diff --git a/FirebaseAI/CHANGELOG.md b/FirebaseAI/CHANGELOG.md
index ccc1dd6ceea..9bfd0f3b810 100644
--- a/FirebaseAI/CHANGELOG.md
+++ b/FirebaseAI/CHANGELOG.md
@@ -194,7 +194,7 @@
To start using the new SDK, import the `FirebaseAI` module and use the
top-level `FirebaseAI` class. See details in the [migration guide
- ](https://firebase.google.com/docs/vertex-ai/migrate-to-latest-sdk).
+ ](https://firebase.google.com/docs/ai-logic/migrate-to-latest-sdk).
- [fixed] Fixed `ModalityTokenCount` decoding when the `tokenCount` field is
omitted; this occurs when the count is 0. (#14745)
- [fixed] Fixed `Candidate` decoding when `SafetyRating` values are missing a
@@ -229,7 +229,7 @@
# 11.9.0
- [feature] **Public Preview**: Added support for
- [generating images](https://firebase.google.com/docs/vertex-ai/generate-images-imagen?platform=ios)
+ [generating images](https://firebase.google.com/docs/ai-logic/generate-images-imagen?platform=ios)
using the Imagen 3 models.
Note: This feature is in Public Preview, which means that it is not subject to
@@ -263,9 +263,9 @@
Carthage distributions.
- If you're new to this library, visit the
- [getting started guide](http://firebase.google.com/docs/vertex-ai/get-started?platform=ios).
+ [getting started guide](https://firebase.google.com/docs/ai-logic/get-started?platform=ios).
- If you used the preview version of the library, visit the
- [migration guide](https://firebase.google.com/docs/vertex-ai/migrate-to-ga?platform=ios)
+ [migration guide](https://firebase.google.com/docs/ai-logic/migrate-to-ga?platform=ios)
to learn about some important updates.
- [changed] **Breaking Change**: The `HarmCategory` enum is no longer nested
inside the `SafetySetting` struct and the `unspecified` case has been
@@ -366,7 +366,7 @@
instead of the `Any` type. (#13575)
- [added] Added support for specifying a JSON `responseSchema` in
`GenerationConfig`; see
- [control generated output](https://firebase.google.com/docs/vertex-ai/structured-output?platform=ios)
+ [control generated output](https://firebase.google.com/docs/ai-logic/structured-output?platform=ios)
for more details. (#13576)
# 10.29.0
@@ -376,7 +376,7 @@
- [changed] Removed uses of the `gemini-1.5-flash-preview-0514` model in docs
and samples. Developers should now use the auto-updated versions,
`gemini-1.5-pro` or `gemini-1.5-flash`, or a specific stable version; see
- [available model names](https://firebase.google.com/docs/vertex-ai/gemini-models#available-model-names)
+ [available model names](https://firebase.google.com/docs/ai-logic/models#available-model-names)
for more details. (#13099)
- [feature] Added community support for tvOS and visionOS. (#13090, #13092)
@@ -384,7 +384,7 @@
- [changed] Removed uses of the `gemini-1.5-pro-preview-0409` model in docs and
samples. Developers should now use `gemini-1.5-pro-preview-0514` or
`gemini-1.5-flash-preview-0514`; see
- [available model names](https://firebase.google.com/docs/vertex-ai/gemini-models#available-model-names)
+ [available model names](https://firebase.google.com/docs/ai-logic/models#available-model-names)
for more details. (#12979)
- [changed] Logged additional details when required APIs for Vertex AI are
not enabled or response payloads when requests fail. (#13007, #13009)
@@ -392,5 +392,5 @@
# 10.26.0
- [feature] Initial release of the Vertex AI for Firebase SDK (public preview).
Learn how to
- [get started](https://firebase.google.com/docs/vertex-ai/get-started?platform=ios)
+ [get started](https://firebase.google.com/docs/ai-logic/get-started?platform=ios)
with the SDK in your app.
diff --git a/FirebaseAI/Sources/FirebaseAI.swift b/FirebaseAI/Sources/FirebaseAI.swift
index 6234d1b5751..8c7312f937d 100644
--- a/FirebaseAI/Sources/FirebaseAI.swift
+++ b/FirebaseAI/Sources/FirebaseAI.swift
@@ -65,13 +65,13 @@ public final class FirebaseAI: Sendable {
/// Initializes a generative model with the given parameters.
