Examples

This page provides complete, ready-to-use examples that demonstrate common workflows with the Runtime Local LLM plugin. Each example includes both Blueprint and C++ implementations.

Make sure you've read How to use the plugin first for an overview of the API.

Simple Chat

Create an LLM instance, load a model by name, send a message, and display the response token by token.

Blueprint

Copyable nodes.

C++

// Assuming "this" is an AActor with a UPROPERTY() URuntimeLocalLLM* LLM member
// Note: Callback functions (OnModelReady, OnToken, OnComplete, OnLLMError) must be marked as UFUNCTION() in your header file

void AMyActor::BeginPlay()
{
    Super::BeginPlay();

    LLM = URuntimeLocalLLM::CreateRuntimeLocalLLM();

    LLM->OnModelLoadedNative.AddUObject(this, &AMyActor::OnModelReady);
    LLM->OnTokenGeneratedNative.AddUObject(this, &AMyActor::OnToken);
    LLM->OnGenerationCompleteNative.AddUObject(this, &AMyActor::OnComplete);
    LLM->OnErrorNative.AddUObject(this, &AMyActor::OnLLMError);

    FLLMInferenceParams Params;
    Params.MaxTokens = 512;
    Params.Temperature = 0.7f;
    Params.SystemPrompt = TEXT("You are a helpful assistant.");

    TArray<FLLMModelMetadata> DownloadedModels = URuntimeLLMLibrary::GetAllDownloadedModelMetadata();

    // For demonstration purposes, we simply pick the first available model, swap this with your own selection logic as needed
    if (DownloadedModels.Num() > 0)
    {
        const FLLMModelMetadata& Model = DownloadedModels[0]; // Select the first available model
        FString ModelFileName = URuntimeLLMLibrary::GetModelFileName(Model);
        LLM->LoadModelByName(FName(*ModelFileName), Params);
    }
}

void AMyActor::OnModelReady(const FLLMModelMetadata& Metadata)
{
    UE_LOG(LogTemp, Log, TEXT("Model ready: %s"), *Metadata.ModelDisplayName);
    LLM->SendMessage(TEXT("Hello! Tell me a fun fact."));
}

void AMyActor::OnToken(const FString& Token)
{
    // Handle each token as it's generated (e.g. append to a string, update UI, stream to audio, etc)
    UE_LOG(LogTemp, Log, TEXT("%s"), *Token);
}

void AMyActor::OnComplete(const FString& FullResponse, float Duration, int32 Tokens, float TPS)
{
    UE_LOG(LogTemp, Log, TEXT("Done: %d tokens in %.1fs (%.1f tok/s)"), Tokens, Duration, TPS);
}

void AMyActor::OnLLMError(ELLMErrorCode ErrorCode)
{
    FText Desc = URuntimeLLMUtils::GetLLMErrorDescription(ErrorCode);
    UE_LOG(LogTemp, Error, TEXT("LLM Error: %s"), *Desc.ToString());
}

Download, Load, and Chat

Download a model from a URL at runtime, load it, and start a conversation. The download is skipped if the model already exists on disk.

Blueprint

Copyable nodes.

C++

// Assuming "this" is an AActor with a UPROPERTY() URuntimeLocalLLM* LLM member
// Note: Callback functions (OnProgress, OnModelReady, OnToken, OnComplete, OnLLMError) must be marked as UFUNCTION() in your header file

void AMyActor::BeginPlay()
{
    Super::BeginPlay();

    LLM = URuntimeLocalLLM::CreateRuntimeLocalLLM();

    LLM->OnDownloadProgressNative.AddUObject(this, &AMyActor::OnProgress);
    LLM->OnModelLoadedNative.AddUObject(this, &AMyActor::OnModelReady);
    LLM->OnTokenGeneratedNative.AddUObject(this, &AMyActor::OnToken);
    LLM->OnGenerationCompleteNative.AddUObject(this, &AMyActor::OnComplete);
    LLM->OnErrorNative.AddUObject(this, &AMyActor::OnLLMError);

    FLLMInferenceParams Params;
    Params.MaxTokens = 256;
    LLM->LoadModelFromURLSimple(
        TEXT("https://huggingface.co/bartowski/Llama-3.2-1B-Instruct-GGUF/resolve/main/Llama-3.2-1B-Instruct-Q4_K_M.gguf"), Params);
}

void AMyActor::OnProgress(float Progress, int64 BytesReceived, int64 TotalBytes)
{
    FString ProgressText = URuntimeLLMUtils::FormatDownloadProgress(BytesReceived, TotalBytes);
    UE_LOG(LogTemp, Log, TEXT("Downloading: %s"), *ProgressText);
}

void AMyActor::OnModelReady(const FLLMModelMetadata& Metadata)
{
    LLM->SendMessage(TEXT("What is the capital of France?"));
}

