generativelanguage library

The Google Cloud client for the Generative Language API.

The Gemini API allows developers to build generative AI applications using Gemini models. Gemini is our most capable model, built from the ground up to be multimodal. It can generalize and seamlessly understand, operate across, and combine different types of information including language, images, audio, video, and code. You can use the Gemini API for use cases like reasoning across text and images, content generation, dialogue agents, summarization and classification systems, and more.

Classes

AttributionSourceId: Identifier for the source contributing to this attribution.
AttributionSourceId_GroundingPassageId: Identifier for a part within a GroundingPassage.
AttributionSourceId_SemanticRetrieverChunk: Identifier for a Chunk retrieved via Semantic Retriever specified in the GenerateAnswerRequest using SemanticRetrieverConfig.
AudioTranscriptionConfig: The audio transcription configuration.
BatchCreateChunksRequest: Request to batch create Chunks.
BatchCreateChunksResponse: Response from BatchCreateChunks containing a list of created Chunks.
BatchDeleteChunksRequest: Request to batch delete Chunks.
BatchEmbedContentsRequest: Batch request to get embeddings from the model for a list of prompts.
BatchEmbedContentsResponse: The response to a BatchEmbedContentsRequest.
BatchEmbedTextRequest: Batch request to get a text embedding from the model.
BatchEmbedTextResponse: The response to a EmbedTextRequest.
BatchUpdateChunksRequest: Request to batch update Chunks.
BatchUpdateChunksResponse: Response from BatchUpdateChunks containing a list of updated Chunks.
BidiGenerateContentClientContent: Incremental update of the current conversation delivered from the client. All of the content here is unconditionally appended to the conversation history and used as part of the prompt to the model to generate content.
BidiGenerateContentClientMessage: Messages sent by the client in the BidiGenerateContent call.
BidiGenerateContentRealtimeInput: User input that is sent in real time.
BidiGenerateContentRealtimeInput_ActivityEnd: Marks the end of user activity.
BidiGenerateContentRealtimeInput_ActivityStart: Marks the start of user activity.
BidiGenerateContentServerContent: Incremental server update generated by the model in response to client messages.
BidiGenerateContentServerMessage: Response message for the BidiGenerateContent call.
BidiGenerateContentSetup: Message to be sent in the first (and only in the first) BidiGenerateContentClientMessage. Contains configuration that will apply for the duration of the streaming RPC.
BidiGenerateContentSetupComplete: Sent in response to a BidiGenerateContentSetup message from the client.
BidiGenerateContentToolCall: Request for the client to execute the function_calls and return the responses with the matching ids.
BidiGenerateContentToolCallCancellation: Notification for the client that a previously issued ToolCallMessage with the specified ids should not have been 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.
BidiGenerateContentToolResponse: Client generated response to a ToolCall received from the server. Individual FunctionResponse objects are matched to the respective FunctionCall objects by the id field.
BidiGenerateContentTranscription: Transcription of audio (input or output).
Blob: Raw media bytes.
CachedContent: Content that has been preprocessed and can be used in subsequent request to GenerativeService.
CachedContent_UsageMetadata: Metadata on the usage of the cached content.
CacheService: API for managing cache of content (CachedContent resources) that can be used in GenerativeService requests. This way generate content requests can benefit from preprocessing work being done earlier, possibly lowering their computational cost. It is intended to be used with large contexts.
Candidate: A response candidate generated from the model.
Candidate_FinishReason: Defines the reason why the model stopped generating tokens.
Chunk: A Chunk is a subpart of a Document that is treated as an independent unit for the purposes of vector representation and storage. A Corpus can have a maximum of 1 million Chunks.
Chunk_State: States for the lifecycle of a Chunk.
ChunkData: Extracted data that represents the Chunk content.
CitationMetadata: A collection of source attributions for a piece of content.
CitationSource: A citation to a source for a portion of a specific response.
CodeExecution: Tool that executes code generated by the model, and automatically returns the result to the model.
CodeExecutionResult: Result of executing the ExecutableCode.
CodeExecutionResult_Outcome: Enumeration of possible outcomes of the code execution.
Condition: Filter condition applicable to a single key.
Condition_Operator: Defines the valid operators that can be applied to a key-value pair.
Content: The base structured datatype containing multi-part content of a message.
ContentEmbedding: A list of floats representing an embedding.
