Bắt đầu sử dụng LiteRT-LM trên Android

import com.google.ai.edge.litertlm.*

suspend fun main() {
  Engine.setNativeMinLogSeverity(LogSeverity.ERROR) // Hide log for TUI app

  val engineConfig = EngineConfig(modelPath = "/path/to/model.litertlm")
  Engine(engineConfig).use { engine ->
    engine.initialize()

    engine.createConversation().use { conversation ->
      while (true) {
        print("\n>>> ")
        conversation.sendMessageAsync(readln()).collect { print(it) }
      }
    }
  }
}

bazel run -c opt //kotlin/java/com/google/ai/edge/litertlm/example:main -- <abs_model_path>

dependencies {
    // For Android
    implementation("com.google.ai.edge.litertlm:litertlm-android:latest.release")

    // For JVM (Linux, MacOS, Windows)
    implementation("com.google.ai.edge.litertlm:litertlm-jvm:latest.release")
}

import com.google.ai.edge.litertlm.Backend
import com.google.ai.edge.litertlm.Engine
import com.google.ai.edge.litertlm.EngineConfig

val engineConfig = EngineConfig(
    modelPath = "/path/to/your/model.litertlm", // Replace with your model path
    backend = Backend.GPU(), // Or Backend.NPU(nativeLibraryDir = "...")
    // Optional: Pick a writable dir. This can improve 2nd load time.
    // cacheDir = "/tmp/" or context.cacheDir.path (for Android)
)

val engine = Engine(engineConfig)
engine.initialize()
// ... Use the engine to create a conversation ...

// Close the engine when done
engine.close()

  <application>
    <uses-native-library android:name="libvndksupport.so" android:required="false"/>
    <uses-native-library android:name="libOpenCL.so" android:required="false"/>
  </application>

val engineConfig = EngineConfig(
    modelPath = modelPath,
    backend = Backend.NPU(nativeLibraryDir = context.applicationInfo.nativeLibraryDir)
)

import com.google.ai.edge.litertlm.ConversationConfig
import com.google.ai.edge.litertlm.Message
import com.google.ai.edge.litertlm.SamplerConfig

// Optional: Configure the system instruction, initial messages, sampling
// parameters, etc.
val conversationConfig = ConversationConfig(
    systemInstruction = Contents.of("You are a helpful assistant."),
    initialMessages = listOf(
        Message.user("What is the capital city of the United States?"),
        Message.model("Washington, D.C."),
    ),
    samplerConfig = SamplerConfig(topK = 10, topP = 0.95, temperature = 0.8),
)

val conversation = engine.createConversation(conversationConfig)
// Or with default config:
// val conversation = engine.createConversation()

// ... Use the conversation ...

// Close the conversation when done
conversation.close()

engine.createConversation(conversationConfig).use { conversation ->
    // Interact with the conversation
}

import com.google.ai.edge.litertlm.Content
import com.google.ai.edge.litertlm.Message

print(conversation.sendMessage("What is the capital of France?"))

import com.google.ai.edge.litertlm.Content
import com.google.ai.edge.litertlm.Message
import com.google.ai.edge.litertlm.MessageCallback
import java.util.concurrent.CountDownLatch
import java.util.concurrent.TimeUnit

val callback = object : MessageCallback {
    override fun onMessage(message: Message) {
        print(message)
    }

    override fun onDone() {
        // Streaming completed
    }

    override fun onError(throwable: Throwable) {
        // Error during streaming
    }
}

conversation.sendMessageAsync("What is the capital of France?", callback)

import com.google.ai.edge.litertlm.Content
import com.google.ai.edge.litertlm.Message
import kotlinx.coroutines.flow.catch
import kotlinx.coroutines.launch

// Within a coroutine scope
conversation.sendMessageAsync("What is the capital of France?")
    .catch { ... } // Error during streaming
    .collect { print(it.toString()) }

