Tool: generate_content
Generates content (text, image, etc.) based on a balanced prompt and given modality-specific configurations. Use this for Gemini model inference.
The following sample demonstrate how to use curl
to invoke the generate_content
MCP tool.
| Curl Request |
|---|
curl --location 'https://aiplatform.googleapis.com/mcp/generate' \ --header 'content-type: application/json' \ --header 'accept: application/json, text/event-stream' \ --data '{ "method": "tools/call", "params": { "name": "generate_content", "arguments": { // provide these details according to the tool' s MCP specification } } , "jsonrpc" : "2.0" , "id" : 1 } ' |
Input Schema
Request message for [PredictionService.GenerateContent].
GenerateContentRequest
| JSON representation |
|---|
{ "model" : string , "contents" : [ { object ( |
model
string
Required. The fully qualified name of the publisher model or tuned model endpoint to use.
Publisher model format: projects/{project}/locations/{location}/publishers/*/models/*
Tuned model endpoint format: projects/{project}/locations/{location}/endpoints/{endpoint}
contents[]
object (
Content
)
Required. The content of the current conversation with the model.
For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request.
cachedContent
string
Optional. The name of the cached content used as context to serve the prediction. Note: only used in explicit caching, where users can have control over caching (e.g. what content to cache) and enjoy guaranteed cost savings. Format: projects/{project}/locations/{location}/cachedContents/{cachedContent}
tools[]
object (
Tool
)
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.
toolConfig
object (
ToolConfig
)
Optional. Tool config. This config is shared for all tools provided in the request.
labels
map (key: string, value: string)
Optional. The labels with user-defined metadata for the request. It is used for billing and reporting only.
Label keys and values can be no longer than 63 characters (Unicode codepoints) and can only contain lowercase letters, numeric characters, underscores, and dashes. International characters are allowed. Label values are optional. Label keys must start with a letter.
An object containing a list of "key": value
pairs. Example: { "name": "wrench", "mass": "1.3kg", "count": "3" }
.
safetySettings[]
object (
SafetySetting
)
Optional. Per request settings for blocking unsafe content. Enforced on GenerateContentResponse.candidates.
modelArmorConfig
object (
ModelArmorConfig
)
Optional. Settings for prompt and response sanitization using the Model Armor service. If supplied, safety_settings must not be supplied.
generationConfig
object (
GenerationConfig
)
Optional. Generation config.
Union field _system_instruction
.
_system_instruction
can be only one of the following:
systemInstruction
object (
Content
)
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.
Content
| JSON representation |
|---|
{
"role"
:
string
,
"parts"
:
[
{
object (
|
| Fields | |
|---|---|
role
|
Optional. The producer of the content. Must be either 'user' or 'model'. If not set, the service will default to 'user'. |
parts[]
|
Required. A list of A |
Part
| JSON representation |
|---|
{ "thought" : boolean , "thoughtSignature" : string , "mediaResolution" : { object ( |
thought
boolean
Optional. Indicates whether the part
represents the model's thought process or reasoning.
thoughtSignature
string ( bytes
format)
Optional. An opaque signature for the thought so it can be reused in subsequent requests.
A base64-encoded string.
mediaResolution
object (
MediaResolution
)
per part media resolution. Media resolution for the input media.
Union field data
.
data
can be only one of the following:
text
string
Optional. The text content of the part. When sent from the VSCode Gemini Code Assist extension, references to @mentioned items will be converted to markdown boldface text. For example @my-repo
will be converted to and sent as **my-repo**
by the IDE agent.
inlineData
object (
Blob
)
Optional. The inline data content of the part. This can be used to include images, audio, or video in a request.
fileData
object (
FileData
)
Optional. The URI-based data of the part. This can be used to include files from Google Cloud Storage.
functionCall
object (
FunctionCall
)
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.
functionResponse
object (
FunctionResponse
)
Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
executableCode
object (
ExecutableCode
)
Optional. Code generated by the model that is intended to be executed.
codeExecutionResult
object (
CodeExecutionResult
)
Optional. The result of executing the ExecutableCode
.
Union field metadata
.
metadata
can be only one of the following:
videoMetadata
object (
VideoMetadata
)
Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
Blob
| JSON representation |
|---|
{ "mimeType" : string , "data" : string , "displayName" : string } |
| Fields | |
|---|---|
mimeType
|
Required. The IANA standard MIME type of the source data. |
data
|
Required. The raw bytes of the data. A base64-encoded string. |
displayName
|
Optional. The display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in |
FileData
| JSON representation |
|---|
{ "mimeType" : string , "fileUri" : string , "displayName" : string } |
| Fields | |
|---|---|
mimeType
|
Required. The IANA standard MIME type of the source data. |
fileUri
|
Required. The URI of the file in Google Cloud Storage. |
displayName
|
Optional. The display name of the file. Used to provide a label or filename to distinguish files. This field is only returned in |
FunctionCall
| JSON representation |
|---|
{
"id"
:
string
,
"name"
:
string
,
"args"
:
{
object
}
,
"partialArgs"
:
[
{
object (
|
| Fields | |
|---|---|
id
|
Optional. The unique id of the function call. If populated, the client to execute the |
name
|
Optional. The name of the function to call. Matches |
args
|
Optional. The function parameters and values in JSON object format. See |
partialArgs[]
|
Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. |
willContinue
|
Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. |
Struct
| JSON representation |
|---|
{ "fields" : { string : value , ... } } |
| Fields | |
|---|---|
fields
|
Unordered map of dynamically typed values. An object containing a list of |
FieldsEntry
| JSON representation |
|---|
{ "key" : string , "value" : value } |
| Fields | |
|---|---|
key
|
|
value
|
|
Value
| JSON representation |
|---|
{ // Union field |
kind
. The kind of value. kind
can be only one of the following:nullValue
null
Represents a JSON null
.
numberValue
number
Represents a JSON number. Must not be NaN
, Infinity
or -Infinity
, since those are not supported in JSON. This also cannot represent large Int64 values, since JSON format generally does not support them in its number type.
stringValue
string
Represents a JSON string.
boolValue
boolean
Represents a JSON boolean ( true
or false
literal in JSON).
structValue
object (
Struct
format)
Represents a JSON object.
listValue
array (
ListValue
format)
Represents a JSON array.
ListValue
| JSON representation |
|---|
{ "values" : [ value ] } |
| Fields | |
|---|---|
values[]
|
Repeated field of dynamically typed values. |
PartialArg
| JSON representation |
|---|
{ "jsonPath" : string , "willContinue" : boolean , // Union field |
jsonPath
string
Required. A JSON Path (RFC 9535) to the argument being streamed. https://datatracker.ietf.org/doc/html/rfc9535 . e.g. "$.foo.bar[0].data".
willContinue
boolean
Optional. Whether this is not the last part of the same json_path. If true, another PartialArg message for the current json_path is expected to follow.
delta
. The delta of field value being streamed. delta
can be only one of the following:nullValue
null
Optional. Represents a null value.
numberValue
number
Optional. Represents a double value.
stringValue
string
Optional. Represents a string value.
boolValue
boolean
Optional. Represents a boolean value.
