Does the Foundation Model provide Objective-C compatible APIs?

Overview I'm experiencing a critical issue where TensorFlow-metal and PyArrow seem to be incompatible when installed together in the same environment. Whenever both packages are present, TensorFlow crashes and the kernel dies during execution. Environment Details Environment Details macOS Version: 15.3.2 Mac Model: MacBook Pro Max M3 Python Version: 3.11 TensorFlow Version: 2.19 PyArrow Version: 19.0.0 Issue Description: When both TensorFlow-metal and PyArrow are installed in the same Python environment, any attempt to use TensorFlow results in immediate kernel crashes. The issue appears to be a compatibility problem between these two packages rather than a problem with either package individually. Steps to Reproduce Create a new Python environment: conda create -n tf-metal python=3.11 Install TensorFlow-metal: pip install tensorflow tensorflow-metal Install PyArrow: pip install pyarrow Run the following minimal example: # Create a simple model model = tf.keras.Sequential([ tf.keras.layers.Input(shape=(2,)), tf.keras.layers.Dense(1) ]) model.compile(optimizer='adam', loss='mse') model.summary() # This works fine # Generate some dummy data X = np.random.random((100, 2)) y = np.random.random((100, 1)) # The crash happens exactly at this line model.fit(X, y, epochs=5, batch_size=32) # CRASH: Kernel dies here Result: Kernel crashes with no error message What I've Tried Reinstalling both packages in different orders Using different versions of both packages Creating isolated environments Checking system logs for additional error information The only workaround I've found is to use separate environments for each package, which isn't practical for my workflow as I need both libraries for my data processing and machine learning pipeline. Questions Has anyone else encountered this specific compatibility issue? Are there known workarounds that allow both packages to coexist? Is this a known issue that's being addressed in upcoming releases? Any insights, suggestions, or assistance would be greatly appreciated. I'm happy to provide any additional information that might help diagnose this problem. Thank you in advance for your help! Thank you in advance for your help!

Just tried to write a very simple test of using foundation models, but it gave me the error like this "ModelManager received unentitled request. Expected entitlement com.apple.modelmanager.inference establishment of session failed with Missing entitlement: com.apple.modelmanager.inference" The simple code is listed below: let session: LanguageModelSession = LanguageModelSession() let response = try? await session.respond(to: "What is the capital of France?") print("Response: (response)") So what's the problem of this one?

I have a series of shortcuts that I’ve written that use the “Use Model” action to do various things. For example, I have a shortcut “Clipboard Markdown to Notes” that takes the content of the clipboard, creates a new note in Notes, converts the markdown content to rich text, adds it to the note etc. One key step is to analyze the markdown content with “Use Model” and generate a short descriptive title for the note. I use the on-device model for this, but sometimes the content and prompt exceed the context window size and the action fails with an error message to that effect. In that case, I’d like to either repeat the action using the Cloud model, or, if the error was a refusal, to prompt the user to enter a title to use. I‘ve tried using an IF based on whether the response had any text in it, but that didn’t work. No matter what I’ve tried, I can’t seem to find a way to catch the error from Use Model, determine what the error was, and take appropriate action. Is there a way to do this? (And by the way, a huge ”thank you” to whoever had the idea of making AppIntents visible in Shortcuts and adding the Use Model action — has made a huge difference already, and it lets us see what Siri will be able to use as well.)

