Feat/docker

.dockerignore

@@ -0,0 +1,71 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+*.egg-info/
+dist/
+build/
+.venv/
+venv/
+ENV/
+env/
+
+# Node
+node_modules/
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+frontend/build/
+frontend/node_modules/
+website/node_modules/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+.tox/
+
+# Documentation
+docs/_build/
+*.md
+!README.md
+
+# Git
+.git/
+.gitignore
+
+# Docker
+Dockerfile*
+docker-compose*.yml
+.dockerignore
+
+# Data
+data/*.db
+data/*.db-journal
+
+# Logs
+*.log
+
+# Environment
+.env
+.env.local
+.env.*.local
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Misc
+*.bak
+*.tmp
+.cache/
+

DOCKER.md

@@ -0,0 +1,79 @@
+# Docker Setup
+
+This document describes how to run DataGenFlow using Docker.
+
+## Quick Start
+
+1. **Build and start the application:**
+
+   ```bash
+   docker-compose up -d
+   ```
+
+2. **Access the application:**
+   - Frontend: <http://localhost:8000>
+   - API: <http://localhost:8000/api>
+
+3. **Stop the application:**
+
+   ```bash
+   docker-compose down
+   ```
+
+## Custom Blocks
+
+Custom blocks can be added to `lib/blocks/custom/` on your host system. They will be automatically available after restarting the backend container:
+
+```bash
+docker-compose restart backend
+```
+
+The `lib/blocks/custom/` directory is mounted as a volume, so you can add new block files directly from your host system without rebuilding the image.
+
+## Environment Variables
+
+You can configure the application using environment variables. Create a `.env` file in the project root:
+
+```env
+LLM_ENDPOINT=http://localhost:11434/api/generate
+LLM_API_KEY=
+LLM_MODEL=llama3
+DEBUG=false
+```
+
+These variables are automatically passed to the container via `docker-compose.yml`.
+
+## Data Persistence
+
+The `data/` directory is mounted as a volume, so your database and other data will persist between container restarts.
+
+## Building Images
+
+To rebuild the images:
+
+```bash
+docker-compose build
+```
+
+Or rebuild without cache:
+
+```bash
+docker-compose build --no-cache
+```
+
+## Development
+
+For development, you may want to mount additional directories or use volume mounts for live code reloading. Modify `docker-compose.yml` as needed.
+
+## Architecture
+
+- **Backend**: Python 3.11 with uv, serves both API and frontend
+- **Frontend**: Built with yarn/vite, served as static files by the backend
+- **Port**: 8000 (both API and frontend)
+
+The backend Dockerfile:
+
+- Uses multi-stage builds for optimization
+- Compiles Python bytecode for faster startup
+- Builds the frontend and includes it in the final image
+- Serves the frontend at the root path via FastAPI

Dockerfile

@@ -0,0 +1,77 @@
+# Backend Dockerfile using uv
+FROM python:3.10-slim AS builder
+
+# Install uv
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv
+
+# Set working directory
+WORKDIR /app
+
+# Copy dependency files
+COPY pyproject.toml uv.lock ./
+
+# Install dependencies using uv
+RUN uv sync --frozen --no-dev
+
+# Copy application code
+COPY . .
+
+# Compile Python bytecode for faster startup
+# Compile all Python files recursively in lib/ and root
+RUN python -m compileall -b -q -r lib/ && \
+    python -m compileall -b -q app.py config.py models.py mock_llm.py debug_pipeline.py 2>/dev/null || true
+
+# Frontend build stage
+FROM node:20-alpine AS frontend-builder
+
+WORKDIR /app
+
+# Copy frontend package files
+COPY frontend/package.json frontend/yarn.lock ./
+
+# Install dependencies
+RUN yarn install --frozen-lockfile
+
+# Copy frontend source
+COPY frontend/ ./
+
+# Build the frontend
+RUN yarn build
+
+# Production stage
+FROM python:3.10-slim
+
+WORKDIR /app
+
+# Install uv in production image
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv
+
+# Copy virtual environment from builder
+COPY --from=builder /app/.venv /app/.venv
+
+# Copy application code and compiled bytecode
+# Copy lib directory (includes templates, blocks, etc. and their .pyc files)
+COPY --from=builder /app/lib /app/lib
+# Copy main application files (including .pyc files if they exist)
+COPY --from=builder /app/app.py* /app/
+COPY --from=builder /app/config.py* /app/
+COPY --from=builder /app/models.py* /app/
+COPY --from=builder /app/pyproject.toml /app/pyproject.toml
+
+# Copy built frontend from frontend-builder
+COPY --from=frontend-builder /app/build /app/frontend/build
+
+# Create data directory and ensure custom blocks directory exists
+RUN mkdir -p /app/data /app/lib/blocks/custom
+
+# Set environment variables
+ENV PATH="/app/.venv/bin:$PATH"
+ENV PYTHONUNBUFFERED=1
+ENV PYTHONDONTWRITEBYTECODE=1
+
+# Expose port
+EXPOSE 8000
+
+# Run the application
+CMD ["uv", "run", "uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]
+

Makefile

@@ -24,11 +24,11 @@ check-deps:
 	@echo "✅ All dependencies are installed"
 
 install: check-deps
-	uv pip install -e .
+	uv venv && uv sync
 	cd frontend && yarn install
 
 dev: check-deps
-	uv pip install -e ".[dev]"
+	uv venv && uv sync --extra dev
 	cd frontend && yarn install
 
 dev-ui:

app.py

@@ -35,6 +35,11 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
 app = FastAPI(title="DataGenFlow", version="0.1.0", lifespan=lifespan)
 
 
+@app.get("/health")
+async def health() -> dict[str, str]:
+    return {"status": "healthy"}
+
+
 @app.post("/generate_from_file")
 async def generate_from_file(
     file: UploadFile = File(...), pipeline_id: int = Form(...)

docker-compose.yml

@@ -0,0 +1,26 @@
+services:
+  backend:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    container_name: datagenflow
+    ports:
+      - "8000:8000"
+    env_file:
+      - .env
+    volumes:
+      # Mount data directory for persistence
+      - ./data:/app/data
+      # Mount custom blocks directory for hot-reloading (restart required for new blocks)
+      - ./lib/blocks/custom:/app/lib/blocks/custom
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/api/health')"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+
+volumes:
+  data:
+