Close httplib2 connections.
createGuest(body=None, x__xgafv=None)
Create a guest user with access to a [subset of Workspace capabilities](https://support.google.com/a/answer/16558545?hl=en). This feature is currently in Alpha. Please reach out to support if you are interested in trying this feature.
+Create a guest user with access to a [subset of Workspace capabilities](https://support.google.com/a/answer/16558545). This feature is currently in Alpha. Please reach out to support if you are interested in trying this feature.
delete(userKey, x__xgafv=None)
Deletes a user.
@@ -131,7 +131,7 @@createGuest(body=None, x__xgafv=None)
- Create a guest user with access to a [subset of Workspace capabilities](https://support.google.com/a/answer/16558545?hl=en). This feature is currently in Alpha. Please reach out to support if you are interested in trying this feature. +Create a guest user with access to a [subset of Workspace capabilities](https://support.google.com/a/answer/16558545). This feature is currently in Alpha. Please reach out to support if you are interested in trying this feature. Args: body: object, The request body. diff --git a/docs/dyn/admin_reports_v1.activities.html b/docs/dyn/admin_reports_v1.activities.html index 003badf70f..98fa9f3374 100644 --- a/docs/dyn/admin_reports_v1.activities.html +++ b/docs/dyn/admin_reports_v1.activities.html @@ -320,7 +320,25 @@Method Details
"title": "A String", # Title of the label }, ], - "id": "A String", # Identifier of the resource. + "id": "A String", # Identifier of the resource, such as a doc_id for a Drive document, a conference_id for a Meet conference, or a "gaia_id/rfc2822_message_id" for an email. + "ownerDetails": { # Details of the owner of the resource. # Owner details of the resource. + "ownerIdentity": [ # Identity details of the owner(s) of the resource. + { # Identity details of the owner of the resource. + "customerIdentity": { # Identity of the Google Workspace customer who owns the resource. # Identity of the Google Workspace customer who owns the resource. + "id": "A String", # Customer id. + }, + "groupIdentity": { # Identity of the group who owns the resource. # Identity of the group who owns the resource. + "groupEmail": "A String", # Group email. + "id": "A String", # Group gaia id. + }, + "userIdentity": { # Identity of the user who owns the resource. # Identity of the user who owns the resource. + "id": "A String", # User gaia id. + "userEmail": "A String", # User email. + }, + }, + ], + "ownerType": "A String", # Type of the owner of the resource. + }, "relation": "A String", # Defines relationship of the resource to the events "title": "A String", # Title of the resource. For instance, in case of a drive document, this would be the title of the document. In case of an email, this would be the subject. "type": "A String", # Type of the resource - document, email, chat message diff --git a/docs/dyn/aiplatform_v1.endpoints.html b/docs/dyn/aiplatform_v1.endpoints.html index c270881c10..26a6612b79 100644 --- a/docs/dyn/aiplatform_v1.endpoints.html +++ b/docs/dyn/aiplatform_v1.endpoints.html @@ -128,11 +128,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -141,11 +141,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -158,8 +158,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -243,11 +243,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -256,11 +256,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -273,8 +273,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -328,6 +328,7 @@Method Details
}, "imageSize": "A String", # Optional. Specifies the size of generated images. Supported values are `1K`, `2K`, `4K`. If not specified, the model will use default value `1K`. "personGeneration": "A String", # Optional. Controls whether the model can generate people. + "prominentPeople": "A String", # Optional. Controls whether prominent people (celebrities) generation is allowed. If used with personGeneration, personGeneration enum would take precedence. For instance, if ALLOW_NONE is set, all person generation would be blocked. If this field is unspecified, the default behavior is to allow prominent people. }, "logprobs": 42, # Optional. The number of top log probabilities to return for each token. This can be used to see which other tokens were considered likely candidates for a given position. A higher value will return more options, but it will also increase the size of the response. "maxOutputTokens": 42, # Optional. The maximum number of tokens to generate in the response. A token is approximately four characters. The default value varies by model. This parameter can be used to control the length of the generated text and prevent overly long responses. @@ -348,7 +349,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -434,11 +435,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -447,11 +448,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -464,8 +465,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -507,7 +508,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next 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. { # 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). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -534,7 +535,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -574,7 +575,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -615,6 +616,12 @@Method Details
"excludeDomains": [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: ["amazon.com", "facebook.com"]. "A String", ], + "searchTypes": { # Different types of search that can be enabled on the GoogleSearch tool. # Optional. The set of search types to enable. If not set, web search is enabled by default. + "imageSearch": { # Image search for grounding and related configurations. # Optional. Setting this field enables image search. Image bytes are returned. + }, + "webSearch": { # Standard web search for grounding and related configurations. Only text results are returned. # Optional. Setting this field enables web search. Only text results are returned. + }, + }, }, "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. Specialized retrieval tool that is powered by Google Search. "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source. @@ -794,11 +801,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -807,11 +814,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -824,8 +831,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -879,6 +886,7 @@Method Details
}, "imageSize": "A String", # Optional. Specifies the size of generated images. Supported values are `1K`, `2K`, `4K`. If not specified, the model will use default value `1K`. "personGeneration": "A String", # Optional. Controls whether the model can generate people. + "prominentPeople": "A String", # Optional. Controls whether prominent people (celebrities) generation is allowed. If used with personGeneration, personGeneration enum would take precedence. For instance, if ALLOW_NONE is set, all person generation would be blocked. If this field is unspecified, the default behavior is to allow prominent people. }, "logprobs": 42, # Optional. The number of top log probabilities to return for each token. This can be used to see which other tokens were considered likely candidates for a given position. A higher value will return more options, but it will also increase the size of the response. "maxOutputTokens": 42, # Optional. The maximum number of tokens to generate in the response. A token is approximately four characters. The default value varies by model. This parameter can be used to control the length of the generated text and prevent overly long responses. @@ -899,7 +907,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -995,11 +1003,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1008,11 +1016,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1025,8 +1033,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1068,11 +1076,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -1084,7 +1092,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next 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. { # 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). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1111,7 +1119,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -1151,7 +1159,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -1192,6 +1200,12 @@Method Details