ContentFilter: Content filtering metadata associated with processing a single request.
ContentFilter_BlockedReason: A list of reasons why content may have been blocked.
ContextWindowCompressionConfig: Enables context window compression — a mechanism for managing the model's context window so that it does not exceed a given length.
ContextWindowCompressionConfig_SlidingWindow: The SlidingWindow method operates by discarding content at the beginning of the context window. The resulting context will always begin at the start of a USER role turn. System instructions and any BidiGenerateContentSetup.prefix_turns will always remain at the beginning of the result.
Corpus: A Corpus is a collection of Documents. A project can create up to 5 corpora.
CountMessageTokensRequest: Counts the number of tokens in the prompt sent to a model.
CountMessageTokensResponse: A response from CountMessageTokens.
CountTextTokensRequest: Counts the number of tokens in the prompt sent to a model.
CountTextTokensResponse: A response from CountTextTokens.
CountTokensRequest: Counts the number of tokens in the prompt sent to a model.
CountTokensResponse: A response from CountTokens.
CreateCachedContentRequest: Request to create CachedContent.
CreateChunkRequest: Request to create a Chunk.
CreateCorpusRequest: Request to create a Corpus.
CreateDocumentRequest: Request to create a Document.
CreateFileRequest: Request for CreateFile.
CreateFileResponse: Response for CreateFile.
CreatePermissionRequest: Request to create a Permission.
CreateTunedModelMetadata: Metadata about the state and progress of creating a tuned model returned from the long-running operation
CreateTunedModelRequest: Request to create a TunedModel.
CustomMetadata: User provided metadata stored as key-value pairs.
Dataset: Dataset for training or validation.
DeleteCachedContentRequest: Request to delete CachedContent.
DeleteChunkRequest: Request to delete a Chunk.
DeleteCorpusRequest: Request to delete a Corpus.
DeleteDocumentRequest: Request to delete a Document.
DeleteFileRequest: Request for DeleteFile.
DeletePermissionRequest: Request to delete the Permission.
DeleteTunedModelRequest: Request to delete a TunedModel.
DiscussService: An API for using Generative Language Models (GLMs) in dialog applications.
Document: A Document is a collection of Chunks. A Corpus can have a maximum of 10,000 Documents.
DownloadFileRequest: Request for DownloadFile.
DownloadFileResponse: Response for DownloadFile.
DynamicRetrievalConfig: Describes the options to customize dynamic retrieval.
DynamicRetrievalConfig_Mode: The mode of the predictor to be used in dynamic retrieval.
EmbedContentRequest: Request containing the Content for the model to embed.
EmbedContentResponse: The response to an EmbedContentRequest.
Embedding: A list of floats representing the embedding.
EmbedTextRequest: Request to get a text embedding from the model.
EmbedTextResponse: The response to a EmbedTextRequest.
Example: An input/output example used to instruct the Model.
ExecutableCode: Code generated by the model that is meant to be executed, and the result returned to the model.
ExecutableCode_Language: Supported programming languages for the generated code.
File: A file uploaded to the API. Next ID: 15
File_Source
File_State: States for the lifecycle of a File.
FileData: URI based data.
FileService: An API for uploading and managing files.
FunctionCall: A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name with the arguments and their values.
FunctionCallingConfig: Configuration for specifying function calling behavior.
FunctionCallingConfig_Mode: Defines the execution behavior for function calling by defining the execution mode.
FunctionDeclaration: Structured representation of a function declaration as defined by the OpenAPI 3.03 specification. Included in this declaration are the function name and parameters. 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.
FunctionDeclaration_Behavior: Defines the function behavior. Defaults to BLOCKING.
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 aFunctionCall made based on model prediction.
FunctionResponse_Scheduling: Specifies how the response should be scheduled in the conversation.
FunctionResponseBlob: Raw media bytes for function response.
FunctionResponsePart: A datatype containing media that is part of a FunctionResponse message.
GenerateAnswerRequest: Request to generate a grounded answer from the Model.
GenerateAnswerRequest_AnswerStyle: Style for grounded answers.
GenerateAnswerResponse: Response from the model for a grounded answer.
GenerateAnswerResponse_InputFeedback: Feedback related to the input data used to answer the question, as opposed to the model-generated response to the question.
GenerateAnswerResponse_InputFeedback_BlockReason: Specifies what was the reason why input was blocked.
GenerateContentRequest: Request to generate a completion from the model. NEXT ID: 18
GenerateContentResponse: Response from the model supporting multiple candidate responses.
