Hi everyone, I’m currently exploring the use of Foundation models on Apple platforms to build a chatbot-style assistant within an app. While the integration part is straightforward using the new FoundationModel APIs, I’m trying to figure out how to control the assistant’s responses more tightly — particularly: Ensuring the assistant adheres to a specific tone, context, or domain (e.g. hospitality, healthcare, etc.) Preventing hallucinations or unrelated outputs Constraining responses based on app-specific rules, structured data, or recent interactions I’ve experimented with prompt, systemMessage, and few-shot examples to steer outputs, but even with carefully generated prompts, the model occasionally produces incorrect or out-of-scope responses. Additionally, when using multiple tools, I'm unsure how best to structure the setup so the model can select the correct pathway/tool and respond appropriately. Is there a recommended approach to guiding the model's decision-making when several tools or structured contexts are involved? Looking forward to hearing your thoughts or being pointed toward related WWDC sessions, Apple docs, or sample projects.

I’m developing an activity classifier that I’d like to input using the JSON format of CoreMotion data. I am getting the error: Unable to parse /Users/DewG/Downloads/Testing/Step1/Testing.json. It does not appear to be in JSON record format. A SequenceType of dictionaries is expected I've verified that the format I am using is JSON via various JSON validators, so I am expecting I'm just holding it wrong. Is there an example of a JSON file with CoreMotion data that I can model after?

Is there anywhere we can reference error codes? I'm getting this error: "The operation couldn’t be completed. (FoundationModels.LanguageModelSession.GenerationError error 4.)" and I have no idea of what it means or what to attempt to fix.

I am writing a custom package wrapping Foundation Models which provides a chain-of-thought with intermittent self-evaluation among other things. At first I was designing this package with the command line in mind, but after seeing how well it augments the models and makes them more intelligent I wanted to try and build a SwiftUI wrapper around the package. When I started I was using synchronous generation rather than streaming, but to give the best user experience (as I've seen in the WWDC sessions) it is necessary to provide constant feedback to the user that something is happening. I have created a super simplified example of my setup so it's easier to understand. First, there is the Reasoning conversation item, which can be converted to an XML representation which is then fed back into the model (I've found XML works best for structured input) public typealias ConversationContext = XMLDocument extension ConversationContext { public func toPlainText() -> String { return xmlString(options: [.nodePrettyPrint]) } } /// Represents a reasoning item in a conversation, which includes a title and reasoning content. /// Reasoning items are used to provide detailed explanations or justifications for certain decisions or responses within a conversation. @Generable(description: "A reasoning item in a conversation, containing content and a title.") struct ConversationReasoningItem: ConversationItem { @Guide(description: "The content of the reasoning item, which is your thinking process or explanation") public var reasoningContent: String @Guide(description: "A short summary of the reasoning content, digestible in an interface.") public var title: String @Guide(description: "Indicates whether reasoning is complete") public var done: Bool } extension ConversationReasoningItem: ConversationContextProvider { public func toContext() -> ConversationContext { // <ReasoningItem title="${title}"> // ${reasoningContent} // </ReasoningItem> let root = XMLElement(name: "ReasoningItem") root.addAttribute(XMLNode.attribute(withName: "title", stringValue: title) as! XMLNode) root.stringValue = reasoningContent return ConversationContext(rootElement: root) } } Then there is the generator, which creates a reasoning item from a user query and previously generated items: struct ReasoningItemGenerator { var instructions: String { """ <omitted for brevity> """ } func generate(from input: (String, [ConversationReasoningItem])) async throws -> sending LanguageModelSession.ResponseStream<ConversationReasoningItem> { let session = LanguageModelSession(instructions: instructions) // build the context for the reasoning item out of the user's query and the previous reasoning items let userQuery = "User's query: \(input.0)" let reasoningItemsText = input.1.map { $0.toContext().toPlainText() }.joined(separator: "\n") let context = userQuery + "\n" + reasoningItemsText let reasoningItemResponse = try await session.streamResponse( to: context, generating: ConversationReasoningItem.self) return reasoningItemResponse } } I'm not sure if returning LanguageModelSession.ResponseStream<ConversationReasoningItem> is the right move, I am just trying to imitate what session.streamResponse returns. Then there is the orchestrator, which I can't figure out. It receives the streamed ConversationReasoningItems from the Generator and is responsible for streaming those to SwiftUI later and also for evaluating each reasoning item after it is complete to see if it needs to be regenerated (to keep the model on-track). I want the users of the orchestrator to receive partially generated reasoning items as they are being generated by the generator. Later, when they finish, if the evaluation passes, the item is kept, but if it fails, the reasoning item should be removed from the stream before a new one is generated. So in-flight reasoning items should be outputted aggresively. I really am having trouble figuring this out so if someone with more knowledge about asynchronous stuff in Swift, or- even better- someone who has worked on the Foundation Models framework could point me in the right direction, that would be awesome!

