Add sandbox dockerfile generator script

.github/workflows/build-push-codespace.yml

@@ -0,0 +1,171 @@
+name: Build and Push Project Codespace Images
+
+on:
+  push:
+    branches:
+      - main
+    paths-ignore:
+      - "_assets/**"
+      - ".github/**"
+      - ".gitignore"
+      - ".gitmodules"
+      - ".typos.toml"
+      - "CODE-OF-CONDUCT.md"
+      - "CONTRIBUTING.md"
+      - "scripts/**"
+      - "LICENSE"
+      - "pyproject.toml"
+      - "README.md"
+
+  workflow_dispatch:
+    inputs:
+      project:
+        description: "Project to build (leave empty to detect from changed files)"
+        required: false
+        default: ""
+
+jobs:
+  detect-changes:
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+
+      - name: Detect changed projects
+        id: set-matrix
+        run: |
+          # If this was a manual dispatch _and_ they provided a project, just use that
+          if [[ "${{ github.event_name }}" == "workflow_dispatch" && -n "${{ github.event.inputs.project }}" ]]; then
+            PROJECTS="[\"${{ github.event.inputs.project }}\"]"
+          else
+            # Otherwise auto-diff HEAD^ → HEAD for any changed top-level dirs
+            CHANGED_FILES=$(git diff --name-only HEAD^ HEAD)
+            CHANGED_DIRS=$(echo "$CHANGED_FILES" \
+              | awk -F/ '{print $1}' \
+              | sort -u \
+              | grep -v '^$')
+            ALL_PROJECT_DIRS=$(find . -maxdepth 1 -type d \
+              -not -path '*/\.*' \
+              -not -path '.' \
+              | sed 's|^\./||' \
+              | grep -v '^_')
+            PROJECTS="["
+            sep=""
+            for d in $CHANGED_DIRS; do
+              if echo "$ALL_PROJECT_DIRS" | grep -qx "$d"; then
+                PROJECTS+="${sep}\"$d\""
+                sep=","
+              fi
+            done
+            PROJECTS+="]"
+          fi
+
+          echo "matrix=$PROJECTS" >> $GITHUB_OUTPUT
+          echo "Projects to build: $PROJECTS"
+
+  check-dockerfile:
+    needs: detect-changes
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        project: ${{ fromJson(needs.detect-changes.outputs.matrix) }}
+    outputs:
+      dockerfile_exists: ${{ steps.check-dockerfile.outputs.dockerfile_exists }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Check for Dockerfile.codespace
+        id: check-dockerfile
+        run: |
+          if [ -f "${{ matrix.project }}/Dockerfile.codespace" ]; then
+            echo "dockerfile_exists=true" >> $GITHUB_OUTPUT
+          else
+            echo "dockerfile_exists=false" >> $GITHUB_OUTPUT
+          fi
+
+  generate-dockerfile:
+    needs: [detect-changes, check-dockerfile]
+    if: needs.check-dockerfile.outputs.dockerfile_exists == 'false'
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        project: ${{ fromJson(needs.detect-changes.outputs.matrix) }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+
+      - name: Generate Dockerfile.codespace
+        id: generate-dockerfile
+        run: |
+          python scripts/generate_codespace_dockerfile.py "${{ matrix.project }}"
+          echo "Generated Dockerfile.codespace for ${{ matrix.project }}"
+
+      - name: Create Pull Request for new Dockerfile
+        uses: peter-evans/create-pull-request@v5
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          commit-message: "Auto-generate Dockerfile.codespace for ${{ matrix.project }}"
+          title: "Auto-generate Dockerfile.codespace for ${{ matrix.project }}"
+          body: |
+            This PR adds a generated Dockerfile.codespace for the ${{ matrix.project }} project.
+
+            Please review the changes and merge if they look good.
+
+            Once merged, the Docker image will be built and pushed automatically.
+          branch: "auto-dockerfile-${{ matrix.project }}"
+          base: main
+          labels: |
+            automated-pr
+            dockerfile
+            codespace
+
+  build-and-push:
+    needs: [detect-changes, check-dockerfile]
+    if: needs.check-dockerfile.outputs.dockerfile_exists == 'true'
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        project: ${{ fromJson(needs.detect-changes.outputs.matrix) }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      # Generate timestamp for image tag
+      - name: Generate timestamp
+        id: timestamp
+        run: echo "timestamp=$(date -u +'%Y%m%d%H%M%S')" >> $GITHUB_OUTPUT
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - name: Login to DockerHub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_PASSWORD }}
+
+      - name: Build and push
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          file: ${{ matrix.project }}/Dockerfile.codespace
+          push: true
+          tags: zenmldocker/projects-${{ matrix.project }}:${{ steps.timestamp.outputs.timestamp }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

omni-reader/Dockerfile.codespace

@@ -0,0 +1,49 @@
+# Sandbox base image
+FROM zenmldocker/zenml-sandbox:latest
+
+# Install uv from official distroless image
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
+
+# Set uv environment variables for optimization
+ENV UV_SYSTEM_PYTHON=1
+ENV UV_COMPILE_BYTECODE=1
+
+# Project metadata
+LABEL project_name="omni-reader"
+LABEL project_version="0.1.0"
+
+# Install dependencies with uv and cache optimization
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv pip install --system \
+    "instructor" \
+    "jiwer" \
+    "jiter" \
+    "importlib-metadata<7.0,>=1.4.0" \
+    "litellm" \
+    "mistralai==1.0.3" \
+    "numpy<2.0,>=1.9.0" \
+    "openai==1.69.0" \
+    "Pillow==11.1.0" \
+    "polars-lts-cpu==1.26.0" \
+    "pyarrow>=7.0.0" \
+    "python-dotenv" \
+    "streamlit==1.44.0" \
+    "pydantic>=2.8.2,<2.9.0" \
+    "tqdm==4.66.4" \
+    "zenml>=0.80.0"
+
+# Set workspace directory
+WORKDIR /workspace
+
+# Clone only the project directory and reorganize
+RUN git clone --depth 1 https://github.com/zenml-io/zenml-projects.git /tmp/zenml-projects && \
+    cp -r /tmp/zenml-projects/omni-reader/* /workspace/ && \
+    rm -rf /tmp/zenml-projects
+
+# VSCode settings
+RUN mkdir -p /workspace/.vscode && \
+    printf '{\n  "workbench.colorTheme": "Default Dark Modern"\n}' > /workspace/.vscode/settings.json
+
+# Copy .env.example
+COPY .env.example /workspace/.env
+ENV POLARS_SKIP_CPU_CHECK=1