Class Tool (1.0.0)

publicfinalclass ToolextendsGeneratedMessageV3implementsToolOrBuilder

Tool details that the model may use to generate response.

A Tool is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).

Protobuf type google.cloud.vertexai.v1.Tool

Inheritance

Object > AbstractMessageLite<MessageType,BuilderType> > AbstractMessage > GeneratedMessageV3 > Tool

Implements

ToolOrBuilder

Inherited Members

publicstaticfinalintFUNCTION_DECLARATIONS_FIELD_NUMBER

publicstaticfinalintGOOGLE_SEARCH_RETRIEVAL_FIELD_NUMBER

publicstaticfinalintRETRIEVAL_FIELD_NUMBER

publicstaticToolgetDefaultInstance()

publicstaticfinalDescriptors.DescriptorgetDescriptor()

publicstaticTool.BuildernewBuilder()

publicstaticTool.BuildernewBuilder(Toolprototype)

publicstaticToolparseDelimitedFrom(InputStreaminput)

publicstaticToolparseDelimitedFrom(InputStreaminput,ExtensionRegistryLiteextensionRegistry)

publicstaticToolparseFrom(byte[]data)

publicstaticToolparseFrom(byte[]data,ExtensionRegistryLiteextensionRegistry)

publicstaticToolparseFrom(ByteStringdata)

publicstaticToolparseFrom(ByteStringdata,ExtensionRegistryLiteextensionRegistry)

publicstaticToolparseFrom(CodedInputStreaminput)

publicstaticToolparseFrom(CodedInputStreaminput,ExtensionRegistryLiteextensionRegistry)

publicstaticToolparseFrom(InputStreaminput)

publicstaticToolparseFrom(InputStreaminput,ExtensionRegistryLiteextensionRegistry)

publicstaticToolparseFrom(ByteBufferdata)

publicstaticToolparseFrom(ByteBufferdata,ExtensionRegistryLiteextensionRegistry)

publicstaticParser<Tool>parser()

publicbooleanequals(Objectobj)

AbstractMessage.equals(Object other)

publicToolgetDefaultInstanceForType()

publicFunctionDeclarationgetFunctionDeclarations(intindex)

Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 64 function declarations can be provided.

repeated .google.cloud.vertexai.v1.FunctionDeclaration function_declarations = 1 [(.google.api.field_behavior) = OPTIONAL];

publicintgetFunctionDeclarationsCount()

Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 64 function declarations can be provided.

repeated .google.cloud.vertexai.v1.FunctionDeclaration function_declarations = 1 [(.google.api.field_behavior) = OPTIONAL];

publicList<FunctionDeclaration>getFunctionDeclarationsList()

Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 64 function declarations can be provided.

repeated .google.cloud.vertexai.v1.FunctionDeclaration function_declarations = 1 [(.google.api.field_behavior) = OPTIONAL];

publicFunctionDeclarationOrBuildergetFunctionDeclarationsOrBuilder(intindex)

Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 64 function declarations can be provided.

repeated .google.cloud.vertexai.v1.FunctionDeclaration function_declarations = 1 [(.google.api.field_behavior) = OPTIONAL];

publicList<?extendsFunctionDeclarationOrBuilder>getFunctionDeclarationsOrBuilderList()

Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 64 function declarations can be provided.

repeated .google.cloud.vertexai.v1.FunctionDeclaration function_declarations = 1 [(.google.api.field_behavior) = OPTIONAL];

publicGoogleSearchRetrievalgetGoogleSearchRetrieval()

Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search.

.google.cloud.vertexai.v1.GoogleSearchRetrieval google_search_retrieval = 3 [(.google.api.field_behavior) = OPTIONAL];

publicGoogleSearchRetrievalOrBuildergetGoogleSearchRetrievalOrBuilder()

Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search.

.google.cloud.vertexai.v1.GoogleSearchRetrieval google_search_retrieval = 3 [(.google.api.field_behavior) = OPTIONAL];

publicParser<Tool>getParserForType()

GeneratedMessageV3.getParserForType()

publicRetrievalgetRetrieval()

Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation.

.google.cloud.vertexai.v1.Retrieval retrieval = 2 [(.google.api.field_behavior) = OPTIONAL];

publicRetrievalOrBuildergetRetrievalOrBuilder()

Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation.

.google.cloud.vertexai.v1.Retrieval retrieval = 2 [(.google.api.field_behavior) = OPTIONAL];

publicintgetSerializedSize()

GeneratedMessageV3.getSerializedSize()

publicbooleanhasGoogleSearchRetrieval()

Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search.

.google.cloud.vertexai.v1.GoogleSearchRetrieval google_search_retrieval = 3 [(.google.api.field_behavior) = OPTIONAL];

publicbooleanhasRetrieval()

Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation.

.google.cloud.vertexai.v1.Retrieval retrieval = 2 [(.google.api.field_behavior) = OPTIONAL];

publicinthashCode()

AbstractMessage.hashCode()

protectedGeneratedMessageV3.FieldAccessorTableinternalGetFieldAccessorTable()

GeneratedMessageV3.internalGetFieldAccessorTable()

publicfinalbooleanisInitialized()

GeneratedMessageV3.isInitialized()

publicTool.BuildernewBuilderForType()

protectedTool.BuildernewBuilderForType(GeneratedMessageV3.BuilderParentparent)

GeneratedMessageV3.newBuilderForType(GeneratedMessageV3.BuilderParent parent)

protectedObjectnewInstance(GeneratedMessageV3.UnusedPrivateParameterunused)

GeneratedMessageV3.newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)

publicTool.BuildertoBuilder()

publicvoidwriteTo(CodedOutputStreamoutput)

GeneratedMessageV3.writeTo(CodedOutputStream output)