Namespace Google.GenAI.Types

Classes

ActivityEnd: Marks the end of user activity. This can only be sent if automatic (i.e. server-side) activity detection is disabled.

ActivityHandlingConverter

ActivityStart: Marks the start of user activity. This can only be sent if automatic (i.e. server-side) activity detection is disabled.

AdapterSizeConverter

AggregationMetricConverter

AggregationOutput: The aggregation result for the entire dataset and all metrics. This data type is not supported in Gemini API.

AggregationResult: The aggregation result for a single metric. This data type is not supported in Gemini API.

ApiAuth: The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead. This data type is not supported in Gemini API.

ApiAuthApiKeyConfig: The API secret. This data type is not supported in Gemini API.

ApiKeyConfig: Config for authentication with API key. This data type is not supported in Gemini API.

ApiSpecConverter

AudioTranscriptionConfig: The audio transcription configuration in Setup.

AuthConfig: The authentication config to access the API.

AuthConfigGoogleServiceAccountConfig: Config for Google Service Account Authentication. This data type is not supported in Gemini API.

AuthConfigHttpBasicAuthConfig: Config for HTTP Basic Authentication. This data type is not supported in Gemini API.

AuthConfigOauthConfig: Config for user oauth. This data type is not supported in Gemini API.

AuthConfigOidcConfig: Config for user OIDC auth. This data type is not supported in Gemini API.

AuthToken: Config for auth_tokens.create parameters.

AuthTypeConverter

AutomaticActivityDetection: Configures automatic detection of activity.

AutoraterConfig: Autorater config used for evaluation.

AvatarConfig: Configures the avatar to be used in the session.

BatchJob: Config for batches.create return value.

BatchJobDestination: Config for dest parameter.

BatchJobOutputInfo: Represents the output_info field in batch jobs.

BatchJobSource: Config for src parameter.

BehaviorConverter

BigQuerySource: The BigQuery location for the input content. This data type is not supported in Gemini API.

BleuMetricValue: Bleu metric value for an instance. This data type is not supported in Gemini API.

Blob: A content blob. A Blob contains data of a specific media type. It is used to represent images, audio, and video.

BlockedReasonConverter

CachedContent: A resource used in LLM queries for users to explicitly specify what to cache.

CachedContentUsageMetadata: Metadata on the usage of the cached content.

CancelBatchJobConfig: Optional parameters.

CancelTuningJobConfig: Optional parameters for tunings.cancel method.

CancelTuningJobResponse: Empty response for tunings.cancel method.

Candidate: A response candidate generated from the model.

Checkpoint: Describes the machine learning model version checkpoint.

Citation: A citation for a piece of generatedcontent. This data type is not supported in Gemini API.

CitationMetadata: Citation information when the model quotes another source.

ClientOptions: Client options to be used in the client instantiation.

CodeExecutionResult: Result of executing the ExecutableCode. Generated only when the CodeExecution tool is used.

CompletionStats: Success and error statistics of processing multiple entities (for example, DataItems or structured data rows) in batch. This data type is not supported in Gemini API.

CompositeReinforcementTuningRewardConfig: Composite reinforcement tuning reward config.

CompositeReinforcementTuningRewardConfigWeightedRewardConfig: Composite reinforcement tuning reward config weighted reward config.

ComputeTokensConfig: Optional parameters for computing tokens.

ComputeTokensResponse: Response for computing tokens.

ComputerUse: Tool to support computer use.

Content: Contains the multi-part content of a message.

ContentEmbedding: The embedding generated from an input content.

ContentEmbeddingStatistics: Statistics of the input text associated with the result of content embedding.

ContentReferenceImage: A content reference image. A content reference image represents a subject to reference (ex. person, product, animal) provided by the user. It can optionally be provided in addition to a style reference image (ex. background, style reference).

ContextWindowCompressionConfig: Enables context window compression -- mechanism managing model context window so it does not exceed given length.

ControlReferenceConfig: Configuration for a Control reference image.

ControlReferenceImage: A control reference image. The image of the control reference image is either a control image provided by the user, or a regular image which the backend will use to generate a control image of. In the case of the latter, the enable_control_image_computation field in the config should be set to True. A control image is an image that represents a sketch image of areas for the model to fill in based on the prompt.

ControlReferenceTypeConverter

CountTokensConfig: Config for the count_tokens method.

CountTokensResponse: Response for counting tokens.

CreateAuthTokenConfig: Optional parameters.

CreateBatchJobConfig: Config for optional parameters.

CreateCachedContentConfig: Optional configuration for cached content creation.

CreateEmbeddingsBatchJobConfig: Config for optional parameters.

CreateFileConfig: Used to override the default configuration.

CreateFileResponse: Response for the create file method.