///
- /// - Note: Refer to [Gemini models](https://firebase.google.com/docs/vertex-ai/gemini-models) for
+ /// - Note: Refer to [Gemini models](https://firebase.google.com/docs/ai-logic/models) for
/// guidance on choosing an appropriate model for your use case.
///
/// - Parameters:
/// - modelName: The name of the model to use; see
/// [available model names
- /// ](https://firebase.google.com/docs/vertex-ai/gemini-models#available-model-names) for a
+ /// ](https://firebase.google.com/docs/ai-logic/models#available-model-names) for a
/// list of supported model names.
/// - generationConfig: The content generation parameters your model should use.
/// - safetySettings: A value describing what types of harmful content your model should allow.
@@ -92,7 +92,7 @@ public final class FirebaseAI: Sendable {
&& !modelName.starts(with: GenerativeModel.gemmaModelNamePrefix) {
AILog.warning(code: .unsupportedGeminiModel, """
Unsupported Gemini model "\(modelName)"; see \
- https://firebase.google.com/docs/vertex-ai/models for a list supported Gemini model names.
+ https://firebase.google.com/docs/ai-logic/models for a list of supported Gemini model names.
""")
}
@@ -119,7 +119,7 @@ public final class FirebaseAI: Sendable {
///
/// - Parameters:
/// - name: The name of the model to use; see [available model names
- /// ](https://firebase.google.com/docs/vertex-ai/gemini-models#available-model-names)
+ /// ](https://firebase.google.com/docs/ai-logic/models#available-model-names)
/// for a list of supported model names.
/// - safetySettings: Settings to adjust the safety filters for potentially harmful content
/// generated by the model.
@@ -143,7 +143,7 @@ public final class FirebaseAI: Sendable {
///
/// - Parameters:
/// - model: The name of the model to use; see [available model names
- /// ](https://firebase.google.com/docs/vertex-ai/gemini-models#available-model-names)
+ /// ](https://firebase.google.com/docs/ai-logic/models#available-model-names)
/// for a list of supported model names.
/// - tools: A list of tools that extend the capabilities of the model. These are typically
/// native Gemini ``FirebaseAILogic/Tool``s, such as ``ToolRepresentable/googleSearch(_:)``,
@@ -168,7 +168,7 @@ public final class FirebaseAI: Sendable {
///
/// - Parameters:
/// - model: The name of the model to use; see [available model names
- /// ](https://firebase.google.com/docs/vertex-ai/gemini-models#available-model-names)
+ /// ](https://firebase.google.com/docs/ai-logic/models#available-model-names)
/// for a list of supported model names.
/// - tools: A list of tools that extend the capabilities of the model. These tools must be
/// instances conforming to `FoundationModels.Tool` for automatic function calling.
@@ -310,7 +310,7 @@ public final class FirebaseAI: Sendable {
.allSatisfy({ !$0.isWhitespace && !$0.isNewline && $0 != "/" }) else {
fatalError("""
Invalid model name "\(modelName)" specified; see \
- https://firebase.google.com/docs/vertex-ai/gemini-model#available-models for a list of \
+ https://firebase.google.com/docs/ai-logic/models#available-model-names for a list of \
available models.
""")
}
@@ -328,7 +328,7 @@ public final class FirebaseAI: Sendable {
.allSatisfy({ !$0.isWhitespace && !$0.isNewline && $0 != "/" }) else {
fatalError("""
Invalid location "\(location)" specified; see \
- https://firebase.google.com/docs/vertex-ai/locations?platform=ios#available-locations \
+ https://firebase.google.com/docs/ai-logic/locations?platform=ios#available-locations \
for a list of available locations.
""")
}
diff --git a/FirebaseAI/Sources/GenerateContentResponse.swift b/FirebaseAI/Sources/GenerateContentResponse.swift
index 0abcb3f650a..0fcf8924264 100644
--- a/FirebaseAI/Sources/GenerateContentResponse.swift
+++ b/FirebaseAI/Sources/GenerateContentResponse.swift
@@ -368,7 +368,7 @@ public struct FinishReason: DecodableProtoEnum, Hashable, Sendable {
/// Returns the raw string representation of the `FinishReason` value.
///
/// > Note: This value directly corresponds to the values in the [REST
- /// > API](https://cloud.google.com/vertex-ai/docs/reference/rest/v1beta1/GenerateContentResponse#FinishReason).
