Discovery Engine v1 API - Class StreamAssistRequest.Types.ToolsSpec.Types.VertexAiSearchSpec (1.9.0) 

public sealed class StreamAssistRequest.Types.ToolsSpec.Types.VertexAiSearchSpec : IMessage<StreamAssistRequest.Types.ToolsSpec.Types.VertexAiSearchSpec>, IEquatable<StreamAssistRequest.Types.ToolsSpec.Types.VertexAiSearchSpec>, IDeepCloneable<StreamAssistRequest.Types.ToolsSpec.Types.VertexAiSearchSpec>, IBufferMessage, IMessage

Reference documentation and code samples for the Discovery Engine v1 API class StreamAssistRequest.Types.ToolsSpec.Types.VertexAiSearchSpec.

Specification of the Vertex AI Search tool.

Inheritance

object > StreamAssistRequest.Types.ToolsSpec.Types.VertexAiSearchSpec

Namespace

Google.Cloud.DiscoveryEngine.V1

Assembly

Google.Cloud.DiscoveryEngine.V1.dll

Constructors

VertexAiSearchSpec()

public VertexAiSearchSpec()

VertexAiSearchSpec(VertexAiSearchSpec)

public VertexAiSearchSpec(StreamAssistRequest.Types.ToolsSpec.Types.VertexAiSearchSpec other)
Parameter
Name Description
other StreamAssistRequestTypesToolsSpecTypesVertexAiSearchSpec

Properties

DataStoreSpecs

public RepeatedField<SearchRequest.Types.DataStoreSpec> DataStoreSpecs { get; }

Optional. Specs defining [DataStore][google.cloud.discoveryengine.v1.DataStore]s to filter on in a search call and configurations for those data stores. This is only considered for [Engine][google.cloud.discoveryengine.v1.Engine]s with multiple data stores.

Property Value
Type Description
RepeatedFieldSearchRequestTypesDataStoreSpec

Filter

public string Filter { get; set; }

Optional. 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

Property Value
Type Description
string