FirebaseVertexAI Framework Reference

Structures

The following structures are available globally.

• FunctionDeclaration

  Structured representation of a function declaration.

  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.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct FunctionDeclaration : Sendable

  extension FunctionDeclaration: Encodable

• Tool

  A helper tool that the model may use when generating responses.

  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.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct Tool : Sendable

  extension Tool: Encodable

• FunctionCallingConfig

  Configuration for specifying function calling behavior.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct FunctionCallingConfig : Sendable

  extension FunctionCallingConfig: Encodable

• ToolConfig

  Tool configuration for any Tool specified in the request.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct ToolConfig : Sendable

  extension ToolConfig: Encodable

• GenerateContentResponse

  The model’s response to a generate content request.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct GenerateContentResponse : Sendable

  extension GenerateContentResponse: Decodable

• Candidate

  A struct representing a possible reply to a content generation prompt. Each content generation prompt may produce multiple candidate responses.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct Candidate : Sendable

  extension Candidate: Decodable

• CitationMetadata

  A collection of source attributions for a piece of content.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct CitationMetadata : Sendable

  extension CitationMetadata: Decodable

• Citation

  A struct describing a source attribution.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct Citation : Sendable

  extension Citation: Decodable

• FinishReason

  A value enumerating possible reasons for a model to terminate a content generation request.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct FinishReason : DecodableProtoEnum, Hashable, Sendable

• PromptFeedback

  A metadata struct containing any feedback the model had on the prompt it was provided.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct PromptFeedback : Sendable

  extension PromptFeedback: Decodable

• GenerationConfig

  A struct defining model parameters to be used when sending generative AI requests to the backend model.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct GenerationConfig : Sendable

  extension GenerationConfig: Encodable

• RequestOptions

  Configuration parameters for sending requests to the backend.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct RequestOptions : Sendable

  extension RequestOptions: Equatable

• ModalityTokenCount

  Represents token counting info for a single modality.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct ModalityTokenCount : Sendable

  extension ModalityTokenCount: Decodable

• ContentModality

  Content part modality.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct ContentModality : DecodableProtoEnum, Hashable, Sendable

• ModelContent

  A type describing data in media formats interpretable by an AI model. Each generative AI request or response contains an Array of ModelContents, and each ModelContent value may comprise multiple heterogeneous Parts.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct ModelContent : Equatable, Sendable

  extension ModelContent: Codable

• SafetyRating

  A type defining potentially harmful media categories and their model-assigned ratings. A value of this type may be assigned to a category for every model-generated response, not just responses that exceed a certain threshold.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct SafetyRating : Equatable, Hashable, Sendable

  extension SafetyRating: Decodable

• SafetySetting

  A type used to specify a threshold for harmful content, beyond which the model will return a fallback response instead of generated content.

  See safety settings for Gemini models for more details.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct SafetySetting : Sendable

  extension SafetySetting: Encodable

• HarmCategory

  Categories describing the potential harm a piece of content may pose.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct HarmCategory : CodableProtoEnum, Hashable, Sendable

• CountTokensResponse

  The model’s response to a count tokens request.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct CountTokensResponse

  extension CountTokensResponse: Decodable

• ImagenAspectRatio

  An aspect ratio for images generated by Imagen.

  To specify an aspect ratio for generated images, set aspectRatio in your ImagenGenerationConfig. See the Cloud documentation for more details and examples of the supported aspect ratios.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct ImagenAspectRatio : Sendable

• ImagenGenerationConfig

  Configuration options for generating images with Imagen.

  See Parameters for Imagen models to learn about parameters available for use with Imagen models, including how to configure them.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct ImagenGenerationConfig

• ImagenGenerationResponse

  A response from a request to generate images with Imagen.

  The type placeholder T is an image type; this is currently always an ImagenInlineImage.

  This type is returned from:

  • generateImages(prompt:) where T is ImagenInlineImage

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct ImagenGenerationResponse<T>

  extension ImagenGenerationResponse: Decodable where T: Decodable

• ImagenImageFormat

  An image format for images generated by Imagen.

  To specify an image format for generated images, set imageFormat in your ImagenGenerationConfig. See the Cloud documentation for more details.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct ImagenImageFormat

• ImagenImagesBlockedError

  An error that occurs when image generation fails due to all generated images being blocked.

  The images may have been blocked due to the specified ImagenSafetyFilterLevel, the ImagenPersonFilterLevel, or filtering included in the model. These filter levels may be adjusted in your ImagenSafetySettings. See the Responsible AI and usage guidelines for Imagen for more details.

  Declaration

  Swift

  public struct ImagenImagesBlockedError : Error

  extension ImagenImagesBlockedError: CustomNSError

• ImagenInlineImage

  An image generated by Imagen, represented as inline data.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct ImagenInlineImage

  extension ImagenInlineImage: Equatable

  extension ImagenInlineImage: Decodable

• ImagenPersonFilterLevel

  A filter level controlling whether generation of images containing people or faces is allowed.

  See the personGeneration documentation for more details.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct ImagenPersonFilterLevel : ProtoEnum

• ImagenSafetyFilterLevel

  A filter level controlling how aggressively to filter sensitive content.

  Text prompts provided as inputs and images (generated or uploaded) through Imagen on Vertex AI are assessed against a list of safety filters, which include ‘harmful categories’ (for example, violence, sexual, derogatory, and toxic). This filter level controls how aggressively to filter out potentially harmful content from responses. See the safetySetting documentation and the Responsible AI and usage guidelines for more details.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct ImagenSafetyFilterLevel : ProtoEnum, Sendable

• ImagenSafetySettings

  Settings for controlling the aggressiveness of filtering out sensitive content.

  See the Responsible AI and usage guidelines for more details.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct ImagenSafetySettings

• TextPart

  A text part containing a string value.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct TextPart : Part

• InlineDataPart

  A data part that is provided inline in requests.

  Data provided as an inline data part is encoded as base64 and included directly (inline) in the request. For large files, see FileDataPart which references content by URI instead of including the data in the request.

  Important

  Only small files can be sent as inline data because of limits on total request sizes; see input files and requirements for more details and size limits.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct InlineDataPart : Part

• FileDataPart

  File data stored in Cloud Storage for Firebase, referenced by URI.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct FileDataPart : Part

• FunctionCallPart

  A predicted function call returned from the model.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct FunctionCallPart : Part

• FunctionResponsePart

  Result output from a function call.

  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 FunctionCallPart made based on model prediction.

  Declaration

  Swift

  @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
  public struct FunctionResponsePart : Part