Overview

Create characters in Unity with LLMs!

LLM for Unity enables seamless integration of Large Language Models (LLMs) within the Unity engine.
It allows to create intelligent characters that your players can interact with for an immersive experience.
The package also features a Retrieval-Augmented Generation (RAG) system that allows to performs semantic search across your data, which can be used to enhance the character's knowledge. LLM for Unity is built on top of the awesome llama.cpp library.

At a glance

• 💻 Runs anywhere: PC, mobile or VR!
• 🏠 Runs locally without internet access. No data ever leave the game!
• ⚡ Blazing fast inference on CPU and GPU (Nvidia, AMD, Apple Metal)
• 🤗 Supports all major LLM models
• 🔧 Easy to setup, call with a single line of code
• 💰 Free to use for both personal and commercial purposes

🧪 Tested on Unity: 2021 LTS, 2022 LTS, 2023, Unity 6
🚦 Upcoming Releases

How to help

• ⭐ Star the repo, leave us a review and spread the word about the project!
• Join us at Discord and say hi.
• Contribute by submitting feature requests, bugs or even your own PR.
• this work to allow even cooler features!

Games / Projects using LLM for Unity

• Verbal Verdict
• I, Chatbot: AISYLUM
• Nameless Souls of the Void
• Murder in Aisle 4
• Finicky Food Delivery AI
• AI Emotional Girlfriend
• Case Closed
• MaiMai AI Agent System
• Claria Chat
• Endless Casual Drive
• Dating App Simulator
• Virtual Reality Mock Interview
• Velesio AI server
• Dungeon Chat
• Tomonaka Desk
• Digital Humans

Contact us to add your project!

Setup

Method 1: Install using the asset store

• Open the LLM for Unity asset page and click Add to My Assets
• Open the Package Manager in Unity: Window > Package Manager
• Select the Packages: My Assets option from the drop-down
• Select the LLM for Unity package, click Download and then Import

Method 2: Install using the GitHub repo:

• Open the Package Manager in Unity: Window > Package Manager
• Click the + button and select Add package from git URL
• Use the repository URL https://github.com/undreamai/LLMUnity.git and click Add

How to use

First you will setup the LLM for your game 🏎:

• Create an empty GameObject.
  In the GameObject Inspector click Add Component and select the LLM script.
• Download one of the default models with the Download Model button (~GBs).
  Or load your own .gguf model with the Load model button (see LLM model management).

Then you can setup each of your characters as follows 🙋‍♀️:

• Create an empty GameObject for the character.
  In the GameObject Inspector click Add Component and select the LLMCharacter script.
• Define the role of your AI in the Prompt. You can define the name of the AI (AI Name) and the player (Player Name).
• (Optional) Select the LLM constructed above in the LLM field if you have more than one LLM GameObjects.

You can also adjust the LLM and character settings according to your preference (see Options).

In your script you can then use it as follows 🦄:

using LLMUnity;
 
public class MyScript {
  public LLMCharacter llmCharacter;
  
  void HandleReply(string reply){
    // do something with the reply from the model
    Debug.Log(reply);
  }
  
  void Game(){
    // your game function
    ...
    string message = "Hello bot!";
    _ = llmCharacter.Chat(message, HandleReply);
    ...
  }
}

You can also specify a function to call when the model reply has been completed.
This is useful if the Stream option is enabled for continuous output from the model (default behaviour):

void ReplyCompleted(){
  // do something when the reply from the model is complete
  Debug.Log("The AI replied");
}
 
void Game(){
  // your game function
  ...
  string message = "Hello bot!";
  _ = llmCharacter.Chat(message, HandleReply, ReplyCompleted);
  ...
}

To stop the chat without waiting for its completion you can use:

llmCharacter.CancelRequests();

• Finally, in the Inspector of the GameObject of your script, select the LLMCharacter GameObject created above as the llmCharacter property.

That's all ✨!

You can also:

Build a mobile app

For mobile apps you can use models with up to 1-2 billion parameters ("Tiny models" in the LLM model manager).
Larger models will typically not work due to the limited mobile hardware.

iOS iOS can be built with the default player settings.