void AMyActor::OnToken(const FString& Token)
{
    // Handle each token as it's generated (e.g. append to a string, update UI, stream to audio, etc)
    UE_LOG(LogTemp, Log, TEXT("%s"), *Token);
}

void AMyActor::OnComplete(const FString& FullResponse, float Duration, int32 Tokens, float TPS)
{
    UE_LOG(LogTemp, Log, TEXT("Done: %d tokens in %.1fs (%.1f tok/s)"), Tokens, Duration, TPS);
}

void AMyActor::OnLLMError(ELLMErrorCode ErrorCode)
{
    FText Desc = URuntimeLLMUtils::GetLLMErrorDescription(ErrorCode);
    UE_LOG(LogTemp, Error, TEXT("LLM Error: %s"), *Desc.ToString());
}

Pre-download Models

Download models to disk without loading, useful for a settings screen or loading menu where users pick models to cache ahead of time.

Blueprint

Copyable nodes.

C++

// Assuming "this" is an AActor with a UPROPERTY() URuntimeLocalLLM* LLM member
// Note: Callback functions (OnProgress, OnDownloaded, OnLLMError) must be marked as UFUNCTION() in your header file

void AMyActor::StartPredownload()
{
    LLM = URuntimeLocalLLM::CreateRuntimeLocalLLM();

    LLM->OnDownloadProgressNative.AddUObject(this, &AMyActor::OnProgress);
    LLM->OnModelDownloadedNative.AddUObject(this, &AMyActor::OnDownloaded);
    LLM->OnErrorNative.AddUObject(this, &AMyActor::OnLLMError);

    LLM->DownloadModelFromURL(
        TEXT("https://huggingface.co/user/model/resolve/main/model-Q4_K_M.gguf"));
}

void AMyActor::OnProgress(float Progress, int64 BytesReceived, int64 TotalBytes)
{
    FString ProgressText = URuntimeLLMUtils::FormatDownloadProgress(BytesReceived, TotalBytes);
    UE_LOG(LogTemp, Log, TEXT("Downloading: %s"), *ProgressText);
}

void AMyActor::OnDownloaded(const FString& FilePath, const FLLMModelMetadata& Metadata)
{
    UE_LOG(LogTemp, Log, TEXT("Model saved to: %s"), *FilePath);
    // Model is now on disk - load it later with LoadModelByName or LoadModelFromFile
}

void AMyActor::OnLLMError(ELLMErrorCode ErrorCode)
{
    FText Desc = URuntimeLLMUtils::GetLLMErrorDescription(ErrorCode);
    UE_LOG(LogTemp, Error, TEXT("LLM Error: %s"), *Desc.ToString());
}

NPC Dialogue

A basic NPC dialogue system where the player types a message and the NPC responds. The conversation context persists between messages so the NPC remembers previous exchanges.

Blueprint

Copyable nodes.

C++

// Assuming "this" is an AActor with a UPROPERTY() URuntimeLocalLLM* LLM member
// Note: Callback functions (OnToken, OnComplete, OnLLMError) must be marked as UFUNCTION() in your header file

void ANPCActor::BeginPlay()
{
    Super::BeginPlay();

    LLM = URuntimeLocalLLM::CreateRuntimeLocalLLM();

    LLM->OnTokenGeneratedNative.AddUObject(this, &ANPCActor::OnToken);
    LLM->OnGenerationCompleteNative.AddUObject(this, &ANPCActor::OnComplete);
    LLM->OnErrorNative.AddUObject(this, &AMyActor::OnLLMError);

    FLLMInferenceParams Params;
    Params.MaxTokens = 150;
    Params.Temperature = 0.9f;
    Params.SystemPrompt = TEXT(
        "You are a grumpy blacksmith in a medieval village. "
        "Keep responses to 2-3 sentences. Stay in character.");

    // For demonstration purposes, we simply pick the first available model, swap this with your own selection logic as needed
    if (DownloadedModels.Num() > 0)
    {
        const FLLMModelMetadata& Model = DownloadedModels[0]; // Select the first available model
        FString ModelFileName = URuntimeLLMLibrary::GetModelFileName(Model);
        LLM->LoadModelByName(FName(*ModelFileName), Params);
    }
}

void ANPCActor::OnPlayerInteract(const FString& PlayerMessage)
{
    if (LLM->IsModelLoaded() && !LLM->IsGenerating())
    {
        LLM->SendMessage(PlayerMessage);
    }
}

void ANPCActor::OnToken(const FString& Token)
{
    // Stream token into dialogue widget
}

void ANPCActor::OnComplete(const FString& FullResponse, float Duration, int32 Tokens, float TPS)
{
    // Re-enable player input
}

void ANPCActor::OnPlayerLeaves()
{
    // Reset for next encounter
    LLM->ResetContext(true); // Keep system prompt
}