EVA Agent is the core component responsible for intelligent inference and data processing in EVA.

Complete the Qdrant and vLLM dependency installation before continuing.

🛠️ Prerequisites

• A Kubernetes cluster
• kubectl
• Helm
• AWS CLI credentials when using S3 synchronization, ECR token refresh, or ECR images

aws configure
# Enter the AWS Access Key ID, Secret Access Key, and related information.

🚀 Install EVA Agent

Step 1: Register the Helm Repository

helm repo add eva-agent <https://mellerikat.github.io/eva-agent>
helm repo update

Step 2: Download Values Templates

Choose one standalone provider values file. Download values-secret.yaml separately when secrets are managed through values.

• Common secret values
• k3s values
• AWS values
• NCP values

RELEASE_VERSION="3.0.4"
BASE_URL="<https://raw.githubusercontent.com/mellerikat/eva-agent/chartmuseum/release/3.0.4>"
mkdir -p eva-agent
curl -L "$BASE_URL/eva-agent/values-secret.yaml" -o eva-agent/values-secret.yaml
curl -L "$BASE_URL/eva-agent/values-aws.yaml" -o eva-agent/values-aws.yaml
curl -L "$BASE_URL/eva-agent/values-ncp.yaml" -o eva-agent/values-ncp.yaml
curl -L "$BASE_URL/eva-agent/values-k3s.yaml" -o eva-agent/values-k3s.yaml

Step 3: Update Environment-Specific Settings