Deploy CodeGen in a Kubernetes Cluster

This document outlines the deployment process for a Code Generation (CodeGen) application that utilizes the GenAIComps microservice components on Intel Xeon servers and Gaudi machines.

Install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section “Getting Started” at GMC Install. We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.

If you have only Intel Xeon machines you could use the codegen_xeon.yaml file or if you have a Gaudi cluster you could use codegen_gaudi.yaml In the below example we illustrate on Xeon.

Deploy the RAG application

  1. Create the desired namespace if it does not already exist and deploy the application

    export APP_NAMESPACE=CT
    kubectl create ns $APP_NAMESPACE
    sed -i "s|namespace: codegen|namespace: $APP_NAMESPACE|g"  ./codegen_xeon.yaml
    kubectl apply -f ./codegen_xeon.yaml
    
  2. Check if the application is up and ready

    kubectl get pods -n $APP_NAMESPACE
    
  3. Deploy a client pod for testing

    kubectl create deployment client-test -n $APP_NAMESPACE --image=python:3.8.13 -- sleep infinity
    
  4. Check that client pod is ready

    kubectl get pods -n $APP_NAMESPACE
    
  5. Send request to application

    export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name})
    export accessUrl=$(kubectl get gmc -n $APP_NAMESPACE -o jsonpath="{.items[?(@.metadata.name=='codegen')].status.accessUrl}")
    kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl -s --no-buffer $accessUrl -X POST -d '{"query": "def print_hello_world():"}' -H 'Content-Type: application/json' > $LOG_PATH/gmc_codegen.log