Merge pull request #12 from AustrianDataLAB/feature/operator

Add operator

.github/workflows/build_push_operator.yml

@@ -0,0 +1,87 @@
+name: build-push-operator
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+on:
+#  schedule:
+#    - cron: '40 16 * * *'
+  push:
+    branches: [ "feature/operator" ]
+    # Publish semver tags as releases.
+    #tags: [ 'v*.*.*' ]
+  pull_request:
+    branches: [ "dev","main" ]
+
+env:
+  # Use docker.io for Docker Hub if empty
+  REGISTRY: ghcr.io
+  # github.repository as <account>/<repo>
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build-scan-push:
+    runs-on: ubuntu-latest
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+      -
+        name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+      -
+        name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      -
+        name: Log into registry ${{ env.REGISTRY }}
+        uses: docker/login-action@343f7c4344506bcbf9b4de18042ae17996df046d # v3.0.0
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      -
+        name: Extract Docker metadata
+        id: meta
+        uses: docker/metadata-action@96383f45573cb7f253c731d3b3ab81c87ef81934 # v5.0.0
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+      -
+        name: Build and load
+        uses: docker/build-push-action@v4
+        with:
+          load: true
+          context: ./operator
+          file: ./operator/Dockerfile
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+      -
+        name: Scan for vulnerabilities
+        id: scan
+        uses: crazy-max/ghaction-container-scan@v3
+        with:
+          image: ${{ steps.meta.outputs.tags }}
+          dockerfile: ./operator/Dockerfile
+
+      -
+        name: Upload SARIF file
+        if: ${{ steps.scan.outputs.sarif != '' }}
+        uses: github/codeql-action/upload-sarif@v2
+        with:
+          sarif_file: ${{ steps.scan.outputs.sarif }}
+
+      -
+        name: Build and push Docker image
+        id: build-and-push
+        uses: docker/build-push-action@0565240e2d4ab88bba5387d719585280857ece09 # v5.0.0
+        with:
+          context: ./operator
+          file: ./operator/Dockerfile
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

operator/.env_example

@@ -0,0 +1,6 @@
+NAMESPACE=mlaas
+TRAINING_IMAGE=hello-world
+SERVING_IMAGE=nginx
+SERVING_PORT=80
+PERSISTENCE_SERVICE_URI=http://persistence-service.mlaas.svc.cluster.local:5000
+DOMAIN=mlaas.aocc.at

operator/.gitignore

@@ -0,0 +1,5 @@
+__pycache__/
+.pytest_cache/
+userdata/
+*.xml
+.env

operator/Dockerfile

@@ -0,0 +1,20 @@
+FROM cgr.dev/chainguard/python:latest-dev as builder
+
+WORKDIR /app
+
+COPY requirements.txt .
+
+RUN pip install -r requirements.txt --user
+
+
+
+FROM cgr.dev/chainguard/python:latest
+
+WORKDIR /app
+
+# Make sure you update Python version in path
+COPY --from=builder /home/nonroot/.local/lib/python3.12/site-packages /home/nonroot/.local/lib/python3.12/site-packages
+
+COPY main.py .
+
+ENTRYPOINT [ "python", "/app/main.py" ]

operator/README.md

@@ -0,0 +1,100 @@
+# Flask Kubernetes Application
+
+This application provides a Flask-based API to manage Kubernetes resources, specifically for training jobs and serving deployments. It utilizes the Kubernetes Python client to interact with a Kubernetes cluster, handling tasks like creating, monitoring, and deleting jobs and deployments.
+
+## Prerequisites
+
+Ensure you have the following environment variables set before running the application:
+
+- `TRAINING_IMAGE`
+- `SERVING_IMAGE`
+- `NAMESPACE`
+- `SERVING_PORT`
+- `PERSISTENCE_SERVICE_URI`
+- `DOMAIN`
+
+These environment variables are essential for the application to interact with Kubernetes and handle the deployment configurations.
+
+## API Endpoints
+
+### Create a Training Job
+**Endpoint:** `/training`  
+**Method:** `POST`  
+**Headers:**  
+- `Authorization`: Tenant identifier
+
+**Description:** Creates a new training job if no job is currently running for the tenant. If a job is already running, it returns an error.
+
+**Response:**
+- `202 Accepted`: Training job created.
+- `400 Bad Request`: Training job is already running.
+- `500 Internal Server Error`: An error occurred with the Kubernetes API.
+
+### Get Status of All Training Jobs
+**Endpoint:** `/training`  
+**Method:** `GET`  
+**Headers:**  
+- `Authorization`: Tenant identifier
+
+**Description:** Retrieves the status of all training jobs for the tenant.
+
+**Response:**
+- `200 OK`: List of jobs and their statuses.
+- `404 Not Found`: No jobs found for the tenant.
+- `500 Internal Server Error`: An error occurred with the Kubernetes API.
+
+### Get Status of a Specific Training Job
+**Endpoint:** `/training/<id>`  
+**Method:** `GET`  
+**Headers:**  
+- `Authorization`: Tenant identifier
+
+**Description:** Retrieves the status of a specific training job by its ID.
+
+**Response:**
+- `200 OK`: Status of the job.
+- `404 Not Found`: Job not found.
+- `500 Internal Server Error`: An error occurred with the Kubernetes API.
+
+### Create a Serving Deployment
+**Endpoint:** `/serving`  
+**Method:** `POST`  
+**Headers:**  
+- `Authorization`: Tenant identifier
+
+**Description:** Creates a new serving deployment for the tenant. If a deployment already exists, it returns an error.
+
+**Response:**
+- `201 Created`: Serving deployment created.
+- `400 Bad Request`: Serving deployment already exists.
+- `500 Internal Server Error`: An error occurred with the Kubernetes API.
+
+### Get Status of Serving Deployment
+**Endpoint:** `/serving`  
+**Method:** `GET`  
+**Headers:**  
+- `Authorization`: Tenant identifier
+
+**Description:** Retrieves the status of the serving deployment for the tenant.
+
+**Response:**
+- `200 OK`: Status of the deployment.
+- `404 Not Found`: Deployment not found.
+- `500 Internal Server Error`: An error occurred with the Kubernetes API.
+
+### Delete Serving Deployment
+**Endpoint:** `/serving`  
+**Method:** `DELETE`  
+**Headers:**  
+- `Authorization`: Tenant identifier
+
+**Description:** Deletes the serving deployment for the tenant.
+
+**Response:**
+- `200 OK`: Deployment deleted.
+- `404 Not Found`: Deployment not found.
+- `500 Internal Server Error`: An error occurred with the Kubernetes API.
+
+## Installation
+
+Apply the manifest.yaml file to your kubernetes cluster.