"excludeDomains": [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: ["amazon.com", "facebook.com"]. "A String", ], + "searchTypes": { # Different types of search that can be enabled on the GoogleSearch tool. # Optional. The set of search types to enable. If not set, web search is enabled by default. + "imageSearch": { # Image search for grounding and related configurations. # Optional. Setting this field enables image search. Image bytes are returned. + }, + "webSearch": { # Standard web search for grounding and related configurations. Only text results are returned. # Optional. Setting this field enables web search. Only text results are returned. + }, + }, }, "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. Specialized retrieval tool that is powered by Google Search. "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source. @@ -1325,11 +1339,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1338,11 +1352,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1355,8 +1369,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1402,6 +1416,12 @@Method Details
"googleMapsWidgetContextToken": "A String", # Optional. Output only. A token that can be used to render a Google Maps widget with the contextual data. This field is populated only when the grounding source is Google Maps. "groundingChunks": [ # A list of supporting references retrieved from the grounding source. This field is populated when the grounding source is Google Search, Vertex AI Search, or Google Maps. { # A piece of evidence that supports a claim made by the model. This is used to show a citation for a claim made by the model. When grounding is enabled, the model returns a `GroundingChunk` that contains a reference to the source of the information. + "image": { # An `Image` chunk is a piece of evidence that comes from an image search result. It contains the URI of the image search result and the URI of the image. This is used to provide the user with a link to the source of the information. # A grounding chunk from an image search result. See the `Image` message for details. + "domain": "A String", # The domain of the image search result page. + "imageUri": "A String", # The URI of the image. + "sourceUri": "A String", # The URI of the image search result page. + "title": "A String", # The title of the image search result page. + }, "maps": { # A `Maps` chunk is a piece of evidence that comes from Google Maps, containing information about places or routes. This is used to provide the user with rich, location-based information. # A grounding chunk from Google Maps. See the `Maps` message for details. "placeAnswerSources": { # The sources that were used to generate the place answer. This includes review snippets and photos that were used to generate the answer, as well as URIs to flag content. # The sources that were used to generate the place answer. This includes review snippets and photos that were used to generate the answer, as well as URIs to flag content. "reviewSnippets": [ # Snippets of reviews that were used to generate the answer. @@ -1413,6 +1433,11 @@Method Details
], }, "placeId": "A String", # This Place's resource name, in `places/{place_id}` format. This can be used to look up the place in the Google Maps API. + "route": { # Route information from Google Maps. # Output only. Route information. + "distanceMeters": 42, # The total distance of the route, in meters. + "duration": "A String", # The total duration of the route. + "encodedPolyline": "A String", # An encoded polyline of the route. See https://developers.google.com/maps/documentation/utilities/polylinealgorithm + }, "text": "A String", # The text of the place answer. "title": "A String", # The title of the place. "uri": "A String", # The URI of the place. @@ -1438,13 +1463,16 @@Method Details
}, ], "groundingSupports": [ # Optional. A list of grounding supports that connect the generated content to the grounding chunks. This field is populated when the grounding source is Google Search or Vertex AI Search. - { # A collection of supporting references for a segment of the model's response. + { # A collection of supporting references for a segment or part of the model's response. "confidenceScores": [ # The confidence scores for the support references. This list is parallel to the `grounding_chunk_indices` list. A score is a value between 0.0 and 1.0, with a higher score indicating a higher confidence that the reference supports the claim. For Gemini 2.0 and before, this list has the same size as `grounding_chunk_indices`. For Gemini 2.5 and later, this list is empty and should be ignored. 3.14, ], "groundingChunkIndices": [ # A list of indices into the `grounding_chunks` field of the `GroundingMetadata` message. These indices specify which grounding chunks support the claim made in the content segment. For example, if this field has the values `[1, 3]`, it means that `grounding_chunks[1]` and `grounding_chunks[3]` are the sources for the claim in the content segment. 42, ], + "renderedParts": [ # Indices into the `rendered_parts` field of the `GroundingMetadata` message. These indices specify which rendered parts are associated with this support message. + 42, + ], "segment": { # A segment of the content. # The content segment that this support message applies to. "endIndex": 42, # Output only. The end index of the segment in the `Part`, measured in bytes. This marks the end of the segment and is exclusive, meaning the segment includes content up to, but not including, the byte at this index. "partIndex": 42, # Output only. The index of the `Part` object that this segment belongs to. This is useful for associating the segment with a specific part of the content. @@ -1453,6 +1481,9 @@Method Details
}, }, ], + "imageSearchQueries": [ # Optional. The image search queries that were used to generate the content. This field is populated only when the grounding source is Google Search with the Image Search search_type enabled. + "A String", + ], "retrievalMetadata": { # Metadata related to the retrieval grounding source. This is part of the `GroundingMetadata` returned when grounding is enabled. # Optional. Output only. Metadata related to the retrieval grounding source. "googleSearchDynamicRetrievalScore": 3.14, # Optional. A score indicating how likely it is that a Google Search query could help answer the prompt. The score is in the range of `[0, 1]`. A score of 1 means the model is confident that a search will be helpful, and 0 means it is not. This score is populated only when Google Search grounding and dynamic retrieval are enabled. The score is used to determine whether to trigger a search. }, @@ -1665,11 +1696,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1678,11 +1709,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1695,8 +1726,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1750,6 +1781,7 @@Method Details