Hi all, I'm working on an app that utilizes the FoundationModels found in iOS 26. I updated my phone to iOS 26 beta 3 and am now receiving the following error when trying to run code that worked in beta 2: Al Error: The operation couldn't be completed. (FoundationModels.LanguageModelSession.Genera- tionError error 2.) I admit I'm a bit of a new developer, but any idea if this is an issue with beta 3 or work that I'll need to do to adapt my code to some changes in the AI API? Thank you!

Testing Foundation Models framework with a health-focused recipe generation app. The on-device approach is appealing but performance is rough. Taking 20+ seconds just to get recipe name and description. Same content from Claude API: 4 seconds. I know it's beta and on-device has different tradeoffs, but this is approaching unusable territory for real-time user experience. The streaming helps psychologically but doesn't mask the underlying latency.The privacy/cost benefits are compelling but not if users abandon the feature before it completes. Anyone else seeing similar performance? Is this expected for beta, or are there optimization techniques I'm missing?

When context window size exceeded, this error is not called (instead another error has shown up) to handle new session. LanguageModelSession.GenerationError.exceededContextWindowSize Or am I doing things wrong?

I've spent way too long today trying to convert an Object Detection TensorFlow2 model to a CoreML object classifier (with bounding boxes, labels and probability score) The 'SSD MobileNet v2 320x320' is here: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md And I've been following all sorts of posts and ChatGPT https://apple.github.io/coremltools/docs-guides/source/tensorflow-2.html#convert-a-tensorflow-concrete-function https://developer.apple.com/videos/play/wwdc2020/10153/?time=402 To convert it. I keep hitting the same errors though, mostly around: NotImplementedError: Expected model format: [SavedModel | concrete_function | tf.keras.Model | .h5 | GraphDef], got <ConcreteFunction signature_wrapper(input_tensor) at 0x366B87790> I've had varying success including missing output labels/predictions. But I simply want to create the CoreML model with all the right inputs and outputs (including correct names) as detailed in the docs here: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/running_on_mobile_tf2.md It goes without saying I don't have much (any) experience with this stuff including Python so the whole thing's been a bit of a headache. If anyone is able to help that would be great. FWIW I'm not attached to any one specific model, but what I do need at minimum is a CoreML model that can detect objects (has to at least include lights and lamps) within a live video image, detecting where in the image the object is. The simplest script I have looks like this: import coremltools as ct import tensorflow as tf model = tf.saved_model.load("~/tf_models/ssd_mobilenet_v2_320x320_coco17_tpu-8/saved_model") concrete_func = model.signatures[tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY] mlmodel = ct.convert( concrete_func, source="tensorflow", inputs=[ct.TensorType(shape=(1, 320, 320, 3))] ) mlmodel.save("YourModel.mlpackage", save_format="mlpackage")

Hi all, I’m encountering an issue when trying to run Apple Foundation Models in a blank project targeting iOS 26. Below are the details: Xcode: Latest version with iOS 26 SDK macOS: macOS 26 Tahoe (installed on main disk) Mac: 16” MacBook Pro with M2 Pro chip Apple Intelligence: Available and functional on this machine Problem: I created a new blank iOS project, set the deployment target to iOS 26, and ran the following minimal code using Foundation Models. However, I get no response at all in the output - not even an error. The app runs, but the model does not produce any output. #Playground { let session = LanguageModelSession() let response = try await session.respond(to: "Tell me a story") } Then, I tried to catch an error with this code: #Playground { let session = LanguageModelSession() do { let response = try await session.respond(to: "Tell me a story") print(response) } catch { print("Failed to get response:", error) } print("This line, never gets executed") } And got these results: I’ve done further testing and discovered something important: I tried running the Code Along sample project, and there the #Playground macro worked without issues. The only significant difference I noticed was the Canvas run destination: In my original project, I was using iPhone 16 Pro (iOS 26) as the run target in Canvas. Apple Intelligence was enabled on the simulator, but no response was returned when executing the prompt. In the sample project, the Canvas was running on My Mac. I attempted to match that setup, but at first, my destination was My Mac (Designed for iPad), which still didn’t work. The macro finally executed properly once I switched to My Mac (AppKit). So the question is ... it seems that for now, Foundation Models and the #Playground macro only run correctly when the canvas or destination is set to “My Mac (AppKit)”?