FunctionResponse
| JSON representation |
|---|
{
"id"
:
string
,
"name"
:
string
,
"response"
:
{
object
}
,
"parts"
:
[
{
object (
|
| Fields | |
|---|---|
id
|
Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call |
name
|
Required. The name of the function to call. Matches |
response
|
Required. The function response in JSON object format. Use "output" key to specify function output and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as function output. |
parts[]
|
Optional. Ordered |
FunctionResponsePart
| JSON representation |
|---|
{ // Union field |
data
. The data of the function response part. data
can be only one of the following:inlineData
object (
FunctionResponseBlob
)
Inline media bytes.
fileData
object (
FunctionResponseFileData
)
URI based data.
FunctionResponseBlob
| JSON representation |
|---|
{ "mimeType" : string , "data" : string , "displayName" : string } |
| Fields | |
|---|---|
mimeType
|
Required. The IANA standard MIME type of the source data. |
data
|
Required. Raw bytes. A base64-encoded string. |
displayName
|
Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled. |
FunctionResponseFileData
| JSON representation |
|---|
{ "mimeType" : string , "fileUri" : string , "displayName" : string } |
| Fields | |
|---|---|
mimeType
|
Required. The IANA standard MIME type of the source data. |
fileUri
|
Required. URI. |
displayName
|
Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled. |
ExecutableCode
| JSON representation |
|---|
{
"language"
:
enum (
|
| Fields | |
|---|---|
language
|
Required. Programming language of the |
code
|
Required. The code to be executed. |
CodeExecutionResult
| JSON representation |
|---|
{
"outcome"
:
enum (
|
| Fields | |
|---|---|
outcome
|
Required. Outcome of the code execution. |
output
|
Optional. Contains stdout when code execution is successful, stderr or other description otherwise. |
VideoMetadata
| JSON representation |
|---|
{ "startOffset" : string , "endOffset" : string , "fps" : number } |
| Fields | |
|---|---|
startOffset
|
Optional. The start offset of the video. A duration in seconds with up to nine fractional digits, ending with ' |
endOffset
|
Optional. The end offset of the video. A duration in seconds with up to nine fractional digits, ending with ' |
fps
|
Optional. The frame rate of the video sent to the model. If not specified, the default value is 1.0. The valid range is (0.0, 24.0]. |
Duration
| JSON representation |
|---|
{ "seconds" : string , "nanos" : integer } |
| Fields | |
|---|---|
seconds
|
Signed seconds of the span of time. Must be from -315,576,000,000 to +315,576,000,000 inclusive. Note: these bounds are computed from: 60 sec/min * 60 min/hr * 24 hr/day * 365.25 days/year * 10000 years |
nanos
|
Signed fractions of a second at nanosecond resolution of the span of time. Durations less than one second are represented with a 0 |
MediaResolution
| JSON representation |
|---|
{ // Union field |
Union field value
.
value
can be only one of the following:
level
enum (
Level
)
The tokenization quality used for given media.
Tool
| JSON representation |
|---|
{ "functionDeclarations" : [ { object ( |
| Fields | |
|---|---|
functionDeclarations[]
|
Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating |
retrieval
|
Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation. |
googleSearch
|
Optional. GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google. |
googleSearchRetrieval
|
Optional. Specialized retrieval tool that is powered by Google Search. |
googleMaps
|
Optional. GoogleMaps tool type. Tool to support Google Maps in Model. |
enterpriseWebSearch
|
Optional. Tool to support searching public web data, powered by Vertex AI Search and Sec4 compliance. |
codeExecution
|
Optional. CodeExecution tool type. Enables the model to execute code as part of generation. |
urlContext
|
Optional. Tool to support URL context retrieval. |
computerUse
|
Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. |
FunctionDeclaration
| JSON representation |
|---|
{ "name" : string , "description" : string , "parameters" : { object ( |
| Fields | |
|---|---|
name
|
Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots, colons and dashes, with a maximum length of 128. |
description
|
Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. |
parameters
|
Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 |
parametersJsonSchema
|
Optional. Describes the parameters to the function in JSON Schema format. The schema must describe an object where the properties are the parameters to the function. For example:
This field is mutually exclusive with |
response
|
Optional. Describes the output from this function in JSON Schema format. Reflects the Open API 3.03 Response Object. The Schema defines the type used for the response value of the function. |
responseJsonSchema
|
Optional. Describes the output from this function in JSON Schema format. The value specified by the schema is the response value of the function. This field is mutually exclusive with |
Schema
| JSON representation |
|---|
{ "type" : enum ( |
| Fields | |
|---|---|
type
|
Optional. Data type of the schema field. |
format
|
Optional. The format of the data. For |
title
|
Optional. Title for the schema. |
description
|
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. |
nullable
|
Optional. Indicates if the value of this field can be null. |
default
|
Optional. Default value to use if the field is not specified. |
items
|
Optional. If type is |
minItems
|
Optional. If type is |
maxItems
|
Optional. If type is |
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 |
properties
|
Optional. If type is An object containing a list of |
propertyOrdering[]
|
Optional. Order of properties displayed or used where order matters. This is not a standard field in OpenAPI specification, but can be used to control the order of properties. |
required[]
|
Optional. If type is |
minProperties
|
Optional. If type is |
maxProperties
|
Optional. If type is |
minimum
|
Optional. If type is |
maximum
|
Optional. If type is |
minLength
|
Optional. If type is |
maxLength
|
Optional. If type is |
pattern
|
Optional. If type is |
example
|
Optional. Example of an instance of this schema. |
anyOf[]
|
Optional. The instance must be valid against any (one or more) of the subschemas listed in |
additionalProperties
|
Optional. If |
ref
|
Optional. Allows referencing another schema definition to use in place of this schema. The value must be a valid reference to a schema in For example, the following schema defines a reference to a schema node named "Pet": type: object properties: pet: ref: #/defs/Pet defs: Pet: type: object properties: name: type: string The value of the "pet" property is a reference to the schema node named "Pet". See details in https://json-schema.org/understanding-json-schema/structuring |
defs
|
Optional. An object containing a list of |
PropertiesEntry
| JSON representation |
|---|
{
"key"
:
string
,
"value"
:
{
object (
|
| Fields | |
|---|---|
key
|
|
value
|
|
DefsEntry
| JSON representation |
|---|
{
"key"
:
string
,
"value"
:
{
object (
|
| Fields | |
|---|---|
key
|
|
value
|
|
Retrieval
| JSON representation |
|---|
{ "disableAttribution" : boolean , // Union field |
disableAttribution
(deprecated)
boolean
Optional. Deprecated. This option is no longer supported.
source
. The source of the retrieval. source
can be only one of the following:vertexAiSearch
object (
VertexAISearch
)
Set to use data source powered by Vertex AI Search.
vertexRagStore
object (
VertexRagStore
)
Set to use data source powered by Vertex RAG store. User data is uploaded via the VertexRagDataService.