+ /// > API](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/rest#FinishReason).
public let rawValue: String
static let unrecognizedValueMessageCode =
@@ -401,7 +401,7 @@ public struct PromptFeedback: Sendable {
/// Returns the raw string representation of the `BlockReason` value.
///
/// > Note: This value directly corresponds to the values in the [REST
- /// > API](https://cloud.google.com/vertex-ai/docs/reference/rest/v1beta1/GenerateContentResponse#BlockedReason).
+ /// > API](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/rest#BlockedReason).
public let rawValue: String
static let unrecognizedValueMessageCode =
diff --git a/FirebaseAI/Sources/GenerationConfig.swift b/FirebaseAI/Sources/GenerationConfig.swift
index e7aca54004a..b31f79fc976 100644
--- a/FirebaseAI/Sources/GenerationConfig.swift
+++ b/FirebaseAI/Sources/GenerationConfig.swift
@@ -67,19 +67,19 @@ public struct GenerationConfig: Sendable, Equatable {
/// Creates a new `GenerationConfig` value.
///
/// See the
- /// [Configure model parameters](https://firebase.google.com/docs/vertex-ai/model-parameters)
+ /// [Configure model parameters](https://firebase.google.com/docs/ai-logic/model-parameters)
/// guide and the
- /// [Cloud documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#generationconfig)
+ /// [Cloud documentation](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/models/inference#generationconfig)
/// for more details.
///
/// - Parameters:
/// - maxOutputTokens: Maximum number of tokens that can be generated in the response.
- /// See the configure model parameters [documentation](https://firebase.google.com/docs/vertex-ai/model-parameters?platform=ios#max-output-tokens)
+ /// See the configure model parameters [documentation](https://firebase.google.com/docs/ai-logic/model-parameters?platform=ios#max-output-tokens)
/// for more details.
/// - stopSequences: A set of up to 5 `String`s that will stop output generation. If specified,
/// the API will stop at the first appearance of a stop sequence. The stop sequence will not
/// be included as part of the response. See the
- /// [Cloud documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#generationconfig)
+ /// [Cloud documentation](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/models/inference#generationconfig)
/// for more details.
/// - responseMIMEType: Output response MIME type of the generated candidate text.
///
@@ -96,12 +96,12 @@ public struct GenerationConfig: Sendable, Equatable {
///
/// Refer to the
/// [Generate structured
- /// output](https://firebase.google.com/docs/vertex-ai/structured-output?platform=ios) guide
+ /// output](https://firebase.google.com/docs/ai-logic/structured-output?platform=ios) guide
/// for more details.
/// - responseModalities: The data types (modalities) that may be returned in model responses.
///
/// See the [multimodal
- /// responses](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal-response-generation)
+ /// responses](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/capabilities/image-generation)
/// documentation for more details.
///
/// > Warning: Specifying response modalities is a **Public Preview** feature, which means
@@ -150,19 +150,19 @@ public struct GenerationConfig: Sendable, Equatable {
/// Creates a new `GenerationConfig` value without deprecated tuning parameters.
///
/// See the
- /// [Configure model parameters](https://firebase.google.com/docs/vertex-ai/model-parameters)
+ /// [Configure model parameters](https://firebase.google.com/docs/ai-logic/model-parameters)
/// guide and the
- /// [Cloud documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#generationconfig)
+ /// [Cloud documentation](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/models/inference#generationconfig)
/// for more details.
///
/// - Parameters:
/// - maxOutputTokens: Maximum number of tokens that can be generated in the response.
- /// See the configure model parameters [documentation](https://firebase.google.com/docs/vertex-ai/model-parameters?platform=ios#max-output-tokens)
+ /// See the configure model parameters [documentation](https://firebase.google.com/docs/ai-logic/model-parameters?platform=ios#max-output-tokens)
/// for more details.
/// - stopSequences: A set of up to 5 `String`s that will stop output generation. If specified,
/// the API will stop at the first appearance of a stop sequence. The stop sequence will not
/// be included as part of the response. See the
- /// [Cloud documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#generationconfig)
+ /// [Cloud documentation](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/models/inference#generationconfig)
/// for more details.
/// - responseMIMEType: Output response MIME type of the generated candidate text.
///
@@ -179,12 +179,12 @@ public struct GenerationConfig: Sendable, Equatable {
///
/// Refer to the
/// [Generate structured
- /// output](https://firebase.google.com/docs/vertex-ai/structured-output?platform=ios) guide
+ /// output](https://firebase.google.com/docs/ai-logic/structured-output?platform=ios) guide
/// for more details.