}, "imageSize": "A String", # Optional. Specifies the size of generated images. Supported values are `1K`, `2K`, `4K`. If not specified, the model will use default value `1K`. "personGeneration": "A String", # Optional. Controls whether the model can generate people. + "prominentPeople": "A String", # Optional. Controls whether prominent people (celebrities) generation is allowed. If used with personGeneration, personGeneration enum would take precedence. For instance, if ALLOW_NONE is set, all person generation would be blocked. If this field is unspecified, the default behavior is to allow prominent people. }, "logprobs": 42, # Optional. The number of top log probabilities to return for each token. This can be used to see which other tokens were considered likely candidates for a given position. A higher value will return more options, but it will also increase the size of the response. "maxOutputTokens": 42, # Optional. The maximum number of tokens to generate in the response. A token is approximately four characters. The default value varies by model. This parameter can be used to control the length of the generated text and prevent overly long responses. @@ -1770,7 +1802,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -1866,11 +1898,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1879,11 +1911,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1896,8 +1928,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1939,11 +1971,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -1955,7 +1987,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next 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. { # 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). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1982,7 +2014,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -2022,7 +2054,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -2063,6 +2095,12 @@Method Details
"excludeDomains": [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: ["amazon.com", "facebook.com"]. "A String", ], + "searchTypes": { # Different types of search that can be enabled on the GoogleSearch tool. # Optional. The set of search types to enable. If not set, web search is enabled by default. + "imageSearch": { # Image search for grounding and related configurations. # Optional. Setting this field enables image search. Image bytes are returned. + }, + "webSearch": { # Standard web search for grounding and related configurations. Only text results are returned. # Optional. Setting this field enables web search. Only text results are returned. + }, + }, }, "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. Specialized retrieval tool that is powered by Google Search. "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source. @@ -2196,11 +2234,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2209,11 +2247,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2226,8 +2264,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2273,6 +2311,12 @@Method Details
"googleMapsWidgetContextToken": "A String", # Optional. Output only. A token that can be used to render a Google Maps widget with the contextual data. This field is populated only when the grounding source is Google Maps. "groundingChunks": [ # A list of supporting references retrieved from the grounding source. This field is populated when the grounding source is Google Search, Vertex AI Search, or Google Maps. { # A piece of evidence that supports a claim made by the model. This is used to show a citation for a claim made by the model. When grounding is enabled, the model returns a `GroundingChunk` that contains a reference to the source of the information. + "image": { # An `Image` chunk is a piece of evidence that comes from an image search result. It contains the URI of the image search result and the URI of the image. This is used to provide the user with a link to the source of the information. # A grounding chunk from an image search result. See the `Image` message for details. + "domain": "A String", # The domain of the image search result page. + "imageUri": "A String", # The URI of the image. + "sourceUri": "A String", # The URI of the image search result page. + "title": "A String", # The title of the image search result page. + }, "maps": { # A `Maps` chunk is a piece of evidence that comes from Google Maps, containing information about places or routes. This is used to provide the user with rich, location-based information. # A grounding chunk from Google Maps. See the `Maps` message for details. "placeAnswerSources": { # The sources that were used to generate the place answer. This includes review snippets and photos that were used to generate the answer, as well as URIs to flag content. # The sources that were used to generate the place answer. This includes review snippets and photos that were used to generate the answer, as well as URIs to flag content. "reviewSnippets": [ # Snippets of reviews that were used to generate the answer. @@ -2284,6 +2328,11 @@Method Details
], }, "placeId": "A String", # This Place's resource name, in `places/{place_id}` format. This can be used to look up the place in the Google Maps API. + "route": { # Route information from Google Maps. # Output only. Route information. + "distanceMeters": 42, # The total distance of the route, in meters. + "duration": "A String", # The total duration of the route. + "encodedPolyline": "A String", # An encoded polyline of the route. See https://developers.google.com/maps/documentation/utilities/polylinealgorithm + }, "text": "A String", # The text of the place answer. "title": "A String", # The title of the place. "uri": "A String", # The URI of the place. @@ -2309,13 +2358,16 @@Method Details
}, ], "groundingSupports": [ # Optional. A list of grounding supports that connect the generated content to the grounding chunks. This field is populated when the grounding source is Google Search or Vertex AI Search. - { # A collection of supporting references for a segment of the model's response. + { # A collection of supporting references for a segment or part of the model's response. "confidenceScores": [ # The confidence scores for the support references. This list is parallel to the `grounding_chunk_indices` list. A score is a value between 0.0 and 1.0, with a higher score indicating a higher confidence that the reference supports the claim. For Gemini 2.0 and before, this list has the same size as `grounding_chunk_indices`. For Gemini 2.5 and later, this list is empty and should be ignored. 3.14, ], "groundingChunkIndices": [ # A list of indices into the `grounding_chunks` field of the `GroundingMetadata` message. These indices specify which grounding chunks support the claim made in the content segment. For example, if this field has the values `[1, 3]`, it means that `grounding_chunks[1]` and `grounding_chunks[3]` are the sources for the claim in the content segment. 42, ], + "renderedParts": [ # Indices into the `rendered_parts` field of the `GroundingMetadata` message. These indices specify which rendered parts are associated with this support message. + 42, + ], "segment": { # A segment of the content. # The content segment that this support message applies to. "endIndex": 42, # Output only. The end index of the segment in the `Part`, measured in bytes. This marks the end of the segment and is exclusive, meaning the segment includes content up to, but not including, the byte at this index. "partIndex": 42, # Output only. The index of the `Part` object that this segment belongs to. This is useful for associating the segment with a specific part of the content. @@ -2324,6 +2376,9 @@Method Details