VertexAISearch
| JSON representation |
|---|
{
"datastore"
:
string
,
"engine"
:
string
,
"maxResults"
:
integer
,
"filter"
:
string
,
"dataStoreSpecs"
:
[
{
object (
|
| Fields | |
|---|---|
datastore
|
Optional. Fully-qualified Vertex AI Search data store resource ID. Format: |
engine
|
Optional. Fully-qualified Vertex AI Search engine resource ID. Format: |
maxResults
|
Optional. Number of search results to return per query. The default value is 10. The maximumm allowed value is 10. |
filter
|
Optional. Filter strings to be passed to the search API. |
dataStoreSpecs[]
|
Specifications that define the specific DataStores to be searched, along with configurations for those data stores. This is only considered for Engines with multiple data stores. It should only be set if engine is used. |
DataStoreSpec
| JSON representation |
|---|
{ "dataStore" : string , "filter" : string } |
| Fields | |
|---|---|
dataStore
|
Full resource name of DataStore, such as Format: |
filter
|
Optional. Filter specification to filter documents in the data store specified by data_store field. For more information on filtering, see Filtering |
VertexRagStore
| JSON representation |
|---|
{ "ragCorpora" : [ string ] , "ragResources" : [ { object ( |
ragCorpora[]
(deprecated)
string
Optional. Deprecated. Please use rag_resources instead.
ragResources[]
object (
RagResource
)
Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support.
ragRetrievalConfig
object (
RagRetrievalConfig
)
Optional. The retrieval config for the Rag query.
storeContext
boolean
Optional. Currently only supported for Gemini Multimodal Live API.
In Gemini Multimodal Live API, if store_context
bool is specified, Gemini will leverage it to automatically memorize the interactions between the client and Gemini, and retrieve context when needed to augment the response generation for users' ongoing and future interactions.
Union field _similarity_top_k
.
_similarity_top_k
can be only one of the following:
similarityTopK
(deprecated)
integer
Optional. Number of top k results to return from the selected corpora.
Union field _vector_distance_threshold
.
_vector_distance_threshold
can be only one of the following:
vectorDistanceThreshold
(deprecated)
number
Optional. Only return results with vector distance smaller than the threshold.
RagResource
| JSON representation |
|---|
{ "ragCorpus" : string , "ragFileIds" : [ string ] } |
| Fields | |
|---|---|
ragCorpus
|
Optional. RagCorpora resource name. Format: |
ragFileIds[]
|
Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field. |
RagRetrievalConfig
| JSON representation |
|---|
{ "topK" : integer , "hybridSearch" : { object ( |
| Fields | |
|---|---|
topK
|
Optional. The number of contexts to retrieve. |
hybridSearch
|
Optional. Config for Hybrid Search. |
filter
|
Optional. Config for filters. |
ranking
|
Optional. Config for ranking and reranking. |
HybridSearch
| JSON representation |
|---|
{ // Union field |
Union field _alpha
.
_alpha
can be only one of the following:
alpha
number
Optional. Alpha value controls the weight between dense and sparse vector search results. The range is [0, 1], while 0 means sparse vector search only and 1 means dense vector search only. The default value is 0.5 which balances sparse and dense vector search equally.
Filter
| JSON representation |
|---|
{ "metadataFilter" : string , // Union field |
metadataFilter
string
Optional. String for metadata filtering.
vector_db_threshold
. Filter contexts retrieved from the vector DB based on either vector distance or vector similarity. vector_db_threshold
can be only one of the following:vectorDistanceThreshold
number
Optional. Only returns contexts with vector distance smaller than the threshold.
vectorSimilarityThreshold
number
Optional. Only returns contexts with vector similarity larger than the threshold.
Ranking
| JSON representation |
|---|
{ // Union field |
ranking_config
. Config options for ranking. Currently only Rank Service is supported. ranking_config
can be only one of the following:rankService
object (
RankService
)
Optional. Config for Rank Service.
llmRanker
object (
LlmRanker
)
Optional. Config for LlmRanker.
RankService
| JSON representation |
|---|
{ // Union field |
Union field _model_name
.
_model_name
can be only one of the following:
modelName
string
Optional. The model name of the rank service. Format: semantic-ranker-512@latest
LlmRanker
| JSON representation |
|---|
{ // Union field |
Union field _model_name
.
_model_name
can be only one of the following:
modelName
string
Optional. The model name used for ranking. See Supported models .
GoogleSearch
| JSON representation |
|---|
{ "excludeDomains" : [ string ] , // Union field |
excludeDomains[]
string
Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: ["amazon.com", "facebook.com"].
Union field _blocking_confidence
.
_blocking_confidence
can be only one of the following:
blockingConfidence
enum (
PhishBlockThreshold
)
Optional. Sites with confidence level chosen & above this value will be blocked from the search results.
GoogleSearchRetrieval
| JSON representation |
|---|
{
"dynamicRetrievalConfig"
:
{
object (
|
| Fields | |
|---|---|
dynamicRetrievalConfig
|
Specifies the dynamic retrieval configuration for the given source. |
DynamicRetrievalConfig
| JSON representation |
|---|
{ "mode" : enum ( |
mode
enum (
Mode
)
The mode of the predictor to be used in dynamic retrieval.
Union field _dynamic_threshold
.
_dynamic_threshold
can be only one of the following:
dynamicThreshold
number
Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used.
GoogleMaps
| JSON representation |
|---|
{ "enableWidget" : boolean } |
| Fields | |
|---|---|
enableWidget
|
Optional. If true, include the widget context token in the response. |
EnterpriseWebSearch
| JSON representation |
|---|
{ "excludeDomains" : [ string ] , // Union field |
excludeDomains[]
string
Optional. List of domains to be excluded from the search results. The default limit is 2000 domains.
Union field _blocking_confidence
.
_blocking_confidence
can be only one of the following:
blockingConfidence
enum (
PhishBlockThreshold
)
Optional. Sites with confidence level chosen & above this value will be blocked from the search results.
ComputerUse
| JSON representation |
|---|
{
"environment"
:
enum (
|
| Fields | |
|---|---|
environment
|
Required. The environment being operated. |
excludedPredefinedFunctions[]
|
Optional. By default, predefined functions are included in the final model call. Some of them can be explicitly excluded from being automatically included. This can serve two purposes: 1. Using a more restricted / different action space. 2. Improving the definitions / instructions of predefined functions. |
ToolConfig
| JSON representation |
|---|
{ "functionCallingConfig" : { object ( |
| Fields | |
|---|---|
functionCallingConfig
|
Optional. Function calling config. |
retrievalConfig
|
Optional. Retrieval config. |
FunctionCallingConfig
| JSON representation |
|---|
{
"mode"
:
enum (
|
| Fields | |
|---|---|
mode
|
Optional. Function calling mode. |
allowedFunctionNames[]
|
Optional. Function names to call. Only set when the Mode is ANY. Function names should match |
streamFunctionCallArguments
|
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 |
RetrievalConfig
| JSON representation |
|---|
{ // Union field |
Union field _lat_lng
.