/// - responseModalities: The data types (modalities) that may be returned in model responses.
///
/// See the [multimodal
- /// responses](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal-response-generation)
+ /// responses](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/capabilities/image-generation)
/// documentation for more details.
///
/// > Warning: Specifying response modalities is a **Public Preview** feature, which means
diff --git a/FirebaseAI/Sources/Protocols/Public/LanguageModelProvider.swift b/FirebaseAI/Sources/Protocols/Public/LanguageModelProvider.swift
index 8d12fb92ee6..63c8a52c983 100644
--- a/FirebaseAI/Sources/Protocols/Public/LanguageModelProvider.swift
+++ b/FirebaseAI/Sources/Protocols/Public/LanguageModelProvider.swift
@@ -31,7 +31,7 @@
///
/// - Parameters:
/// - name: The name of the model to use; see [available model names
- /// ](https://firebase.google.com/docs/vertex-ai/gemini-models#available-model-names)
+ /// ](https://firebase.google.com/docs/ai-logic/models#available-model-names)
/// for a list of supported model names.
/// - safetySettings: Settings to adjust the safety filters for potentially harmful content
/// generated by the model.
diff --git a/FirebaseAI/Sources/Safety.swift b/FirebaseAI/Sources/Safety.swift
index 8b4366e8fae..f0ca9c4188b 100644
--- a/FirebaseAI/Sources/Safety.swift
+++ b/FirebaseAI/Sources/Safety.swift
@@ -35,7 +35,7 @@ public struct SafetyRating: Equatable, Hashable, Sendable {
///
/// The probability safety score is a confidence score between 0.0 and 1.0, rounded to one decimal
/// place; it is discretized into a ``HarmProbability`` in ``probability``. See [probability
- /// scores](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/configure-safety-filters#comparison_of_probability_scores_and_severity_scores)
+ /// scores](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/capabilities/configure-safety-filters#comparison_of_probability_scores_and_severity_scores)
/// in the Google Cloud documentation for more details.
public let probabilityScore: Float
@@ -48,7 +48,7 @@ public struct SafetyRating: Equatable, Hashable, Sendable {
/// The severity score is the magnitude of how harmful a model response might be.
///
/// The severity score ranges from 0.0 to 1.0, rounded to one decimal place; it is discretized
- /// into a ``HarmSeverity`` in ``severity``. See [severity scores](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/configure-safety-filters#comparison_of_probability_scores_and_severity_scores)
+ /// into a ``HarmSeverity`` in ``severity``. See [severity scores](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/capabilities/configure-safety-filters#comparison_of_probability_scores_and_severity_scores)
/// in the Google Cloud documentation for more details.
public let severityScore: Float
@@ -105,7 +105,7 @@ public struct SafetyRating: Equatable, Hashable, Sendable {
/// Returns the raw string representation of the `HarmProbability` value.
///
/// > Note: This value directly corresponds to the values in the [REST
- /// > API](https://cloud.google.com/vertex-ai/docs/reference/rest/v1beta1/GenerateContentResponse#SafetyRating).
+ /// > API](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/rest#SafetyRating).
public let rawValue: String
static let unrecognizedValueMessageCode =
@@ -140,7 +140,7 @@ public struct SafetyRating: Equatable, Hashable, Sendable {
/// Returns the raw string representation of the `HarmSeverity` value.
///
/// > Note: This value directly corresponds to the values in the [REST
- /// > API](https://cloud.google.com/vertex-ai/docs/reference/rest/v1beta1/GenerateContentResponse#HarmSeverity).
+ /// > API](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/rest#HarmSeverity).
public let rawValue: String
static let unrecognizedValueMessageCode =
@@ -152,7 +152,7 @@ public struct SafetyRating: Equatable, Hashable, Sendable {
/// fallback response instead of generated content.
///
/// See [safety settings for Gemini
-/// models](https://firebase.google.com/docs/vertex-ai/safety-settings?platform=ios#gemini) for
+/// models](https://firebase.google.com/docs/ai-logic/safety-settings?platform=ios#gemini) for
/// more details.
public struct SafetySetting: Sendable, Hashable {
/// Block at and beyond a specified ``SafetyRating/HarmProbability``.
@@ -221,7 +221,7 @@ public struct SafetySetting: Sendable, Hashable {
/// - threshold: The threshold describing what content should be blocked.
