chore: Update Dockerfile.unstructured to include system dependencies …

…and Python packages (#1169)

.github/workflows/build-unst-docker.yml

@@ -0,0 +1,54 @@
+name: Build and Publish Unstructured Docker Image
+
+on:
+  workflow_dispatch:
+
+env:
+  REGISTRY_BASE: ragtoriches
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
+      - name: Install toml package
+        run: pip install toml
+
+      - name: Determine version
+        id: version
+        run: |
+          echo "REGISTRY_IMAGE=${{ env.REGISTRY_BASE }}/unst-prod" >> $GITHUB_OUTPUT
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Docker Auth
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.RAGTORICHES_DOCKER_UNAME }}
+          password: ${{ secrets.RAGTORICHES_DOCKER_TOKEN }}
+
+      - name: Build and push image
+        uses: docker/build-push-action@v5
+        with:
+          context: ./py
+          file: ./py/Dockerfile.unstructured
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: |
+            ${{ steps.version.outputs.REGISTRY_IMAGE }}:${{ steps.version.outputs.RELEASE_VERSION }}
+            ${{ steps.version.outputs.REGISTRY_IMAGE }}:latest
+          provenance: false
+          sbom: false
+
+      - name: Verify manifest
+        run: |
+          docker buildx imagetools inspect ${{ steps.version.outputs.REGISTRY_IMAGE }}:${{ steps.version.outputs.RELEASE_VERSION }}
+          docker buildx imagetools inspect ${{ steps.version.outputs.REGISTRY_IMAGE }}:latest

py/Dockerfile.unstructured

@@ -0,0 +1,29 @@
+FROM python:3.10-slim AS builder
+
+# Install system dependencies (including those needed for Unstructured and OpenCV)
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    gcc g++ musl-dev curl libffi-dev gfortran libopenblas-dev \
+    tesseract-ocr libtesseract-dev libleptonica-dev pkg-config \
+    poppler-utils libmagic1 pandoc libreoffice \
+    libgl1-mesa-glx libglib2.0-0 \
+    && apt-get clean && rm -rf /var/lib/apt/lists/*
+
+ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/5/tessdata
+
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+RUN pip install --no-cache-dir unstructured "unstructured[all-docs]"
+
+
+RUN python -c "from unstructured.partition.model_init import initialize; initialize()"
+
+RUN pip install gunicorn uvicorn fastapi httpx
+
+COPY core/integrations/unstructured/main.py .
+
+EXPOSE 7275
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7275"]