Using Kubernetes (Beta)

Deploy LangDB AI Gateway on Kubernetes using Helm, connecting to external Postgres, Redis, and ClickHouse for scalable, cloud-native operations.

Work in Progress.

This guide walks you through deploying the LangDB AI Gateway enterp Refer to individual database links for deploying and scaling clusters for postgres, redis and clickhouse.

Checkout the repository https://github.com/langdb/helm-chart

Deploy using Helm

Clone the Repository

git clone [email protected]:langdb/helm-chart.git
cd helm-chart/helm/ai-gateway

This will deploy:

• ai-gateway (using the default image)

• uses External Postgres, Redis, and ClickHouse

Configure values.yaml

env:
  CLICKHOUSE_HOST: <external-clickhouse-host>
  REDIS_HOST: <external-redis-host>
  POSTGRES_HOST: <external-postgres-host>
  POSTGRES_USER: <your-user>
  POSTGRES_PASSWORD: <your-password>
  POSTGRES_DB: <your-db>
config: |
  # ai-gateway configuration
  http:
    host: "0.0.0.0"
    port: 8080

This will automatically mount your config.yaml into the container at /app/config.yaml and the ai-gateway will use it on startup.

Deploy Using Helm

Run the following command to install the AI Gateway:

helm install ai-gateway .

This deploys:

• ai-gateway using the default image.

• Connections to external Postgres, Redis, and ClickHouse instances.

Accessing AI Gateway

By default, the service is exposed as a ClusterIP. To access it externally, you can port-forward:

kubectl port-forward svc/ai-gateway 8080:80

Then access the gateway at http://localhost:8080.

---

Uninstall

To remove the deployment:

helm uninstall ai-gateway

---

Check out the full source repository here: https://github.com/langdb/helm-chart