I'm new to Swift and was hoping the Playground would support loading adaptors. When I tried, I got a permissions error - thinking it's because it's not in the project and Playgrounds don't like going outside the project? A tutorial and some sample code would be helpful. Also some benchmarks on how long it's expected to take. Selfishly I'm on an M2 Mac Mini.

Download the Foundation Models Adaptor Training Toolkit Hi, after I clicked on the download button, I was redirected to this page https://developer.apple.com and did not download the toolkit.

Hello, We have been encountering a persistent crash in our application, which is deployed exclusively on iPad devices. The crash occurs in the following code block: let requestHandler = ImageRequestHandler(paddedImage) var request = CoreMLRequest(model: model) request.cropAndScaleAction = .scaleToFit let results = try await requestHandler.perform(request) The client using this code is wrapped inside an actor, following Swift concurrency principles. The issue has been consistently reproduced across multiple iPadOS versions, including: iPad OS - 18.4.0 iPad OS - 18.4.1 iPad OS - 18.5.0 This is the crash log - Crashed: com.apple.VN.detectorSyncTasksQueue.VNCoreMLTransformer 0 libobjc.A.dylib 0x7b98 objc_retain + 16 1 libobjc.A.dylib 0x7b98 objc_retain_x0 + 16 2 libobjc.A.dylib 0xbf18 objc_getProperty + 100 3 Vision 0x326300 -[VNCoreMLModel predictWithCVPixelBuffer:options:error:] + 148 4 Vision 0x3273b0 -[VNCoreMLTransformer processRegionOfInterest:croppedPixelBuffer:options:qosClass:warningRecorder:error:progressHandler:] + 748 5 Vision 0x2ccdcc __119-[VNDetector internalProcessUsingQualityOfServiceClass:options:regionOfInterest:warningRecorder:error:progressHandler:]_block_invoke_5 + 132 6 Vision 0x14600 VNExecuteBlock + 80 7 Vision 0x14580 __76+[VNDetector runSuccessReportingBlockSynchronously:detector:qosClass:error:]_block_invoke + 56 8 libdispatch.dylib 0x6c98 _dispatch_block_sync_invoke + 240 9 libdispatch.dylib 0x1b584 _dispatch_client_callout + 16 10 libdispatch.dylib 0x11728 _dispatch_lane_barrier_sync_invoke_and_complete + 56 11 libdispatch.dylib 0x7fac _dispatch_sync_block_with_privdata + 452 12 Vision 0x14110 -[VNControlledCapacityTasksQueue dispatchSyncByPreservingQueueCapacity:] + 60 13 Vision 0x13ffc +[VNDetector runSuccessReportingBlockSynchronously:detector:qosClass:error:] + 324 14 Vision 0x2ccc80 __119-[VNDetector internalProcessUsingQualityOfServiceClass:options:regionOfInterest:warningRecorder:error:progressHandler:]_block_invoke_4 + 336 15 Vision 0x14600 VNExecuteBlock + 80 16 Vision 0x2cc98c __119-[VNDetector internalProcessUsingQualityOfServiceClass:options:regionOfInterest:warningRecorder:error:progressHandler:]_block_invoke_3 + 256 17 libdispatch.dylib 0x1b584 _dispatch_client_callout + 16 18 libdispatch.dylib 0x6ab0 _dispatch_block_invoke_direct + 284 19 Vision 0x2cc454 -[VNDetector internalProcessUsingQualityOfServiceClass:options:regionOfInterest:warningRecorder:error:progressHandler:] + 632 20 Vision 0x2cd14c __111-[VNDetector processUsingQualityOfServiceClass:options:regionOfInterest:warningRecorder:error:progressHandler:]_block_invoke + 124 21 Vision 0x14600 VNExecuteBlock + 80 22 Vision 0x2ccfbc -[VNDetector processUsingQualityOfServiceClass:options:regionOfInterest:warningRecorder:error:progressHandler:] + 340 23 Vision 0x125410 __swift_memcpy112_8 + 4852 24 libswift_Concurrency.dylib 0x5c134 swift::runJobInEstablishedExecutorContext(swift::Job*) + 292 25 libswift_Concurrency.dylib 0x5d5c8 swift_job_runImpl(swift::Job*, swift::SerialExecutorRef) + 156 26 libdispatch.dylib 0x13db0 _dispatch_root_queue_drain + 364 27 libdispatch.dylib 0x1454c _dispatch_worker_thread2 + 156 28 libsystem_pthread.dylib 0x9d0 _pthread_wqthread + 232 29 libsystem_pthread.dylib 0xaac start_wqthread + 8 We found an issue similar to us - https://developer.apple.com/forums/thread/770771. But the crash logs are quite different, we believe this warrants further investigation to better understand the root cause and potential mitigation strategies. Please let us know if any additional information would help diagnose this issue.

