‫LiteRT-LM Cross-Platform C++ API

#include "runtime/engine/engine.h"

// ...

// 1. Define model assets and engine settings.
auto model_assets = ModelAssets::Create(model_path);
CHECK_OK(model_assets);

auto engine_settings = EngineSettings::CreateDefault(
    model_assets,
    /*backend=*/litert::lm::Backend::CPU);

// 2. Create the main Engine object.
absl::StatusOr<std::unique_ptr<Engine>> engine = Engine::CreateEngine(engine_settings);
CHECK_OK(engine);

// 3. Create a Conversation
auto conversation_config = ConversationConfig::CreateDefault(**engine);
CHECK_OK(conversation_config)
absl::StatusOr<std::unique_ptr<Conversation>> conversation = Conversation::Create(**engine, *conversation_config);
CHECK_OK(conversation);

// 4. Send message to the LLM with blocking call.
absl::StatusOr<Message> model_message = (*conversation)->SendMessage(
    JsonMessage{
        {"role", "user"},
        {"content", "What is the tallest building in the world?"}
    });
CHECK_OK(model_message);

// 5. Print the model message.
std::cout << *model_message << std::endl;

// 6. Send message to the LLM with asynchronous call
// where CreatePrintMessageCallback is a users implemented callback that would
// process the message once a chunk of message output is received.
std::stringstream captured_output;
(*conversation)->SendMessageAsync(
    JsonMessage{
        {"role", "user"},
        {"content", "What is the tallest building in the world?"}
    },
    CreatePrintMessageCallback(std::stringstream& captured_output)
);
// Wait until asynchronous finish or timeout.
*engine->WaitUntilDone(absl::Seconds(10));

// To use multimodality, the engine must be created with vision and audio
// backend depending on the multimodality to be used
auto engine_settings = EngineSettings::CreateDefault(
    model_assets,
    /*backend=*/litert::lm::Backend::CPU,
    /*vision_backend*/litert::lm::Backend::GPU,
    /*audio_backend*/litert::lm::Backend::CPU,
);

// The same steps to create Engine and Conversation as above...

// Send message to the LLM with image data.
absl::StatusOr<Message> model_message = (*conversation)->SendMessage(
    JsonMessage{
        {"role", "user"},
        {"content", { // Now content must be an array.
          {
            {"type", "text"}, {"text", "Describe the following image: "}
          },
          {
            {"type", "image"}, {"path", "/file/path/to/image.jpg"}
          }
        }},
    });
CHECK_OK(model_message);

// Print the model message.
std::cout << *model_message << std::endl;

// Send message to the LLM with audio data.
model_message = (*conversation)->SendMessage(
    JsonMessage{
        {"role", "user"},
        {"content", { // Now content must be an array.
          {
            {"type", "text"}, {"text", "Transcribe the audio: "}
          },
          {
            {"type", "audio"}, {"path", "/file/path/to/audio.wav"}
          }
        }},
    });
CHECK_OK(model_message);

// Print the model message.
std::cout << *model_message << std::endl;

// The content can include multiple image or audio data.
model_message = (*conversation)->SendMessage(
    JsonMessage{
        {"role", "user"},
        {"content", { // Now content must be an array.
          {
            {"type", "text"}, {"text", "First briefly describe the two images "}
          },
          {
            {"type", "image"}, {"path", "/file/path/to/image1.jpg"}
          },
          {
            {"type", "text"}, {"text", "and "}
          },
          {
            {"type", "image"}, {"path", "/file/path/to/image2.jpg"}
          },
          {
            {"type", "text"}, {"text", " then transcribe the content in the audio"}
          },
          {
            {"type", "audio"}, {"path", "/file/path/to/audio.wav"}
          }
        }},
    });
CHECK_OK(model_message);

// Print the model message.
std::cout << *model_message << std::endl;

{
  "role": "model", // Represent who the message is sent from.
  "content": "Hello World!" // Naive text only content.
}

{
  "role": "user",
  "content": [  // Multimodal content.
    // Now the content is composed of parts
    {
      "type": "text",
      "text": "Describe the image in details: "
    },
    {
      "type": "image",
      "path": "/path/to/image.jpg"
    }
  ]
}

{
  "type": "text",
  "text": "this is a text"
}

{
  "type": "image",
  "path": "/path/to/image.jpg"
}

{
  "type": "image",
  "blob": "base64 encoded image bytes as string",
}

{
  "type": "audio",
  "path": "/path/to/audio.wav"
}

{
  "type": "audio",
  "blob": "base64 encoded audio bytes as string",
}

Preface preface = JsonPreface({
  .messages = {
      {"role", "system"},
      {"content", {"You are a model that can do function calling."}}
    },
  .tools = {
    {
      {"name", "get_weather"},
      {"description", "Returns the weather for a given location."},
      {"parameters", {
        {"type", "object"},
        {"properties", {
          {"location", {
            {"type", "string"},
            {"description", "The location to get the weather for."}
          }}
        }},
        {"required", {"location"}}
      }}
    },
    {
      {"name", "get_stock_price"},
      {"description", "Returns the stock price for a given stock symbol."},
      {"parameters", {
        {"type", "object"},
        {"properties", {
          {"stock_symbol", {
            {"type", "string"},
            {"description", "The stock symbol to get the price for."}
          }}
        }},
        {"required", {"stock_symbol"}}
      }}
    }
  },
  .extra_context = {
    {"enable_thinking": false}
  }
});

{
  "role": "model",
  "content": [
    "type": "text",
    "text": "Hello World!"
  ]
}

// 1st Message
{
  "role": "model",
  "content": [
    "type": "text",
    "text": "He"
  ]
}

// 2nd Message
{
  "role": "model",
  "content": [
    "type": "text",
    "text": "llo"
  ]
}

// 3rd Message
{
  "role": "model",
  "content": [
    "type": "text",
    "text": " Wo"
  ]
}

// 4th Message
{
  "role": "model",
  "content": [
    "type": "text",
    "text": "rl"
  ]
}

// 5th Message
{
  "role": "model",
  "content": [
    "type": "text",
    "text": "d!"
  ]
}

LlGuidanceConstraintArg constraint_arg;
constraint_arg.constraint_type = LlgConstraintType::kRegex;
constraint_arg.constraint_string = "a+b+"; // Force output to match this regex

auto response = conversation->SendMessage(
    user_message,
    {.decoding_constraint = constraint_arg}
);