}, }, ], + "imageSearchQueries": [ # Optional. The image search queries that were used to generate the content. This field is populated only when the grounding source is Google Search with the Image Search search_type enabled. + "A String", + ], "retrievalMetadata": { # Metadata related to the retrieval grounding source. This is part of the `GroundingMetadata` returned when grounding is enabled. # Optional. Output only. Metadata related to the retrieval grounding source. "googleSearchDynamicRetrievalScore": 3.14, # Optional. A score indicating how likely it is that a Google Search query could help answer the prompt. The score is in the range of `[0, 1]`. A score of 1 means the model is confident that a search will be helpful, and 0 means it is not. This score is populated only when Google Search grounding and dynamic retrieval are enabled. The score is used to determine whether to trigger a search. }, diff --git a/docs/dyn/aiplatform_v1.projects.locations.cachedContents.html b/docs/dyn/aiplatform_v1.projects.locations.cachedContents.html index b129084fc1..08987a541a 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.cachedContents.html +++ b/docs/dyn/aiplatform_v1.projects.locations.cachedContents.html @@ -115,11 +115,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -128,11 +128,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -145,8 +145,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -198,11 +198,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -211,11 +211,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -228,8 +228,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -271,11 +271,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Input only. Immutable. Tool config. This config is shared for all tools "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -287,7 +287,7 @@Method Details
}, "tools": [ # Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response { # 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). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -314,7 +314,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -354,7 +354,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -395,6 +395,12 @@Method Details
"excludeDomains": [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: ["amazon.com", "facebook.com"]. "A String", ], + "searchTypes": { # Different types of search that can be enabled on the GoogleSearch tool. # Optional. The set of search types to enable. If not set, web search is enabled by default. + "imageSearch": { # Image search for grounding and related configurations. # Optional. Setting this field enables image search. Image bytes are returned. + }, + "webSearch": { # Standard web search for grounding and related configurations. Only text results are returned. # Optional. Setting this field enables web search. Only text results are returned. + }, + }, }, "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. Specialized retrieval tool that is powered by Google Search. "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source. @@ -519,11 +525,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -532,11 +538,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -549,8 +555,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -602,11 +608,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -615,11 +621,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -632,8 +638,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -675,11 +681,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Input only. Immutable. Tool config. This config is shared for all tools "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -691,7 +697,7 @@Method Details
}, "tools": [ # Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response { # 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). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -718,7 +724,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -758,7 +764,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -799,6 +805,12 @@Method Details
"excludeDomains": [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: ["amazon.com", "facebook.com"]. "A String", ], + "searchTypes": { # Different types of search that can be enabled on the GoogleSearch tool. # Optional. The set of search types to enable. If not set, web search is enabled by default. + "imageSearch": { # Image search for grounding and related configurations. # Optional. Setting this field enables image search. Image bytes are returned. + }, + "webSearch": { # Standard web search for grounding and related configurations. Only text results are returned. # Optional. Setting this field enables web search. Only text results are returned. + }, + }, }, "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. Specialized retrieval tool that is powered by Google Search. "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source. @@ -948,11 +960,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -961,11 +973,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -978,8 +990,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1031,11 +1043,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1044,11 +1056,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1061,8 +1073,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1104,11 +1116,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Input only. Immutable. Tool config. This config is shared for all tools "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -1120,7 +1132,7 @@Method Details
}, "tools": [ # Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response { # 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). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1147,7 +1159,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -1187,7 +1199,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -1228,6 +1240,12 @@Method Details
"excludeDomains": [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: ["amazon.com", "facebook.com"]. "A String", ], + "searchTypes": { # Different types of search that can be enabled on the GoogleSearch tool. # Optional. The set of search types to enable. If not set, web search is enabled by default. + "imageSearch": { # Image search for grounding and related configurations. # Optional. Setting this field enables image search. Image bytes are returned. + }, + "webSearch": { # Standard web search for grounding and related configurations. Only text results are returned. # Optional. Setting this field enables web search. Only text results are returned. + }, + }, }, "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. Specialized retrieval tool that is powered by Google Search. "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source. @@ -1363,11 +1381,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1376,11 +1394,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1393,8 +1411,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1446,11 +1464,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1459,11 +1477,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1476,8 +1494,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1519,11 +1537,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Input only. Immutable. Tool config. This config is shared for all tools "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -1535,7 +1553,7 @@Method Details
