Setting up AI Designer API Server

SECRET=Please request from https://intelligence.int.joget.cloud/ or set your own

MODEL_TEMPERATURE=0.2

LOG_LEVEL=info

FASTAPI_APPLICATION_PORT=8000
APPLICATION_WORKERS=1
APPLICATION_THREADS=1

MAX_ATTEMPTS=2

HUGGING_FACE_TOKEN=Please add your hugging face token if using custom open source models

BACKEND_CORS_ORIGINS=*

ENVIRONMENT=server

BUILD_CELERY=false
BUILD_MONGO=false

version: "3.3"
services:
 llm_workflow_api:
   image: quay.io/joget/ai-designer-api:8.1-BETA
   command: gunicorn -k uvicorn.workers.UvicornWorker --bind 0.0.0.0:8000 --workers ${APPLICATION_WORKERS} --threads ${APPLICATION_THREADS} llm_workflow.fastapi_application --timeout 400 --log-level=${LOG_LEVEL}
   env_file:
     - .env
   container_name: ai_designer_api
   restart: unless-stopped
   ports:
     - ${FASTAPI_APPLICATION_PORT}:8000
   environment:
     LOG_LEVEL: ${LOG_LEVEL}
     ENVIRONMENT: server
   volumes:
     - ./datafiles:/LLMWorkflow/llm_workflow/datafiles
   networks:
     - llm_workflow
   healthcheck:
     test: ["CMD", "curl", "-f", "-X", "POST", "http://localhost:8000/health-check"]
     interval: 30s
     timeout: 10s
     retries: 5
networks:
 llm_workflow:

sudo docker compose -f ./docker-compose.yml --env-file .env up --build -d

---
apiVersion: apps/v1
kind: Deployment
metadata:
 name: ai-designer-api
spec:
 replicas: 1
 selector:
   matchLabels:
     app: ai-designer-api
 template:
   metadata:
     labels:
       app: ai-designer-api
   spec:
     containers:
     - name: ai-designer-api
       image: ${DOCKER_IMAGE}
       imagePullPolicy: Always
       workingDir: /LLMWorkflow
       command: ["gunicorn", "-k", "uvicorn.workers.UvicornWorker", "--bind", "0.0.0.0:8000", "--workers", "$(APPLICATION_WORKERS)", "--threads", "$(APPLICATION_THREADS)", "llm_workflow.fastapi_application", "--timeout", "400", "--log-level=$(LOG_LEVEL)"]
       ports:
       - containerPort: 8000
       envFrom:
       - configMapRef:
           name: llm-wflow-config
       resources:
         requests:
           # cpu: 4000m
           memory: 2Gi
         limits:
           # cpu: 8000m
           memory: 6Gi
       livenessProbe:
         exec:
           command:
           - curl
           - -f
           - -X
           - POST
           - http://localhost:8000/health-check
         initialDelaySeconds: 30
         timeoutSeconds: 5
         periodSeconds: 10
         successThreshold: 1
         failureThreshold: 6
       volumeMounts:
       - name: datafiles
         mountPath: /LLMWorkflow/llm_workflow/datafiles
     volumes:
     - name: datafiles
       emptyDir: {}  # For demonstration. Consider using a PersistentVolume in production.
---
  apiVersion: v1
  kind: Service
  metadata:
    name: ai-designer-api-service
  spec:
    selector:
      app: ai-designer-api
    ports:
      - protocol: TCP
        port: 8000
        targetPort: 8000
    type: NodePort  # Changed from LoadBalancer to NodePort

---
 apiVersion: networking.k8s.io/v1
 kind: Ingress
 metadata:
   name: ai-designer-api-ingress
   annotations:
     nginx.ingress.kubernetes.io/affinity: "cookie"
     nginx.ingress.kubernetes.io/ssl-redirect: "false"
     nginx.ingress.kubernetes.io/proxy-body-size: "10M"
     cert-manager.io/cluster-issuer: letsencrypt-issuer
 spec:
   ingressClassName: nginx
   tls:
   - hosts:
     - ${INGRESS_HOST}
     secretName: joget-cloud-tls
   rules:
     - host: ${INGRESS_HOST}
       http:
         paths:
           - path: /
             pathType: Prefix
             backend:
               service:
                 name: ai-designer-api-service
                 port:
                   number: 8000

#!/bin/bash

TAG=${TAG:-"8.1-BETA"}
DOCKER_IMAGE=${DOCKER_IMAGE:-"quay.io/joget/ai-designer-api:$TAG"}
K8S_NAMESPACE=${K8S_NAMESPACE:-"ai-designer"}
INGRESS_HOST=${INGRESS_HOST:-"YOUR HOSTNAME"}

# Load environment variables from the .env file
if [ -f llm_workflow/.env ]; then
 set -a # Automatically export all variables
 source llm_workflow/.env
 set +a # Stop exporting variables automatically
else
 echo "Environment file llm_workflow/.env not found!"
 exit 1
Fi

echo Create Namespace $K8S_NAMESPACE
kubectl get namespace $K8S_NAMESPACE || 
 kubectl create namespace $K8S_NAMESPACE

echo Create ConfigMap
kubectl -n $K8S_NAMESPACE create configmap llm-wflow-config --from-env-file=./llm_workflow/.env.k8s --dry-run=client -o yaml > ./kubernetes/llm-config-configmap.yaml
kubectl -n $K8S_NAMESPACE apply -f ./kubernetes/llm-config-configmap.yaml

echo Deploy API Server
envsubst <  ./kubernetes/wflow-api-deployment.yaml | kubectl -n $K8S_NAMESPACE apply -f -

echo Wait for Deployment and Display Pods and Ingress
kubectl -n $K8S_NAMESPACE rollout status deploy ai-designer-api
kubectl -n $K8S_NAMESPACE get po

kubectl -n $K8S_NAMESPACE get ingress