feat: Docker runtime improvements and srsly dependency removal

.dockerignore

@@ -0,0 +1,68 @@
+# Git
+.git/
+.gitignore
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+*.egg-info/
+dist/
+build/
+.pytest_cache/
+.coverage
+htmlcov/
+.tox/
+.mypy_cache/
+.ruff_cache/
+
+# Virtual environments
+venv/
+env/
+ENV/
+.venv/
+
+# IDEs
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+.DS_Store
+
+# Project specific
+tests/
+docs/
+examples/
+scripts/
+*.md
+!README.md
+pytest.ini
+.github/
+.gitlab-ci.yml
+coordination/
+memory/
+output/
+rdf_output/
+metadata-tmp/
+rdf-tmp/
+tmp/
+tmp-sample-data/
+sample_data/
+test-cli/
+task_log.jsonl
+task_queue.jsonl
+
+# Docker
+docker-compose*.yml
+Dockerfile*
+!Dockerfile
+.dockerignore
+
+# Buildpack
+project.toml
+pack.toml
+
+# Keep only essential files for runtime

.github/workflows/build-artifacts.yml

@@ -0,0 +1,86 @@
+name: Build Artifacts
+
+on:
+  push:
+    branches: [ main ]
+    tags: [ 'v*' ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build-docker:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v3
+
+    - name: Build Docker image
+      run: |
+        docker build -t knowledgebase-processor:latest .
+        docker save knowledgebase-processor:latest | gzip > knowledgebase-processor-docker.tar.gz
+
+    - name: Upload Docker artifact
+      uses: actions/upload-artifact@v4
+      with:
+        name: docker-image
+        path: knowledgebase-processor-docker.tar.gz
+
+  build-wheel:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.12'
+
+    - name: Install Poetry
+      uses: snok/install-poetry@v1
+
+    - name: Build wheel
+      run: |
+        poetry build
+
+    - name: Upload wheel
+      uses: actions/upload-artifact@v4
+      with:
+        name: python-wheel
+        path: dist/
+
+  # build-executable:
+  #   runs-on: ${{ matrix.os }}
+  #   strategy:
+  #     matrix:
+  #       os: [ubuntu-latest, windows-latest, macos-latest]
+
+  #   steps:
+  #   - uses: actions/checkout@v4
+
+  #   - name: Set up Python
+  #     uses: actions/setup-python@v4
+  #     with:
+  #       python-version: '3.12'
+
+  #   - name: Install Poetry
+  #     uses: snok/install-poetry@v1
+
+  #   - name: Install dependencies
+  #     run: |
+  #       poetry install --only=main
+
+  #   - name: Install PyInstaller
+  #     run: |
+  #       poetry add --group dev pyinstaller
+
+  #   - name: Build executable
+  #     run: |
+  #       poetry run pyinstaller --onefile --name kb src/knowledgebase_processor/cli_v2/main.py
+
+  #   - name: Upload executable
+  #     uses: actions/upload-artifact@v4
+  #     with:
+  #       name: executable-${{ matrix.os }}
+  #       path: dist/kb*

.python-version

@@ -0,0 +1 @@
+3.12

Dockerfile

@@ -0,0 +1,45 @@
+# Multi-stage build to handle Python dependencies with C extensions
+FROM python:3.12-slim as builder
+
+# Install build dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    gcc \
+    g++ \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install poetry
+RUN pip install poetry
+
+# Copy dependency files
+COPY pyproject.toml poetry.lock ./
+
+# Configure poetry to not create virtual environment
+RUN poetry config virtualenvs.create false
+
+# Install dependencies
+RUN poetry install --only=main --no-root
+
+# Production stage
+FROM python:3.12-slim as runtime
+
+# Create non-root user
+RUN useradd --create-home --shell /bin/bash kbp
+
+# Copy installed packages from builder
+COPY --from=builder /usr/local/lib/python3.12/site-packages /usr/local/lib/python3.12/site-packages
+COPY --from=builder /usr/local/bin /usr/local/bin
+
+# Copy application code
+COPY src/ /app/src/
+COPY pyproject.toml README.md /app/
+
+WORKDIR /app
+
+# Install the package
+RUN pip install -e .
+
+USER kbp
+
+# Default command
+CMD ["kb", "--help"]

Dockerfile.alpine

@@ -0,0 +1,75 @@
+# Alpine-based Dockerfile for knowledgebase-processor
+# Smaller image size but requires more careful dependency management
+
+# Build stage
+FROM python:3.12-alpine as builder
+
+# Install build dependencies for Alpine
+# Note: Alpine uses musl libc which can cause compatibility issues
+RUN apk add --no-cache \
+    gcc \
+    g++ \
+    musl-dev \
+    linux-headers \
+    python3-dev \
+    openblas-dev \
+    gfortran \
+    build-base \
+    cmake \
+    # Required for some Python packages
+    libffi-dev \
+    openssl-dev
+
+# Install poetry
+RUN pip install --no-cache-dir poetry==1.8.2
+
+WORKDIR /app
+
+# Copy dependency files
+COPY pyproject.toml poetry.lock ./
+
+# Configure poetry
+RUN poetry config virtualenvs.create false
+
+# Install dependencies - longer build time due to compilation
+RUN poetry install --no-interaction --no-ansi --no-root --only main
+
+# Copy and install application
+COPY src/ ./src/
+COPY README.md ./
+RUN poetry install --no-interaction --no-ansi --only-root
+
+# Runtime stage
+FROM python:3.12-alpine
+
+# Install runtime dependencies only
+RUN apk add --no-cache \
+    openblas \
+    libgfortran \
+    libstdc++ \
+    # For health checks
+    curl
+
+# Create non-root user
+RUN adduser -D -u 1000 kbuser
+
+# Copy from builder
+COPY --from=builder /usr/local/lib/python3.12/site-packages /usr/local/lib/python3.12/site-packages
+COPY --from=builder /usr/local/bin /usr/local/bin
+
+WORKDIR /app
+COPY --from=builder /app/src ./src
+COPY pyproject.toml README.md ./
+
+# Create data directories
+RUN mkdir -p /app/data /app/output /app/metadata && \
+    chown -R kbuser:kbuser /app
+
+USER kbuser
+
+ENV PYTHONUNBUFFERED=1
+
+HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
+    CMD kb --version || exit 1
+
+CMD ["kb", "--help"]