/// - method: The method of computing whether the threshold has been exceeded; if not specified,
/// the default method is ``HarmBlockMethod/severity`` for most models. See [harm block
- /// methods](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/configure-safety-filters#how_to_configure_safety_filters)
+ /// methods](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/capabilities/configure-safety-filters#how_to_configure_safety_filters)
/// in the Google Cloud documentation for more details.
/// > Note: For models older than `gemini-1.5-flash` and `gemini-1.5-pro`, the default method
/// > is ``HarmBlockMethod/probability``.
@@ -265,7 +265,7 @@ public struct HarmCategory: CodableProtoEnum, Hashable, Sendable {
/// Returns the raw string representation of the `HarmCategory` value.
///
/// > Note: This value directly corresponds to the values in the
- /// > [REST API](https://cloud.google.com/vertex-ai/docs/reference/rest/v1beta1/HarmCategory).
+ /// > [REST API](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/rest).
public let rawValue: String
static let unrecognizedValueMessageCode =
diff --git a/FirebaseAI/Sources/Tool.swift b/FirebaseAI/Sources/Tool.swift
index 809448d2140..73e072652dc 100644
--- a/FirebaseAI/Sources/Tool.swift
+++ b/FirebaseAI/Sources/Tool.swift
@@ -249,7 +249,7 @@ public extension ToolRepresentable where Self == FirebaseAILogic.Tool {
/// was trained (for example, the current date or weather conditions) or to allow it to interact
/// with external systems (for example, making an API request or querying/updating a database).
/// For more details and use cases, see [Function calling using the Gemini
- /// API](http://firebase.google.com/docs/vertex-ai/function-calling?platform=ios).
+ /// API](https://firebase.google.com/docs/ai-logic/function-calling?platform=ios).
///
/// - Parameters:
/// - functionDeclarations: A list of `FunctionDeclarations` available to the model that can be
diff --git a/FirebaseAI/Sources/Types/Internal/ProtoDate.swift b/FirebaseAI/Sources/Types/Internal/ProtoDate.swift
index e6a8accd310..352e25786ab 100644
--- a/FirebaseAI/Sources/Types/Internal/ProtoDate.swift
+++ b/FirebaseAI/Sources/Types/Internal/ProtoDate.swift
@@ -24,7 +24,7 @@ import Foundation
/// - A year and month value, with a zero day, such as a credit card expiration date
///
/// This represents a
-/// [`google.type.Date`](https://cloud.google.com/vertex-ai/docs/reference/rest/Shared.Types/Date).
+/// [`google.type.Date`](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/rest/Shared.Types/Date).
struct ProtoDate {
/// Year of the date.
///
diff --git a/FirebaseAI/Sources/Types/Public/Backend.swift b/FirebaseAI/Sources/Types/Public/Backend.swift
index 6566a4b85db..f2e02464bcc 100644
--- a/FirebaseAI/Sources/Types/Public/Backend.swift
+++ b/FirebaseAI/Sources/Types/Public/Backend.swift
@@ -19,7 +19,7 @@ public struct Backend {
/// Initializes a `Backend` configured for the Gemini API in Vertex AI.
///
/// Defaults to the location `us-central1`; see
- /// [Vertex AI locations](https://firebase.google.com/docs/vertex-ai/locations?platform=ios#available-locations)
+ /// [Agent Platform locations](https://firebase.google.com/docs/ai-logic/locations?platform=ios#available-locations)
/// for a list of supported locations.
@available(*, deprecated, message: """
Use agentPlatform(location:) instead; note that the default location is now "global" instead of "us-central1"
@@ -37,7 +37,7 @@ public struct Backend {
///
/// - Parameters:
/// - location: The region identifier; see
- /// [Vertex AI locations](https://firebase.google.com/docs/vertex-ai/locations?platform=ios#available-locations)
+ /// [Agent Platform locations](https://firebase.google.com/docs/ai-logic/locations?platform=ios#available-locations)
/// for a list of supported locations.
@available(*, deprecated, renamed: "agentPlatform(location:)", message: """
Vertex AI has been renamed to the Agent Platform Gemini API.
