khoj/.github/workflows/dockerize.yml

name: dockerize

on:
  push:
    tags:
      - "*"
    branches:
      - master
    paths:
      - src/khoj/**
      - src/interface/web/**
      - pyproject.toml
      - Dockerfile
      - prod.Dockerfile
      - docker-compose.yml
      - .github/workflows/dockerize.yml
  workflow_dispatch:
    inputs:
      tag:
        description: 'Docker image tag'
        default: 'dev'
      khoj:
        description: 'Build Khoj docker image'
        type: boolean
        default: true
      khoj-cloud:
        description: 'Build Khoj cloud docker image'
        type: boolean
        default: true

env:
  # Tag Image with tag name on release
  # else with user specified tag (default 'dev') if triggered via workflow
  # else with run_id if triggered via a pull request
  # else with 'pre' (if push to master)
  DOCKER_IMAGE_TAG: ${{ github.ref_type == 'tag' && github.ref_name || github.event_name == 'workflow_dispatch' && github.event.inputs.tag || 'pre' }}

jobs:
  build:
    name: Publish Khoj Docker Images
    strategy:
      fail-fast: false
      matrix:
        include:
          - image: 'local'
            platform: linux/amd64
            runner: ubuntu-latest
          - image: 'local'
            platform: linux/arm64
            runner: ubuntu-linux-arm64
          - image: 'cloud'
            platform: linux/amd64
            runner: ubuntu-latest
          - image: 'cloud'
            platform: linux/arm64
            runner: ubuntu-linux-arm64
    runs-on: ${{ matrix.runner }}
    steps:
      - name: Checkout Code
        uses: actions/checkout@v3
        with:
          # Get all history to correctly infer Khoj version using hatch
          fetch-depth: 0

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v2

      - name: Login to GitHub Container Registry
        uses: docker/login-action@v2
        with:
          registry: ghcr.io
          username: ${{ github.repository_owner }}
          password: ${{ secrets.PAT }}

      - name: Get App Version
        id: hatch
        run: echo "version=$(pipx run hatch version)" >> $GITHUB_OUTPUT

      - name: 🧹 Delete huge unnecessary tools folder
        run: rm -rf /opt/hostedtoolcache

      - name: 📦 Build and Push Docker Image
        uses: docker/build-push-action@v4
        if: (matrix.image == 'local' && github.event_name == 'workflow_dispatch') && github.event.inputs.khoj == 'true' || (matrix.image == 'local' && github.event_name == 'push')
        with:
          context: .
          file: Dockerfile
          push: true
          tags: |
            ghcr.io/${{ github.repository }}:${{ env.DOCKER_IMAGE_TAG }}-${{ matrix.platform == 'linux/amd64' && 'amd64' || 'arm64' }}            
          build-args: |
            VERSION=${{ steps.hatch.outputs.version }}
            PORT=42110            
          cache-from: type=gha,scope=${{ matrix.image }}-${{ matrix.platform }}
          cache-to: type=gha,mode=max,scope=${{ matrix.image }}-${{ matrix.platform}}
          labels: |
            org.opencontainers.image.description=Khoj AI - Your second brain powered by LLMs and Neural Search
            org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }}            

      - name: 📦️⛅️ Build and Push Cloud Docker Image
        uses: docker/build-push-action@v4
        if: (matrix.image == 'cloud' && github.event_name == 'workflow_dispatch') && github.event.inputs.khoj-cloud == 'true' || (matrix.image == 'cloud' && github.event_name == 'push')
        with:
          context: .
          file: prod.Dockerfile
          push: true
          tags: |
            ghcr.io/${{ github.repository }}-cloud:${{ env.DOCKER_IMAGE_TAG }}-${{ matrix.platform == 'linux/amd64' && 'amd64' || 'arm64' }}            
          build-args: |
            VERSION=${{ steps.hatch.outputs.version }}
            PORT=42110            
          cache-from: type=gha,scope=${{ matrix.image }}-${{ matrix.platform }}
          cache-to: type=gha,mode=max,scope=${{ matrix.image }}-${{ matrix.platform}}
          labels: |
            org.opencontainers.image.description=Khoj AI Cloud - Your second brain powered by LLMs and Neural Search
            org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }}            

  manifest:
    needs: build
    runs-on: ubuntu-latest
    if: github.event_name != 'pull_request'
    steps:
      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3

      - name: Login to GitHub Container Registry
        uses: docker/login-action@v2
        with:
          registry: ghcr.io
          username: ${{ github.repository_owner }}
          password: ${{ secrets.PAT }}

      - name: Create and Push Local Manifest
        if: github.event.inputs.khoj == 'true' || github.event_name == 'push'
        run: |
          docker buildx imagetools create \
            -t ghcr.io/${{ github.repository }}:${{ env.DOCKER_IMAGE_TAG }} \
            -t ghcr.io/${{ github.repository }}:${{ github.ref_type == 'tag' && 'latest' || env.DOCKER_IMAGE_TAG }} \
            ghcr.io/${{ github.repository }}:${{ env.DOCKER_IMAGE_TAG }}-amd64 \
            ghcr.io/${{ github.repository }}:${{ env.DOCKER_IMAGE_TAG }}-arm64          

      - name: Create and Push Cloud Manifest
        if: github.event.inputs.khoj-cloud == 'true' || github.event_name == 'push'
        run: |
          docker buildx imagetools create \
            -t ghcr.io/${{ github.repository }}-cloud:${{ env.DOCKER_IMAGE_TAG }} \
            -t ghcr.io/${{ github.repository }}-cloud:${{ github.ref_type == 'tag' && 'latest' || env.DOCKER_IMAGE_TAG }} \
            ghcr.io/${{ github.repository }}-cloud:${{ env.DOCKER_IMAGE_TAG }}-amd64 \
            ghcr.io/${{ github.repository }}-cloud:${{ env.DOCKER_IMAGE_TAG }}-arm64