LLM Node Demo

​

Run the Template

1. Go to Assets/InworldRuntime/Scenes/Nodes and play the LLMNode scene.
2. Enter your request. The AI agent will respond.

​

Understanding the Graph

​

InworldController

​

Workflow

1. When the game starts, InworldController initializes its only module, LLMModule, which creates the LLMInterface.
2. Next, InworldGraphExecutor initializes its graph asset by calling each component’s CreateRuntime(). In this case, only LLMNode.CreateRuntime() is called, using the created LLMInterface as input.
3. After initialization, the graph calls Compile() and returns the executor handle.
4. After compilation, the OnGraphCompiled event is invoked. In this demo, LLMNodeTemplate subscribes to it and enables the UI components. Users can then interact with the graph system.

protected override void OnGraphCompiled(InworldGraphAsset obj)
{
    foreach (InworldUIElement element in m_UIElements)
        element.Interactable = true;

}

5. When the user sends text, this demo wraps the message into an LLMChatRequest and sends it to the LLM as raw input.

public async void SendText()
{
    if (!InworldController.LLM)
    {
        Debug.LogError("Cannot find LLM Module!");
        return;
    }
    // Compose the input into `LLMChatRequest`
    InworldMessage message = PlayerSpeaks(m_InputField.text);
    m_InputField.text = "";
    LLMChatRequest llmChatRequest = new LLMChatRequest(m_Messages);
    await m_InworldGraphExecutor.ExecuteGraphAsync("LLM", llmChatRequest);
}

6. Calling ExecuteGraphAsync() eventually produces a result and invokes OnGraphResult(), which LLMCanvas subscribes to in order to receive the data.