@@ -57,7 +57,7 @@ public struct Backend {
///
/// - Parameters:
/// - location: The region identifier, defaulting to `global`; see
- /// [Vertex AI locations](https://firebase.google.com/docs/vertex-ai/locations?platform=ios#available-locations)
+ /// [Agent Platform locations](https://firebase.google.com/docs/ai-logic/locations?platform=ios#available-locations)
/// for a list of supported locations.
public static func agentPlatform(location: String = "global") -> Backend {
return Backend(
diff --git a/FirebaseAI/Sources/Types/Public/Live/LiveGenerationConfig.swift b/FirebaseAI/Sources/Types/Public/Live/LiveGenerationConfig.swift
index 7d701537e44..cef3991083f 100644
--- a/FirebaseAI/Sources/Types/Public/Live/LiveGenerationConfig.swift
+++ b/FirebaseAI/Sources/Types/Public/Live/LiveGenerationConfig.swift
@@ -26,19 +26,19 @@ public struct LiveGenerationConfig: Sendable {
/// Creates a new ``LiveGenerationConfig`` value.
///
/// See the
- /// [Configure model parameters](https://firebase.google.com/docs/vertex-ai/model-parameters)
+ /// [Configure model parameters](https://firebase.google.com/docs/ai-logic/model-parameters)
/// guide and the
- /// [Cloud documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#generationconfig)
+ /// [Cloud documentation](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/models/inference#generationconfig)
/// for more details.
///
/// - Parameters:
/// - maxOutputTokens: Maximum number of tokens that can be generated in the response.
- /// See the configure model parameters [documentation](https://firebase.google.com/docs/vertex-ai/model-parameters?platform=ios#max-output-tokens)
+ /// See the configure model parameters [documentation](https://firebase.google.com/docs/ai-logic/model-parameters?platform=ios#max-output-tokens)
/// for more details.
/// - responseModalities: The data types (modalities) that may be returned in model responses.
///
/// See the [multimodal
- /// responses](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal-response-generation)
+ /// responses](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/capabilities/image-generation)
/// documentation for more details.
///
/// > Warning: Specifying response modalities is a **Public Preview** feature, which means
@@ -104,19 +104,19 @@ public struct LiveGenerationConfig: Sendable {
/// Creates a new `LiveGenerationConfig` value.
///
/// See the
- /// [Configure model parameters](https://firebase.google.com/docs/vertex-ai/model-parameters)
+ /// [Configure model parameters](https://firebase.google.com/docs/ai-logic/model-parameters)
/// guide and the
- /// [Cloud documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#generationconfig)
+ /// [Cloud documentation](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/models/inference#generationconfig)
/// for more details.
///
/// - Parameters:
/// - maxOutputTokens: Maximum number of tokens that can be generated in the response.
- /// See the configure model parameters [documentation](https://firebase.google.com/docs/vertex-ai/model-parameters?platform=ios#max-output-tokens)
+ /// See the configure model parameters [documentation](https://firebase.google.com/docs/ai-logic/model-parameters?platform=ios#max-output-tokens)
/// for more details.
/// - responseModalities: The data types (modalities) that may be returned in model responses.
///
/// See the [multimodal
- /// responses](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal-response-generation)
+ /// responses](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/capabilities/image-generation)
/// documentation for more details.
///
/// > Warning: Specifying response modalities is a **Public Preview** feature, which means
diff --git a/FirebaseAI/Sources/Types/Public/Live/LiveServerGoingAwayNotice.swift b/FirebaseAI/Sources/Types/Public/Live/LiveServerGoingAwayNotice.swift
index bafe3dc2882..63b067ac1d1 100644
--- a/FirebaseAI/Sources/Types/Public/Live/LiveServerGoingAwayNotice.swift
+++ b/FirebaseAI/Sources/Types/Public/Live/LiveServerGoingAwayNotice.swift
@@ -16,7 +16,7 @@ import Foundation
/// Server will not be able to service client soon.
///
-/// To learn more about session limits, see the docs on [Maximum session duration](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/multimodal-live#maximum-session-duration)\.
+/// To learn more about session limits, see the docs on [Maximum session duration](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/models/multimodal-live#maximum-session-duration).
@available(watchOS, unavailable)
public struct LiveServerGoingAwayNotice: Sendable {
let goAway: GoAway
diff --git a/FirebaseAI/Sources/Types/Public/Live/LiveSession.swift b/FirebaseAI/Sources/Types/Public/Live/LiveSession.swift
index b60a42afacf..a4fa92a987f 100644
--- a/FirebaseAI/Sources/Types/Public/Live/LiveSession.swift
+++ b/FirebaseAI/Sources/Types/Public/Live/LiveSession.swift
@@ -53,7 +53,7 @@ public final class LiveSession: Sendable {
///
/// To learn more about audio formats, and the required state they should be provided in, see the
/// docs on
- /// [Supported audio formats](https://cloud.google.com/vertex-ai/generative-ai/docs/live-api#supported-audio-formats).