}, "tools": [ # Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response { # 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). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1562,7 +1580,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -1602,7 +1620,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -1643,6 +1661,12 @@Method Details
"excludeDomains": [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: ["amazon.com", "facebook.com"]. "A String", ], + "searchTypes": { # Different types of search that can be enabled on the GoogleSearch tool. # Optional. The set of search types to enable. If not set, web search is enabled by default. + "imageSearch": { # Image search for grounding and related configurations. # Optional. Setting this field enables image search. Image bytes are returned. + }, + "webSearch": { # Standard web search for grounding and related configurations. Only text results are returned. # Optional. Setting this field enables web search. Only text results are returned. + }, + }, }, "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. Specialized retrieval tool that is powered by Google Search. "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source. @@ -1786,11 +1810,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1799,11 +1823,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1816,8 +1840,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1869,11 +1893,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1882,11 +1906,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1899,8 +1923,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1942,11 +1966,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Input only. Immutable. Tool config. This config is shared for all tools "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -1958,7 +1982,7 @@Method Details
}, "tools": [ # Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response { # 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). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1985,7 +2009,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -2025,7 +2049,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -2066,6 +2090,12 @@Method Details
"excludeDomains": [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: ["amazon.com", "facebook.com"]. "A String", ], + "searchTypes": { # Different types of search that can be enabled on the GoogleSearch tool. # Optional. The set of search types to enable. If not set, web search is enabled by default. + "imageSearch": { # Image search for grounding and related configurations. # Optional. Setting this field enables image search. Image bytes are returned. + }, + "webSearch": { # Standard web search for grounding and related configurations. Only text results are returned. # Optional. Setting this field enables web search. Only text results are returned. + }, + }, }, "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. Specialized retrieval tool that is powered by Google Search. "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source. @@ -2191,11 +2221,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2204,11 +2234,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2221,8 +2251,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2274,11 +2304,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2287,11 +2317,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2304,8 +2334,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2347,11 +2377,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Input only. Immutable. Tool config. This config is shared for all tools "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -2363,7 +2393,7 @@Method Details
}, "tools": [ # Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response { # 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). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2390,7 +2420,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -2430,7 +2460,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -2471,6 +2501,12 @@Method Details
"excludeDomains": [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: ["amazon.com", "facebook.com"]. "A String", ], + "searchTypes": { # Different types of search that can be enabled on the GoogleSearch tool. # Optional. The set of search types to enable. If not set, web search is enabled by default. + "imageSearch": { # Image search for grounding and related configurations. # Optional. Setting this field enables image search. Image bytes are returned. + }, + "webSearch": { # Standard web search for grounding and related configurations. Only text results are returned. # Optional. Setting this field enables web search. Only text results are returned. + }, + }, }, "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. Specialized retrieval tool that is powered by Google Search. "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source. diff --git a/docs/dyn/aiplatform_v1.projects.locations.endpoints.html b/docs/dyn/aiplatform_v1.projects.locations.endpoints.html index ac8fa0cfe7..e3bb6f47ee 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.endpoints.html +++ b/docs/dyn/aiplatform_v1.projects.locations.endpoints.html @@ -196,11 +196,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -209,11 +209,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -226,8 +226,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -311,11 +311,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -324,11 +324,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -341,8 +341,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -396,6 +396,7 @@Method Details
}, "imageSize": "A String", # Optional. Specifies the size of generated images. Supported values are `1K`, `2K`, `4K`. If not specified, the model will use default value `1K`. "personGeneration": "A String", # Optional. Controls whether the model can generate people. + "prominentPeople": "A String", # Optional. Controls whether prominent people (celebrities) generation is allowed. If used with personGeneration, personGeneration enum would take precedence. For instance, if ALLOW_NONE is set, all person generation would be blocked. If this field is unspecified, the default behavior is to allow prominent people. }, "logprobs": 42, # Optional. The number of top log probabilities to return for each token. This can be used to see which other tokens were considered likely candidates for a given position. A higher value will return more options, but it will also increase the size of the response. "maxOutputTokens": 42, # Optional. The maximum number of tokens to generate in the response. A token is approximately four characters. The default value varies by model. This parameter can be used to control the length of the generated text and prevent overly long responses. @@ -416,7 +417,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -502,11 +503,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -515,11 +516,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -532,8 +533,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -575,7 +576,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next 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. { # 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). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -602,7 +603,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -642,7 +643,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -683,6 +684,12 @@Method Details