_lat_lng
can be only one of the following:
latLng
object (
LatLng
)
The location of the user.
Union field _language_code
.
_language_code
can be only one of the following:
languageCode
string
The language code of the user.
LatLng
| JSON representation |
|---|
{ "latitude" : number , "longitude" : number } |
| Fields | |
|---|---|
latitude
|
The latitude in degrees. It must be in the range [-90.0, +90.0]. |
longitude
|
The longitude in degrees. It must be in the range [-180.0, +180.0]. |
LabelsEntry
| JSON representation |
|---|
{ "key" : string , "value" : string } |
| Fields | |
|---|---|
key
|
|
value
|
|
SafetySetting
| JSON representation |
|---|
{ "category" : enum ( |
| Fields | |
|---|---|
category
|
Required. The harm category to be blocked. |
threshold
|
Required. The threshold for blocking content. If the harm probability exceeds this threshold, the content will be blocked. |
method
|
Optional. The method for blocking content. If not specified, the default behavior is to use the probability score. |
ModelArmorConfig
| JSON representation |
|---|
{ "promptTemplateName" : string , "responseTemplateName" : string } |
| Fields | |
|---|---|
promptTemplateName
|
Optional. The resource name of the Model Armor template to use for prompt screening. A Model Armor template is a set of customized filters and thresholds that define how Model Armor screens content. If specified, Model Armor will use this template to check the user's prompt for safety and security risks before it is sent to the model. The name must be in the format |
responseTemplateName
|
Optional. The resource name of the Model Armor template to use for response screening. A Model Armor template is a set of customized filters and thresholds that define how Model Armor screens content. If specified, Model Armor will use this template to check the model's response for safety and security risks before it is returned to the user. The name must be in the format |
GenerationConfig
| JSON representation |
|---|
{ "stopSequences" : [ string ] , "responseMimeType" : string , "responseModalities" : [ enum ( |
stopSequences[]
string
Optional. A list of character sequences that will stop the model from generating further tokens. If a stop sequence is generated, the output will end at that point. This is useful for controlling the length and structure of the output. For example, you can use ["\n", "###"] to stop generation at a new line or a specific marker.
responseMimeType
string
Optional. The IANA standard MIME type of the response. The model will generate output that conforms to this MIME type. Supported values include 'text/plain' (default) and 'application/json'. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined.
responseModalities[]
enum (
Modality
)
Optional. The modalities of the response. The model will generate a response that includes all the specified modalities. For example, if this is set to [TEXT, IMAGE]
, the response will include both text and an image.
thinkingConfig
object (
ThinkingConfig
)
Optional. Configuration for thinking features. An error will be returned if this field is set for models that don't support thinking.
modelConfig
(deprecated)
object (
ModelConfig
)
Optional. Config for model selection.
Union field _temperature
.
_temperature
can be only one of the following:
temperature
number
Optional. Controls the randomness of the output. A higher temperature results in more creative and diverse responses, while a lower temperature makes the output more predictable and focused. The valid range is (0.0, 2.0].
Union field _top_p
.
_top_p
can be only one of the following:
topP
number
Optional. Specifies the nucleus sampling threshold. The model considers only the smallest set of tokens whose cumulative probability is at least top_p
. This helps generate more diverse and less repetitive responses. For example, a top_p
of 0.9 means the model considers tokens until the cumulative probability of the tokens to select from reaches 0.9. It's recommended to adjust either temperature or top_p
, but not both.
Union field _top_k
.
_top_k
can be only one of the following:
topK
number
Optional. Specifies the top-k sampling threshold. The model considers only the top k most probable tokens for the next token. This can be useful for generating more coherent and less random text. For example, a top_k
of 40 means the model will choose the next word from the 40 most likely words.
Union field _candidate_count
.
_candidate_count
can be only one of the following:
candidateCount
integer
Optional. The number of candidate responses to generate.
A higher candidate_count
can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
Union field _max_output_tokens
.
_max_output_tokens
can be only one of the following:
maxOutputTokens
integer
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.
Union field _response_logprobs
.
_response_logprobs
can be only one of the following:
responseLogprobs
boolean
Optional. If set to true, the log probabilities of the output tokens are returned.
Log probabilities are the logarithm of the probability of a token appearing in the output. A higher log probability means the token is more likely to be generated. This can be useful for analyzing the model's confidence in its own output and for debugging.
Union field _logprobs
.
_logprobs
can be only one of the following:
logprobs
integer
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.
Union field _presence_penalty
.
_presence_penalty
can be only one of the following:
presencePenalty
number
Optional. Penalizes tokens that have already appeared in the generated text. A positive value encourages the model to generate more diverse and less repetitive text. Valid values can range from [-2.0, 2.0].
Union field _frequency_penalty
.
_frequency_penalty
can be only one of the following:
frequencyPenalty
number
Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
Union field _seed
.
_seed
can be only one of the following:
seed
integer
Optional. A seed for the random number generator.
By setting a seed, you can make the model's output mostly deterministic. For a given prompt and parameters (like temperature, top_p, etc.), the model will produce the same response every time. However, it's not a guaranteed absolute deterministic behavior. This is different from parameters like temperature
, which control the level
of randomness. seed
ensures that the "random" choices the model makes are the same on every run, making it essential for testing and ensuring reproducible results.
Union field _response_schema
.
_response_schema
can be only one of the following:
responseSchema
object (
Schema
)
Optional. Lets you to specify a schema for the model's response, ensuring that the output conforms to a particular structure. This is useful for generating structured data such as JSON. The schema is a subset of the OpenAPI 3.0 schema object object.
When this field is set, you must also set the response_mime_type
to application/json
.
Union field _response_json_schema
.
_response_json_schema
can be only one of the following:
responseJsonSchema
value (
Value
format)
Optional. When this field is set, response_schema
must be omitted and response_mime_type
must be set to application/json
.
Union field _routing_config
.
_routing_config
can be only one of the following:
routingConfig
object (
RoutingConfig
)
Optional. Routing configuration.
Union field _audio_timestamp
.
_audio_timestamp
can be only one of the following:
audioTimestamp
boolean
Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
Union field _media_resolution
.
_media_resolution
can be only one of the following:
mediaResolution
enum (
MediaResolution
)
Optional. The token resolution at which input media content is sampled. This is used to control the trade-off between the quality of the response and the number of tokens used to represent the media. A higher resolution allows the model to perceive more detail, which can lead to a more nuanced response, but it will also use more tokens. This does not affect the image dimensions sent to the model.
Union field _speech_config
.
_speech_config
can be only one of the following:
speechConfig
object (
SpeechConfig
)
Optional. The speech generation config.
Union field _enable_affective_dialog
.
_enable_affective_dialog
can be only one of the following:
enableAffectiveDialog
boolean
Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
Union field _image_config
.
_image_config
can be only one of the following:
imageConfig
object (
ImageConfig
)
Optional. Config for image generation features.