+ /// [Supported audio formats](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/live-api#supported-audio-formats).
///
/// - Parameters:
/// - audio: Raw 16-bit PCM audio at 16Hz, used to update the model on the client's
diff --git a/FirebaseAI/Sources/Types/Public/Part.swift b/FirebaseAI/Sources/Types/Public/Part.swift
index a8a71c43afc..e8f3749a669 100644
--- a/FirebaseAI/Sources/Types/Public/Part.swift
+++ b/FirebaseAI/Sources/Types/Public/Part.swift
@@ -60,7 +60,7 @@ public struct TextPart: Part {
/// > Important: Only small files can be sent as inline data because of limits on total request
/// sizes;
/// see [input files and requirements
-/// ](https://firebase.google.com/docs/vertex-ai/input-file-requirements#provide-file-as-inline-data)
+/// ](https://firebase.google.com/docs/ai-logic/input-file-requirements#provide-file-as-inline-data)
/// for more details and size limits.
public struct InlineDataPart: Part {
let inlineData: InlineData
@@ -79,16 +79,16 @@ public struct InlineDataPart: Part {
/// Creates an inline data part from data and a MIME type.
///
/// > Important: Supported input types depend on the model on the model being used; see [input
- /// files and requirements](https://firebase.google.com/docs/vertex-ai/input-file-requirements)
+ /// files and requirements](https://firebase.google.com/docs/ai-logic/input-file-requirements)
/// for more details.
///
/// - Parameters:
/// - data: The data representation of an image, video, audio or document; see [input files and
- /// requirements](https://firebase.google.com/docs/vertex-ai/input-file-requirements) for
+ /// requirements](https://firebase.google.com/docs/ai-logic/input-file-requirements) for
/// supported media types.
/// - mimeType: The IANA standard MIME type of the data, for example, `"image/jpeg"` or
/// `"video/mp4"`; see [input files and
- /// requirements](https://firebase.google.com/docs/vertex-ai/input-file-requirements) for
+ /// requirements](https://firebase.google.com/docs/ai-logic/input-file-requirements) for
/// supported values.
public init(data: Data, mimeType: String) {
self.init(InlineData(data: data, mimeType: mimeType), isThought: nil, thoughtSignature: nil)
@@ -118,7 +118,7 @@ public struct FileDataPart: Part {
/// `"gs://bucket-name/path/image.jpg"`.
/// - mimeType: The IANA standard MIME type of the uploaded file, for example, `"image/jpeg"`
/// or `"video/mp4"`; see [supported input files and
- /// requirements](https://firebase.google.com/docs/vertex-ai/input-file-requirements) for
+ /// requirements](https://firebase.google.com/docs/ai-logic/input-file-requirements) for
/// supported values.
public init(uri: String, mimeType: String) {
self.init(FileData(fileURI: uri, mimeType: mimeType), isThought: nil, thoughtSignature: nil)
diff --git a/FirebaseAI/Sources/Types/Public/ResponseModality.swift b/FirebaseAI/Sources/Types/Public/ResponseModality.swift
index 080dbf89ec9..6df5cbee7a3 100644
--- a/FirebaseAI/Sources/Types/Public/ResponseModality.swift
+++ b/FirebaseAI/Sources/Types/Public/ResponseModality.swift
@@ -18,7 +18,7 @@ import Foundation
///
/// To configure the desired output modalities for model requests, set the `responseModalities`
/// parameter when initializing a ``GenerationConfig``. See the [multimodal
-/// responses](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal-response-generation)
+/// responses](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/capabilities/image-generation)
/// documentation for more details.
///
/// > Important: Support for each response modality, or combination of modalities, depends on the
@@ -40,7 +40,7 @@ public struct ResponseModality: EncodableProtoEnum, Sendable, Equatable {
///
/// Use this modality when you want the model to create visual content based on the provided input
/// or prompts. The response might contain one or more generated images. See the [image
- /// generation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal-response-generation#image-generation)
+ /// generation](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/capabilities/image-generation#image-generation)
/// documentation for more details.
///
/// > Warning: Image generation using Gemini 2.0 Flash is a **Public Experimental** feature, which