I'm using a custom create ML model to classify the movement of a user's hand in a game, The classifier has 3 different spell movements, but my code constantly predicts all of them at an equal 1/3 probability regardless of movement which leads me to believe my code isn't correct (as opposed to the model) which in CreateML at least gives me a heavily weighted prediction My code is below. On adding debug prints everywhere all the data looks good to me and matches similar to my test CSV data So I'm thinking my issue must be in the setup of my model code? /// Feeds samples into the model and keeps a sliding window of the last N frames. final class WandGestureStreamer { static let shared = WandGestureStreamer() private let model: SpellActivityClassifier private var samples: [Transform] = [] private let windowSize = 100 // number of frames the model expects /// RNN hidden state passed between inferences private var stateIn: MLMultiArray /// Last transform dropped from the window for continuity private var lastDropped: Transform? private init() { let config = MLModelConfiguration() self.model = try! SpellActivityClassifier(configuration: config) // Initialize stateIn to the model’s required shape let constraint = self.model.model.modelDescription .inputDescriptionsByName["stateIn"]! .multiArrayConstraint! self.stateIn = try! MLMultiArray(shape: constraint.shape, dataType: .double) } /// Call once per frame with the latest wand position (or any feature vector). func appendSample(_ sample: Transform) { samples.append(sample) // drop oldest frame if over capacity, retaining it for delta at window start if samples.count > windowSize { lastDropped = samples.removeFirst() } } func classifyIfReady(threshold: Double = 0.6) -> (label: String, confidence: Double)? { guard samples.count == windowSize else { return nil } do { let input = try makeInput(initialState: stateIn) let output = try model.prediction(input: input) // Save state for continuity stateIn = output.stateOut let best = output.label let conf = output.labelProbability[best] ?? 0 // If you’ve recognized a gesture with high confidence: if conf > threshold { return (best, conf) } else { return nil } } catch { print("Error", error.localizedDescription, error) return nil } } /// Constructs a SpellActivityClassifierInput from recorded wand transforms. func makeInput(initialState: MLMultiArray) throws -> SpellActivityClassifierInput { let count = samples.count as NSNumber let shape = [count] let timeArr = try MLMultiArray(shape: shape, dataType: .double) let dxArr = try MLMultiArray(shape: shape, dataType: .double) let dyArr = try MLMultiArray(shape: shape, dataType: .double) let dzArr = try MLMultiArray(shape: shape, dataType: .double) let rwArr = try MLMultiArray(shape: shape, dataType: .double) let rxArr = try MLMultiArray(shape: shape, dataType: .double) let ryArr = try MLMultiArray(shape: shape, dataType: .double) let rzArr = try MLMultiArray(shape: shape, dataType: .double) for (i, sample) in samples.enumerated() { let previousSample = i > 0 ? samples[i - 1] : lastDropped let model = WandMovementRecording.DataModel(transform: sample, previous: previousSample) // print("model", model) timeArr[i] = NSNumber(value: model.timestamp) dxArr[i] = NSNumber(value: model.dx) dyArr[i] = NSNumber(value: model.dy) dzArr[i] = NSNumber(value: model.dz) let rot = model.rotation rwArr[i] = NSNumber(value: rot.w) rxArr[i] = NSNumber(value: rot.x) ryArr[i] = NSNumber(value: rot.y) rzArr[i] = NSNumber(value: rot.z) } return SpellActivityClassifierInput( dx: dxArr, dy: dyArr, dz: dzArr, rotation_w: rwArr, rotation_x: rxArr, rotation_y: ryArr, rotation_z: rzArr, timestamp: timeArr, stateIn: initialState ) } }