CreateTuningJobConfig: Fine-tuning job creation request - optional fields.

CustomCodeExecutionResult: Result for custom code execution metric. This data type is not supported in Gemini API.

CustomOutput: Spec for custom output. This data type is not supported in Gemini API.

CustomizedAvatar: Configures the customized avatar to be used in the session.

DatasetDistribution: Distribution computed over a tuning dataset. This data type is not supported in Gemini API.

DatasetDistributionDistributionBucket: Dataset bucket used to create a histogram for the distribution given a population of values. This data type is not supported in Gemini API.

DatasetStats: Statistics computed over a tuning dataset. This data type is not supported in Gemini API.

DeleteBatchJobConfig: Optional parameters for models.get method.

DeleteCachedContentConfig: Optional parameters for caches.delete method.

DeleteCachedContentResponse: Empty response for caches.delete method.

DeleteFileConfig: Used to override the default configuration.

DeleteFileResponse: Response for the delete file method.

DeleteModelConfig: Configuration for deleting a tuned model.

DeleteModelResponse

DeleteResourceJob: The return value of delete operation.

DistillationDataStats: Statistics for distillation prompt dataset. These statistics do not include the responses sampled from the teacher model. This data type is not supported in Gemini API.

DistillationHyperParameters: Distillation hyperparameters for tuning.

DistillationSamplingSpec: Distillation sampling spec for tuning.

DistillationSpec: Distillation tuning spec for tuning.

DownloadFileConfig: Used to override the default configuration.

DynamicRetrievalConfig: Describes the options to customize dynamic retrieval.

DynamicRetrievalConfigModeConverter

EditImageConfig: Configuration for editing an image.

EditImageResponse: Response for the request to edit an image.

EditModeConverter

EmbedContentBatch: Parameters for the embed_content method.

EmbedContentConfig: Optional parameters for the embed_content method.

EmbedContentMetadata: Request-level metadata for the Gemini Enterprise Agent Platform Embed Content API.

EmbedContentResponse: Response for the embed_content method.

EmbeddingApiTypeConverter

EmbeddingsBatchJobSource

EncryptionSpec: Represents a customer-managed encryption key specification that can be applied to a Vertex AI resource. This data type is not supported in Gemini API.

EndSensitivityConverter

Endpoint: An endpoint where you deploy models.

EnterpriseWebSearch: Tool to search public web data, powered by Vertex AI Search and Sec4 compliance. This data type is not supported in Gemini API.

EntityLabel: An entity representing the segmented area.

EnvironmentConverter

EvaluateDatasetResponse: The results from an evaluation run performed by the EvaluationService. This data type is not supported in Gemini API.

EvaluateDatasetRun: Evaluate Dataset Run Result for Tuning Job. This data type is not supported in Gemini API.

EvaluationDataset: The dataset used for evaluation. This data type is not supported in Gemini API.

ExactMatchMetricValue: Exact match metric value for an instance. This data type is not supported in Gemini API.

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.

ExternalApi: Retrieve from data source powered by external API for grounding. The external API is not owned by Google, but need to follow the pre-defined API spec. This data type is not supported in Gemini API.

ExternalApiElasticSearchParams: The search parameters to use for the ELASTIC_SEARCH spec. This data type is not supported in Gemini API.

ExternalApiSimpleSearchParams: The search parameters to use for SIMPLE_SEARCH spec. This data type is not supported in Gemini API.

FeatureSelectionPreferenceConverter

FetchPredictOperationConfig

File: A file uploaded to the API.

FileData: URI-based data. A FileData message contains a URI pointing to data of a specific media type. It is used to represent images, audio, and video stored in Google Cloud Storage.

FileSearch: The FileSearch tool that retrieves knowledge from Semantic Retrieval corpora. Files are imported to Semantic Retrieval corpora using the ImportFile API. This data type is not supported in Vertex AI.

FileSourceConverter

FileStateConverter

FileStatus: Status of a File that uses a common error model.

FinishReasonConverter

FullFineTuningSpec: Tuning Spec for Full Fine Tuning. This data type is not supported in Gemini API.

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.

FunctionCallingConfig: Function calling config.

FunctionCallingConfigModeConverter

FunctionDeclaration: Structured representation of a function declaration as defined by the OpenAPI 3.0 specification (https://spec.openapis.org/oas/v3.0.3). Included in this declaration are the function name, description, parameters and response type. This FunctionDeclaration is a representation of a block of code that can be used as a Tool by the model and executed by the client.

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.

FunctionResponseBlob: Raw media bytes for function response. Text should not be sent as raw bytes, use the 'text' field.

FunctionResponseFileData: URI based data for function response. This data type is not supported in Gemini API.

FunctionResponsePart: 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.

FunctionResponseSchedulingConverter

GcsSource: The Google Cloud Storage location for the input content. This data type is not supported in Gemini API.

