Ví dụ
Trang này cung cấp các ví dụ hoàn chỉnh, sẵn sàng sử dụng để minh họa các quy trình làm việc phổ biến với plugin Runtime Local LLM. Mỗi ví dụ bao gồm cả triển khai bằng Blueprint và C++.
Hãy đảm bảo bạn đã đọc Cách sử dụng plugin trước để có cái nhìn tổng quan về API.
Simple Chat
Tạo một phiên bản LLM, tải một mô hình theo tên, gửi một tin nhắn và hiển thị phản hồi từng token một.
- Blueprint
- 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());
}
Tải xuống, Tải lên và Trò chuyện
Tải xuống một mô hình từ URL trong thời gian chạy, tải nó lên và bắt đầu một cuộc trò chuyện. Quá trình tải xuống sẽ được bỏ qua nếu mô hình đã tồn tại trên đĩa.
- Blueprint
- 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());
}
Tải trước Mô hình
Tải các mô hình xuống ổ đĩa mà không cần tải vào bộ nhớ, hữu ích cho màn hình cài đặt hoặc menu tải, nơi người dùng chọn mô hình để lưu vào bộ nhớ đệm trước.
- Blueprint
- 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
Một hệ thống hội thoại NPC cơ bản, nơi người chơi nhập tin nhắn và NPC phản hồi. Ngữ cảnh hội thoại được duy trì giữa các tin nhắn để NPC có thể nhớ các trao đổi trước đó.
- Blueprint
- 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
}