RoutingConfig
| JSON representation |
|---|
{ // Union field |
routing_config
. The routing mode for the request. routing_config
can be only one of the following:autoMode
object (
AutoRoutingMode
)
In this mode, the model is selected automatically based on the content of the request.
manualMode
object (
ManualRoutingMode
)
In this mode, the model is specified manually.
AutoRoutingMode
| JSON representation |
|---|
{ // Union field |
Union field _model_routing_preference
.
_model_routing_preference
can be only one of the following:
modelRoutingPreference
enum (
ModelRoutingPreference
)
The model routing preference.
ManualRoutingMode
| JSON representation |
|---|
{ // Union field |
Union field _model_name
.
_model_name
can be only one of the following:
modelName
string
The name of the model to use. Only public LLM models are accepted.
SpeechConfig
| JSON representation |
|---|
{ "voiceConfig" : { object ( |
| Fields | |
|---|---|
voiceConfig
|
The configuration for the voice to use. |
languageCode
|
Optional. The language code (ISO 639-1) for the speech synthesis. |
multiSpeakerVoiceConfig
|
The configuration for a multi-speaker text-to-speech request. This field is mutually exclusive with |
VoiceConfig
| JSON representation |
|---|
{ // Union field |
voice_config
. The configuration for the speaker to use. voice_config
can be only one of the following:prebuiltVoiceConfig
object (
PrebuiltVoiceConfig
)
The configuration for a prebuilt voice.
replicatedVoiceConfig
object (
ReplicatedVoiceConfig
)
Optional. The configuration for a replicated voice. This enables users to replicate a voice from an audio sample.
PrebuiltVoiceConfig
| JSON representation |
|---|
{ // Union field |
Union field _voice_name
.
_voice_name
can be only one of the following:
voiceName
string
The name of the prebuilt voice to use.
ReplicatedVoiceConfig
| JSON representation |
|---|
{ "mimeType" : string , "voiceSampleAudio" : string } |
| Fields | |
|---|---|
mimeType
|
Optional. The mimetype of the voice sample. The only currently supported value is |
voiceSampleAudio
|
Optional. The sample of the custom voice. A base64-encoded string. |
MultiSpeakerVoiceConfig
| JSON representation |
|---|
{
"speakerVoiceConfigs"
:
[
{
object (
|
| Fields | |
|---|---|
speakerVoiceConfigs[]
|
Required. A list of configurations for the voices of the speakers. Exactly two speaker voice configurations must be provided. |
SpeakerVoiceConfig
| JSON representation |
|---|
{
"speaker"
:
string
,
"voiceConfig"
:
{
object (
|
| Fields | |
|---|---|
speaker
|
Required. The name of the speaker. This should be the same as the speaker name used in the prompt. |
voiceConfig
|
Required. The configuration for the voice of this speaker. |
ThinkingConfig
| JSON representation |
|---|
{ // Union field |
Union field _include_thoughts
.
_include_thoughts
can be only one of the following:
includeThoughts
boolean
Optional. If true, the model will include its thoughts in the response. "Thoughts" are the intermediate steps the model takes to arrive at the final response. They can provide insights into the model's reasoning process and help with debugging. If this is true, thoughts are returned only when available.
Union field _thinking_budget
.
_thinking_budget
can be only one of the following:
thinkingBudget
integer
Optional. The token budget for the model's thinking process. The model will make a best effort to stay within this budget. This can be used to control the trade-off between response quality and latency.
Union field _thinking_level
.
_thinking_level
can be only one of the following:
thinkingLevel
enum (
ThinkingLevel
)
Optional. The number of thoughts tokens that the model should generate.
ModelConfig
| JSON representation |
|---|
{
"featureSelectionPreference"
:
enum (
|
| Fields | |
|---|---|
featureSelectionPreference
|
Required. Feature selection preference. |
ImageConfig
| JSON representation |
|---|
{ // Union field |
Union field _image_output_options
.
_image_output_options
can be only one of the following:
imageOutputOptions
object (
ImageOutputOptions
)
Optional. The image output format for generated images.
Union field _aspect_ratio
.
_aspect_ratio
can be only one of the following:
aspectRatio
string
Optional. The desired aspect ratio for the generated images. The following aspect ratios are supported:
"1:1" "2:3", "3:2" "3:4", "4:3" "4:5", "5:4" "9:16", "16:9" "21:9"
Union field _person_generation
.
_person_generation
can be only one of the following:
personGeneration
enum (
PersonGeneration
)
Optional. Controls whether the model can generate people.
Union field _image_size
.
_image_size
can be only one of the following:
imageSize
string
Optional. Specifies the size of generated images. Supported values are 1K
, 2K
, 4K
. If not specified, the model will use default value 1K
.
ImageOutputOptions
| JSON representation |
|---|
{ // Union field |
Union field _mime_type
.
_mime_type
can be only one of the following:
mimeType
string
Optional. The image format that the output should be saved as.
Union field _compression_quality
.
_compression_quality
can be only one of the following:
compressionQuality
integer
Optional. The compression quality of the output image.
Output Schema
Response message for [PredictionService.GenerateContent].
GenerateContentResponse
| JSON representation |
|---|
{ "candidates" : [ { object ( |
| Fields | |
|---|---|
candidates[]
|
Output only. Generated candidates. |
modelVersion
|
Output only. The model version used to generate the response. |
createTime
|
Output only. Timestamp when the request is made to the server. Uses RFC 3339, where generated output will always be Z-normalized and use 0, 3, 6 or 9 fractional digits. Offsets other than "Z" are also accepted. Examples: |
responseId
|
Output only. response_id is used to identify each response. It is the encoding of the event_id. |
promptFeedback
|
Output only. Content filter results for a prompt sent in the request. Note: Sent only in the first stream chunk. Only happens when no candidates were generated due to content violations. |
usageMetadata
|
Usage metadata about the response(s). |
Candidate
| JSON representation |
|---|
{ "index" : integer , "content" : { object ( |
index
integer
Output only. The 0-based index of this candidate in the list of generated responses. This is useful for distinguishing between multiple candidates when candidate_count
> 1.
content
object (
Content
)
Output only. The content of the candidate.
avgLogprobs
number
Output only. The average log probability of the tokens in this candidate. This is a length-normalized score that can be used to compare the quality of candidates of different lengths. A higher average log probability suggests a more confident and coherent response.
logprobsResult
object (
LogprobsResult
)
Output only. The detailed log probability information for the tokens in this candidate. This is useful for debugging, understanding model uncertainty, and identifying potential "hallucinations".
finishReason
enum (
FinishReason
)
Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating.
safetyRatings[]
object (
SafetyRating
)
Output only. A list of ratings for the safety of a response candidate.
There is at most one rating per category.
citationMetadata
object (
CitationMetadata
)
Output only. A collection of citations that apply to the generated content.
groundingMetadata
object (
GroundingMetadata
)
Output only. Metadata returned when grounding is enabled. It contains the sources used to ground the generated content.
urlContextMetadata
object (
UrlContextMetadata
)
Output only. Metadata returned when the model uses the url_context
tool to get information from a user-provided URL.
