Liquid4All · iamstuffed · Mar 27, 2026 · Mar 27, 2026 · Mar 27, 2026
@@ -164,4 +164,5 @@ Thumbs.db
 env
 env/*
 
-__pycache__/
+__pycache__/
+devlog/
@@ -3,6 +3,11 @@
 description: "API reference for constrained generation and function calling in the LEAP Android SDK"
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 ## Constrained Generation
 
 Please refer to [Constrained Generation](./constrained-generation) guide on detailed usage.
@@ -28,7 +33,7 @@
 - `klass`: the Kotlin class object created from `T::class`. It must be a data class annotated with `Generatable`.
 - `indentSpaces`: a non null value will format the JSON output into a pretty style with the given indent spaces.

 If the data class cannot be supported or any other issues blocking the generation of JSONSchema, an `LeapGeneratableSchematizationException` will be thrown.

 ### GeneratableFactory

@@ -53,8 +58,8 @@

 The single parameter version can be called if the returned data type can be inferred from the context. It's only a wrapper of the complete version.

 - `jsonObject`: the JSON object as the data source for creating the generatable data class instance.
 - `klass`: the Koltin class object created from `T::class`. It must be a data class annotated with `Generatable`.

 ### Annotations

@@ -68,7 +73,7 @@
 annotation class Guide(val description: String)
 ```

 `Generatable` annotation is for the data class to be used as the generation constraints. `Guide` is for the fields of the generatable data class to add helpful
 descriptions for the fields.

 ## Function Calling
@@ -104,7 +109,7 @@
 )
 ```

 - `name` Name of the paramter.
 - `type` Data type of the parameter.
 - `description` A human and LLM readable description for the parameter.
 - `optional`: Whether this parameter is optional.
@@ -152,7 +157,7 @@
 ```

 - `name` Name of the function to be called
 - `arguments` The arguments (parameters) of this call in a map. Values could be strings, numbers, booleans, null, lists for arrays, or maps for objects.

 ### LeapFunctionCallParser


@@ -3,6 +3,11 @@
 description: "Complete reference for using the LEAP Android SDK"
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 ## Core Architecture
 
 ```
@@ -17,7 +22,7 @@

 ## Installation

 ### Gradle Dependencies

 **Recommended**: Use version catalog for dependency management.

@@ -139,7 +144,7 @@
 }
 ```

 Available models and quantizations: [LEAP Model Library](https://leap.liquid.ai/models)

 ### Method 2: Download Without Loading

@@ -197,7 +202,7 @@

 ### Method 3: Cross-Platform LeapDownloader

 For Kotlin Multiplatform projects (iOS, macOS, JVM, Android):

 ```kotlin
 import ai.liquid.leap.LeapDownloader
@@ -447,7 +452,7 @@
 **Methods**:
 - `createConversation(systemPrompt: String? = null): Conversation` - Start new chat
 - `createConversationFromHistory(history: List<ChatMessage>): Conversation` - Restore chat
 - `suspend fun unload()` - Free memory (MUST call in onCleared with runBlocking)

 ### Conversation
 Manages chat history and generation state.
@@ -622,7 +627,7 @@
 }
 ```

 ## Multimodal Input

 ### Vision (Image + Text)
 ```kotlin
@@ -681,7 +686,7 @@
 - **LFM2-1.2B**: Stable version
 - **LFM2-1.2B-Tool**: Optimized for function calling

 ### Multimodal Models
 - **LFM2.5-VL-1.6B**: Vision + text
 - **LFM2.5-Audio-1.5B**: Audio + text (TTS, ASR, voice chat)

@@ -902,7 +907,7 @@

 ### Model won't load
 - Check internet connection (first download)
 - Verify minSdk = 31 in build.gradle.kts
 - Use physical device (emulators may crash)
 - Check storage space (models: 500MB-2GB)

@@ -917,6 +922,6 @@
 - Check sample rate (16kHz recommended)

 ### Memory issues
 - Call `modelRunner?.unload()` in onCleared
 - Don't load multiple models simultaneously
 - Use appropriate quantization (Q4_K_M recommended)
@@ -3,6 +3,11 @@
 description: "Get up and running with the LEAP Android SDK in minutes. Install the SDK, load models, and start generating content."
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 Latest version: `v0.9.7`
 
 <Info>
@@ -99,7 +104,7 @@
 The SDK uses **GGUF manifests** for loading models (recommended for all new projects due to superior inference performance and better default generation parameters).