GenerateContentResponse_PromptFeedback: A set of the feedback metadata the prompt specified in GenerateContentRequest.content.
GenerateContentResponse_PromptFeedback_BlockReason: Specifies the reason why the prompt was blocked.
GenerateContentResponse_UsageMetadata: Metadata on the generation request's token usage.
GenerateMessageRequest: Request to generate a message response from the model.
GenerateMessageResponse: The response from the model.
GenerateTextRequest: Request to generate a text completion response from the model.
GenerateTextResponse: The response from the model, including candidate completions.
GenerationConfig: Configuration options for model generation and outputs. Not all parameters are configurable for every model. Next ID: 29
GenerationConfig_MediaResolution: Media resolution for the input media.
GenerationConfig_Modality: Supported modalities of the response.
GenerativeService: API for using Large Models that generate multimodal content and have additional capabilities beyond text generation.
GetCachedContentRequest: Request to read CachedContent.
GetChunkRequest: Request for getting information about a specific Chunk.
GetCorpusRequest: Request for getting information about a specific Corpus.
GetDocumentRequest: Request for getting information about a specific Document.
GetFileRequest: Request for GetFile.
GetModelRequest: Request for getting information about a specific Model.
GetPermissionRequest: Request for getting information about a specific Permission.
GetTunedModelRequest: Request for getting information about a specific Model.
GoAway: A notice that the server will soon disconnect.
GoogleSearchRetrieval: Tool to retrieve public web data for grounding, powered by Google.
GroundingAttribution: Attribution for a source that contributed to an answer.
GroundingChunk: Grounding chunk.
GroundingChunk_Web: Chunk from the web.
GroundingMetadata: Metadata returned to client when grounding is enabled.
GroundingPassage: Passage included inline with a grounding configuration.
GroundingPassages: A repeated list of passages.
GroundingSupport: Grounding support.
HarmCategory: The category of a rating.
Hyperparameters: Hyperparameters controlling the tuning process. Read more at https://ai.google.dev/docs/model_tuning_guidance
ImageConfig: Config for image generation features.
ListCachedContentsRequest: Request to list CachedContents.
ListCachedContentsResponse: Response with CachedContents list.
ListChunksRequest: Request for listing Chunks.
ListChunksResponse: Response from ListChunks containing a paginated list of Chunks. The Chunks are sorted by ascending chunk.create_time.
ListCorporaRequest: Request for listing Corpora.
ListCorporaResponse: Response from ListCorpora containing a paginated list of Corpora. The results are sorted by ascending corpus.create_time.
ListDocumentsRequest: Request for listing Documents.
ListDocumentsResponse: Response from ListDocuments containing a paginated list of Documents. The Documents are sorted by ascending document.create_time.
ListFilesRequest: Request for ListFiles.
ListFilesResponse: Response for ListFiles.
ListModelsRequest: Request for listing all Models.
ListModelsResponse: Response from ListModel containing a paginated list of Models.
ListPermissionsRequest: Request for listing permissions.
ListPermissionsResponse: Response from ListPermissions containing a paginated list of permissions.
ListTunedModelsRequest: Request for listing TunedModels.
ListTunedModelsResponse: Response from ListTunedModels containing a paginated list of Models.
LogprobsResult: Logprobs Result
LogprobsResult_Candidate: Candidate for the logprobs token and score.
LogprobsResult_TopCandidates: Candidates with top log probabilities at each decoding step.
Media: A proto encapsulate various type of media.
Message: The base unit of structured text.
MessagePrompt: All of the structured input text passed to the model as a prompt.
MetadataFilter: User provided filter to limit retrieval based on Chunk or Document level metadata values. Example (genre = drama OR genre = action): key = "document.custom_metadata.genre" conditions = {string_value = "drama", operation = EQUAL}, {string_value = "action", operation = EQUAL}
Modality: Content Part modality
ModalityTokenCount: Represents token counting info for a single modality.
Model: Information about a Generative Language Model.
ModelService: Provides methods for getting metadata information about Generative Models.
MultiSpeakerVoiceConfig: The configuration for the multi-speaker setup.
Part: A datatype containing media that is part of a multi-part Content message.
Permission: Permission resource grants user, group or the rest of the world access to the PaLM API resource (e.g. a tuned model, corpus).
Permission_GranteeType: Defines types of the grantee of this permission.
Permission_Role: Defines the role granted by this permission.
PermissionService: Provides methods for managing permissions to PaLM API resources.