Hey everyone I'm Manish Mehta, field CTO at Centific. I recently read Apple's white paper, The Illusion of Thinking and it got me thinking about the current state of AI reasoning. Who here has read it? The paper highlights how LLMs often rely on pattern recognition rather than genuine understanding. When faced with complex tasks, their performance can degrade significantly. I was just thinking that to move beyond this problem, we need to explore approaches that combines Deeper Reasoning Architectures for true cognitive capability with Deep Human Partnership to guide AI toward better judgment and understanding. The first part means fundamentally rewiring AI to reason. This involves advancing deeper architectures like World Models, which can build internal simulations to understand real-world scenarios , and Neurosymbolic systems, which combines neural networks with symbolic reasoning for deeper self-verification. Additionally, we need to look at deep human partnership and scalable oversight. An AI cannot learn certain things from data alone, it lacks the real-world judgment an AI will never have. Among other things, deep domain expert human partners are needed to instill this wisdom , validate the AI's entire reasoning process , build its ethical guardrails , and act as skilled adversaries to find hidden flaws before they can cause harm. What do you all think? Is this focus on a deeper partnership between advanced AI reasoning and deep human judgment the right path forward? Agree? Disagree? Thanks

I am using gemini2.5-flash with SwiftUI. How can I receive a response in JSON?

When I initialize a session with an existing transcript using this initializer: public convenience init(model: SystemLanguageModel = .default, guardrails: LanguageModelSession.Guardrails = .default, tools: [any Tool] = [], transcript: Transcript) The tools get ignored. I noticed that when doing that, the model never use the tools. When inspecting the transcript, I can see that the instruction entry does not have any tools available to it. I tried this for both transcripts that already include an instruction entry and ones that don't - both yielding the same result.. Is this the intended behavior / am I missing something here?

With respond() methods, the foundation model works well enough. With streamResponse() methods, the responses are very repetitive, verbose, and messy. My app with foundation model uses more than 500 MB memory on an iPad Pro when running from Xcode. Devices supporting Apple Intelligence have at least 8GB memory. Should Apple use a bigger model (using 3 ~ 4 GB memory) for better stream responses?

Does CoreML object detection only support AABB (Axis-Aligned Bounding Boxes) or also OBB (Oriented Bounded Boxes)? If not, any way to do it using Apple frameworks?

We are really excited to have introduced the Foundation Models framework in WWDC25. When using the framework, you might have feedback about how it can better fit your use cases. Starting in macOS/iOS 26 Beta 4, the best way to provide feedback is to use #Playground in Xcode. To do so: In Xcode, create a playground using #Playground. Fore more information, see Running code snippets using the playground macro. Reproduce the issue by setting up a session and generating a response with your prompt. In the canvas on the right, click the thumbs-up icon to the right of the response. Follow the instructions on the pop-up window and submit your feedback by clicking Share with Apple. Another way to provide your feedback is to file a feedback report with relevant details. Specific to the Foundation Models framework, it’s super important to add the following information in your report: Language model feedback This feedback contains the session transcript, including the instructions, the prompts, the responses, etc. Without that, we can’t reason the model’s behavior, and hence can hardly take any action. Use logFeedbackAttachment(sentiment:issues:desiredOutput: ) to retrieve the feedback data of your current model session, as shown in the usage example, write the data into a file, and then attach the file to your feedback report. If you believe what you’d report is related to the system configuration, please capture a sysdiagnose and attach it to your feedback report as well. The framework is still new. Your actionable feedback helps us evolve the framework quickly, and we appreciate that. Thanks, The Foundation Models framework team