 <Info>
 Legacy Executorch bundle support is available in the accordion below for existing projects.
 </Info>

 ## Loading from GGUF Manifest
@@ -108,7 +113,7 @@

 ### Android: Using LeapModelDownloader (Recommended)

 For Android, `LeapModelDownloader` provides the best experience with background downloads, WorkManager integration, and notification support. This function takes some time to finish as loading the model is a heavy I/O operation, but it is safe to call on the main thread. The function should be executed in a coroutine scope.

 **ViewModel**

@@ -302,7 +307,7 @@

  ### Loading from local bundle file

  The `LeapClient.loadModel` suspend function loads a model bundle file and returns a model runner instance for invoking the model. This function takes some time to finish as loading the model is a heavy I/O operation, but it is safe to call on the main thread. The function should be executed in a coroutine scope.

  ```kotlin
  lifecycleScope.launch {

@@ -4,8 +4,13 @@
 sidebar_position: 5
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 If you are familiar with cloud-based AI APIs (e.g. [OpenAI API](https://openai.com/api/)), this document
 shows the similarity and differences between these clould APIs and Leap.
 
 We will inspect this piece of Python-based OpenAI API chat completion request to figure out how to migrate it to LeapSDK.
 This example code is modified from [OpenAI API documentation](https://platform.openai.com/docs/guides/streaming-responses?api-mode=chat).
@@ -138,10 +143,10 @@
 }.collect()
 ```

 ## Coroutine scope

 Hopefully by now it is clear how similar LeapSDK API is to cloud-based APIs. It is worth noting that most LeapSDK
 Android APIs are based on [Kotlin coroutine](https://kotlinlang.org/docs/coroutines-basics.html). You will need to use
 a coroutine scope to execute these functions. In Android, we recommend using `viewModelScope` in a ViewModel:

 ```kotlin

@@ -4,6 +4,11 @@
 sidebar_position: 3
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 Setting the `jsonSchemaConstraint` field in [`GenerationOptions`](./conversation-generation#generationoptions) will enable constrained generation. While it is possible to
 directly set the constraint with raw JSON Schema strings, we recommend to create the constraints with the `Generatable` annotation.
 
@@ -18,7 +23,7 @@

 Only Kotlin data classes can be annotated with `Generatable`, and all the fields of the data class should be declared in the parameter of the constructor. `Guide` annotation can be used to add further descriptions to the fields.

 For example, here is a generatable data class for holding information of a city:

 ```kotlin
 @Generatable(description="Facts about a city")
@@ -37,7 +42,7 @@
 )
 ```

 ## Apply Generatable data class in GenerationOptions

 Then we can use `setResponseFormatType()` in `GenerationOptions` to set up the constraint.

@@ -53,7 +58,7 @@
 conversation.generateResponse("Show the city facts about Tokyo", options)
 ```

 If you want to add the JSON Schema into the prompt to help the generation, you can get the raw JSONSchema with `JSONSchemaGenerator`:

 ```kotlin
 val jsonSchema = JSONSchemaGenerator.getJSONSchema(CityFact::class)
@@ -67,9 +72,9 @@

 If the JSON Schema cannot be created from the provided data class, a `LeapGeneratableSchematizationException` will be thrown.

 ## Deserialize Generatable data class

 Finally, you can use `GeneratableFactory.createFromJSONObject()` to deserialize the JSON string generated by the model into the generatable data class:

 ```kotlin
 import ai.liquid.leap.structuredoutput.GeneratableFactory
@@ -90,7 +95,7 @@
 }.collect()
 ```

 If the JSON string generated by the model is not valid for creating instances of the generatable data class, a `LeapGeneratableDeserializationException` will be thrown.

 ## Supported data types

@@ -101,7 +106,7 @@
 - Number (`Float` and `Double` in Kotlin)
 - Boolean (`Boolean` in Kotlin)
 - Enum (Enum class in Kotlin. The plain name string will be used as values)
 - Object (Any data classes annotated with [Generatable])
 - Array (`List` and `MutableList` of any other supported data types, and arrays of integer, float numbers and boolean in Kotlin)

 Only if the data types of the fields of object types and the items of array types are supported, these composition data types can be supported.
@@ -3,6 +3,11 @@
 description: "API reference for conversations, model runners, and generation in the LEAP Android SDK"
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 <Info>
 All functions listed in this document are safe to call from the main or UI thread and all callbacks will be run on the main thread, unless there are explicit instructions or explanations.
 </Info>
@@ -78,7 +83,7 @@

 ### Cancellation of the generation

 Generation will be stopped when the coroutine job that runs the flow is canceled, but it may (no guarantee) keep going as long as the job of the flow is still active.

 We highly recommend using a ViewModel with `viewModelScope` to manage generation lifecycle. The generation will be automatically canceled when the ViewModel is cleared. Here is an example:

@@ -225,7 +230,7 @@

 ### `generateFromConversation`

 This function is **not** recommended to be called by the app directly. It is an internal interface for the model runner implementation to expose the generation ability to LEAP SDK. `Conversation.generateResponse` is the better wrapper of this method, which relies on Kotlin coroutines to connect with lifecycle-aware components.

 <Warning>
 This function may block the caller thread. If you must use it, please call it outside the main

@@ -4,6 +4,11 @@
 sidebar_position: 4
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 <Warning>
 Not all models support function calling. Please check the model card before using the model for function calling.
 </Warning>
@@ -31,7 +36,7 @@
 )
 ```

 Generally speaking, function names and parameter names should be normal identifiers that are recongized by most common programming languages (e.g. Python, Javascript, etc).
 We recommend to use descriptive names that are composed by only letters, underscores and digits (not as the beginning).

 ## Handle Function Calling Response
@@ -106,7 +111,7 @@
 )
 ```

 `name` is the function name. It is recommneded to use only English letters, underscores and digits (not to start with digits) to compose the
 function names because this format is supported by most models. `description` tells the model what this function is doing. `parameters` is
 the ordered list to declare what arguments (parameters) this function accepts.

@@ -126,7 +131,7 @@
 - `description` Tells the model what this parameter is about.
 - `optional` Whether the function is optional.

 `LeapFunctionParameterType` describes the data types of the parameteres. They will be translated into JSON Schema for model to understand.
 Following types are supported:

 ```kotlin
@@ -150,7 +155,7 @@
 - `Object`: Objects which has its own properties. `properties` is the map between the property names to the property data types. `required` list contains the name of
  all non-optional properties.

 All fields accepts an optional parameter of `description`, but it will be overrided if it is directly used as `LeapFunctionParameter.type`. It only plays a role if
 the type instance is used as `Array.itemType` or the types in object properties.

 For any type that accepts a parameter of `enumValues`, this parameter provides the instructions to the models on the legit values to fill.

@@ -3,6 +3,11 @@
 description: "API reference for chat messages and content types in the LEAP Android SDK"
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 ## `ChatMessage`
 
 Data class that is compatible with the message object in OpenAI chat completion API.
@@ -38,7 +43,7 @@
 Construct a `ChatMessage` instance from a `JSONObject`. Not all JSON object variants in `ChatCompletionRequestMessage` of OpenAI API are acceptable. As of now, `role` supports `user`, `system` and `assistant`; `content` can be a string or an array.