GeminiPreferenceExample: Input example for preference optimization. This data type is not supported in Gemini API.

GeminiPreferenceExampleCompletion: Completion and its preference score. This data type is not supported in Gemini API.

GenerateContentConfig: Optional model configuration parameters. For more information, see Content generation parameters (https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/content-generation-parameters).

GenerateContentResponse: Response message for PredictionService.GenerateContent.

GenerateContentResponsePromptFeedback: Content filter results for a prompt sent in the request. Note: This is sent only in the first stream chunk and only if no candidates were generated due to content violations.

GenerateContentResponseUsageMetadata: Usage metadata about the content generation request and response. This message provides a detailed breakdown of token usage and other relevant metrics. This data type is not supported in Gemini API.

GenerateImagesConfig: The config for generating an images.

GenerateImagesResponse: The output images response.

GenerateVideosConfig: Configuration for generating videos.

GenerateVideosOperation: A video generation operation.

GenerateVideosResponse: Response with generated videos.

GenerateVideosSource: A set of source input(s) for video generation.

GeneratedImage: An output image.

GeneratedImageMask: A generated image mask.

GeneratedVideo: A generated video.

GenerationConfig: Generation config.

GenerationConfigRoutingConfig: The configuration for routing the request to a specific model. This can be used to control which model is used for the generation, either automatically or by specifying a model name. This data type is not supported in Gemini API.

GenerationConfigRoutingConfigAutoRoutingMode: The configuration for automated routing. When automated routing is specified, the routing will be determined by the pretrained routing model and customer provided model routing preference. This data type is not supported in Gemini API.

GenerationConfigRoutingConfigManualRoutingMode: The configuration for manual routing. When manual routing is specified, the model will be selected based on the model name provided. This data type is not supported in Gemini API.

GenerationConfigThinkingConfig: Config for thinking features.

GetBatchJobConfig: Optional parameters.

GetCachedContentConfig: Optional parameters for caches.get method.

GetFileConfig: Used to override the default configuration.

GetModelConfig: Optional parameters for models.get method.

GetOperationConfig

GetTuningJobConfig: Optional parameters for tunings.get method.

GoogleMaps: Tool to retrieve knowledge from Google Maps.

GoogleRpcStatus: The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC (https://github.com/grpc). Each Status message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the API Design Guide (https://cloud.google.com/apis/design/errors). This data type is not supported in Gemini API.

GoogleSearch: GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google.

GoogleSearchRetrieval: Tool to retrieve public web data for grounding, powered by Google.

GoogleTypeDate: Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp. This data type is not supported in Gemini API.

GroundingChunk: 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.

GroundingChunkCustomMetadata: User provided metadata about the GroundingFact. This data type is not supported in Vertex AI.

GroundingChunkImage: 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.

GroundingChunkMaps: A Maps chunk is a piece of evidence that comes from Google Maps. It contains information about a place, such as its name, address, and reviews. This is used to provide the user with rich, location-based information.

GroundingChunkMapsPlaceAnswerSources: 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.

GroundingChunkMapsPlaceAnswerSourcesAuthorAttribution: Author attribution for a photo or review.

GroundingChunkMapsPlaceAnswerSourcesReviewSnippet: Encapsulates a review snippet.

GroundingChunkMapsRoute: Route information from Google Maps. This data type is not supported in Gemini API.

GroundingChunkRetrievedContext: Context retrieved from a data source to ground the model's response. This is used when a retrieval tool fetches information from a user-provided corpus or a public dataset.

GroundingChunkStringList: A list of string values. This data type is not supported in Vertex AI.

GroundingChunkWeb: A Web chunk is a piece of evidence that comes from a web page. It contains the URI of the web page, the title of the page, and the domain of the page. This is used to provide the user with a link to the source of the information.

GroundingMetadata: Information for various kinds of grounding.

GroundingMetadataSourceFlaggingUri: A URI that can be used to flag a place or review for inappropriate content. This is populated only when the grounding source is Google Maps. This data type is not supported in Gemini API.

GroundingSupport: Grounding support.

HarmBlockMethodConverter

HarmBlockThresholdConverter

HarmCategoryConverter

HarmProbabilityConverter

HarmSeverityConverter

HttpElementLocationConverter

HttpOptions: HTTP options to be used in each of the requests.

HttpResponse: A wrapper class for the http response.

Image: An image.

ImageConfig: The image generation configuration to be used in GenerateContentConfig.

ImageConfigImageOutputOptions: The image output format for generated images. This data type is not supported in Gemini API.

ImagePromptLanguageConverter

ImageResizeModeConverter

ImageSearch: Image search for grounding and related configurations.

ImportFileOperation: Long-running operation for importing a file to a FileSearchStore.

ImportFileResponse: Response for ImportFile to import a File API file with a file search store.

InlinedEmbedContentResponse: Config for inlined_embedding_responses parameter.

InlinedRequest: Config for inlined request.

InlinedResponse: Config for inlined_responses parameter.

Interval: Represents a time interval, encoded as a Timestamp start (inclusive) and a Timestamp end (exclusive). The start must be less than or equal to the end. When the start equals the end, the interval is empty (matches no time). When both start and end are unspecified, the interval matches any time.

JobError: Job error.

JobStateConverter

LanguageAuto: Indicates the language of the audio should be automatically detected.

LanguageConverter

LanguageHints: Provides hints to the model about possible languages present in the audio.

LatLng: An object that represents a latitude/longitude pair. This is expressed as a pair of doubles to represent degrees latitude and degrees longitude. Unless specified otherwise, this object must conform to the WGS84 standard. Values must be within normalized ranges.

ListBatchJobsConfig: Config for optional parameters.

ListBatchJobsResponse: Config for batches.list return value.

ListCachedContentsConfig: Config for caches.list method.

ListCachedContentsResponse

ListFilesConfig: Used to override the default configuration.

ListFilesResponse: Response for the list files method.

ListModelsConfig

ListModelsResponse

ListTuningJobsConfig: Configuration for the list tuning jobs method.

ListTuningJobsResponse: Response for the list tuning jobs method.

LiveClientContent: Incremental update of the current conversation delivered from the client. All the content here will unconditionally be appended to the conversation history and used as part of the prompt to the model to generate content. A message here will interrupt any current model generation.

LiveClientMessage: Messages sent by the client in the API call.

LiveClientRealtimeInput: User input that is sent in real time. This is different from LiveClientContent in a few ways: - Can be sent continuously without interruption to model generation. - If there is a need to mix data interleaved across the LiveClientContent and the LiveClientRealtimeInput, server attempts to optimize for best response, but there are no guarantees. - End of turn is not explicitly specified, but is rather derived from user activity (for example, end of speech). - Even before the end of turn, the data is processed incrementally to optimize for a fast start of the response from the model. - Is always assumed to be the user's input (cannot be used to populate conversation history).

LiveClientSetup: Message contains configuration that will apply for the duration of the streaming session.

LiveClientToolResponse: Client generated response to a ToolCall received from the server. Individual FunctionResponse objects are matched to the respective FunctionCall objects by the id field. Note that in the unary and server-streaming GenerateContent APIs function calling happens by exchanging the Content parts, while in the bidi GenerateContent APIs function calling happens over this dedicated set of messages.

LiveConnectConfig: Session config for the API connection.

LiveConnectConstraints: Config for LiveConnectConstraints for Auth Token creation.

LiveConnectParameters: Parameters for connecting to the live API.

LiveSendClientContentParameters: Parameters for sending client content to the live API.

LiveSendRealtimeInputParameters: Parameters for sending realtime input to the live API.

LiveSendToolResponseParameters: Parameters for sending tool responses to the live API.

LiveServerContent: Incremental server update generated by the model in response to client messages. Content is generated as quickly as possible, and not in real time. Clients may choose to buffer and play it out in real time.

LiveServerGoAway: Server will not be able to service client soon.

LiveServerMessage: Response message for API call.

LiveServerSessionResumptionUpdate: Update of the session resumption state. Only sent if session_resumption was set in the connection config.

LiveServerSetupComplete: Sent in response to a LiveGenerateContentSetup message from the client.

LiveServerToolCall: Request for the client to execute the function_calls and return the responses with the matching ids.

LiveServerToolCallCancellation: Notification for the client that a previously issued ToolCallMessage with the specified ids should have been not executed and should be cancelled. If there were side-effects to those tool calls, clients may attempt to undo the tool calls. This message occurs only in cases where the clients interrupt server turns.

LogprobsResult: The log probabilities of the tokens generated by the model. This is useful for understanding the model's confidence in its predictions and for debugging. For example, you can use log probabilities to identify when the model is making a less confident prediction or to explore alternative responses that the model considered. A low log probability can also indicate that the model is "hallucinating" or generating factually incorrect information.

LogprobsResultCandidate: A single token and its associated log probability.

LogprobsResultTopCandidates: A list of the top candidate tokens and their log probabilities at each decoding step. This can be used to see what other tokens the model considered.

MaskReferenceConfig: Configuration for a Mask reference image.

MaskReferenceImage: A mask reference image. This encapsulates either a mask image provided by the user and configs for the user provided mask, or only config parameters for the model to generate a mask. A mask image is an image whose non-zero values indicate where to edit the base image. If the user provides a mask image, the mask must be in the same dimensions as the raw image.

