GenAI on EKS Starter Kit¶
A starter kit for deploying and managing GenAI components and examples on Amazon EKS (Elastic Kubernetes Service). This project provides a collection of tools, configurations, components, and examples to help you quickly set up a GenAI project on Kubernetes.
-
Quick Start
Get up and running in minutes with the demo setup
-
Components
Browse 25+ deployable components across 10 categories
-
Examples
Explore AI agents, MCP servers, and more
-
Reference
CLI commands, configuration, FAQ, and security
What's Included¶
| Category | Components |
|---|---|
| NVIDIA Platform | GPU Operator, Monitoring, Dynamo Platform, Dynamo vLLM, AIPerf Benchmark, AIConfigurator |
| AI Gateway | LiteLLM, Kong AI Gateway |
| LLM Model | vLLM, SGLang, TGI, Ollama |
| Embedding Model | Text Embedding Inference (TEI) |
| Guardrail | Guardrails AI |
| Observability | Langfuse, MLflow, Phoenix |
| GUI App | Open WebUI |
| Vector Database | Qdrant, Chroma, Milvus |
| Workflow Automation | n8n |
| AI Agent | OpenClaw |
Architecture Overview¶
graph TB
subgraph EKS["Amazon EKS Cluster"]
subgraph Gateway["AI Gateway"]
LiteLLM
Kong
end
subgraph Models["LLM / Embedding Models"]
vLLM
SGLang
TGI
Ollama
TEI
end
subgraph Apps["Applications"]
OpenWebUI["Open WebUI"]
n8n
OpenClaw
end
subgraph Observability
Langfuse
Phoenix
MLflow
end
subgraph Storage["Vector Databases"]
Qdrant
Chroma
Milvus
end
subgraph NVIDIA["NVIDIA Platform"]
Dynamo["Dynamo Platform"]
GPUOp["GPU Operator"]
end
end
OpenWebUI --> Gateway
Gateway --> Models
Gateway --> Langfuse
Models --> NVIDIA
Apps --> Gateway Disclaimer¶
Warning
This repository is intended for demonstration and learning purposes only. It is not intended for production use. The code provided here is for educational purposes and should not be used in a live environment without proper testing, validation, and modifications.