Skip to main content

AWS Solutions Library

Guidance for Dynamic Non-Player Character (NPC) Dialogue on AWS

Go to sample code

Overview

This Guidance helps game developers automate the creation of non-player characters (NPCs) that dynamically respond to player questions based on custom in-game knowledge and personality. This deployable template sets up API access to large language models (LLMs) in Amazon Bedrock, enabling a game client to connect and prompt the models with player input. Any of the available models in Amazon Bedrock, such as Amazon Nova, Claude, and Llama, can be used to generate dynamic responses from the NPC, enhancing scripted dialogue and creating unique player interactions. At the same time, it ensures that the NPC has secure access to a comprehensive knowledge base of game lore. This Guidance includes architecture sample code and engine integration example for quick and effective deployment.

How it works

Overview

This architecture diagram shows an overview workflow for hosting a generative AI NPC on AWS.

Download architecture diagram
Architecture diagram showing how Unreal Engine integrates with various AWS services such as Amazon Bedrock, Amazon API Gateway, AWS Lambda, Amazon Polly, Amazon OpenSearch Service, and Amazon S3 to enable dynamic NPC dialogue. Infrastructure engineer and narrative writer roles are included, along with LLMOps and fine-tuning pipelines, RAG API, and vector database hydration steps.

LLMOps Pipeline

This architecture diagram shows the processes of deploying an LLMOps pipeline on AWS.

Download architecture diagram
Missing alt text value

FMOps Pipeline

This architecture diagram shows the process of tuning a generative AI model using FMOps.

Download architecture diagram
Missing alt text value

Database Hydration

This architecture diagram shows the process for database hydration by vectorizing and storing gamer lore for RAG.

Download architecture diagram
Missing alt text value

Well-Architected Pillars

The architecture diagram above is an example of a Solution created with Well-Architected best practices in mind. To be fully Well-Architected, you should follow as many Well-Architected best practices as possible.

This Guidance uses Lambda, API Gateway, and CloudWatch to track all API requests for generated NPC dialogue between the Unreal Engine client and the Amazon Bedrock foundation model. This provides end-to-end visibility into the status of the Guidance, allowing you to granularly track each request and response from the game client so you can quickly identify issues and react accordingly. Additionally, this Guidance is codified as a CDK application using CodePipeline,sooperations teams and developers can address faults and bugs through appropriate change control methodologies and quickly deploy these updates or fixes using the CI/CD pipeline.

Read the Operational Excellence whitepaper

Amazon S3 provides encrypted protection for storing game lore documentation at rest in addition to encrypted access for data in transit, while ingesting game lore documentation into the vector or fine-tuning an Amazon Bedrock foundation model. API Gateway adds an additional layer of security between the Unreal Engine and the Amazon Bedrock foundation model by providing TLS-based encryption of all data between the NPC and the model. Lastly, Amazon Bedrock implements automated abuse detection mechanisms to further identify and mitigate violations of the AWS Acceptable Use Policy and the AWS Responsible AI Policy.

Read the Security whitepaper

API Gateway manages the automated scaling and throttling of requests by the NPC to the foundation model. Additionally, since the entire infrastructure is codified using CI/CD pipelines, you can provision resources across multiple AWS accounts and multiple AWS Regions in parallel. This enables multiple simultaneous infrastructure re-deployment scenarios to help you overcome AWS Region-level failures. As serverless infrastructure resources, API Gateway and Lambda allow you to focus on game development instead of manually managing resource allocation and usage patterns for API requests.

Read the Reliability whitepaper

Serverless resources, such as Lambda and API Gateway, contribute to the efficiency of the Guidance by providing both elasticity and scalability. This allows the Guidance to dynamically adapt to an increase or decrease in API calls from the NPC client. An elastic and scalable approach helps you right-size resources for optimal performance and to address unforeseen increases or decreases in API requests—without having to manually manage provisioned infrastructure resources.

Read the Performance Efficiency whitepaper

Codifying the Guidance as a CDK application provides game developers with the ability to quickly prototype and deploy their NPC characters into production. Amazon Bedrock gives developers quick access to foundation models hosted on Amazon Bedrock through an API Gateway REST API without having to engineer, build, and pre-train them. Turning around quick prototypes helps reduce the time and operations costs associated with building foundation models from scratch.

Read the Cost Optimization whitepaper

Lambda provides a serverless, scalable, and event-driven approach without having to provision dedicated compute resources. Amazon S3 implements data lifecycle policies along with compression for all data across this Guidance, allowing for energy-efficient storage. Amazon Bedrock hosts foundation models on AWS silicon, offering better performance per watt of standard compute resources.

Read the Sustainability whitepaper

Implementation Resources

The sample code is a starting point. It is industry validated, prescriptive but not definitive, and a peek under the hood to help you begin.
Open sample code on GitHub

Disclaimer

The sample code; software libraries; command line tools; proofs of concept; templates; or other related technology (including any of the foregoing that are provided by our personnel) is provided to you as AWS Content under the AWS Customer Agreement, or the relevant written agreement between you and AWS (whichever applies). You should not use this AWS Content in your production accounts, or on production or other critical data. You are responsible for testing, securing, and optimizing the AWS Content, such as sample code, as appropriate for production grade use based on your specific quality control practices and standards. Deploying AWS Content may incur AWS charges for creating or using AWS chargeable resources, such as running Amazon EC2 instances or using Amazon S3 storage.