feat: add production Dockerfile and CI/CD workflow for automated image builds

Author: zieen

.github/workflows/docker-publish.yml .github/workflows/docker-publish-base.yml.github/workflows/docker-publish.yml renamed to .github/workflows/docker-publish-base.yml

@@ -1,8 +1,8 @@
-name: Docker Build and Push
+name: Docker Build and Push Base
 
 on:
   push:
-    tags: ["v*.*.*"]
+    tags: ["base-*"]
 
 env:
   # Use docker.io for Docker Hub if empty
@@ -53,20 +53,19 @@ jobs:
         with:
           images: ${{ env.IMAGE_NAME }}
           tags: |
-            type=raw,value=latest,enable=${{ github.ref == 'refs/heads/main' }}
-            type=semver,pattern={{version}}
-            type=sha
+            type=raw,value=base-latest
+            type=ref,event=tag
 
       - name: Build and push Docker image
         id: build-and-push
         uses: docker/build-push-action@v5
         with:
           context: .
-          # Ensure the downloaded file is included in the context
+          file: ./Dockerfile.base
           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
+          cache-from: type=gha,scope=base
+          cache-to: type=gha,mode=max,scope=base
           # Important: we found this platform works best
           platforms: linux/amd64

.github/workflows/docker-publish-prod.yml

@@ -0,0 +1,74 @@
+name: Docker Build and Push Prod
+
+on:
+  push:
+    tags: ["prod-*"]
+
+env:
+  # Use docker.io for Docker Hub if empty
+  REGISTRY: docker.io
+  # github.repository as <account>/<repo>
+  IMAGE_NAME: enzii/deepseek-ocr2-service
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      # The image is ~16GB, so we need to free up space on the runner
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # This might take a few minutes to run, but is necessary for large images
+          tool-cache: false
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: true
+          swap-storage: true
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log into Docker Hub
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Extract Docker metadata
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.IMAGE_NAME }}
+          tags: |
+            type=raw,value=latest
+            type=match,pattern=prod-(.*),group=1
+            type=sha
+
+      - name: Build and push Docker image
+        id: build-and-push
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: ./Dockerfile.prod
+          build-args: |
+            BASE_IMAGE=${{ env.IMAGE_NAME }}:base-latest
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha,scope=prod
+          cache-to: type=gha,mode=max,scope=prod
+          # Important: we found this platform works best
+          platforms: linux/amd64

Dockerfile Dockerfile.baseDockerfile renamed to Dockerfile.base

@@ -38,12 +38,3 @@ COPY requirements.txt install.sh ./
 # Make install script executable and run it
 # This script installs PyTorch, vLLM, and other requirements
 RUN chmod +x install.sh && ./install.sh
-
-# Copy the rest of the application code
-COPY . .
-
-# Expose the API port
-EXPOSE 8000
-
-# Default command to run the FastAPI server
-CMD ["python3", "serve_pdf.py"]

Dockerfile.prod

@@ -0,0 +1,15 @@
+# Use the base image that contains all dependencies
+# Build the base image first with: docker build -t dpsk-ocr2-base -f Dockerfile.base .
+ARG BASE_IMAGE=dpsk-ocr2-base:latest
+FROM ${BASE_IMAGE}
+
+WORKDIR /app
+
+# Copy the rest of the application code
+COPY . .
+
+# Expose the API port
+EXPOSE 8000
+
+# Default command to run the FastAPI server
+CMD ["python3", "serve_pdf.py"]