generate()

val result = RunAnywhere.generate(
    prompt = "Write a haiku about Kotlin programming",
    options = LLMGenerationOptions(
        maxTokens = 50,
        temperature = 1.0f,
        topP = 0.9f,
        stopSequences = listOf("###")
    )
)

println("Response: ${result.text}")
println("Model: ${result.modelUsed}")
println("Tokens: ${result.tokensUsed}")
println("Speed: ${result.tokensPerSecond} tok/s")
println("Latency: ${result.latencyMs}ms")

// For reasoning models (e.g., models with thinking capability)
result.thinkingContent?.let { thinking ->
    println("Reasoning: $thinking")
}

data class LLMGenerationOptions(
    val maxTokens: Int = 100,           // Maximum tokens to generate
    val temperature: Float = 0.8f,      // Creativity (0.0-2.0)
    val topP: Float = 1.0f,             // Nucleus sampling (0.0-1.0)
    val stopSequences: List<String> = emptyList(),
    val streamingEnabled: Boolean = false,
    val systemPrompt: String? = null    // System behavior prompt
)

val story = RunAnywhere.generate(
    prompt = "Write a short story about a robot learning to paint",
    options = LLMGenerationOptions(
        maxTokens = 500,
        temperature = 1.2f,   // Higher = more creative
        topP = 0.95f
    )
)

val facts = RunAnywhere.generate(
    prompt = "List the planets in our solar system",
    options = LLMGenerationOptions(
        maxTokens = 200,
        temperature = 0.1f,   // Lower = more deterministic
        topP = 0.5f
    )
)

// Start generation in a coroutine
val job = lifecycleScope.launch {
    val result = RunAnywhere.generate(longPrompt, options)
}

// Cancel if needed
cancelButton.setOnClickListener {
    RunAnywhere.cancelGeneration()
    job.cancel()
}