MaskReferenceModeConverter

MatchOperationConverter

McpServer: A MCPServer is a server that can be called by the model to perform actions. It is a server that implements the MCP protocol. Next ID: 6. This data type is not supported in Vertex AI.

MediaModalityConverter

MediaResolutionConverter

ModalityConverter

ModalityTokenCount: Represents a breakdown of token usage by modality. This message is used in CountTokensResponse and GenerateContentResponse.UsageMetadata to provide a detailed view of how many tokens are used by each modality (e.g., text, image, video) in a request. This is particularly useful for multimodal models, allowing you to track and manage token consumption for billing and quota purposes.

Model: A trained machine learning model.

ModelArmorConfig: Configuration for Model Armor. Model Armor is a Google Cloud service that provides safety and security filtering for prompts and responses. It helps protect your AI applications from risks such as harmful content, sensitive data leakage, and prompt injection attacks. This data type is not supported in Gemini API.

ModelSelectionConfig: Config for model selection.

ModelStageConverter

ModelStatus: The status of the underlying model. This is used to indicate the stage of the underlying model and the retirement time if applicable. This data type is not supported in Vertex AI.

MultiSpeakerVoiceConfig: Configuration for a multi-speaker text-to-speech request.

Operation<TOperation>: An abstract operation.

OutcomeConverter

OutputInfo: Describes the info for output of EvaluationService. This data type is not supported in Gemini API.

PairwiseChoiceConverter

PairwiseMetricResult: Spec for pairwise metric result. This data type is not supported in Gemini API.

Part: A datatype containing media content. Exactly one field within a Part should be set, representing the specific type of content being conveyed. Using multiple fields within the same Part instance is considered invalid.

PartMediaResolution: Media resolution for the input media.

PartMediaResolutionLevelConverter

PartialArg: Partial argument value of the function call. This data type is not supported in Gemini API.

PartnerModelTuningSpec: Tuning spec for Partner models. This data type is not supported in Gemini API.

PersonGenerationConverter

PhishBlockThresholdConverter

PointwiseMetricResult: Spec for pointwise metric result. This data type is not supported in Gemini API.

PreTunedModel: A pre-tuned model for continuous tuning. This data type is not supported in Gemini API.

PrebuiltVoiceConfig: Configuration for a prebuilt voice.

PreferenceOptimizationDataStats: Statistics computed for datasets used for preference optimization. This data type is not supported in Gemini API.

PreferenceOptimizationHyperParameters: Hyperparameters for Preference Optimization. This data type is not supported in Gemini API.

PreferenceOptimizationSpec: Preference optimization tuning spec for tuning.

ProactivityConfig: Config for proactivity features.

ProductImage: An image of the product.

ProminentPeopleConverter

RagChunk: A RagChunk includes the content of a chunk of a RagFile, and associated metadata. This data type is not supported in Gemini API.

RagChunkPageSpan: Represents where the chunk starts and ends in the document. This data type is not supported in Gemini API.

RagRetrievalConfig: Specifies the context retrieval config. This data type is not supported in Gemini API.

RagRetrievalConfigFilter: Config for filters. This data type is not supported in Gemini API.

RagRetrievalConfigHybridSearch: Config for Hybrid Search. This data type is not supported in Gemini API.

RagRetrievalConfigRanking: Config for ranking and reranking. This data type is not supported in Gemini API.

RagRetrievalConfigRankingLlmRanker: Config for LlmRanker. This data type is not supported in Gemini API.

RagRetrievalConfigRankingRankService: Config for Rank Service. This data type is not supported in Gemini API.

RawOutput: Raw output. This data type is not supported in Gemini API.

RawReferenceImage: A raw reference image. A raw reference image represents the base image to edit, provided by the user. It can optionally be provided in addition to a mask reference image or a style reference image.

RealtimeInputConfig: Marks the end of user activity. This can only be sent if automatic (i.e. server-side) activity detection is disabled.

RecontextImageConfig: Configuration for recontextualizing an image.

RecontextImageResponse: The output images response.

RecontextImageSource: A set of source input(s) for image recontextualization.

RegisterFilesConfig: Used to override the default configuration.

RegisterFilesResponse: Response for the _register file method.

ReinforcementTuningAutoraterScorer: Reinforcement tuning autorater scorer.

ReinforcementTuningAutoraterScorerExactMatchScorer: Scores autorater responses by using exact string match reward scorer.

ReinforcementTuningAutoraterScorerParsedResponseConversionScorer: Scores responses by directly converting parsed autorater response to float reward (reward is clipped to be within [-1, 1]).

ReinforcementTuningCloudRunRewardScorer: Scores parsed responses by calling a Cloud Run service.

ReinforcementTuningCodeExecutionRewardScorer: Scores parsed responses for code execution use cases.

