Important
The Hybrid deployment option requires an Enterprise plan.
Prerequisites
- Use the LangGraph CLI to test your application locally.
- Use the LangGraph CLI to build a Docker image (i.e.
langgraph build
) and push it to a registry your Kubernetes cluster or Amazon ECS cluster has access to.
Kubernetes
Prerequisites
KEDA
is installed on your cluster.
- A valid
Ingress
controller is installed on your cluster. - You have slack space in your cluster for multiple deployments.
Cluster-Autoscaler
is recommended to automatically provision new nodes. - You will need to enable egress to two control plane URLs. The listener polls these endpoints for deployments:
Setup
- You give us your LangSmith organization ID. We will enable the Self-Hosted Data Plane for your organization.
- We provide you a Helm chart which you run to setup your Kubernetes cluster. This chart contains a few important components.
langgraph-listener
: This is a service that listens to LangChain’s control plane for changes to your deployments and creates/updates downstream CRDs.LangGraphPlatform CRD
: A CRD for LangGraph Platform deployments. This contains the spec for managing an instance of a LangGraph Platform deployment.langgraph-platform-operator
: This operator handles changes to your LangGraph Platform CRDs.
- Configure your
langgraph-dataplane-values.yaml
file.
- Deploy
langgraph-dataplane
Helm chart.
- If successful, you will see three services start up in your namespace.
- You create a deployment from the control plane UI.