Add Docker config

.dockerignore

@@ -0,0 +1,57 @@
+# Version control
+.git
+.gitignore
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual environments
+.env*
+!.env.example
+.venv
+env/
+venv/
+ENV/
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# Testing
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Project specific
+nltk_data/
+.pdm-python
+.pdm.toml
+__pypackages__/ 

Dockerfile

@@ -0,0 +1,44 @@
+# Use Python slim image as base
+FROM python:3.10-slim AS builder
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PIP_NO_CACHE_DIR=1
+
+# Create and set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    curl \
+    git \
+    cmake \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy project files
+COPY . .
+
+# Install project in editable mode
+RUN pip install -e .
+
+# Create non-root user
+RUN useradd -m -u 1000 appuser && \
+    chown -R appuser:appuser /app
+
+# Switch to non-root user
+USER appuser
+
+# Expose Gradio port
+EXPOSE 7860
+
+# Set default environment variables for configuration
+ENV MODEL="meta-llama/Llama-3.1-8B-Instruct" \
+    MAGPIE_PRE_QUERY_TEMPLATE="llama3" \
+    MAX_NUM_TOKENS=2048 \
+    MAX_NUM_ROWS=1000 \
+    DEFAULT_BATCH_SIZE=5
+
+# Start command
+CMD ["python", "-m", "synthetic_dataset_generator"] 

docker-compose.yml

@@ -0,0 +1,25 @@
+version: '3.8'
+
+services:
+  app:
+    build: .
+    ports:
+      - "7860:7860"
+    env_file:
+      - .env
+    #volumes:
+    #  - nltk_data:/app/nltk_data
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:7860/"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+    restart: unless-stopped
+
+volumes:
+  nltk_data:
+
+networks:
+  app-network:
+    driver: bridge