PrebuiltVoiceConfig: The configuration for the prebuilt speaker to use.
PredictionService: A service for online predictions and explanations.
PredictLongRunningGeneratedVideoResponse: Veo response.
PredictLongRunningMetadata: Metadata for PredictLongRunning long running operations.
PredictLongRunningRequest: Request message for PredictionService.PredictLongRunning.
PredictLongRunningResponse: Response message for PredictionService.PredictLongRunning
PredictRequest: Request message for PredictionService.Predict.
PredictResponse: Response message for PredictionService.Predict.
QueryCorpusRequest: Request for querying a Corpus.
QueryCorpusResponse: Response from QueryCorpus containing a list of relevant chunks.
QueryDocumentRequest: Request for querying a Document.
QueryDocumentResponse: Response from QueryDocument containing a list of relevant chunks.
RealtimeInputConfig: Configures the realtime input behavior in BidiGenerateContent.
RealtimeInputConfig_ActivityHandling: The different ways of handling user activity.
RealtimeInputConfig_AutomaticActivityDetection: Configures automatic detection of activity.
RealtimeInputConfig_AutomaticActivityDetection_EndSensitivity: Determines how end of speech is detected.
RealtimeInputConfig_AutomaticActivityDetection_StartSensitivity: Determines how start of speech is detected.
RealtimeInputConfig_TurnCoverage: Options about which input is included in the user's turn.
RelevantChunk: The information for a chunk relevant to a query.
RetrievalMetadata: Metadata related to retrieval in the grounding flow.
RetrieverService: An API for semantic search over a corpus of user uploaded content.
SafetyFeedback: Safety feedback for an entire request.
SafetyRating: Safety rating for a piece of content.
SafetyRating_HarmProbability: The probability that a piece of content is harmful.
SafetySetting: Safety setting, affecting the safety-blocking behavior.
SafetySetting_HarmBlockThreshold: Block at and beyond a specified harm probability.
Schema: The Schema object allows the definition of input and output data types. These types can be objects, but also primitives and arrays. Represents a select subset of an OpenAPI 3.0 schema object.
SearchEntryPoint: Google search entry point.
Segment: Segment of the content.
SemanticRetrieverConfig: Configuration for retrieving grounding content from a Corpus or Document created using the Semantic Retriever API.
SessionResumptionConfig: Session resumption configuration.
SessionResumptionUpdate: Update of the session resumption state.
SpeakerVoiceConfig: The configuration for a single speaker in a multi speaker setup.
SpeechConfig: The speech generation config.
StringList: User provided string values assigned to a single metadata key.
TaskType: Type of task for which the embedding will be used.
TextCompletion: Output text returned from a model.
TextPrompt: Text given to the model as a prompt.
TextService: API for using Generative Language Models (GLMs) trained to generate text.
ThinkingConfig: Config for thinking features.
Tool: Tool details that the model may use to generate response.
Tool_ComputerUse: Computer Use tool type.
Tool_ComputerUse_Environment: Represents the environment being operated, such as a web browser.
Tool_GoogleSearch: GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google.
ToolConfig: The Tool configuration containing parameters for specifying Tool use in the request.
TransferOwnershipRequest: Request to transfer the ownership of the tuned model.
TransferOwnershipResponse: Response from TransferOwnership.
TunedModel: A fine-tuned model created using ModelService.CreateTunedModel.
TunedModel_State: The state of the tuned model.
TunedModelSource: Tuned model as a source for training a new model.
TuningExample: A single example for tuning.
TuningExamples: A set of tuning examples. Can be training or validation data.
TuningSnapshot: Record for a single tuning step.
TuningTask: Tuning tasks that create tuned models.
Type: Type contains the list of OpenAPI data types as defined by https://spec.openapis.org/oas/v3.0.3#data-types
UpdateCachedContentRequest: Request to update CachedContent.
UpdateChunkRequest: Request to update a Chunk.
UpdateCorpusRequest: Request to update a Corpus.
UpdateDocumentRequest: Request to update a Document.
UpdatePermissionRequest: Request to update the Permission.
UpdateTunedModelRequest: Request to update a TunedModel.
UrlContext: Tool to support URL context retrieval.
UrlContextMetadata: Metadata related to url context retrieval tool.
UrlMetadata: Context of the a single url retrieval.
UrlMetadata_UrlRetrievalStatus: Status of the url retrieval.
UsageMetadata: Usage metadata about response(s).
Video: Representation of a video.
VideoFileMetadata: Metadata for a video File.
VideoMetadata: Metadata describes the input video content.
VoiceConfig: The configuration for the voice to use.

generativelanguage library

Classes

google_cloud_ai_generativelanguage_v1beta package

generativelanguage library