use Google Analytics Client ID for this field.

engine

string

The Engine resource name, in the form of projects/{project}/locations/{location}/collections/{collection_id}/engines/{engine_id}.

Optional. Only required for Engine produced user events. For example, user events from blended search.

data_store

string

The DataStore resource full name, of the form projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}.

Optional. Only required for user events whose data store can't by determined by UserEvent.engine or UserEvent.documents. If data store is set in the parent of write/import/collect user event requests, this field can be omitted.

event_time

Timestamp

Only required for UserEventService.ImportUserEvents method. Timestamp of when the user event happened.

user_info

UserInfo

Information about the end user.

direct_user_request

bool

Should set to true if the request is made directly from the end user, in which case the UserEvent.user_info.user_agent can be populated from the HTTP request.

This flag should be set only if the API request is made directly from the end user such as a mobile app (and not if a gateway or a server is processing and pushing the user events).

This should not be set when using the JavaScript tag in UserEventService.CollectUserEvent.

session_id

string

A unique identifier for tracking a visitor session with a length limit of 128 bytes. A session is an aggregation of an end user behavior in a time span.

A general guideline to populate the session_id:

  1. If user has no activity for 30 min, a new session_id should be assigned.
  2. The session_id should be unique across users, suggest use uuid or add UserEvent.user_pseudo_id as prefix.
page_info

PageInfo

Page metadata such as categories and other critical information for certain event types such as view-category-page.

attribution_token

string

Token to attribute an API response to user action(s) to trigger the event.

Highly recommended for user events that are the result of RecommendationService.Recommend. This field enables accurate attribution of recommendation model performance.

The value must be one of:

This token enables us to accurately attribute page view or conversion completion back to the event and the particular predict response containing this clicked/purchased product. If user clicks on product K in the recommendation results, pass RecommendResponse.attribution_token as a URL parameter to product K's page. When recording events on product K's page, log the RecommendResponse.attribution_token to this field.

filter

string

The filter syntax consists of an expression language for constructing a predicate from one or more fields of the documents being filtered.

One example is for search events, the associated SearchRequest may contain a filter expression in SearchRequest.filter conforming to https://google.aip.dev/160#filtering.

Similarly, for view-item-list events that are generated from a RecommendRequest, this field may be populated directly from RecommendRequest.filter conforming to https://google.aip.dev/160#filtering.

The value must be a UTF-8 encoded string with a length limit of 1,000 characters. Otherwise, an INVALID_ARGUMENT error is returned.

documents[]

DocumentInfo

List of Documents associated with this user event.

This field is optional except for the following event types:

  • view-item
  • add-to-cart
  • purchase
  • media-play
  • media-complete

In a search event, this field represents the documents returned to the end user on the current page (the end user may have not finished browsing the whole page yet). When a new page is returned to the end user, after pagination/filtering/ordering even for the same query, a new search event with different UserEvent.documents is desired.

panel

PanelInfo

Panel metadata associated with this user event.

search_info

SearchInfo

SearchService.Search details related to the event.

This field should be set for search event.

completion_info

CompletionInfo

CompletionService.CompleteQuery details related to the event.

This field should be set for search event when autocomplete function is enabled and the user clicks a suggestion for search.

transaction_info

TransactionInfo

The transaction metadata (if any) associated with this user event.

tag_ids[]

string

A list of identifiers for the independent experiment groups this user event belongs to. This is used to distinguish between user events associated with different experiment setups.

promotion_ids[]

string

The promotion IDs if this is an event associated with promotions. Currently, this field is restricted to at most one ID.

attributes

map<string, CustomAttribute>

Extra user event features to include in the recommendation model. These attributes must NOT contain data that needs to be parsed or processed further, e.g. JSON or other encodings.

If you provide custom attributes for ingested user events, also include them in the user events that you associate with prediction requests. Custom attribute formatting must be consistent between imported events and events provided with prediction requests. This lets the Discovery Engine API use those custom attributes when training models and serving predictions, which helps improve recommendation quality.

This field needs to pass all below criteria, otherwise an INVALID_ARGUMENT error is returned:

  • The key must be a UTF-8 encoded string with a length limit of 5,000 characters.
  • For text attributes, at most 400 values are allowed. Empty values are not allowed. Each value must be a UTF-8 encoded string with a length limit of 256 characters.
  • For number attributes, at most 400 values are allowed.

For product recommendations, an example of extra user information is traffic_channel, which is how a user arrives at the site. Users can arrive at the site by coming to the site directly, coming through Google search, or in other ways.

media_info

MediaInfo

Media-specific info.

UserInfo

Information of an end user.

Fields
user_id

string

Highly recommended for logged-in users. Unique identifier for logged-in user, such as a user name. Don't set for anonymous users.

Always use a hashed value for this ID.

Don't set the field to the same fixed ID for different users. This mixes the event history of those users together, which results in degraded model quality.

The field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an INVALID_ARGUMENT error is returned.

user_agent

string

User agent as included in the HTTP header.

The field must be a UTF-8 encoded string with a length limit of 1,000 characters. Otherwise, an INVALID_ARGUMENT error is returned.

This should not be set when using the client side event reporting with GTM or JavaScript tag in UserEventService.CollectUserEvent or if UserEvent.direct_user_request is set.

WorkspaceConfig

Config to store data store type configuration for workspace data

Fields
type

Type

The Google Workspace data source.

dasher_customer_id

string

Obfuscated Dasher customer ID.

super_admin_service_account

string

Optional. The super admin service account for the workspace that will be used for access token generation. For now we only use it for Native Google Drive connector data ingestion.

super_admin_email_address

string

Optional. The super admin email address for the workspace that will be used for access token generation. For now we only use it for Native Google Drive connector data ingestion.

Type

Specifies the type of Workspace App supported by this DataStore

Enums
TYPE_UNSPECIFIED Defaults to an unspecified Workspace type.
GOOGLE_DRIVE Workspace Data Store contains Drive data
GOOGLE_MAIL Workspace Data Store contains Mail data
GOOGLE_SITES Workspace Data Store contains Sites data
GOOGLE_CALENDAR Workspace Data Store contains Calendar data
GOOGLE_CHAT Workspace Data Store contains Chat data
GOOGLE_GROUPS Workspace Data Store contains Groups data
GOOGLE_KEEP Workspace Data Store contains Keep data

WriteUserEventRequest

Request message for WriteUserEvent method.

Fields
parent

string

Required. The parent resource name. If the write user event action is applied in DataStore level, the format is: projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}. If the write user event action is applied in [Location][] level, for example, the event with Document across multiple DataStore, the format is: projects/{project}/locations/{location}.

write_async

bool

If set to true, the user event is written asynchronously after validation, and the API responds without waiting for the write.

user_event

UserEvent

Required. User event to write.