"excludeDomains": [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: ["amazon.com", "facebook.com"]. "A String", ], + "searchTypes": { # Different types of search that can be enabled on the GoogleSearch tool. # Optional. The set of search types to enable. If not set, web search is enabled by default. + "imageSearch": { # Image search for grounding and related configurations. # Optional. Setting this field enables image search. Image bytes are returned. + }, + "webSearch": { # Standard web search for grounding and related configurations. Only text results are returned. # Optional. Setting this field enables web search. Only text results are returned. + }, + }, }, "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. Specialized retrieval tool that is powered by Google Search. "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source. @@ -1758,11 +1765,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1771,11 +1778,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1788,8 +1795,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1843,6 +1850,7 @@Method Details
}, "imageSize": "A String", # Optional. Specifies the size of generated images. Supported values are `1K`, `2K`, `4K`. If not specified, the model will use default value `1K`. "personGeneration": "A String", # Optional. Controls whether the model can generate people. + "prominentPeople": "A String", # Optional. Controls whether prominent people (celebrities) generation is allowed. If used with personGeneration, personGeneration enum would take precedence. For instance, if ALLOW_NONE is set, all person generation would be blocked. If this field is unspecified, the default behavior is to allow prominent people. }, "logprobs": 42, # Optional. The number of top log probabilities to return for each token. This can be used to see which other tokens were considered likely candidates for a given position. A higher value will return more options, but it will also increase the size of the response. "maxOutputTokens": 42, # Optional. The maximum number of tokens to generate in the response. A token is approximately four characters. The default value varies by model. This parameter can be used to control the length of the generated text and prevent overly long responses. @@ -1863,7 +1871,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -1959,11 +1967,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1972,11 +1980,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1989,8 +1997,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2032,11 +2040,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -2048,7 +2056,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next 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. { # 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). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2075,7 +2083,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -2115,7 +2123,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -2156,6 +2164,12 @@Method Details
"excludeDomains": [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: ["amazon.com", "facebook.com"]. "A String", ], + "searchTypes": { # Different types of search that can be enabled on the GoogleSearch tool. # Optional. The set of search types to enable. If not set, web search is enabled by default. + "imageSearch": { # Image search for grounding and related configurations. # Optional. Setting this field enables image search. Image bytes are returned. + }, + "webSearch": { # Standard web search for grounding and related configurations. Only text results are returned. # Optional. Setting this field enables web search. Only text results are returned. + }, + }, }, "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. Specialized retrieval tool that is powered by Google Search. "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source. @@ -2289,11 +2303,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2302,11 +2316,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2319,8 +2333,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2366,6 +2380,12 @@Method Details
"googleMapsWidgetContextToken": "A String", # Optional. Output only. A token that can be used to render a Google Maps widget with the contextual data. This field is populated only when the grounding source is Google Maps. "groundingChunks": [ # A list of supporting references retrieved from the grounding source. This field is populated when the grounding source is Google Search, Vertex AI Search, or Google Maps. { # A piece of evidence that supports a claim made by the model. This is used to show a citation for a claim made by the model. When grounding is enabled, the model returns a `GroundingChunk` that contains a reference to the source of the information. + "image": { # An `Image` chunk is a piece of evidence that comes from an image search result. It contains the URI of the image search result and the URI of the image. This is used to provide the user with a link to the source of the information. # A grounding chunk from an image search result. See the `Image` message for details. + "domain": "A String", # The domain of the image search result page. + "imageUri": "A String", # The URI of the image. + "sourceUri": "A String", # The URI of the image search result page. + "title": "A String", # The title of the image search result page. + }, "maps": { # A `Maps` chunk is a piece of evidence that comes from Google Maps, containing information about places or routes. This is used to provide the user with rich, location-based information. # A grounding chunk from Google Maps. See the `Maps` message for details. "placeAnswerSources": { # The sources that were used to generate the place answer. This includes review snippets and photos that were used to generate the answer, as well as URIs to flag content. # The sources that were used to generate the place answer. This includes review snippets and photos that were used to generate the answer, as well as URIs to flag content. "reviewSnippets": [ # Snippets of reviews that were used to generate the answer. @@ -2377,6 +2397,11 @@Method Details
], }, "placeId": "A String", # This Place's resource name, in `places/{place_id}` format. This can be used to look up the place in the Google Maps API. + "route": { # Route information from Google Maps. # Output only. Route information. + "distanceMeters": 42, # The total distance of the route, in meters. + "duration": "A String", # The total duration of the route. + "encodedPolyline": "A String", # An encoded polyline of the route. See https://developers.google.com/maps/documentation/utilities/polylinealgorithm + }, "text": "A String", # The text of the place answer. "title": "A String", # The title of the place. "uri": "A String", # The URI of the place. @@ -2402,13 +2427,16 @@Method Details
}, ], "groundingSupports": [ # Optional. A list of grounding supports that connect the generated content to the grounding chunks. This field is populated when the grounding source is Google Search or Vertex AI Search. - { # A collection of supporting references for a segment of the model's response. + { # A collection of supporting references for a segment or part of the model's response. "confidenceScores": [ # The confidence scores for the support references. This list is parallel to the `grounding_chunk_indices` list. A score is a value between 0.0 and 1.0, with a higher score indicating a higher confidence that the reference supports the claim. For Gemini 2.0 and before, this list has the same size as `grounding_chunk_indices`. For Gemini 2.5 and later, this list is empty and should be ignored. 3.14, ], "groundingChunkIndices": [ # A list of indices into the `grounding_chunks` field of the `GroundingMetadata` message. These indices specify which grounding chunks support the claim made in the content segment. For example, if this field has the values `[1, 3]`, it means that `grounding_chunks[1]` and `grounding_chunks[3]` are the sources for the claim in the content segment. 42, ], + "renderedParts": [ # Indices into the `rendered_parts` field of the `GroundingMetadata` message. These indices specify which rendered parts are associated with this support message. + 42, + ], "segment": { # A segment of the content. # The content segment that this support message applies to. "endIndex": 42, # Output only. The end index of the segment in the `Part`, measured in bytes. This marks the end of the segment and is exclusive, meaning the segment includes content up to, but not including, the byte at this index. "partIndex": 42, # Output only. The index of the `Part` object that this segment belongs to. This is useful for associating the segment with a specific part of the content. @@ -2417,6 +2445,9 @@Method Details