 <Info>
 `LeapSerializationException` will be thrown if the provided JSONObject cannot be recognized as a
 message.
 </Info>

@@ -86,7 +91,7 @@
 - `Audio`: WAV-encoded audio content

 <Info>
 `LeapSerializationException` will be thrown if the provided JSONObject cannot be recognized as a
 message.
 </Info>

@@ -135,7 +140,7 @@
 | Property | Required Value | Notes |
 |----------|---------------|-------|
 | **Format** | WAV (RIFF) | Only WAV format is supported |
 | **Sample Rate** | 16000 Hz (16 kHz) recommended | Other sample rates are automatically resampled to 16 kHz |
 | **Encoding** | PCM (various bit depths) | Supports Float32, Int16, Int24, Int32 |
 | **Channels** | Mono (1 channel) | **Required** - stereo audio will be rejected |
 | **Byte Order** | Little-endian | Standard WAV format |
@@ -151,7 +156,7 @@
 </Warning>

 <Info>
 **Automatic Resampling**: The inference engine automatically resamples audio to 16 kHz if provided at a different sample rate. However, for best performance and quality, provide audio at 16 kHz to avoid resampling overhead.
 </Info>

 <Warning>

@@ -3,6 +3,11 @@
 description: "API reference for loading models in the LEAP SDK"
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 <Info>
 The LEAP SDK is now **Kotlin Multiplatform** and provides two model loading options:
 - **`LeapModelDownloader`** - Android-specific, recommended for Android apps (background downloads, notifications, WorkManager)
@@ -104,7 +109,7 @@
 The `LeapDownloader` class is a **cross-platform** model loader available in the core `leap-sdk` module. It works on Android, iOS, macOS, and JVM platforms. Use this for:
 - iOS and macOS applications
 - JVM/Desktop applications
 - Cross-platform Kotlin Multiplatform code
 - Android apps that don't need background download features

 ```kotlin
@@ -113,7 +118,7 @@

 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `config` | `LeapDownloaderConfig` | No | `LeapDownloaderConfig()` | Configuration options for the downloader. See [`LeapDownloaderConfig`](#leapdownloaderconfig) for more details. |

 <br/>
 ### `loadModel`
@@ -233,7 +238,7 @@

  - `path`: A local path pointing to model bundle file. Both `.bundle` files and `.gguf` files are supported.
  - `options`: Options for loading the model.
  - `mmprojPath`: Optional multimodal projection model path. This parameter should only be filled if the model needs a separate multimodal projection model to parsing multimodal (image, audio, etc.) contents.

  <Info>
  The function will throw `LeapModelLoadingException` if LEAP fails to load the model.
@@ -253,9 +258,9 @@
  ```

  - `modelPath`: Main model path.
  - `mmprojPath`: Multimodal projection model path.
  - `audioDecoderPath`: Audio decoder model path.
  - `audioTokenizerPath`: Audio tokenizer model path.

  ### `loadModelAsResult`


@@ -3,6 +3,11 @@
 description: "API reference for error handling, serialization, and utilities in the LEAP Android SDK"
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 ## Error Handling
 
 All errors are thrown as `LeapException`, which has following subclasses:
@@ -10,11 +15,11 @@
 - `LeapModelLoadingException` : error in loading the model
 - `LeapGenerationException` : error in generating content
 - `LeapGenerationPromptExceedContextLengthException`: the prompt text exceeds the maximum context length so no content will be generated
 - `LeapSerializationException` : error in serializing / deserializing data.

 ## Serialization Support

 The LEAP SDK uses [kotlinx.serialization](https://github.com/Kotlin/kotlinx.serialization) for JSON serialization and deserialization. This is built into the core SDK and requires no additional dependencies.

 The following types are `@Serializable`:

@@ -23,7 +28,7 @@
 - [`LeapFunctionCall`](./function-calling)
 - [`Manifest`](./model-loading#manifest)

 ### Serializing and Deserializing Conversation History

 **Add kotlinx.serialization to your project:**

@@ -84,11 +89,11 @@
 `LeapModelDownloader` is the **recommended** option for Android applications. It provides background downloads with WorkManager, foreground service notifications, and robust handling of network interruptions.
 </Info>

 The LeapSDK Android Model Downloader module is a production-ready helper for downloading models from the LEAP Model Library on Android. It runs as a [foreground service](https://developer.android.com/develop/background-work/services/fgs) and displays notifications to users during downloads.

 ### Permission Setup

 The model downloader requires notification permissions to display download progress. You need to:

 1. **Add permissions to AndroidManifest.xml**:
 ```xml
@@ -184,7 +189,7 @@
  fun getModelFile(model: DownloadableModel): File
  fun requestDownloadModel(model: DownloadableModel, forceDownload: Boolean = false)
  fun requestStopDownload(model: DownloadableModel)
  suspend fun queryStatus(model: DownloadableModel): ModelDownloadStatus
  fun requestStopService()
 }
 ```
@@ -205,7 +210,7 @@
 Make a request to download the model. If the model file already exists locally, it won't be downloaded.

 - `model`: A [`DownloadableModel`](#downloadablemodel) instance.
 - `forceDownload`: If it's true, downloader will remove the model bundle file that exists locally and to conduct the download.

 #### requestStopDownload

@@ -236,11 +241,11 @@

 #### requestStopService

 Make a request to stop the foreground service of the model downloader.

 ### DownloadableModel

 `DownloadableModel` is an interface to describe the model can be downloaded by the LeapSDK Model Downloader.

 ```kotlin
 interface DownloadableModel {
@@ -271,4 +276,4 @@
 The `resolve` method accepts 2 parameters:

 - `modelSlug`: The model slug that identifies the model. It is usually the lowercase string of the model name. For example, the slug of `LFM2-1.2B` is `lfm2-1.2b`.
 - `quantizationSlug`: The model quantization slug. It can be found in the "Available quantizations" section of the model card.
@@ -3,6 +3,11 @@
 description: "API reference for constrained generation and function calling in the LEAP iOS SDK"
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 ## `GenerationOptions`
 
 Tune generation behavior with `GenerationOptions`.
@@ -28,7 +33,7 @@
 ```

 - Leave a field as `nil` to fall back to the defaults packaged with the model bundle.
 - `functionCallParser` controls how tool-call tokens are parsed. `LFMFunctionCallParser` (the default) handles Liquid Foundation Model Pythonic function calling. Supply `HermesFunctionCallParser()` for Hermes/Qwen3 formats, or set the parser to `nil` to receive raw tool-call text in `MessageResponse.chunk`.
 - `jsonSchemaConstraint` activates constrained generation. Use `setResponseFormat(type:)` to populate it from a type annotated with the `@Generatable` macro.

 ```swift

@@ -3,6 +3,11 @@
 description: "Complete reference for using the LEAP iOS SDK"
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 ## Core Architecture
 
 ```
@@ -66,7 +71,7 @@
 }
 ```

 Available models and quantizations: [LEAP Model Library](https://leap.liquid.ai/models)

 ### Method 2: Download Without Loading

@@ -424,7 +429,7 @@
 }
 ```

 ### Multimodal Input (Vision)

 ```swift
 func sendImageMessage(image: UIImage, prompt: String) {
@@ -879,5 +884,5 @@

 - **iOS:** 15.0+
 - **macOS:** 12.0+
 - **Xcode:** 15.0+ with Swift 5.9+
 - **Device RAM:** 3GB minimum (6GB+ recommended for larger models)

@@ -4,8 +4,13 @@
 sidebar_position: 5
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 If you are familiar with cloud-based AI APIs (e.g. [OpenAI API](https://openai.com/api/)), this document
 shows the similarity and differences between these clould APIs and Leap.
 
 We will inspect this piece of Python-based OpenAI API chat completion request to figure out how to migrate it to LeapSDK.
 This example code is modified from [OpenAI API document](https://platform.openai.com/docs/guides/streaming-responses?api-mode=chat).
@@ -100,7 +105,7 @@

 ## Process generated contents

 In clould API Python code, a for-loop on the stream object retrieves the contents.

 ```python
 for chunk in stream:

@@ -4,6 +4,11 @@
 sidebar_position: 3
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 LeapSDK provides powerful constrained generation capabilities using Swift macros that enable you to generate structured JSON output with compile-time validation. This feature ensures the AI model produces responses that conform to your predefined Swift types.
 
 ## Overview
@@ -145,7 +150,7 @@

 ### Complex Nested Structures

 You can define complex types with arrays, optionals, and nested objects:

 ```swift
 @Generatable("A recipe with ingredients and instructions")
@@ -419,7 +424,7 @@
 This typically means there's an issue with the macro plugin. Try:

 1. Clean your build folder (Cmd+Shift+K)
 2. Restart Xcode
 3. Ensure you're using Swift 5.9 or later

 ### Generated JSON doesn't match expected format

@@ -3,6 +3,11 @@
 description: "API reference for conversations, model runners, and generation in the LEAP iOS SDK"
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 <Info>
 All functions listed in this document are safe to call from the main thread and all callbacks will be run on the main thread, unless there are explicit instructions or explanations.
 </Info>
@@ -30,7 +35,7 @@

 - Create conversations using `createConversation(systemPrompt:)` or `createConversationFromHistory(history:)`.
 - Hold a strong reference to the `ModelRunner` for as long as you need to perform generations.
 - Call `unload()` when you are done to release native resources (optional, happens automatically on deinit).
 - Access `modelId` to identify the loaded model (for analytics, debugging, or UI labels).

 ### Low-level generation API
@@ -234,7 +239,7 @@
 ```

 - Leave a field as `nil` to fall back to the defaults packaged with the model bundle.
 - `functionCallParser` controls how tool-call tokens are parsed. `LFMFunctionCallParser` (the default) handles Liquid Foundation Model Pythonic function calling. Supply `HermesFunctionCallParser()` for Hermes/Qwen3 formats, or set the parser to `nil` to receive raw tool-call text in `MessageResponse.chunk`.
 - `jsonSchemaConstraint` activates constrained generation. Use `setResponseFormat(type:)` to populate it from a type annotated with the `@Generatable` macro.

 ```swift

@@ -4,6 +4,11 @@ description: "Function calling allows the model to make requests to call some pr
 sidebar_position: 4
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 <Warning>
 Not all models support function calling. Please check the model card before using the model for function calling.
 </Warning>

@@ -3,13 +3,18 @@
 description: "Get up and running with the LEAP iOS SDK in minutes. Install the SDK, load models, and start generating content."
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 Latest version: `v0.9.2`
 
 ## Prerequisites[](#prerequisites "Direct link to Prerequisites")

 Make sure you have:

 * Xcode 15.0 or later with Swift 5.9.
 * An iOS project targeting **iOS 15.0+** (macOS 12.0+ or Mac Catalyst 15.0+ are also supported).
 * A physical iPhone or iPad with at least 3 GB RAM for best performance. The simulator works for development but runs models much slower.

@@ -49,7 +54,7 @@
  </Tab>
  <Tab title="Manual">
    1. Download `LeapSDK.xcframework.zip` (and optionally `LeapModelDownloader.xcframework.zip`) from the [GitHub releases](https://github.com/Liquid4All/leap-ios/releases).
    2. Unzip and drag the XCFramework(s) into Xcode.
    3. Set the Embed setting to **Embed & Sign** for each framework.
  </Tab>
 </Tabs>
@@ -63,7 +68,7 @@
 The SDK uses **GGUF manifests** for loading models (recommended for all new projects due to superior inference performance and better default generation parameters).

 <Info>
 Legacy Executorch bundle support is available in the accordion below for existing projects.
 </Info>

 ### Loading from GGUF manifest
@@ -151,7 +156,7 @@

  You can either:

  * **Ship it with the app** - drag the bundle into your Xcode project and ensure it is added to the main target.
  * **Download at runtime** - use `LeapModelDownloader` to fetch bundles on demand.

  <Accordion title="Alternative: Download at runtime">
@@ -275,7 +280,7 @@

 ### Send images and audio (optional)[](#send-images-and-audio-optional "Direct link to Send images and audio (optional)")

 When the loaded model ships with multimodal weights (and companion files were detected), you can mix text, image, and audio content in the same message:

 ```swift
 let message = ChatMessage(

@@ -3,6 +3,11 @@
 description: "API reference for chat messages and content types in the LEAP iOS SDK"
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 ## Chat Messages
 
 ### Roles
@@ -54,7 +59,7 @@
 }
 ```

 Provide JPEG-encoded bytes for `.image` and WAV data for `.audio`. Helper initializers such as `ChatMessageContent.fromUIImage`, `ChatMessageContent.fromNSImage`, `ChatMessageContent.fromWAVData`, and `ChatMessageContent.fromFloatSamples(_:sampleRate:channelCount:)` simplify interop with platform-native buffers. On the wire, image parts are encoded as OpenAI-style `image_url` payloads and audio parts as `input_audio` arrays with Base64 data.

 ### Audio Format Requirements

@@ -63,7 +68,7 @@
 | Property | Required Value | Notes |
 |----------|---------------|-------|
 | **Format** | WAV (RIFF) | Only WAV format is supported |
 | **Sample Rate** | 16000 Hz (16 kHz) recommended | Other sample rates are automatically resampled to 16 kHz |
 | **Encoding** | PCM (various bit depths) | Supports Float32, Int16, Int24, Int32 |
 | **Channels** | Mono (1 channel) | **Required** - stereo audio will be rejected |
 | **Byte Order** | Little-endian | Standard WAV format |
@@ -79,7 +84,7 @@
 </Warning>

 <Info>
 **Automatic Resampling**: The inference engine automatically resamples audio to 16 kHz if provided at a different sample rate. However, for best performance and quality, provide audio at 16 kHz to avoid resampling overhead.
 </Info>

 <Warning>

@@ -3,6 +3,11 @@
 description: "API reference for loading models in the LEAP iOS SDK"
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 ## `Leap`
 
 `Leap` is the static entry point for loading on-device models.
@@ -87,7 +92,7 @@

  - Throws `LeapError.modelLoadingFailure` if the file cannot be loaded.
  - Automatically detects companion files placed alongside your model:
  - `mmproj-*.gguf` enables multimodal vision tokens for both bundle and GGUF flows.
  - Audio decoder artifacts whose filename contains "audio" and "decoder" with a `.gguf` or `.bin` extension unlock audio input/output for compatible checkpoints.
  - Must be called from an async context (for example inside an `async` function or a `Task`). Keep the returned `ModelRunner` alive while you interact with the model.

@@ -126,17 +131,17 @@
 - `cpuThreads`: Number of CPU threads for token generation.
 - `contextSize`: Override the default maximum context length for the model.
 - `nGpuLayers`: Number of layers to offload to GPU (for macOS/macCatalyst targets with Metal support).
 - `mmProjPath`: Optional path to an auxiliary multimodal projection model. Leave `nil` to auto-detect a sibling `mmproj-*.gguf`.
 - `audioDecoderPath`: Optional audio decoder model. Leave `nil` to auto-detect nearby decoder artifacts.
 - `chatTemplate`: Advanced override for backend chat templating.
 - `audioTokenizerPath`: Optional tokenizer for audio-capable checkpoints.
 - `extras`: Backend-specific configuration payload (advanced use only).

 <Info>
 Backend selection is automatic: `.bundle` files run on the ExecuTorch backend, while `.gguf`
 checkpoints use the embedded llama.cpp backend. Bundled models reference their projection data in
 metadata; GGUF checkpoints look for sibling companion files (multimodal projection, audio decoder,
 audio tokenizer) unless you override the paths through `LiquidInferenceEngineOptions`. Ensure
 these artifacts are co-located when you want vision or audio features.
 </Info>


@@ -3,6 +3,11 @@ title: "Utilities"
 description: "API reference for error handling and utilities in the LEAP iOS SDK"
 ---
 
+<Warning>
+**Legacy Documentation** — This page documents the standalone iOS/Android SDK which has been superseded by the unified [LEAP SDK](/deployment/on-device/leap-sdk/quick-start-guide). New projects should use the LEAP SDK.
+</Warning>
+
+
 ## Errors
 
 Errors are surfaced as `LeapError` values. The most common cases are:
-Original file line number
+Diff line change
@@ Expand Up / @@ -164,4 +164,5 @@ Thumbs.db @@
     env
     env/*
-    __pycache__/
+    __pycache__/
+    devlog/