Union field _finish_message
.
_finish_message
can be only one of the following:
finishMessage
string
Output only. Describes the reason the model stopped generating tokens in more detail. This field is returned only when finish_reason
is set.
Content
| JSON representation |
|---|
{
"role"
:
string
,
"parts"
:
[
{
object (
|
| Fields | |
|---|---|
role
|
Optional. The producer of the content. Must be either 'user' or 'model'. If not set, the service will default to 'user'. |
parts[]
|
Required. A list of A |
Part
| JSON representation |
|---|
{ "thought" : boolean , "thoughtSignature" : string , "mediaResolution" : { object ( |
thought
boolean
Optional. Indicates whether the part
represents the model's thought process or reasoning.
thoughtSignature
string ( bytes
format)
Optional. An opaque signature for the thought so it can be reused in subsequent requests.
A base64-encoded string.
mediaResolution
object (
MediaResolution
)
per part media resolution. Media resolution for the input media.
Union field data
.
data
can be only one of the following:
text
string
Optional. The text content of the part. When sent from the VSCode Gemini Code Assist extension, references to @mentioned items will be converted to markdown boldface text. For example @my-repo
will be converted to and sent as **my-repo**
by the IDE agent.
inlineData
object (
Blob
)
Optional. The inline data content of the part. This can be used to include images, audio, or video in a request.
fileData
object (
FileData
)
Optional. The URI-based data of the part. This can be used to include files from Google Cloud Storage.
functionCall
object (
FunctionCall
)
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.
functionResponse
object (
FunctionResponse
)
Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
executableCode
object (
ExecutableCode
)
Optional. Code generated by the model that is intended to be executed.
codeExecutionResult
object (
CodeExecutionResult
)
Optional. The result of executing the ExecutableCode
.
Union field metadata
.
metadata
can be only one of the following:
videoMetadata
object (
VideoMetadata
)
Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
Blob
| JSON representation |
|---|
{ "mimeType" : string , "data" : string , "displayName" : string } |
| Fields | |
|---|---|
mimeType
|
Required. The IANA standard MIME type of the source data. |
data
|
Required. The raw bytes of the data. A base64-encoded string. |
displayName
|
Optional. The display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in |
FileData
| JSON representation |
|---|
{ "mimeType" : string , "fileUri" : string , "displayName" : string } |
| Fields | |
|---|---|
mimeType
|
Required. The IANA standard MIME type of the source data. |
fileUri
|
Required. The URI of the file in Google Cloud Storage. |
displayName
|
Optional. The display name of the file. Used to provide a label or filename to distinguish files. This field is only returned in |
FunctionCall
| JSON representation |
|---|
{
"id"
:
string
,
"name"
:
string
,
"args"
:
{
object
}
,
"partialArgs"
:
[
{
object (
|
| Fields | |
|---|---|
id
|
Optional. The unique id of the function call. If populated, the client to execute the |
name
|
Optional. The name of the function to call. Matches |
args
|
Optional. The function parameters and values in JSON object format. See |
partialArgs[]
|
Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. |
willContinue
|
Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. |
Struct
| JSON representation |
|---|
{ "fields" : { string : value , ... } } |
| Fields | |
|---|---|
fields
|
Unordered map of dynamically typed values. An object containing a list of |
FieldsEntry
| JSON representation |
|---|
{ "key" : string , "value" : value } |
| Fields | |
|---|---|
key
|
|
value
|
|
Value
| JSON representation |
|---|
{ // Union field |
kind
. The kind of value. kind
can be only one of the following:nullValue
null
Represents a JSON null
.
numberValue
number
Represents a JSON number. Must not be NaN
, Infinity
or -Infinity
, since those are not supported in JSON. This also cannot represent large Int64 values, since JSON format generally does not support them in its number type.
stringValue
string
Represents a JSON string.
boolValue
boolean
Represents a JSON boolean ( true
or false
literal in JSON).
structValue
object (
Struct
format)
Represents a JSON object.
listValue
array (
ListValue
format)
Represents a JSON array.
ListValue
| JSON representation |
|---|
{ "values" : [ value ] } |
| Fields | |
|---|---|
values[]
|
Repeated field of dynamically typed values. |
PartialArg
| JSON representation |
|---|
{ "jsonPath" : string , "willContinue" : boolean , // Union field |
jsonPath
string
Required. A JSON Path (RFC 9535) to the argument being streamed. https://datatracker.ietf.org/doc/html/rfc9535 . e.g. "$.foo.bar[0].data".
willContinue
boolean
Optional. Whether this is not the last part of the same json_path. If true, another PartialArg message for the current json_path is expected to follow.
delta
. The delta of field value being streamed. delta
can be only one of the following:nullValue
null
Optional. Represents a null value.
numberValue
number
Optional. Represents a double value.
stringValue
string
Optional. Represents a string value.
boolValue
boolean
Optional. Represents a boolean value.
FunctionResponse
| JSON representation |
|---|
{
"id"
:
string
,
"name"
:
string
,
"response"
:
{
object
}
,
"parts"
:
[
{
object (
|
| Fields | |
|---|---|
id
|
Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call |
name
|
Required. The name of the function to call. Matches |
response
|
Required. The function response in JSON object format. Use "output" key to specify function output and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as function output. |
parts[]
|
Optional. Ordered |
FunctionResponsePart
| JSON representation |
|---|
{ // Union field |
data
. The data of the function response part. data
can be only one of the following:inlineData
object (
FunctionResponseBlob
)
Inline media bytes.
fileData
object (
FunctionResponseFileData
)
URI based data.
FunctionResponseBlob
| JSON representation |
|---|
{ "mimeType" : string , "data" : string , "displayName" : string } |
| Fields | |
|---|---|
mimeType
|
Required. The IANA standard MIME type of the source data. |
data
|
Required. Raw bytes. A base64-encoded string. |
displayName
|
Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled. |
FunctionResponseFileData
| JSON representation |
|---|
{ "mimeType" : string , "fileUri" : string , "displayName" : string } |
| Fields | |
|---|---|
mimeType
|
Required. The IANA standard MIME type of the source data. |
fileUri
|
Required. URI. |
displayName
|
Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled. |
ExecutableCode
| JSON representation |
|---|
{
"language"
:
enum (
|
| Fields | |
|---|---|
language
|
Required. Programming language of the |
code
|
Required. The code to be executed. |
CodeExecutionResult
| JSON representation |
|---|
{
"outcome"
:
enum (
|
| Fields | |
|---|---|
outcome
|
Required. Outcome of the code execution. |
output
|
Optional. Contains stdout when code execution is successful, stderr or other description otherwise. |
VideoMetadata
| JSON representation |
|---|
{ "startOffset" : string , "endOffset" : string , "fps" : number } |
| Fields | |
|---|---|
startOffset
|
Optional. The start offset of the video. A duration in seconds with up to nine fractional digits, ending with ' |
endOffset
|
Optional. The end offset of the video. A duration in seconds with up to nine fractional digits, ending with ' |
fps
|
Optional. The frame rate of the video sent to the model. If not specified, the default value is 1.0. The valid range is (0.0, 24.0]. |
Duration
| JSON representation |
|---|
{ "seconds" : string , "nanos" : integer } |
| Fields | |
|---|---|
seconds
|
Signed seconds of the span of time. Must be from -315,576,000,000 to +315,576,000,000 inclusive. Note: these bounds are computed from: 60 sec/min * 60 min/hr * 24 hr/day * 365.25 days/year * 10000 years |
nanos
|
Signed fractions of a second at nanosecond resolution of the span of time. Durations less than one second are represented with a 0 |
MediaResolution
| JSON representation |
|---|
{ // Union field |
Union field value
.
value
can be only one of the following:
level
enum (
Level
)
The tokenization quality used for given media.