// Initialize the `visionBackend` and/or the `audioBackend`
val engineConfig = EngineConfig(
    modelPath = "/path/to/your/model.litertlm", // Replace with your model path
    backend = Backend.CPU(), // Or Backend.GPU() or Backend.NPU(...)
    visionBackend = Backend.GPU(), // Or Backend.NPU(...)
    audioBackend = Backend.CPU(), // Or Backend.NPU(...)
)

// Sends a message with multi-modality.
// See the Content class for other variants.
conversation.sendMessage(Contents.of(
    Content.ImageFile("/path/to/image"),
    Content.AudioBytes(audioBytes), // ByteArray of the audio
    Content.Text("Describe this image and audio."),
))

import com.google.ai.edge.litertlm.Tool
import com.google.ai.edge.litertlm.ToolParam

class SampleToolSet: ToolSet {
    @Tool(description = "Get the current weather for a city")
    fun getCurrentWeather(
        @ToolParam(description = "The city name, e.g., San Francisco") city: String,
        @ToolParam(description = "Optional country code, e.g., US") country: String? = null,
        @ToolParam(description = "Temperature unit (celsius or fahrenheit). Default: celsius") unit: String = "celsius"
    ): Map<String, Any> {
        // In a real application, you would call a weather API here
        return mapOf("temperature" to 25, "unit" to  unit, "condition" to "Sunny")
    }

    @Tool(description = "Get the sum of a list of numbers.")
    fun sum(
        @ToolParam(description = "The numbers, could be floating point.") numbers: List<Double>,
    ): Double {
        return numbers.sum()
    }
}

import com.google.ai.edge.litertlm.OpenApiTool

class SampleOpenApiTool : OpenApiTool {

    override fun getToolDescriptionJsonString(): String {
        return """
        {
          "name": "addition",
          "description": "Add all numbers.",
          "parameters": {
            "type": "object",
            "properties": {
              "numbers": {
                "type": "array",
                "items": {
                  "type": "number"
                }
              },
              "description": "The list of numbers to sum."
            },
            "required": [
              "numbers"
            ]
          }
        }
        """.trimIndent() // Tip: trim to save tokens
    }

    override fun execute(paramsJsonString: String): String {
        // Parse paramsJsonString with your choice of parser/deserializer and
        // execute the tool.

        // Return the result as a JSON string
        return """{"result": 1.4142}"""
    }
}

val conversation = engine.createConversation(
    ConversationConfig(
        tools = listOf(
            tool(SampleToolSet()),
            tool(SampleOpenApiTool()),
        ),
        // ... other configs
    )
)

// Send messages that might trigger the tool
conversation.sendMessageAsync("What's the weather like in London?", callback)

val conversation = engine.createConversation(
    ConversationConfig(
        tools = listOf(
            tool(SampleOpenApiTool()),
        ),
        automaticToolCalling = false,
    )
)

// Send a message that triggers a tool call.
val responseMessage = conversation.sendMessage("What's the weather like in London?")

// The model returns a Message with `toolCalls` populated.
if (responseMessage.toolCalls.isNotEmpty()) {
    val toolResponses = mutableListOf<Content.ToolResponse>()
    // There can be multiple tool calls in a single response.
    for (toolCall in responseMessage.toolCalls) {
        println("Model wants to call: ${toolCall.name} with arguments: ${toolCall.arguments}")

        // Execute the tool manually with your own logic. `executeTool` is just an example here.
        val toolResponseJson = executeTool(toolCall.name, toolCall.arguments)

        // Collect tool responses.
        toolResponses.add(Content.ToolResponse(toolCall.name, toolResponseJson))
    }

    // Use Message.tool to create the tool response message.
    val toolResponseMessage = Message.tool(Contents.of(toolResponses))

    // Send the tool response message to the model.
    val finalMessage = conversation.sendMessage(toolResponseMessage)
    println("Final answer: ${finalMessage.text}") // e.g., "The weather in London is 25c."
}

bazel run -c opt //kotlin/java/com/google/ai/edge/litertlm/example:tool -- <abs_model_path>