ReinforcementTuningExample: User-facing format for Gemini Reinforcement Tuning examples on Vertex.

ReinforcementTuningHyperParameters: Hyperparameters for Reinforcement Tuning.

ReinforcementTuningParseResponseConfig: Defines how to parse sample response for reinforcement tuning.

ReinforcementTuningRewardInfo: The reward info for a reward function.

ReinforcementTuningSpec: Reinforcement tuning spec for tuning.

ReinforcementTuningStringMatchRewardScorer: Scores parsed responses for string matching use cases.

ReinforcementTuningStringMatchRewardScorerJsonMatchExpression: Converts parsed responses to JSON format, finds the first-level matching key, then performs StringMatchExpression on the value.

ReinforcementTuningStringMatchRewardScorerStringMatchExpression: Evaluates parsed response using match type against expression.

ReinforcementTuningThinkingLevelConverter

ReplayFile: Represents a recorded session.

ReplayInteraction: Represents a single interaction, request and response in a replay.

ReplayRequest: Represents a single request in a replay.

ReplayResponse: Represents a single response in a replay.

ReplicatedVoiceConfig: The configuration for the replicated voice to use.

ResourceScopeConverter

ResponseParseTypeConverter

Retrieval: Defines a retrieval tool that model can call to access external knowledge. This data type is not supported in Gemini API.

RetrievalConfig: Retrieval config.

RetrievalMetadata: Metadata returned to client when grounding is enabled.

RougeMetricValue: Rouge metric value for an instance. This data type is not supported in Gemini API.

SafetyAttributes: Safety attributes of a GeneratedImage or the user-provided prompt.

SafetyFilterLevelConverter

SafetyPolicyConverter

SafetyRating: A safety rating for a piece of content. The safety rating contains the harm category and the harm probability level.

SafetySetting: A safety setting that affects the safety-blocking behavior. A SafetySetting consists of a harm category and a threshold for that category.

Schema: Schema is used to define the format of input/output data. Represents a select subset of an OpenAPI 3.0 schema object (https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed.

ScribbleImage: An image mask representing a brush scribble.

SearchEntryPoint: The entry point used to search for grounding sources.

SearchTypes: Different types of search that can be enabled on the GoogleSearch tool.

Segment: Segment of the content this support belongs to.

SegmentImageConfig: Configuration for segmenting an image.

SegmentImageResponse: The output images response.

SegmentImageSource: A set of source input(s) for image segmentation.

SegmentModeConverter

ServiceTierConverter

SessionResumptionConfig: Configuration of session resumption mechanism. Included in LiveConnectConfig.session_resumption. If included server will send LiveServerSessionResumptionUpdate messages.

SingleEmbedContentResponse: Config for response parameter.

SingleReinforcementTuningRewardConfig: Single reinforcement tuning reward config.

SlidingWindow: Context window will be truncated by keeping only suffix of it. Context window will always be cut at start of USER role turn. System instructions and BidiGenerateContentSetup.prefix_turns will not be subject to the sliding window mechanism, they will always stay at the beginning of context window.

SpeakerVoiceConfig: Configuration for a single speaker in a multi-speaker setup.

SpeechConfig: Config for speech generation and transcription.

StartSensitivityConverter

StreamableHttpTransport: A transport that can stream HTTP requests and responses. Next ID: 6. This data type is not supported in Vertex AI.

StyleReferenceConfig: Configuration for a Style reference image.

StyleReferenceImage: A style reference image. This encapsulates a style reference image provided by the user, and additionally optional config parameters for the style reference image. A raw reference image can also be provided as a destination for the style to be applied to.

SubjectReferenceConfig: Configuration for a Subject reference image.

SubjectReferenceImage: A subject reference image. This encapsulates a subject reference image provided by the user, and additionally optional config parameters for the subject reference image. A raw reference image can also be provided as a destination for the subject to be applied to.

SubjectReferenceTypeConverter

SupervisedHyperParameters: Hyperparameters for SFT. This data type is not supported in Gemini API.

SupervisedTuningDataStats: Tuning data statistics for Supervised Tuning. This data type is not supported in Gemini API.

SupervisedTuningDatasetDistribution: Dataset distribution for Supervised Tuning. This data type is not supported in Gemini API.

SupervisedTuningDatasetDistributionDatasetBucket: Dataset bucket used to create a histogram for the distribution given a population of values. This data type is not supported in Gemini API.

SupervisedTuningSpec: Supervised tuning spec for tuning.

TestTableFile

TestTableItem

ThinkingConfig: The thinking features configuration.

ThinkingLevelConverter

TokensInfo: Tokens info with a list of tokens and the corresponding list of token ids.

Tool: Tool details of a tool that the model may use to generate a response.

