Showing 1-3 of 3 articles in Foundation Models
Apple's system model takes image input in Xcode 27, but not video. This post shows how to route video through LanguageModelSession to Gemini using a custom Transcript.CustomSegment and a LanguageModelExecutor, and how to verify each layer actually does what you think it does.
Apple's Foundation Models framework includes PromptBuilder and InstructionsBuilder—Swift result builders that transform how we compose prompts. This post explores why declarative prompt composition beats string concatenation, and how to build type-safe, composable AI interactions.
Apple Intelligence supports 23 locales, and Foundation Models supports all of them. This chapter shows how to inspect supported locales at runtime and fetch responses in the user's language for regional differences.