LogprobsResult
| JSON representation |
|---|
{ "topCandidates" : [ { object ( |
| Fields | |
|---|---|
topCandidates[]
|
A list of the top candidate tokens at each decoding step. The length of this list is equal to the total number of decoding steps. |
chosenCandidates[]
|
A list of the chosen candidate tokens at each decoding step. The length of this list is equal to the total number of decoding steps. Note that the chosen candidate might not be in |
TopCandidates
| JSON representation |
|---|
{
"candidates"
:
[
{
object (
|
| Fields | |
|---|---|
candidates[]
|
The list of candidate tokens, sorted by log probability in descending order. |
Candidate
| JSON representation |
|---|
{ // Union field |
Union field _token
.
_token
can be only one of the following:
token
string
The token's string representation.
Union field _token_id
.
_token_id
can be only one of the following:
tokenId
integer
The token's numerical ID. While the token
field provides the string representation of the token, the token_id
is the numerical representation that the model uses internally. This can be useful for developers who want to build custom logic based on the model's vocabulary.
Union field _log_probability
.
_log_probability
can be only one of the following:
logProbability
number
The log probability of this token. A higher value indicates that the model was more confident in this token. The log probability can be used to assess the relative likelihood of different tokens and to identify when the model is uncertain.
SafetyRating
| JSON representation |
|---|
{ "category" : enum ( |
| Fields | |
|---|---|
category
|
Output only. The harm category of this rating. |
probability
|
Output only. The probability of harm for this category. |
probabilityScore
|
Output only. The probability score of harm for this category. |
severity
|
Output only. The severity of harm for this category. |
severityScore
|
Output only. The severity score of harm for this category. |
blocked
|
Output only. Indicates whether the content was blocked because of this rating. |
overwrittenThreshold
|
Output only. The overwritten threshold for the safety category of Gemini 2.0 image out. If minors are detected in the output image, the threshold of each safety category will be overwritten if user sets a lower threshold. |
CitationMetadata
| JSON representation |
|---|
{
"citations"
:
[
{
object (
|
| Fields | |
|---|---|
citations[]
|
Output only. A list of citations for the content. |
Citation
| JSON representation |
|---|
{
"startIndex"
:
integer
,
"endIndex"
:
integer
,
"uri"
:
string
,
"title"
:
string
,
"license"
:
string
,
"publicationDate"
:
{
object (
|
| Fields | |
|---|---|
startIndex
|
Output only. The start index of the citation in the content. |
endIndex
|
Output only. The end index of the citation in the content. |
uri
|
Output only. The URI of the source of the citation. |
title
|
Output only. The title of the source of the citation. |
license
|
Output only. The license of the source of the citation. |
publicationDate
|
Output only. The publication date of the source of the citation. |
Date
| JSON representation |
|---|
{ "year" : integer , "month" : integer , "day" : integer } |
| Fields | |
|---|---|
year
|
Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year. |
month
|
Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day. |
day
|
Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant. |
GroundingMetadata
| JSON representation |
|---|
{ "webSearchQueries" : [ string ] , "imageSearchQueries" : [ string ] , "retrievalQueries" : [ string ] , "groundingChunks" : [ { object ( |
webSearchQueries[]
string
Optional. The web search queries that were used to generate the content. This field is populated only when the grounding source is Google Search.
imageSearchQueries[]
string
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.
retrievalQueries[]
string
Optional. The queries that were executed by the retrieval tools. This field is populated only when the grounding source is a retrieval tool, such as Vertex AI Search.
groundingChunks[]
object (
GroundingChunk
)
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.
groundingSupports[]
object (
GroundingSupport
)
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.
sourceFlaggingUris[]
object (
SourceFlaggingUri
)
Optional. Output only. A list of URIs that can be used to flag a place or review for inappropriate content. This field is populated only when the grounding source is Google Maps.
Union field _search_entry_point
.
_search_entry_point
can be only one of the following:
searchEntryPoint
object (
SearchEntryPoint
)
Optional. A web search entry point that can be used to display search results. This field is populated only when the grounding source is Google Search.
Union field _retrieval_metadata
.
_retrieval_metadata
can be only one of the following:
retrievalMetadata
object (
RetrievalMetadata
)
Optional. Output only. Metadata related to the retrieval grounding source.
Union field _google_maps_widget_context_token
.
_google_maps_widget_context_token
can be only one of the following:
googleMapsWidgetContextToken
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.
SearchEntryPoint
| JSON representation |
|---|
{ "renderedContent" : string , "sdkBlob" : string } |
| Fields | |
|---|---|
renderedContent
|
Optional. An HTML snippet that can be embedded in a web page or an application's webview. This snippet displays a search result, including the title, URL, and a brief description of the search result. |
sdkBlob
|
Optional. A base64-encoded JSON object that contains a list of search queries and their corresponding search URLs. This information can be used to build a custom search UI. A base64-encoded string. |
GroundingChunk
| JSON representation |
|---|
{ // Union field |
chunk_type
. The source of the grounding chunk, which can be from Google Search, Vertex AI Search, or Google Maps. chunk_type
can be only one of the following:web
object (
Web
)
A grounding chunk from a web page, typically from Google Search. See the Web
message for details.
retrievedContext
object (
RetrievedContext
)
A grounding chunk from a data source retrieved by a retrieval tool, such as Vertex AI Search. See the RetrievedContext
message for details
maps
object (
Maps
)
A grounding chunk from Google Maps. See the Maps
message for details.
Web
| JSON representation |
|---|
{ // Union field |
Union field _uri
.
_uri
can be only one of the following:
uri
string
The URI of the web page that contains the evidence.
Union field _title
.
_title
can be only one of the following:
title
string
The title of the web page that contains the evidence.
Union field _domain
.
_domain
can be only one of the following:
domain
string
The domain of the web page that contains the evidence. This can be used to filter out low-quality sources.
RetrievedContext
| JSON representation |
|---|
{ // Union field |
context_details
. Provides tool-specific details about the retrieved context. This allows for different types of retrieval tools to return their own specific metadata. context_details
can be only one of the following:ragChunk
object (
RagChunk
)
Additional context for a Retrieval-Augmented Generation (RAG) retrieval result. This is populated only when the RAG retrieval tool is used.
