Optionalagent?: AgentOptionThe agent to interact with.
Optionalagent_config?: Configuration parameters for the agent interaction.
Optionalcached_content?: stringThe 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: cachedContents/{cachedContent}
Optionalcontinuation_token?: stringOpaque token to resume a long decode. Output: set when status is
Optionalcreated?: stringRequired. Output only. The time at which the response was created in ISO 8601 format
Optionalenvironment?: Environment | stringThe environment configuration for the interaction. Can be an object
Optionalenvironment_id?: stringOutput only. The environment ID for the interaction. Only populated if environment
Optionalerrors?: ErrorT[]Output only. Diagnostic faults / platform errors recorded on the interaction.
Optionalgeneration_config?: GenerationConfigConfiguration parameters for model interactions.
Required. Output only. A unique identifier for the interaction completion.
Optionalinput?: InteractionsInputThe input for the interaction.
Optionallabels?: { [k: string]: string }The labels with user-defined metadata for the request.
Optionalmodel?: ModelThe model that will complete your prompt.\n\nSee models for additional details.
Optionaloutput_audio?: AudioContentAn audio content block.
Optionaloutput_image?: ImageContentAn image content block.
Optionaloutput_text?: stringConcatenated text from the last model output in response to the current request.
Optionaloutput_video?: VideoContentA video content block.
Optionalprevious_interaction_id?: stringThe ID of the previous interaction, if any.
Optionalresponse_format?: ResponseFormat | ResponseFormat[]Enforces that the generated response is a JSON object that complies with
Optionalresponse_mime_type?: stringThe mime type of the response. This is required if response_format is set.
Optionalresponse_modalities?: ResponseModality[]The requested modalities of the response (TEXT, IMAGE, AUDIO).
Optionalsafety_settings?: SafetySetting[]Safety settings for the interaction.
Optionalservice_tier?: ServiceTierRequired. Output only. The status of the interaction.
Optionalsteps?: Step[]Required. Output only. The steps that make up the interaction, when included in the response.
Optionalsystem_instruction?: stringSystem instruction for the interaction.
Optionaltools?: Tool[]A list of tool declarations the model may call during interaction.
Optionalupdated?: stringRequired. Output only. The time at which the response was last updated in ISO 8601 format
Optionalusage?: UsageStatistics on the interaction request's token usage.
Optionalwebhook_config?: WebhookConfigMessage for configuring webhook events for a request.
The Interaction resource.