At WWDC25 we launched a new type of Lab event for the developer community - Group Labs. A Group Lab is a panel Q&A designed for a large audience of developers. Group Labs are a unique opportunity for the community to submit questions directly to a panel of Apple engineers and designers. Here are the highlights from the WWDC25 Group Lab for Machine Learning and AI Frameworks. What are you most excited about in the Foundation Models framework? The Foundation Models framework provides access to an on-device Large Language Model (LLM), enabling entirely on-device processing for intelligent features. This allows you to build features such as personalized search suggestions and dynamic NPC generation in games. The combination of guided generation and streaming capabilities is particularly exciting for creating delightful animations and features with reliable output. The seamless integration with SwiftUI and the new design material Liquid Glass is also a major advantage. When should I still bring my own LLM via CoreML? It's generally recommended to first explore Apple's built-in system models and APIs, including the Foundation Models framework, as they are highly optimized for Apple devices and cover a wide range of use cases. However, Core ML is still valuable if you need more control or choice over the specific model being deployed, such as customizing existing system models or augmenting prompts. Core ML provides the tools to get these models on-device, but you are responsible for model distribution and updates. Should I migrate PyTorch code to MLX? MLX is an open-source, general-purpose machine learning framework designed for Apple Silicon from the ground up. It offers a familiar API, similar to PyTorch, and supports C, C++, Python, and Swift. MLX emphasizes unified memory, a key feature of Apple Silicon hardware, which can improve performance. It's recommended to try MLX and see if its programming model and features better suit your application's needs. MLX shines when working with state-of-the-art, larger models. Can I test Foundation Models in Xcode simulator or device? Yes, you can use the Xcode simulator to test Foundation Models use cases. However, your Mac must be running macOS Tahoe. You can test on a physical iPhone running iOS 18 by connecting it to your Mac and running Playgrounds or live previews directly on the device. Which on-device models will be supported? any open source models? The Foundation Models framework currently supports Apple's first-party models only. This allows for platform-wide optimizations, improving battery life and reducing latency. While Core ML can be used to integrate open-source models, it's generally recommended to first explore the built-in system models and APIs provided by Apple, including those in the Vision, Natural Language, and Speech frameworks, as they are highly optimized for Apple devices. For frontier models, MLX can run very large models. How often will the Foundational Model be updated? How do we test for stability when the model is updated? The Foundation Model will be updated in sync with operating system updates. You can test your app against new model versions during the beta period by downloading the beta OS and running your app. It is highly recommended to create an "eval set" of golden prompts and responses to evaluate the performance of your features as the model changes or as you tweak your prompts. Report any unsatisfactory or satisfactory cases using Feedback Assistant. Which on-device model/API can I use to extract text data from images such as: nutrition labels, ingredient lists, cashier receipts, etc? Thank you. The Vision framework offers the RecognizeDocumentRequest which is specifically designed for these use cases. It not only recognizes text in images but also provides the structure of the document, such as rows in a receipt or the layout of a nutrition label. It can also identify data like phone numbers, addresses, and prices. What is the context window for the model? What are max tokens in and max tokens out? The context window for the Foundation Model is 4,096 tokens. The split between input and output tokens is flexible. For example, if you input 4,000 tokens, you'll have 96 tokens remaining for the output. The API takes in text, converting it to tokens under the hood. When estimating token count, a good rule of thumb is 3-4 characters per token for languages like English, and 1 character per token for languages like Japanese or Chinese. Handle potential errors gracefully by asking for shorter prompts or starting a new session if the token limit is exceeded. Is there a rate limit for Foundation Models API that is limited by power or temperature condition on the iPhone? Yes, there are rate limits, particularly when your app is in the background. A budget is allocated for background app usage, but exceeding it will result in rate-limiting errors. In the foreground, there is no rate limit unless the device is under heavy load (e.g., camera open, game mode). The system dynamically balances performance, battery life, and thermal conditions, which can affect the token throughput. Use appropriate quality of service settings for your tasks (e.g., background priority for background work) to help the system manage resources effectively. Do the foundation models support languages other than English? Yes, the on-device Foundation Model is multilingual and supports all languages supported by Apple Intelligence. To get the model to output in a specific language, prompt it with instructions indicating the user's preferred language using the locale API (e.g., "The user's preferred language is en-US"). Putting the instructions in English, but then putting the user prompt in the desired output language is a recommended practice. Are larger server-based models available through Foundation Models? No, the Foundation Models API currently only provides access to the on-device Large Language Model at the core of Apple Intelligence. It does not support server-side models. On-device models are preferred for privacy and for performance reasons. Is it possible to run Retrieval-Augmented Generation (RAG) using the Foundation Models framework? Yes, it is possible to run RAG on-device, but the Foundation Models framework does not include a built-in embedding model. You'll need to use a separate database to store vectors and implement nearest neighbor or cosine distance searches. The Natural Language framework offers simple word and sentence embeddings that can be used. Consider using a combination of Foundation Models and Core ML, using Core ML for your embedding model.