Union field _uri
.
_uri
can be only one of the following:
uri
string
The URI of the retrieved data source.
Union field _title
.
_title
can be only one of the following:
title
string
The title of the retrieved data source.
Union field _text
.
_text
can be only one of the following:
text
string
The content of the retrieved data source.
Union field _document_name
.
_document_name
can be only one of the following:
documentName
string
Output only. The full resource name of the referenced Vertex AI Search document. This is used to identify the specific document that was retrieved. The format is projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document}
.
RagChunk
| JSON representation |
|---|
{ "text" : string , "fileId" : string , "chunkId" : string , // Union field |
text
string
The content of the chunk.
fileId
string
The ID of the file that the chunk belongs to.
chunkId
string
The ID of the chunk.
Union field _page_span
.
_page_span
can be only one of the following:
pageSpan
object (
PageSpan
)
If populated, represents where the chunk starts and ends in the document.
PageSpan
| JSON representation |
|---|
{ "firstPage" : integer , "lastPage" : integer } |
| Fields | |
|---|---|
firstPage
|
Page where chunk starts in the document. Inclusive. 1-indexed. |
lastPage
|
Page where chunk ends in the document. Inclusive. 1-indexed. |
Maps
| JSON representation |
|---|
{ "placeAnswerSources" : { object ( |
placeAnswerSources
object (
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.
Union field _uri
.
_uri
can be only one of the following:
uri
string
The URI of the place.
Union field _title
.
_title
can be only one of the following:
title
string
The title of the place.
Union field _text
.
_text
can be only one of the following:
text
string
The text of the place answer.
Union field _place_id
.
_place_id
can be only one of the following:
placeId
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.
PlaceAnswerSources
| JSON representation |
|---|
{
"reviewSnippets"
:
[
{
object (
|
| Fields | |
|---|---|
reviewSnippets[]
|
Snippets of reviews that were used to generate the answer. |
ReviewSnippet
| JSON representation |
|---|
{ "reviewId" : string , "googleMapsUri" : string , "title" : string } |
| Fields | |
|---|---|
reviewId
|
The ID of the review that is being referenced. |
googleMapsUri
|
A link to show the review on Google Maps. |
title
|
The title of the review. |
GroundingSupport
| JSON representation |
|---|
{ "groundingChunkIndices" : [ integer ] , "confidenceScores" : [ number ] , "renderedParts" : [ integer ] , // Union field |
groundingChunkIndices[]
integer
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.
confidenceScores[]
number
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.
renderedParts[]
integer
Indices into the rendered_parts
field of the GroundingMetadata
message. These indices specify which rendered parts are associated with this support message.
Union field _segment
.
_segment
can be only one of the following:
segment
object (
Segment
)
The content segment that this support message applies to.
Segment
| JSON representation |
|---|
{ "partIndex" : integer , "startIndex" : integer , "endIndex" : integer , "text" : string } |
| Fields | |
|---|---|
partIndex
|
Output only. The index of the |
startIndex
|
Output only. The start index of the segment in the |
endIndex
|
Output only. The end index of the segment in the |
text
|
Output only. The text of the segment. |
RetrievalMetadata
| JSON representation |
|---|
{ "googleSearchDynamicRetrievalScore" : number } |
| Fields | |
|---|---|
googleSearchDynamicRetrievalScore
|
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 |
SourceFlaggingUri
| JSON representation |
|---|
{ "sourceId" : string , "flagContentUri" : string } |
| Fields | |
|---|---|
sourceId
|
The ID of the place or review. |
flagContentUri
|
The URI that can be used to flag the content. |
UrlContextMetadata
| JSON representation |
|---|
{
"urlMetadata"
:
[
{
object (
|
| Fields | |
|---|---|
urlMetadata[]
|
Output only. A list of URL metadata, with one entry for each URL retrieved by the tool. |
UrlMetadata
| JSON representation |
|---|
{
"retrievedUrl"
:
string
,
"urlRetrievalStatus"
:
enum (
|
| Fields | |
|---|---|
retrievedUrl
|
The URL retrieved by the tool. |
urlRetrievalStatus
|
The status of the URL retrieval. |
Timestamp
| JSON representation |
|---|
{ "seconds" : string , "nanos" : integer } |
| Fields | |
|---|---|
seconds
|
Represents seconds of UTC time since Unix epoch 1970-01-01T00:00:00Z. Must be between -62135596800 and 253402300799 inclusive (which corresponds to 0001-01-01T00:00:00Z to 9999-12-31T23:59:59Z). |
nanos
|
Non-negative fractions of a second at nanosecond resolution. This field is the nanosecond portion of the duration, not an alternative to seconds. Negative second values with fractions must still have non-negative nanos values that count forward in time. Must be between 0 and 999,999,999 inclusive. |
PromptFeedback
| JSON representation |
|---|
{ "blockReason" : enum ( |
| Fields | |
|---|---|
blockReason
|
Output only. The reason why the prompt was blocked. |
safetyRatings[]
|
Output only. A list of safety ratings for the prompt. There is one rating per category. |
blockReasonMessage
|
Output only. A readable message that explains the reason why the prompt was blocked. |
UsageMetadata
| JSON representation |
|---|
{ "promptTokenCount" : integer , "candidatesTokenCount" : integer , "totalTokenCount" : integer , "toolUsePromptTokenCount" : integer , "thoughtsTokenCount" : integer , "cachedContentTokenCount" : integer , "promptTokensDetails" : [ { object ( |
| Fields | |
|---|---|
promptTokenCount
|
The total number of tokens in the prompt. This includes any text, images, or other media provided in the request. When |
candidatesTokenCount
|
The total number of tokens in the generated candidates. |
totalTokenCount
|
The total number of tokens for the entire request. This is the sum of |
toolUsePromptTokenCount
|
Output only. The number of tokens in the results from tool executions, which are provided back to the model as input, if applicable. |
thoughtsTokenCount
|
Output only. The number of tokens that were part of the model's generated "thoughts" output, if applicable. |
cachedContentTokenCount
|
Output only. The number of tokens in the cached content that was used for this request. |
promptTokensDetails[]
|
Output only. A detailed breakdown of the token count for each modality in the prompt. |
cacheTokensDetails[]
|
Output only. A detailed breakdown of the token count for each modality in the cached content. |
candidatesTokensDetails[]
|
Output only. A detailed breakdown of the token count for each modality in the generated candidates. |
toolUsePromptTokensDetails[]
|
Output only. A detailed breakdown by modality of the token counts from the results of tool executions, which are provided back to the model as input. |
trafficType
|
Output only. The traffic type for this request. |
ModalityTokenCount
| JSON representation |
|---|
{
"modality"
:
enum (
|
| Fields | |
|---|---|
modality
|
The modality that this token count applies to. |
tokenCount
|
The number of tokens counted for this modality. |
Tool Annotations
Destructive Hint: ❌ | Idempotent Hint: ✅ | Read Only Hint: ✅ | Open World Hint: ✅