I'm trying to train a text classifier model in Create ML. The Create ML app/framework offers five algorithms. I can successfully train the model with all of the algorithms except the BERT transfer learning option. When I select this algorithm, Create ML simply stops the training process immediately after the initial feature extraction phase (with no reported error). What I've tried: I tried simplifying the dataset to just a few classes and short examples in case there was a problem with the data. I tried experimenting with the number of iterations and language/script options. I checked Console.app for logged errors and found the following for the Create ML app: error 10:38:28.385778+0000 Create ML Couldn't read event column - category is invalid. Format string is : <private> error 10:38:30.902724+0000 Create ML Could not encode the entity <private>. Error: <private> I'm not sure if these errors are normal or indicative of a problem. I don't know what it means by the "event" column – I don't have an event column in my data and I don't believe there should be one. These errors are not reported when using the other algorithms. Given that I couldn't get the app to work with BERT, I switched over to the CreateML framework and followed the code samples given in the documentation. (By the way, there's an error in the docs: the line let (trainingData, testingData) = data.stratifiedSplit(on: "text", by: 0.8) should be stratifying on "label", not on "text"). The main chunk of code looks like this: var parameters = MLTextClassifier.ModelParameters( validation: .split(strategy: .automatic), algorithm: .transferLearning(.bertEmbedding, revision: 1), language: .english ) parameters.maxIterations = 100 let sentimentClassifier = try MLTextClassifier( trainingData: trainingData, textColumn: "text", labelColumn: "label", parameters: parameters ) Ultimately I want to train a single multilingual model, and I believe that BERT is the best choice for this. The problem is that there doesn't seem to be a way to choose the multilingual Latin script option in the API. In the Create ML app you can theoretically do this by selecting the Latin script with language set to "Automatic", as recommended in this WWDC video (relevant section starts at around 8:02). But, as far as I can tell, ModelParameters only lets you pick a specific language. I presume the framework must provide some way to do this, since the Create ML app uses the framework under the hood, but I can't see a way to do it. Another possibility is that the Create ML app might be misrepresenting the framework – perhaps selecting a specific language in the app doesn't actually make any difference – for example, maybe all Latin languages actually use the same model under the hood and the language selector is just there to guide people to the right choice (but this is just my speculation). Any help would be much appreciated! If possible, I'd prefer to use the Create ML app if I can get the BERT option to work – is this actually working for anyone? Or failing that, I want to use the framework to train a multilingual Latin model with BERT, so I'm looking for instructions on how to choose that specific option or confirmation that I can just choose .english to get the correct Latin multilingual model. I'm running Xcode 26.2 on Tahoe 21.1 on an M1 Pro MacBook Pro. I have version 6.2 of the Create ML app.

Hi friends, I have just found that the inference speed dropped to only 1/10 of the original model. Had anyone encountered this? Thank you.

iOS26 is supported by a wider range of devices than are able to run AI, e.g iPhone 12 runs iOS26, but does not support AI. How do we determine in code if AI is supported on a device ? How do we determine what features use AI under the hood ? Thanks, Steve.

I'm interested in using Foundation Models to act as an AI support agent for our extensive in-app documentation. We have many pages of in-app documents, which the user can currently search, but it would be great to use Foundation Models to let the user get answers to arbitrary questions. Is this possible with the current version of Foundation Models? It seems like the way to add new context to the model is with the instructions parameter on LanguageModelSession. As I understand it, the combined instructions and prompt need to consume less than 4096 tokens. That definitely wouldn't be enough for the amount of documentation I want the agent to be able to refer to. Is there another way of doing this, maybe as a series of recursive queries? If there is a solution based on multiple queries, should I expect this to be fast enough for interactive use?

I am experimenting with Foundation Models in my time tracking app to analyze users tracked events, but I am finding that the model struggles with even basic computation of time. Specifically converting from seconds to hours and minutes. To give just one example, when I prompt: "Convert 3672 seconds to hours, minutes, and seconds. Don't include the calculations in the resulting output" I get this: "3672 seconds is equal to 1 hour, 0 minutes, and 36 seconds". Which is clearly wrong - it should be 1 hour, 1 minute, and 12 seconds. Another issue that I saw a lot is that seconds were considered to be minutes, or that the hours were just completely off. What can I do to make the support for math better? Or is that just something that the model is not meant to be used for?

Access to VisionPro cameras is required for a research project. The project is on mixed reality software development for healthcare applications in dentistry.