Android On Android you need to specify the IL2CPP scripting backend and the ARM64 as the target architecture in the player settings.
These settings can be accessed from the Edit > Project Settings menu within the Player > Other Settings section.

Since mobile app sizes are typically small, you can download the LLM models the first time the app launches. This functionality can be enabled with the Download on Build option. In your project you can wait until the model download is complete with:

await LLM.WaitUntilModelSetup();

You can also receive calls during the download with the download progress:

await LLM.WaitUntilModelSetup(SetProgress);
 
void SetProgress(float progress){
  string progressPercent = ((int)(progress * 100)).ToString() + "%";
  Debug.Log($"Download progress: {progressPercent}");
}

This is useful to present a progress bar or something similar. The MobileDemo is an example application for Android / iOS.

Restrict the output of the LLM / Function calling

To restrict the output of the LLM you can use a grammar, read more here.
The grammar can be saved in a .gbnf file and loaded at the LLMCharacter with the Load Grammar button (Advanced options).
For instance to receive replies in json format you can use the json.gbnf grammar.
Graamars in JSON schema format are also supported and can be loaded with the Load JSON Grammar button (Advanced options).

Alternatively you can set the grammar directly with code:

// GBNF grammar
llmCharacter.grammarString = "your GBNF grammar here";
 
// or JSON schema grammar
llmCharacter.grammarJSONString = "your JSON schema grammar here";

For function calling you can define similarly a grammar that allows only the function names as output, and then call the respective function.
You can look into the FunctionCalling sample for an example implementation.

Access / Save / Load your chat history

The chat history of a LLMCharacter is retained in the chat variable that is a list of ChatMessage objects.
The ChatMessage is a struct that defines the role of the message and the content.
The first element of the list is always the system prompt and then alternating messages with the player prompt and the AI reply.
You can modify the chat history directly in this list.

To automatically save / load your chat history, you can specify the Save parameter of the LLMCharacter to the filename (or relative path) of your choice. The file is saved in the persistentDataPath folder of Unity. This also saves the state of the LLM which means that the previously cached prompt does not need to be recomputed.

To manually save your chat history, you can use:

llmCharacter.Save("filename");

and to load the history:

llmCharacter.Load("filename");

where filename the filename or relative path of your choice.

Process the prompt at the beginning of your app for faster initial processing time

void WarmupCompleted(){
  // do something when the warmup is complete
  Debug.Log("The AI is nice and ready");
}
 
void Game(){
  // your game function
  ...
  _ = llmCharacter.Warmup(WarmupCompleted);
  ...
}

Decide whether or not to add the message to the chat/prompt history

The last argument of the Chat function is a boolean that specifies whether to add the message to the history (default: true):

void Game(){
  // your game function
  ...
  string message = "Hello bot!";
  _ = llmCharacter.Chat(message, HandleReply, ReplyCompleted, false);
  ...
}

Use pure text completion

void Game(){
  // your game function
  ...
  string message = "The cat is away";
  _ = llmCharacter.Complete(message, HandleReply, ReplyCompleted);
  ...
}

Wait for the reply before proceeding to the next lines of code

For this you can use the async/await functionality:

async void Game(){
  // your game function
  ...
  string message = "Hello bot!";
  string reply = await llmCharacter.Chat(message, HandleReply, ReplyCompleted);
  Debug.Log(reply);
  ...
}

Add a LLM / LLMCharacter component programmatically

using UnityEngine;
using LLMUnity;
 
public class MyScript : MonoBehaviour
{
    LLM llm;
    LLMCharacter llmCharacter;
 
    async void Start()
    {
        // disable gameObject so that theAwake is not called immediately
        gameObject.SetActive(false);
 
        // Add an LLM object
        llm = gameObject.AddComponent<LLM>();
        // set the model using the filename of the model.
        // The model needs to be added to the LLM model manager (see LLM model management) by loading or downloading it.
        // Otherwise the model file can be copied directly inside the StreamingAssets folder.
        llm.SetModel("Phi-3-mini-4k-instruct-q4.gguf");
        // optional: you can also set loras in a similar fashion and set their weights (if needed)
        llm.AddLora("my-lora.gguf");
        llm.SetLoraWeight(0.5f);
        // optional: you can set the chat template of the model if it is not correctly identified
        // You can find a list of chat templates in the ChatTemplate.templates.Keys
        llm.SetTemplate("phi-3");
        // optional: set number of threads
        llm.numThreads = -1;
        // optional: enable GPU by setting the number of model layers to offload to it
        llm.numGPULayers = 10;
 
        // Add an LLMCharacter object
        llmCharacter = gameObject.AddComponent<LLMCharacter>();
        // set the LLM object that handles the model
        llmCharacter.llm = llm;
        // set the character prompt
        llmCharacter.SetPrompt("A chat between a curious human and an artificial intelligence assistant.");
        // set the AI and player name
        llmCharacter.AIName = "AI";
        llmCharacter.playerName = "Human";
        // optional: set streaming to false to get the complete result in one go
        // llmCharacter.stream = true;
        // optional: set a save path
        // llmCharacter.save = "AICharacter1";
        // optional: enable the save cache to avoid recomputation when loading a save file (requires ~100 MB)
        // llmCharacter.saveCache = true;
        // optional: set a grammar
        // await llmCharacter.SetGrammar("json.gbnf");
 
        // re-enable gameObject
        gameObject.SetActive(true);
    }
}

Use a remote server

You can use a remote server to carry out the processing and implement characters that interact with it.

Create the server
To create the server:

• Create a project with a GameObject using the LLM script as described above
• Enable the Remote option of the LLM and optionally configure the server parameters: port, API key, SSL certificate, SSL key
• Build and run to start the server

Alternatively you can use a server binary for easier deployment:

• Run the above scene from the Editor and copy the command from the Debug messages (starting with "Server command:")
• Download the server binaries and DLLs and extract them into the same folder
• Find the architecture you are interested in from the folder above e.g. for Windows and CUDA use the windows-cuda-cu12.2.0.
  You can also check the architecture that works for your system from the Debug messages (starting with "Using architecture").
• From command line change directory to the architecture folder selected and start the server by running the command copied from above.

In both cases you'll need to enable 'Allow Downloads Over HTTP' in the project settings.

Create the characters
Create a second project with the game characters using the LLMCharacter script as described above. Enable the Remote option and configure the host with the IP address (starting with "http://") and port of the server.

Compute embeddings using a LLM

The Embeddings function can be used to obtain the emdeddings of a phrase:

List<float> embeddings = await llmCharacter.Embeddings("hi, how are you?");

A detailed documentation on function level can be found here:

Semantic search with a Retrieval-Augmented Generation (RAG) system

LLM for Unity implements a super-fast similarity search functionality with a Retrieval-Augmented Generation (RAG) system.
It is based on the LLM functionality, and the Approximate Nearest Neighbors (ANN) search from the usearch library.
Semantic search works as follows.

Building the data You provide text inputs (a phrase, paragraph, document) to add to the data.
Each input is split into chunks (optional) and encoded into embeddings with a LLM.

Searching You can then search for a query text input.
The input is again encoded and the most similar text inputs or chunks in the data are retrieved.

To use semantic serch:

• create a GameObject for the LLM as described above. Download one of the provided RAG models or load your own (good options can be found at the MTEB leaderboard).
• create an empty GameObject. In the GameObject Inspector click Add Component and select the RAG script.
• In the Search Type dropdown of the RAG select your preferred search method. SimpleSearch is a simple brute-force search, whileDBSearch is a fast ANN method that should be preferred in most cases.
• In the Chunking Type dropdown of the RAG you can select a method for splitting the inputs into chunks. This is useful to have a more consistent meaning within each data part. Chunking methods for splitting according to tokens, words and sentences are provided.

