An object that represents a back-and-forth chat with a model, capturing the history and saving the context in memory between each message sent.

The Firebase AI SDK provides access to Gemini models directly from your app.

A type that represents a remote multimodal model (like Gemini), with the ability to generate content based on various input types.

A session that handles multi-turn interactions with a generative model, similar to Chat.

A GenerativeModelSession retains history between requests. For single-turn requests to a model, use generativeModelSession(model:tools:instructions:) to start a new session. GenerativeModelSession is particularly useful for generating structured data.

Public Preview: This API is a public preview and may be subject to change.

Example usage:

@Generable
struct UserProfile {
  @Guide(description: "A unique username for the user.")
  var username: String

  @Guide(description: "A short bio about the user, no more than 100 characters.")
  var bio: String

  @Guide(description: "A list of the user's favorite topics.", .count(3))
  var favoriteTopics: [String]
}

let firebaseAI = // ... a `FirebaseAI` instance
let session = firebaseAI.generativeModelSession(model: "gemini-model-name")
let prompt = "Generate a user profile for a cat lover who enjoys hiking."
let response = try await session.respond(to: prompt, generating: UserProfile.self)

print("Username: \(response.content.username)")
print("Bio: \(response.content.bio)")
print("Favorite Topics: \(response.content.favoriteTopics.joined(separator: ", "))")

A type that represents a remote multimodal model (like Gemini), with the ability to generate content based on various input types.

Public Preview: This API is a public preview and may be subject to change.

A multimodal model (like Gemini) capable of real-time content generation based on various input types, supporting bidirectional streaming.

You can create a new session via LiveGenerativeModel/connect().

A live WebSocket session, capable of streaming content to and from the model.

Messages are streamed through responses, and can be sent through either the dedicated realtime API function (such as sendAudioRealtime(_:) and sendTextRealtime(_:)), or through the incremental API (such as sendContent(_:turnComplete:)).

To create an instance of this class, see LiveGenerativeModel.

A 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.