Hi all, I'm capturing a photo using AVCapturePhotoOutput, and I've set: let photoSettings = AVCapturePhotoSettings() photoSettings.isDepthDataDeliveryEnabled = true Then I create the handler like this: let data = photo.fileDataRepresentation() let handler = try ImageRequestHandler(data: data, orientation: .right) Now I’m wondering: If depth data delivery is enabled, is it actually included and used when I pass the Data to ImageRequestHandler? Or do I need to explicitly pass the depth data using the other initializer? let handler = try ImageRequestHandler( cvPixelBuffer: photo.pixelBuffer!, depthData: photo.depthData, orientation: .right ) In short: Does ImageRequestHandler(data:) make use of embedded depth info from AVCapturePhoto.fileDataRepresentation() — or is the pixel buffer + explicit depth data required? Thanks for any clarification!

It is vital for Apple to refine its OCR models to correctly distinguish between Khmer and Thai scripts. Incorrectly labeling Khmer text as Thai is more than a technical bug; it is a culturally insensitive error that impacts national identity, especially given the current geopolitical climate between Cambodia and Thailand. Implementing a more robust language-detection threshold would prevent these harmful misidentifications. There is a significant logic flaw in the VNRecognizeTextRequest language detection when processing Khmer script. When the property automaticallyDetectsLanguage is set to true, the Vision framework frequently misidentifies Khmer characters as Thai. While both scripts share historical roots, they are distinct languages with different alphabets. Currently, the model’s confidence threshold for distinguishing between these two scripts is too low, leading to incorrect OCR output in both developer-facing APIs and Apple’s native ecosystem (Preview, Live Text, and Photos). import SwiftUI import Vision class TextExtractor { func extractText(from data: Data, completion: @escaping (String) -> Void) { let request = VNRecognizeTextRequest { (request, error) in guard let observations = request.results as? [VNRecognizedTextObservation] else { completion("No text found.") return } let recognizedStrings = observations.compactMap { observation in let str = observation.topCandidates(1).first?.string return "{text: \(str!), confidence: \(observation.confidence)}" } completion(recognizedStrings.joined(separator: "\n")) } request.automaticallyDetectsLanguage = true // <-- This is the issue. request.recognitionLevel = .accurate let handler = VNImageRequestHandler(data: data, options: [:]) DispatchQueue.global(qos: .background).async { do { try handler.perform([request]) } catch { completion("Failed to perform OCR: \(error.localizedDescription)") } } } } Recognizing Khmer Confidence Score is low for Khmer text. (The output is in Thai language with low confidence score) Recognizing English Confidence Score is high expected. Recognizing Thai Confidence Score is high as expected Issues on Preview, Photos Khmer text Copied text Kouk Pring Chroum Temple [19121 รอาสายสุกตีนานยารรีสใหิสรราภูชิตีนนสุฐตีย์ [รุก เผือชิษาธอยกัตธ์ตายตราพาษชาณา ถวเชยาใบสราเบรถทีมูสินตราพาษชาณา ทีมูโษา เช็ก อาษเชิษฐอารายสุกบดตพรธุรฯ ตากร"สุก"ผาตากรธกรธุกเยากสเผาพศฐตาสาย รัอรณาษ"ตีพย" สเผาพกรกฐาภูชิสาเครๆผู:สุกรตีพาสเผาพสรอสายใผิตรรารตีพสๆ เดียอลายสุกตีน ธาราชรติ ธิพรหณาะพูชุบละเาหLunet De Lajonquiere ผารูกรสาราพารผรผาสิตภพ ตารสิทูก ธิพิ คุณที่นสายเระพบพเคเผาหนารเกะทรนภาษเราภุพเสารเราษทีเลิกสญาเราหรุฬารชสเกาก เรากุม สงสอบานตรเราะากกต่ายภากายระตารุกเตียน Recommended Solutions 1. Set a Threshold Filter out the detected result where the threshold is less than or equal to 0.5, so that it would not output low quality text which can lead to the issue. For example, let recognizedStrings = observations.compactMap { observation in if observation.confidence <= 0.5 { return nil } let str = observation.topCandidates(1).first?.string return "{text: \(str!), confidence: \(observation.confidence)}" } 2. Add Khmer Language Support This issue would never happen if the model has the capability to detect and recognize image with Khmer language. Doc2Text GitHub: https://github.com/seanghay/Doc2Text-Swift