Alternatively, you can create the RAG from code (where llm is your LLM):

RAG rag = gameObject.AddComponent<RAG>();
rag.Init(SearchMethods.DBSearch, ChunkingMethods.SentenceSplitter, llm);

In your script you can then use it as follows :unicorn::

using LLMUnity;
 
public class MyScript : MonoBehaviour
{
  RAG rag;
 
  async void Game(){
    ...
    string[] inputs = new string[]{
      "Hi! I'm a search system.",
      "the weather is nice. I like it.",
      "I'm a RAG system"
    };
    // add the inputs to the RAG
    foreach (string input in inputs) await rag.Add(input);
    // get the 2 most similar inputs and their distance (dissimilarity) to the search query
    (string[] results, float[] distances) = await rag.Search("hello!", 2);
    // to get the most similar text parts (chnuks) you can enable the returnChunks option
    rag.ReturnChunks(true);
    (results, distances) = await rag.Search("hello!", 2);
    ...
  }
}

You can also add / search text inputs for groups of data e.g. for a specific character or scene:

    // add the inputs to the RAG for a group of data e.g. an orc character
    foreach (string input in inputs) await rag.Add(input, "orc");
    // get the 2 most similar inputs for the group of data e.g. the orc character
    (string[] results, float[] distances) = await rag.Search("how do you feel?", 2, "orc");
...
 
You can save the RAG state (stored in the `Assets/StreamingAssets` folder):

{.cs} rag.Save("rag.zip");

and load it from disk:

{.cs} await rag.Load("rag.zip");

You can use the RAG to feed relevant data to the LLM based on a user message:

{.cs} string message = "How is the weather?"; (string[] similarPhrases, float[] distances) = await rag.Search(message, 3);

string prompt = "Answer the user query based on the provided data. "; prompt += $"User query: {message} "; prompt += $"Data: "; foreach (string similarPhrase in similarPhrases) prompt += $" - {similarPhrase}";

_ = llmCharacter.Chat(prompt, HandleReply, ReplyCompleted); ```

The RAG sample includes an example RAG implementation as well as an example RAG-LLM integration.

That's all :sparkles:!

LLM model management

LLM for Unity uses a model manager that allows to load or download LLMs and ship them directly in your game.
The model manager can be found as part of the LLM GameObject:

You can download models with the Download model button.
LLM for Unity includes different state of the art models built-in for different model sizes, quantised with the Q4_K_M method.
Alternative models can be downloaded from HuggingFace in the .gguf format.
You can download a model locally and load it with the Load model button, or copy the URL in the Download model > Custom URL field to directly download it.
If a HuggingFace model does not provide a gguf file, it can be converted to gguf with this online converter.

The chat template used for constructing the prompts is determined automatically from the model (if a relevant entry exists) or the model name.
If incorrecly identified, you can select another template from the chat template dropdown.

Models added in the model manager are copied to the game during the building process.
You can omit a model from being built in by deselecting the "Build" checkbox.
To remove the model (but not delete it from disk) you can click the bin button.
The the path and URL (if downloaded) of each added model is diplayed in the expanded view of the model manager access with the >> button:

You can create lighter builds by selecting the Download on Build option.
Using this option the models will be downloaded the first time the game starts instead of copied in the build.
If you have loaded a model locally you need to set its URL through the expanded view, otherwise it will be copied in the build.

❕ Before using any model make sure you check their license ❕

Examples

The Samples~ folder contains several examples of interaction 🤖:

• SimpleInteraction: Simple interaction with an AI character
• MultipleCharacters: Simple interaction using multiple AI characters
• FunctionCalling: Function calling sample with structured output from the LLM
• RAG: Semantic search using a Retrieval Augmented Generation (RAG) system. Includes example using a RAG to feed information to a LLM
• MobileDemo: Example mobile app for Android / iOS with an initial screen displaying the model download progress
• ChatBot: Interaction between a player and a AI with a UI similar to a messaging app (see image below)
• KnowledgeBaseGame: Simple detective game using a knowledge base to provide information to the LLM based on google/mysteryofthreebots

To install a sample:

• Open the Package Manager: Window > Package Manager
• Select the LLM for Unity Package. From the Samples Tab, click Import next to the sample you want to install.

The samples can be run with the Scene.unity scene they contain inside their folder.
In the scene, select the LLM GameObject and click the Download Model button to download a default model or Load model to load your own model (see LLM model management).
Save the scene, run and enjoy!

Options

Details on the different parameters are provided as Unity Tooltips. Previous documentation can be found here (deprecated).

License

The license of LLM for Unity is MIT (LICENSE.md) and uses third-party software with MIT and Apache licenses. Some models included in the asset define their own license terms, please review them before using each model. Third-party licenses can be found in the (Third Party Notices.md).