}, }, ], + "imageSearchQueries": [ # Optional. The image search queries that were used to generate the content. This field is populated only when the grounding source is Google Search with the Image Search search_type enabled. + "A String", + ], "retrievalMetadata": { # Metadata related to the retrieval grounding source. This is part of the `GroundingMetadata` returned when grounding is enabled. # Optional. Output only. Metadata related to the retrieval grounding source. "googleSearchDynamicRetrievalScore": 3.14, # Optional. A score indicating how likely it is that a Google Search query could help answer the prompt. The score is in the range of `[0, 1]`. A score of 1 means the model is confident that a search will be helpful, and 0 means it is not. This score is populated only when Google Search grounding and dynamic retrieval are enabled. The score is used to determine whether to trigger a search. }, @@ -4111,11 +4142,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4124,11 +4155,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4141,8 +4172,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4196,6 +4227,7 @@Method Details
}, "imageSize": "A String", # Optional. Specifies the size of generated images. Supported values are `1K`, `2K`, `4K`. If not specified, the model will use default value `1K`. "personGeneration": "A String", # Optional. Controls whether the model can generate people. + "prominentPeople": "A String", # Optional. Controls whether prominent people (celebrities) generation is allowed. If used with personGeneration, personGeneration enum would take precedence. For instance, if ALLOW_NONE is set, all person generation would be blocked. If this field is unspecified, the default behavior is to allow prominent people. }, "logprobs": 42, # Optional. The number of top log probabilities to return for each token. This can be used to see which other tokens were considered likely candidates for a given position. A higher value will return more options, but it will also increase the size of the response. "maxOutputTokens": 42, # Optional. The maximum number of tokens to generate in the response. A token is approximately four characters. The default value varies by model. This parameter can be used to control the length of the generated text and prevent overly long responses. @@ -4216,7 +4248,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -4312,11 +4344,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4325,11 +4357,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4342,8 +4374,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4385,11 +4417,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -4401,7 +4433,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next 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. { # 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). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -4428,7 +4460,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -4468,7 +4500,7 @@Method Details
"defs": { # Optional. `defs` provides a map of schema definitions that can be reused by `ref` elsewhere in the schema. Only allowed at root level of the schema. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, - "description": "A String", # Optional. Description of the schema. + "description": "A String", # Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. "enum": [ # Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` "A String", ], @@ -4509,6 +4541,12 @@Method Details
"excludeDomains": [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: ["amazon.com", "facebook.com"]. "A String", ], + "searchTypes": { # Different types of search that can be enabled on the GoogleSearch tool. # Optional. The set of search types to enable. If not set, web search is enabled by default. + "imageSearch": { # Image search for grounding and related configurations. # Optional. Setting this field enables image search. Image bytes are returned. + }, + "webSearch": { # Standard web search for grounding and related configurations. Only text results are returned. # Optional. Setting this field enables web search. Only text results are returned. + }, + }, }, "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. Specialized retrieval tool that is powered by Google Search. "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source. @@ -4642,11 +4680,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4655,11 +4693,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4672,8 +4710,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4719,6 +4757,12 @@Method Details
"googleMapsWidgetContextToken": "A String", # Optional. Output only. A token that can be used to render a Google Maps widget with the contextual data. This field is populated only when the grounding source is Google Maps. "groundingChunks": [ # A list of supporting references retrieved from the grounding source. This field is populated when the grounding source is Google Search, Vertex AI Search, or Google Maps. { # A piece of evidence that supports a claim made by the model. This is used to show a citation for a claim made by the model. When grounding is enabled, the model returns a `GroundingChunk` that contains a reference to the source of the information. + "image": { # An `Image` chunk is a piece of evidence that comes from an image search result. It contains the URI of the image search result and the URI of the image. This is used to provide the user with a link to the source of the information. # A grounding chunk from an image search result. See the `Image` message for details. + "domain": "A String", # The domain of the image search result page. + "imageUri": "A String", # The URI of the image. + "sourceUri": "A String", # The URI of the image search result page. + "title": "A String", # The title of the image search result page. + }, "maps": { # A `Maps` chunk is a piece of evidence that comes from Google Maps, containing information about places or routes. This is used to provide the user with rich, location-based information. # A grounding chunk from Google Maps. See the `Maps` message for details. "placeAnswerSources": { # The sources that were used to generate the place answer. This includes review snippets and photos that were used to generate the answer, as well as URIs to flag content. # The sources that were used to generate the place answer. This includes review snippets and photos that were used to generate the answer, as well as URIs to flag content. "reviewSnippets": [ # Snippets of reviews that were used to generate the answer. @@ -4730,6 +4774,11 @@Method Details
