mirror of
https://github.com/firebase/firebase-ios-sdk
synced 2026-11-10 22:45:59 +05:45
Andrew Heard
3796a55fdf
Implemented `GeminiLanguageModel`, providing an adapter for Google's Gemini models conforming to Apple's `FoundationModels.LanguageModel` protocol. This PR includes text to text generation capabilities; other modalities and Gemini features will be handled in follow-up PRs. **Note:** The `GeminiLanguageModel` implementation is guarded by the environment variable `GEMINI_LANGUAGE_MODEL`. By default none of the `GeminiLanguageModel` implementation is included. Key additions: - `GeminiLanguageModel`: Implements `LanguageModel` protocol with reasoning capabilities, configuring execution via `ModelResource` and `EndpointConfiguration`. - `GeminiLanguageModelExecutor`: Converts prompt instructions and history into Gemini streaming requests, yielding responses as `LanguageModelSession.ResponseStream`. - `GeminiTranscriptTranslator`: Translates Apple `Transcript` entries and segments into Gemini `Content` structures while preserving thought signatures and validating supported transcript features. - `GeminiLanguageModel.Error` and `GeminiErrorMapper`: Translates Gemini API, HTTP, and network errors into standard `LanguageModelError` cases (`rateLimited`, `timeout`, `guardrailViolation`, `refusal`, and `unsupportedLanguageOrLocale`) or `GeminiLanguageModel.Error` cases (`serviceUnavailable`, `networkFailure`, `modelNotFound`, `apiError`). The `APIError` payload is designed for seamless forward compatibility with both GenerateContent and the upcoming Interactions API. - Testing infrastructure: Adds `ConditionTrait.requireFoundationModels` to conditionally run Foundation Models tests only on supported platforms (macOS 27+, iOS 27+, watchOS 27+, visionOS 27+), along with shared test constants, mock fixtures, and comprehensive unit and integration test suites.
111 lines
4.4 KiB
Swift
111 lines
4.4 KiB
Swift
// Copyright 2026 Google LLC
|
|
//
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
|
|
import Foundation
|
|
|
|
/// An internal data model for `CountTokensResponse`.
|
|
///
|
|
/// ### Gemini Developer API
|
|
///
|
|
/// Type: `GoogleAiGenerativelanguageV1betaCountTokensResponse`
|
|
///
|
|
/// A response from `CountTokens`.
|
|
///
|
|
/// It returns the model's `token_count` for the `prompt`.
|
|
///
|
|
/// ### Gemini Enterprise Agent Platform
|
|
///
|
|
/// Type: `GoogleCloudAiplatformV1beta1CountTokensResponse`
|
|
///
|
|
/// Response message for PredictionService.CountTokens.
|
|
package struct CountTokensResponse: Codable, Sendable, Equatable, Hashable {
|
|
/// The number of tokens that the `Model` tokenizes the `prompt` into. Always
|
|
///
|
|
/// ### Gemini Developer API
|
|
///
|
|
/// The number of tokens that the `Model` tokenizes the `prompt` into. Always
|
|
/// non-negative.
|
|
///
|
|
/// ### Gemini Enterprise Agent Platform
|
|
///
|
|
/// The total number of tokens counted across all instances from the request.
|
|
package let totalTokens: Int?
|
|
|
|
/// Number of tokens in the cached part of the prompt (the cached content).
|
|
///
|
|
/// ### Gemini Developer API
|
|
///
|
|
/// Number of tokens in the cached part of the prompt (the cached content).
|
|
///
|
|
/// ### Gemini Enterprise Agent Platform
|
|
///
|
|
/// > Important: This property is not supported in the Gemini Enterprise Agent Platform.
|
|
package let cachedContentTokenCount: Int?
|
|
|
|
/// Output only. List of modalities that were processed in the request input.
|
|
package let promptTokensDetails: [ModalityTokenCount]?
|
|
|
|
/// Output only. List of modalities that were processed in the cached content.
|
|
///
|
|
/// ### Gemini Developer API
|
|
///
|
|
/// Output only. List of modalities that were processed in the cached content.
|
|
///
|
|
/// ### Gemini Enterprise Agent Platform
|
|
///
|
|
/// > Important: This property is not supported in the Gemini Enterprise Agent Platform.
|
|
package let cacheTokensDetails: [ModalityTokenCount]?
|
|
|
|
/// The total number of billable characters counted across all instances from
|
|
///
|
|
/// ### Gemini Developer API
|
|
///
|
|
/// > Important: This property is not supported in the Gemini Developer API.
|
|
///
|
|
/// ### Gemini Enterprise Agent Platform
|
|
///
|
|
/// The total number of billable characters counted across all instances from
|
|
/// the request.
|
|
package let totalBillableCharacters: Int?
|
|
|
|
/// Creates a new `CountTokensResponse`.
|
|
///
|
|
/// - Parameters:
|
|
/// - totalTokens: The number of tokens that the `Model` tokenizes the `prompt` into. Always (behavior varies by backend). For more details, see ``totalTokens``.
|
|
/// - cachedContentTokenCount: Number of tokens in the cached part of the prompt (the cached content). (Gemini Developer API only). For more details, see ``cachedContentTokenCount``.
|
|
/// - promptTokensDetails: Output only. List of modalities that were processed in the request input.
|
|
/// - cacheTokensDetails: Output only. List of modalities that were processed in the cached content. (Gemini Developer API only). For more details, see ``cacheTokensDetails``.
|
|
/// - totalBillableCharacters: The total number of billable characters counted across all instances from (Gemini Enterprise Agent Platform only). For more details, see ``totalBillableCharacters``.
|
|
package init(
|
|
totalTokens: Int? = nil,
|
|
cachedContentTokenCount: Int? = nil,
|
|
promptTokensDetails: [ModalityTokenCount]? = nil,
|
|
cacheTokensDetails: [ModalityTokenCount]? = nil,
|
|
totalBillableCharacters: Int? = nil
|
|
) {
|
|
self.totalTokens = totalTokens
|
|
self.cachedContentTokenCount = cachedContentTokenCount
|
|
self.promptTokensDetails = promptTokensDetails
|
|
self.cacheTokensDetails = cacheTokensDetails
|
|
self.totalBillableCharacters = totalBillableCharacters
|
|
}
|
|
enum CodingKeys: String, CodingKey {
|
|
case totalTokens = "totalTokens"
|
|
case cachedContentTokenCount = "cachedContentTokenCount"
|
|
case promptTokensDetails = "promptTokensDetails"
|
|
case cacheTokensDetails = "cacheTokensDetails"
|
|
case totalBillableCharacters = "totalBillableCharacters"
|
|
}
|
|
}
|