Skip to main content
Version: 0.1

Getting Started with Envoy AI Gateway

Welcome to the Envoy AI Gateway getting started guide!

This guide will walk you through setting up and using Envoy AI Gateway, a tool for managing GenAI traffic using Envoy.

Guide Structure​

This getting started guide is organized into several sections:

  1. Prerequisites

    • Setting up your Kubernetes cluster
    • Installing required tools
    • Setting up Envoy Gateway

  2. Installation

    • Installing Envoy AI Gateway
    • Configuring the gateway
    • Verifying the installation

  3. Basic Usage

    • Deploying a basic configuration
    • Making your first request
    • Understanding the response format

  4. Connect Providers

    • Setting up OpenAI integration
    • Configuring AWS Bedrock
    • Managing credentials securely

Quick Start​

If you're familiar with Kubernetes and want to get started quickly, run these commands to install Envoy Gateway, Envoy AI Gateway, and deploy a basic configuration:

helm upgrade -i eg oci://docker.io/envoyproxy/gateway-helm \
  --version v1.3.1 \
  --namespace envoy-gateway-system \
  --create-namespace

helm upgrade -i aieg oci://docker.io/envoyproxy/ai-gateway-helm \
  --version v0.1.5 \
  --namespace envoy-ai-gateway-system \
  --create-namespace

kubectl apply -f https://raw.githubusercontent.com/envoyproxy/ai-gateway/refs/tags/v0.1.5/examples/basic/basic.yaml

kubectl wait --timeout=2m -n envoy-gateway-system deployment/envoy-gateway --for=condition=Available
kubectl wait --timeout=2m -n envoy-ai-gateway-system deployment/ai-gateway-controller --for=condition=Available

Make a request​

Check out Making a Request in the Basic Usage Guide

tip

For detailed instructions and explanations, start with the Prerequisites section.

Need Help?​

If you run into any issues: