Merge pull request #963 from arc53/feat/kubes-deployment

feat: k8s deployment

docs/pages/Deploying/Kubernetes-Deploying.md

@@ -0,0 +1,108 @@
+# Self-hosting DocsGPT on Kubernetes
+
+This guide will walk you through deploying DocsGPT on Kubernetes.
+
+## Prerequisites
+
+Ensure you have the following installed before proceeding:
+
+- [kubectl](https://kubernetes.io/docs/tasks/tools/install-kubectl/)
+- Access to a Kubernetes cluster
+
+## Folder Structure
+
+The `k8s` folder contains the necessary deployment and service configuration files:
+
+- `deployments/`
+- `services/`
+- `docsgpt-secrets.yaml`
+
+## Deployment Instructions
+
+1. **Clone the Repository**
+
+   ```sh
+   git clone https://github.com/arc53/DocsGPT.git
+   cd docsgpt/k8s
+   ```
+
+2. **Configure Secrets (optional)**
+
+   Ensure that you have all the necessary secrets in `docsgpt-secrets.yaml`. Update it with your secrets before applying if you want. By default we will use qdrant as a vectorstore and public docsgpt llm as llm for inference.
+
+3. **Apply Kubernetes Deployments**
+
+   Deploy your DocsGPT resources using the following commands:
+
+   ```sh
+   kubectl apply -f deployments/
+   ```
+
+4. **Apply Kubernetes Services**
+
+   Set up your services using the following commands:
+
+   ```sh
+   kubectl apply -f services/
+   ```
+
+5. **Apply Secrets**
+
+   Apply the secret configurations:
+
+   ```sh
+   kubectl apply -f docsgpt-secrets.yaml
+   ```
+
+6. **Substitute API URL**
+
+   After deploying the services, you need to update the environment variable `VITE_API_HOST` in your deployment file `deployments/docsgpt-deploy.yaml` with the actual endpoint URL created by your `docsgpt-api-service`.
+
+   You can get the value of the `docsgpt-api-service` by running:
+
+   ```sh
+   kubectl get services/docsgpt-api-service | awk 'NR>1 {print $4}'
+   ```
+
+   Update the `<your-api-endpoint>` field with your API endpoint URL by running this command and pasting endpoint from previous command:
+
+   ```sh
+   read -p "Enter the API endpoint: " api_endpoint && sed -i "s|<your-api-endpoint>|$api_endpoint|g" deployments/docsgpt-deploy.yaml
+    ```
+
+7. **Rerun Deployment**
+
+   After making the changes, reapply the deployment configuration to update the environment variables:
+
+   ```sh
+   kubectl apply -f deployments/
+   ```
+
+## Verifying the Deployment
+
+To verify if everything is set up correctly, you can run the following:
+
+```sh
+kubectl get pods
+kubectl get services
+```
+
+Ensure that the pods are running and the services are available.
+
+## Accessing DocsGPT
+
+To access DocsGPT, you need to find the external IP address of the frontend service. You can do this by running:
+
+```sh
+kubectl get services/docsgpt-frontend-service | awk 'NR>1 {print "http://" $4}'
+```
+
+## Troubleshooting
+
+If you encounter any issues, you can check the logs of the pods for more details:
+
+```sh
+kubectl logs <pod-name>
+```
+
+Replace `<pod-name>` with the actual name of your DocsGPT pod.

docs/pages/Deploying/_meta.json

@@ -10,5 +10,9 @@
   "Railway-Deploying": {
     "title": "🚂Deploying on Railway",
     "href": "/Deploying/Railway-Deploying"
+  },
+  "Kubernetes-Deploying": {
+    "title": "🚀Deploying on Kubernetes",
+    "href": "/Deploying/Kubernetes-Deploying"
   }
 }

k8s/deployments/docsgpt-deploy.yaml

@@ -0,0 +1,98 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: docsgpt-api
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: docsgpt-api
+  template:
+    metadata:
+      labels:
+        app: docsgpt-api
+    spec:
+      containers:
+      - name: docsgpt-api
+        image: arc53/docsgpt
+        ports:
+        - containerPort: 7091
+        resources:
+          limits:
+            memory: "4Gi"
+            cpu: "2"
+          requests:
+            memory: "2Gi"
+            cpu: "1"
+        envFrom:
+        - secretRef:
+            name: docsgpt-secrets
+        env:
+        - name: FLASK_APP
+          value: "application/app.py"
+        - name: DEPLOYMENT_TYPE
+          value: "cloud"
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: docsgpt-worker
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: docsgpt-worker
+  template:
+    metadata:
+      labels:
+        app: docsgpt-worker
+    spec:
+      containers:
+      - name: docsgpt-worker
+        image: arc53/docsgpt
+        command: ["celery", "-A", "application.app.celery", "worker", "-l", "INFO", "-n", "worker.%h"]
+        resources:
+          limits:
+            memory: "4Gi"
+            cpu: "2"
+          requests:
+            memory: "2Gi"
+            cpu: "1"
+        envFrom:
+        - secretRef:
+            name: docsgpt-secrets
+        env:
+        - name: API_URL
+          value: "http://<your-api-endpoint>"
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: docsgpt-frontend
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: docsgpt-frontend
+  template:
+    metadata:
+      labels:
+        app: docsgpt-frontend
+    spec:
+      containers:
+      - name: docsgpt-frontend
+        image: arc53/docsgpt-fe
+        ports:
+        - containerPort: 5173
+        resources:
+          limits:
+            memory: "1Gi"
+            cpu: "1"
+          requests:
+            memory: "256Mi"
+            cpu: "100m"
+        env:
+        - name: VITE_API_HOST
+          value: "http://<your-api-endpoint>"
+        - name: VITE_API_STREAMING
+          value: "true"

k8s/deployments/mongo-deploy.yaml

@@ -0,0 +1,46 @@
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: mongodb-pvc
+spec:
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 10Gi  # Adjust size as needed
+
+---
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: mongodb
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: mongodb
+  template:
+    metadata:
+      labels:
+        app: mongodb
+    spec:
+      containers:
+      - name: mongodb
+        image: mongo:latest
+        ports:
+        - containerPort: 27017
+        resources:
+          limits:
+            memory: "1Gi"
+            cpu: "0.5"
+          requests:
+            memory: "512Mi"
+            cpu: "250m"
+        volumeMounts:
+        - name: mongodb-data
+          mountPath: /data/db
+      volumes:
+      - name: mongodb-data
+        persistentVolumeClaim:
+          claimName: mongodb-pvc

k8s/deployments/qdrant-deploy.yaml

@@ -0,0 +1,46 @@
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: qdrant-pvc
+spec:
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 10Gi
+
+---
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: qdrant
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: qdrant
+  template:
+    metadata:
+      labels:
+        app: qdrant
+    spec:
+      containers:
+      - name: qdrant
+        image: qdrant/qdrant:latest
+        ports:
+        - containerPort: 6333
+        resources:
+          limits:
+            memory: "2Gi"  # Adjust based on your needs
+            cpu: "1"       # Adjust based on your needs
+          requests:
+            memory: "1Gi"  # Adjust based on your needs
+            cpu: "500m"    # Adjust based on your needs
+        volumeMounts:
+        - name: qdrant-data
+          mountPath: /qdrant/storage
+      volumes:
+      - name: qdrant-data
+        persistentVolumeClaim:
+          claimName: qdrant-pvc

k8s/deployments/redis-deploy.yaml

@@ -0,0 +1,26 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: redis
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: redis
+  template:
+    metadata:
+      labels:
+        app: redis
+    spec:
+      containers:
+      - name: redis
+        image: redis:latest
+        ports:
+        - containerPort: 6379
+        resources:
+          limits:
+            memory: "1Gi"
+            cpu: "0.5"
+          requests:
+            memory: "512Mi"
+            cpu: "250m"

k8s/docsgpt-secrets.yaml

@@ -0,0 +1,16 @@
+apiVersion: v1
+kind: Secret
+metadata:
+  name: docsgpt-secrets
+type: Opaque
+data:
+  LLM_NAME: ZG9jc2dwdA==
+  INTERNAL_KEY: aW50ZXJuYWw=
+  CELERY_BROKER_URL: cmVkaXM6Ly9yZWRpcy1zZXJ2aWNlOjYzNzkvMA==
+  CELERY_RESULT_BACKEND: cmVkaXM6Ly9yZWRpcy1zZXJ2aWNlOjYzNzkvMA==
+  QDRANT_URL: cmVkaXM6Ly9yZWRpcy1zZXJ2aWNlOjYzNzkvMA==
+  QDRANT_PORT: NjM3OQ==
+  MONGO_URI: bW9uZ29kYjovL21vbmdvZGItc2VydmljZToyNzAxNy9kb2NzZ3B0P3JldHJ5V3JpdGVzPXRydWUmdz1tYWpvcml0eQ==
+  VECTOR_STORE: cWRyYW50
+  mongo-user: bW9uZ28tdXNlcg==
+  mongo-password: bW9uZ28tcGFzc3dvcmQ=

k8s/services/docsgpt-service.yaml

@@ -0,0 +1,25 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: docsgpt-api-service
+spec:
+  selector:
+    app: docsgpt-api
+  ports:
+    - protocol: TCP
+      port: 80
+      targetPort: 7091
+  type: LoadBalancer
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: docsgpt-frontend-service
+spec:
+  selector:
+    app: docsgpt-frontend
+  ports:
+    - protocol: TCP
+      port: 80
+      targetPort: 5173
+  type: LoadBalancer