ToolCall: A predicted server-side ToolCall returned from the model. This message contains information about a tool that the model wants to invoke. The client is NOT expected to execute this ToolCall. Instead, the client should pass this ToolCall back to the API in a subsequent turn within a Content message, along with the corresponding ToolResponse.

ToolCodeExecution: 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. This data type is not supported in Gemini API.

ToolConfig: Tool config. This config is shared for all tools provided in the request.

ToolParallelAiSearch: ParallelAiSearch tool type. A tool that uses the Parallel.ai search engine for grounding. This data type is not supported in Gemini API.

ToolResponse: The output from a server-side ToolCall execution. This message contains the results of a tool invocation that was initiated by a ToolCall from the model. The client should pass this ToolResponse back to the API in a subsequent turn within a Content message, along with the corresponding ToolCall.

ToolTypeConverter

TrafficTypeConverter

Transcription: Audio transcription in Server Content.

TranslationConfig: Config for stream translation.

TunedModel: TunedModel for the Tuned Model of a Tuning Job.

TunedModelCheckpoint: TunedModelCheckpoint for the Tuned Model of a Tuning Job.

TunedModelInfo: A tuned machine learning model.

TuningDataStats: The tuning data statistic values for TuningJob. This data type is not supported in Gemini API.

TuningDataset: Supervised fine-tuning training dataset.

TuningExample: A single example for tuning. This data type is not supported in Vertex AI.

TuningJob: A tuning job.

TuningJobMetadata: Tuning job metadata. This data type is not supported in Gemini API.

TuningJobStateConverter

TuningMethodConverter

TuningModeConverter

TuningOperation: A long-running operation.

TuningSpeedConverter

TuningTaskConverter

TuningValidationDataset

TurnCompleteReasonConverter

TurnCoverageConverter

TypeConverter

UpdateCachedContentConfig: Optional parameters for caches.update method.

UpdateModelConfig: Configuration for updating a tuned model.

UploadFileConfig: Used to override the default configuration.

UploadToFileSearchStoreOperation: Long-running operation for uploading a file to a FileSearchStore.

UploadToFileSearchStoreResponse: The response when long-running operation for uploading a file to a FileSearchStore complete.

UpscaleImageConfig: Configuration for upscaling an image. For more information on this configuration, refer to the Imagen API reference documentation (https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/imagen-api).

UpscaleImageResponse

UrlContext: Tool to support URL context.

UrlContextMetadata: Metadata returned when the model uses the url_context tool to get information from a user-provided URL.

UrlMetadata: The metadata for a single URL retrieval.

UrlRetrievalStatusConverter

UsageMetadata: Usage metadata about response(s).

VadSignalTypeConverter

ValidateRewardConfig: Optional parameters for tunings.validate_reward.

ValidateRewardResponse: Response for the validate_reward method. Contains the computed reward for a reinforcement tuning reward configuration.

VeoHyperParameters: Hyperparameters for Veo. This data type is not supported in Gemini API.

VeoLoraTuningSpec: Tuning Spec for Veo LoRA Model Tuning. This data type is not supported in Gemini API.

VeoTuningSpec: Tuning Spec for Veo Model Tuning. This data type is not supported in Gemini API.

VertexAISearch: Retrieve from Vertex AI Search datastore or engine for grounding. datastore and engine are mutually exclusive. See https://cloud.google.com/products/agent-builder. This data type is not supported in Gemini API.

VertexAISearchDataStoreSpec: Define data stores within engine to filter on in a search call and configurations for those data stores. For more information, see https://cloud.google.com/generative-ai-app-builder/docs/reference/rpc/google.cloud.discoveryengine.v1#datastorespec. This data type is not supported in Gemini API.

VertexMultimodalDatasetDestination: This class is experimental and may change in future versions. The specification for an output Vertex AI multimodal dataset.

VertexRagStore: Retrieve from Vertex RAG Store for grounding. This data type is not supported in Gemini API.

VertexRagStoreRagResource: The definition of the Rag resource. This data type is not supported in Gemini API.

Video: A generated video.

VideoCompressionQualityConverter

VideoGenerationMask: A mask for video generation.

VideoGenerationMaskModeConverter

VideoGenerationReferenceImage: A reference image for video generation.

VideoGenerationReferenceTypeConverter

VideoMetadata: Provides metadata for a video, including the start and end offsets for clipping and the frame rate.

VideoOrientationConverter

VoiceActivity: Voice activity signal.

VoiceActivityDetectionSignal

VoiceActivityTypeConverter

VoiceConfig: The configuration for the voice to use.

WebSearch: Standard web search for grounding and related configurations. Only text results are returned.

WebhookConfig: Configuration for webhook notifications. Used to configure webhook endpoints that will receive notifications when long-running operations (e.g., batch jobs, video generation) complete.

Structs

ActivityHandling: The different ways of handling user activity.

AdapterSize: Adapter size for tuning. This enum is not supported in Gemini API.

AggregationMetric: Aggregation metric. This enum is not supported in Gemini API.

ApiSpec: The API spec that the external API implements. This enum is not supported in Gemini API.

AuthType: Type of auth scheme. This enum is not supported in Gemini API.

Behavior: Specifies the function Behavior. Currently only non-blocking functions are supported. If not specified, the system keeps the current function call behavior. This field is currently only supported by the BidiGenerateContent method.

BlockedReason: Output only. The reason why the prompt was blocked.

ControlReferenceType: Enum representing the control type of a control reference image.

DynamicRetrievalConfigMode: The mode of the predictor to be used in dynamic retrieval.

EditMode: Enum representing the editing mode.

EmbeddingApiType: Enum representing the Gemini Enterprise Agent Platform embedding API to use.

EndSensitivity: End of speech sensitivity.

Environment: The environment being operated.

FeatureSelectionPreference: Options for feature selection preference.

FileSource: Source of the File.

FileState: State for the lifecycle of a File.

FinishReason: Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.

FunctionCallingConfigMode: Function calling mode.

FunctionResponseScheduling: Specifies how the response should be scheduled in the conversation. Only applicable to NON_BLOCKING function calls, is ignored otherwise. Defaults to WHEN_IDLE.

HarmBlockMethod: The method for blocking content. If not specified, the default behavior is to use the probability score. This enum is not supported in Gemini API.

HarmBlockThreshold: The threshold for blocking content. If the harm probability exceeds this threshold, the content will be blocked.

HarmCategory: The harm category to be blocked.

HarmProbability: Output only. The probability of harm for this category.

HarmSeverity: Output only. The severity of harm for this category. This enum is not supported in Gemini API.

HttpElementLocation: The location of the API key. This enum is not supported in Gemini API.

ImagePromptLanguage: Enum that specifies the language of the text in the prompt.

ImageResizeMode: Resize mode for the image input for video generation.

JobState: Job state.

Language: Programming language of the code.

MaskReferenceMode: Enum representing the mask mode of a mask reference image.

MatchOperation: Match operation to use for evaluation.

MediaModality: The modality that this token count applies to.

MediaResolution: The media resolution to use.

Modality: Server content modalities.

ModelStage: The stage of the underlying model. This enum is not supported in Vertex AI.

Outcome: Outcome of the code execution.

PairwiseChoice: Output only. Pairwise metric choice. This enum is not supported in Gemini API.

PartMediaResolutionLevel: The tokenization quality used for given media.

PersonGeneration: Enum that controls the generation of people.

PhishBlockThreshold: Sites with confidence level chosen & above this value will be blocked from the search results. This enum is not supported in Gemini API.

ProminentPeople: 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. This enum is not supported in Gemini API.

ReinforcementTuningThinkingLevel: Represents how much to think for the tuning job.

ResourceScope: Resource scope.

ResponseParseType: Defines how to parse sample response.

SafetyFilterLevel: Enum that controls the safety filter level for objectionable content.

SafetyPolicy: SafetyPolicy

SegmentMode: Enum that represents the segmentation mode.

ServiceTier: Pricing and performance service tier.

StartSensitivity: Start of speech sensitivity.

SubjectReferenceType: Enum representing the subject type of a subject reference image.

ThinkingLevel: The number of thoughts tokens that the model should generate.

ToolType: The type of tool in the function call.

TrafficType: Output only. The traffic type for this request. This enum is not supported in Gemini API.

TuningJobState: Output only. The detail state of the tuning job (while the overall JobState is running). This enum is not supported in Gemini API.

TuningMethod: Enum representing the tuning method.

TuningMode: Tuning mode. This enum is not supported in Gemini API.

TuningSpeed: The speed of the tuning job. Only supported for Veo 3.0 models. This enum is not supported in Gemini API.

TuningTask: The tuning task for Veo. This enum is not supported in Gemini API.

TurnCompleteReason: The reason why the turn is complete.

TurnCoverage: Options about which input is included in the user's turn.

Type: Data type of the schema field.

UrlRetrievalStatus: The status of the URL retrieval.

VadSignalType: The type of the VAD signal.

VideoCompressionQuality: Enum that controls the compression quality of the generated videos.

VideoGenerationMaskMode: Enum for the mask mode of a video generation mask.

VideoGenerationReferenceType: Enum for the reference type of a video generation reference image.

VideoOrientation: The orientation of the video. Defaults to LANDSCAPE. This enum is not supported in Gemini API.

VoiceActivityType: The type of the voice activity signal.

Interfaces

IReferenceImage: The interface for ReferenceImage.

Table of Contents

Namespace Google.GenAI.Types

Classes

Structs

Interfaces