Summarize text with the local model

https://github.com/trymirai/uzu-swift.git

import Uzu

public func runSummarization() async throws {
    let engine = try await UzuEngine.create(apiKey: "API_KEY")

    let model = try await engine.chatModel(repoId: "Qwen/Qwen3-0.6B")
    try await engine.downloadChatModel(model) { update in
        print("Progress: \(update.progress)")
    }

    let textToSummarize =
        "A Large Language Model (LLM) is a type of artificial intelligence that processes and generates human-like text. It is trained on vast datasets containing books, articles, and web content, allowing it to understand and predict language patterns. LLMs use deep learning, particularly transformer-based architectures, to analyze text, recognize context, and generate coherent responses. These models have a wide range of applications, including chatbots, content creation, translation, and code generation. One of the key strengths of LLMs is their ability to generate contextually relevant text based on prompts. They utilize self-attention mechanisms to weigh the importance of words within a sentence, improving accuracy and fluency. Examples of popular LLMs include OpenAI's GPT series, Google's BERT, and Meta's LLaMA. As these models grow in size and sophistication, they continue to enhance human-computer interactions, making AI-powered communication more natural and effective."
    let input: Input = .text(
        text: "Text is: \"\(textToSummarize)\". Write only summary itself.")

    let session = try engine.chatSession(model, config: Config(preset: .summarization))
    let runConfig = RunConfig()
        .tokensLimit(256)
        .enableThinking(false)
        .samplingPolicy(.custom(value: .greedy))
    let output = try session.run(
        input: input,
        config: runConfig
    ) { _ in
        return true
    }

    print("Summary: \(output.text.original)")
    print(
        "Model runs: \(output.stats.prefillStats.modelRun.count + (output.stats.generateStats?.modelRun.count ?? 0))"
    )
    print("Tokens count: \(output.stats.totalStats.tokensCountOutput)")
}

var body: some View {
    VStack {
        Text("On-device AI")
    }
    .onAppear() {
        Task {
            try await runSummarization()
        }
    }
}