], }, "placeId": "A String", # This Place's resource name, in `places/{place_id}` format. This can be used to look up the place in the Google Maps API. + "route": { # Route information from Google Maps. # Output only. Route information. + "distanceMeters": 42, # The total distance of the route, in meters. + "duration": "A String", # The total duration of the route. + "encodedPolyline": "A String", # An encoded polyline of the route. See https://developers.google.com/maps/documentation/utilities/polylinealgorithm + }, "text": "A String", # The text of the place answer. "title": "A String", # The title of the place. "uri": "A String", # The URI of the place. @@ -4755,13 +4804,16 @@Method Details
}, ], "groundingSupports": [ # Optional. A list of grounding supports that connect the generated content to the grounding chunks. This field is populated when the grounding source is Google Search or Vertex AI Search. - { # A collection of supporting references for a segment of the model's response. + { # A collection of supporting references for a segment or part of the model's response. "confidenceScores": [ # The confidence scores for the support references. This list is parallel to the `grounding_chunk_indices` list. A score is a value between 0.0 and 1.0, with a higher score indicating a higher confidence that the reference supports the claim. For Gemini 2.0 and before, this list has the same size as `grounding_chunk_indices`. For Gemini 2.5 and later, this list is empty and should be ignored. 3.14, ], "groundingChunkIndices": [ # A list of indices into the `grounding_chunks` field of the `GroundingMetadata` message. These indices specify which grounding chunks support the claim made in the content segment. For example, if this field has the values `[1, 3]`, it means that `grounding_chunks[1]` and `grounding_chunks[3]` are the sources for the claim in the content segment. 42, ], + "renderedParts": [ # Indices into the `rendered_parts` field of the `GroundingMetadata` message. These indices specify which rendered parts are associated with this support message. + 42, + ], "segment": { # A segment of the content. # The content segment that this support message applies to. "endIndex": 42, # Output only. The end index of the segment in the `Part`, measured in bytes. This marks the end of the segment and is exclusive, meaning the segment includes content up to, but not including, the byte at this index. "partIndex": 42, # Output only. The index of the `Part` object that this segment belongs to. This is useful for associating the segment with a specific part of the content. @@ -4770,6 +4822,9 @@Method Details
}, }, ], + "imageSearchQueries": [ # Optional. The image search queries that were used to generate the content. This field is populated only when the grounding source is Google Search with the Image Search search_type enabled. + "A String", + ], "retrievalMetadata": { # Metadata related to the retrieval grounding source. This is part of the `GroundingMetadata` returned when grounding is enabled. # Optional. Output only. Metadata related to the retrieval grounding source. "googleSearchDynamicRetrievalScore": 3.14, # Optional. A score indicating how likely it is that a Google Search query could help answer the prompt. The score is in the range of `[0, 1]`. A score of 1 means the model is confident that a search will be helpful, and 0 means it is not. This score is populated only when Google Search grounding and dynamic retrieval are enabled. The score is used to determine whether to trigger a search. }, diff --git a/docs/dyn/aiplatform_v1.projects.locations.endpoints.openapi.html b/docs/dyn/aiplatform_v1.projects.locations.endpoints.openapi.html index e139657d2a..9749856017 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.endpoints.openapi.html +++ b/docs/dyn/aiplatform_v1.projects.locations.endpoints.openapi.html @@ -83,6 +83,9 @@Instance Methods
embeddings(endpoint, body=None, deployedModelId=None, x__xgafv=None)Forwards arbitrary HTTP requests for both streaming and non-streaming cases. To use this method, invoke_route_prefix must be set to allow the paths that will be specified in the request.
++
+responses(endpoint, body=None, deployedModelId=None, x__xgafv=None)Forwards arbitrary HTTP requests for both streaming and non-streaming cases. To use this method, invoke_route_prefix must be set to allow the paths that will be specified in the request.
Method Details
+close()@@ -167,4 +170,43 @@Method Details
}++responses(endpoint, body=None, deployedModelId=None, x__xgafv=None)+Forwards arbitrary HTTP requests for both streaming and non-streaming cases. To use this method, invoke_route_prefix must be set to allow the paths that will be specified in the request. + +Args: + endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required) + body: object, The request body. + The object takes the form of: + +{ # Message that represents an arbitrary HTTP body. It should only be used for payload formats that can't be represented as JSON, such as raw binary or an HTML page. This message can be used both in streaming and non-streaming API methods in the request as well as the response. It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body. Example: message GetResourceRequest { // A unique request id. string request_id = 1; // The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2; } service ResourceService { rpc GetResource(GetResourceRequest) returns (google.api.HttpBody); rpc UpdateResource(google.api.HttpBody) returns (google.protobuf.Empty); } Example with streaming methods: service CaldavService { rpc GetCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); rpc UpdateCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); } Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged. + "contentType": "A String", # The HTTP Content-Type header value specifying the content type of the body. + "data": "A String", # The HTTP request/response body as raw binary. + "extensions": [ # Application specific response metadata. Must be set in the first response for streaming APIs. + { + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + ], +} + + deployedModelId: string, ID of the DeployedModel that serves the invoke request. + x__xgafv: string, V1 error format. + Allowed values + 1 - v1 error format + 2 - v2 error format + +Returns: + An object of the form: + + { # Message that represents an arbitrary HTTP body. It should only be used for payload formats that can't be represented as JSON, such as raw binary or an HTML page. This message can be used both in streaming and non-streaming API methods in the request as well as the response. It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body. Example: message GetResourceRequest { // A unique request id. string request_id = 1; // The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2; } service ResourceService { rpc GetResource(GetResourceRequest) returns (google.api.HttpBody); rpc UpdateResource(google.api.HttpBody) returns (google.protobuf.Empty); } Example with streaming methods: service CaldavService { rpc GetCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); rpc UpdateCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); } Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged. + "contentType": "A String", # The HTTP Content-Type header value specifying the content type of the body. + "data": "A String", # The HTTP request/response body as raw binary. + "extensions": [ # Application specific response metadata. Must be set in the first response for streaming APIs. + { + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + ], +}+