Hello Apple Team, Thank you for the recent Group Lab and for your continued work on advancing Xcode and developer tools. I’d like to submit a feature request: Are there any plans to introduce support for Agentic AI Mode (MCP protocol) in future versions of iOS or Xcode? As developer tools evolve toward more intelligent and context-aware environments, the integration of agentic AI capabilities could significantly enhance productivity and unlock new creative workflows. Looking forward to your consideration, and thank you again for the excellent session. Best regards

I have a mac (M4, MacBook Pro) running Tahoe 26.0 beta. I am running Xcode beta. I can run code that uses the LLM in a #Preview { }. But when I try to run the same code in the simulator, I get the 'device not ready' error and I see the following in the Settings app. Is there anything I can do to get the simulator to past this point and allowing me to test on it with Apple's LLM?

I get the following dyld error on an iPad Pro with Xcode 26 beta 4: Symbol not found: _$s16FoundationModels20LanguageModelSessionC7prewarm12promptPrefixyAA6PromptVSg_tF Any advice?

Has Apple made any commitment to versioning the Foundation Models on device? What if you build a feature that works great on 26.0 but they change the model or guardrails in 26.1 and it breaks your feature, is your only recourse filing Feedback or pulling the feature from the app? Will there be a way to specify a model version like in all of the server based LLM provider APIs? If not, sounds risky to build on.

I'm developing a macOS application using the FoundationModels framework (LanguageModelSession) and encountering issues with the content sanitizer blocking legitimate text input. ** Issue Description:** The content sanitizer is flagging text strings that contain certain substrings, even when they represent legitimate technical content. For example: F_SEEL_SEX1S.wav (sE Electronics SEX1S microphone model) Technical product identifiers Serial numbers and version codes ** Broader Concern:** The content sanitizer appears to be applying restrictions that seem inappropriate for user-owned content. Even if a filename were something like "human sex.wav", users should have the right to process their own legitimate files on their own devices without content filtering interference. ** Error Messages:** SensitiveContentSettings: Sanitizer model found unsafe content in value FoundationModels.LanguageModelSession.GenerationError error 2 ** Questions:** Is there a way to disable content sanitization for processing user-owned content? 2. What's the recommended approach for applications that need to handle arbitrary user text? 3. Are there APIs to process personal content without filtering restrictions? ** Environment:** macOS 26.0 FoundationModels framework LanguageModelSession Any guidance would be appreciated.

Hi, I'm using LanguageModelSession and giving it two different tools to query data from a local database. I'm wondering how I can have the session generate structured content as the response that includes data one or both tools (or no tool at all). Here is an example of what I'm trying to do: Let's say the app has access to a database that contains information about exercise and sleep data (this is just an analogy). There are two tools, GetExerciseData() and GetSleepData(). The user may then prompt something like, "how well did I sleep in November". I have this working so that it calls through to the right tool, which would return a SleepSummary. However, I can't figure out how to have the session return the right structured data. I can do this and get back good text data: let response = session.respond(to: userInput), but I believe I want to do something like: let response = session.respond(to: trimmed, generating: <SomeStructure?>) Sometimes the model I run one tool or the other, or both tools, or no tool at all. Any help of what the right way to go about this would be much appreciated. Most of the example I found have to do with 1 tool.

I am trying to create a slightly different version of the content tagging code in the documentation: https://developer.apple.com/documentation/foundationmodels/systemlanguagemodel/usecase/contenttagging In the playground I am getting an "Inference Provider crashed with 2:5" error. I have no idea what that means or how to address the error. Any assistance would be appreciated.

Hey, I receive GenerableContent as follows: let response = try await session.respond(to: "", schema: generationSchema) And it wraps GeneratedJSON which seems to be private. What is the best way to get a string / raw value out of it? I noticed it could theoretically be accessed via transcriptEntries but it's not ideal.