Package-level declarations

Identifies the source of an attribution, which can be either a grounding passage or a chunk retrieved by a semantic retriever. This class allows for specifying the origin of content or data used in processing or analysis.

Represents the attribution source id builder.

Represents a batch request for embedding content.

Represents the response for a batch embedding request.

Represents the cached content.

Represents the cached content list.

Represents a candidate entity with associated content and metadata.

Represents the candidate builder.

Contains metadata about citations within a document, including references to the sources of these citations.

Represents the citation metadata builder.

Represents a source of citation, detailing the location within the text and providing reference information such as a URI and license.

Represents the citation source builder.

Represents the code execution.

Represents the code execution result.

Represents the code execution result builder.

Represents the content composed of multiple parts, optionally associated with a specific role.

Represents the content builder.

Represents a request to count the number of tokens in a list of content items. This is typically used to ensure that input does not exceed model or system limits for processing.

Represents a request to embed content using a specified model, optionally including additional parameters such as task type and title.

Represents the response from an embedding operation, containing the computed embedding values.

Represents the executable code.

Represents the executable code builder.

Encapsulates data about a file, including its MIME type and a URI pointing to its location.

Builder class for constructing a FileData object.

Represents a File Search tool.

Represents the file search tool builder.

Represents a call to a function, specifying the function's name and the arguments to be passed to it.

Represents the function call builder.

Configures how function calls are handled within a certain context, specifying the mode of operation and restrictions on which functions can be called.

Represents the function calling config builder.

Describes a function, including its name, a description of its purpose or behavior, and a schema defining its parameters.

Represents the function declaration builder.

Represents the response from a function call, including the function's name and the arguments or values returned by the function.

Represents a client for interacting with the Gemini API, providing methods to extract content, embed content, and retrieve model information.

Represents the detailed error information.

Represents a detail object within the error response. Fields are nullable as different error types provide different details.

Represents the gemini error link.

Represents the top-level error response structure from the Gemini API.

Represents the gemini error violation.

Exception thrown when the Gemini API returns an error.

Represents the gemini file.

Represents the gemini function.

Represents the gemini js export.

Represents the gemini parameter.

Represents a request to generate content, specifying the inputs, tools, and configurations required for content generation.

Represents the generate content request builder.

Represents the response structure for a content generation or analysis request.

Configures the parameters for content generation, including conditions for stopping generation, creativity controls, output limits, and the format of the generated content.

Represents the generation config builder.

Represents a Google Search tool.

Represents the attribution of grounding, linking content to its source.

Represents the grounding attribution builder.

A chunk of content from a grounding source.

Metadata returned to the client when grounding is enabled.

Represents an identifier for a grounding passage, including its unique ID and the index of the part within the passage.

Represents the grounding passage id builder.

Grounding support.

Enumerates categories of harm that content may be classified under, providing a structured way to identify and categorize potentially harmful or sensitive content.

Enum class representing different categories of harmful content.

Configures the image generation parameters.

Represents the image config builder.

Represents inline data that can be included in a request or response, typically for media content.

Represents the inline data builder.

Represents the lat lng.

Represents the logprobs result.

Enumerates the modalities that can be returned by the model.

Represents the modality token count.

Enumerates the possible modes of operation or configuration settings, providing predefined options for various functionalities.

Represents a model with its metadata and configuration parameters, providing detailed information about its capabilities and restrictions.

Represents a collection of models, encapsulating them in a list structure for easy management and access.

Configures the multi-speaker voice parameters.

Represents the multi speaker voice config builder.

Represents a part of content, which can be one of several types such as text, inline data, function call, function response, or file data.

Represents the part builder.

Configures the prebuilt voice parameters.

Represents the prebuilt voice config builder.

Represents feedback on the safety of a prompt, including ratings across various harm categories.

Represents the prompt feedback builder.

Represents the retrieval config.

Represents the retrieval config builder.

Represents a safety assessment for a specific category of potential harm.

Represents the safety rating builder.

Defines a safety setting for filtering or evaluating content based on a specific harm category.

Represents the safety setting builder.

Represents the schema definition for a data model, detailing its structure, type, and various constraints.

Represents the schema builder.

Google search entry point.

Segment of the content.

Represents a chunk of data retrieved by a semantic retriever, containing both the source from which the chunk was extracted and the chunk content itself.

Configures the voice parameters for a specific speaker.

Represents the speaker voice config builder.

Configures the speech generation parameters.

Represents the speech config builder.

Enumerates the types of tasks that can be performed.

Represents the thinking config.

Enumerates the possible thresholds for content blocking or filtering based on safety assessments.

Represents a tool that encapsulates function declarations, providing a structured way to access the functionalities declared.

Represents the tool builder.

Represents a tool that encapsulates function declarations, providing a structured way to access the functionalities declared.

Represents the tool config builder.

Represents the top candidates.

Represents the total count of tokens, typically used to summarize the amount of processed or generated content in terms of tokens.

Represents the url context.

Metadata about the URL context.

Metadata for a single retrieved URL.

Represents the usage metadata.

Represents a container for a list of numeric values.

Represents the values builder.

Configures the voice parameters.

Represents the voice config builder.

Chunk from the web.

Handles attribution source id.

Handles candidate.

Handles citation metadata.

Handles citation source.

Handles code execution result.

Handles content.

Handles executable code.

DSL function to create a FileData object using a builder pattern.

Handles function call.

Handles function calling config.

Handles function declaration.

Handles generate content request.

Handles generation config.

Creates a client for the Live API.

Handles grounding attribution.

Handles grounding passage id.

Handles image config.

Handles inline data.

Handles part.

Handles prompt feedback.

Handles retrieval config.

Handles safety rating.

Handles safety setting.

Handles speech config.

Handles tool.

Handles tool config.

Handles values.