🚀 Enterprise-Grade Enhancements: REST API, Caching, Monitoring & Containerization

.dockerignore

@@ -0,0 +1,81 @@
+# Git
+.git
+.gitignore
+
+# Python
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+env
+pip-log.txt
+pip-delete-this-directory.txt
+.tox
+.coverage
+.coverage.*
+.pytest_cache
+nosetests.xml
+coverage.xml
+*.cover
+*.log
+.cache
+.mypy_cache
+
+# Virtual environments
+venv/
+env/
+ENV/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Project specific
+*.csv
+*.xlsx
+*.xls
+data/
+logs/
+output/
+temp/
+tmp/
+
+# Documentation
+docs/_build/
+*.md
+
+# Docker
+Dockerfile*
+docker-compose*.yml
+.dockerignore
+
+# CI/CD
+.github/
+.gitlab-ci.yml
+
+# Environment files
+.env
+.env.local
+.env.*.local
+
+# Test files
+tests/
+test_*.py
+*_test.py
+
+# Backup files
+*.bak
+*.backup

Dockerfile

@@ -0,0 +1,140 @@
+# Multi-stage Dockerfile for Name Matching Application
+FROM python:3.11-slim as base
+
+# Set environment variables
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PYTHONPATH=/app \
+    PIP_NO_CACHE_DIR=1 \
+    PIP_DISABLE_PIP_VERSION_CHECK=1
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    gcc \
+    g++ \
+    pkg-config \
+    libmysqlclient-dev \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create app user
+RUN groupadd -r appuser && useradd -r -g appuser appuser
+
+# Set work directory
+WORKDIR /app
+
+# Copy requirements first for better caching
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY . .
+
+# Change ownership to app user
+RUN chown -R appuser:appuser /app
+
+# Switch to app user
+USER appuser
+
+# Expose port
+EXPOSE 8000
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:8000/health || exit 1
+
+# Default command
+CMD ["python", "-m", "uvicorn", "src.api.main:app", "--host", "0.0.0.0", "--port", "8000"]
+
+
+# Development stage
+FROM base as development
+
+USER root
+
+# Install development dependencies
+RUN pip install --no-cache-dir pytest pytest-cov black isort flake8 mypy
+
+# Install additional development tools
+RUN apt-get update && apt-get install -y \
+    git \
+    vim \
+    && rm -rf /var/lib/apt/lists/*
+
+USER appuser
+
+# Override command for development
+CMD ["python", "-m", "uvicorn", "src.api.main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]
+
+
+# Production stage
+FROM base as production
+
+# Copy only necessary files for production
+COPY --from=base /app /app
+
+# Set production environment
+ENV ENVIRONMENT=production
+
+# Use production command
+CMD ["python", "-m", "uvicorn", "src.api.main:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "4"]
+
+
+# GPU-enabled stage
+FROM nvidia/cuda:11.8-runtime-ubuntu22.04 as gpu
+
+# Set environment variables
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PYTHONPATH=/app \
+    PIP_NO_CACHE_DIR=1 \
+    PIP_DISABLE_PIP_VERSION_CHECK=1
+
+# Install Python and system dependencies
+RUN apt-get update && apt-get install -y \
+    python3.11 \
+    python3.11-dev \
+    python3-pip \
+    gcc \
+    g++ \
+    pkg-config \
+    libmysqlclient-dev \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create symlink for python
+RUN ln -s /usr/bin/python3.11 /usr/bin/python
+
+# Create app user
+RUN groupadd -r appuser && useradd -r -g appuser appuser
+
+# Set work directory
+WORKDIR /app
+
+# Copy requirements
+COPY requirements.txt requirements-gpu.txt ./
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+RUN pip install --no-cache-dir -r requirements-gpu.txt
+
+# Copy application code
+COPY . .
+
+# Change ownership to app user
+RUN chown -R appuser:appuser /app
+
+# Switch to app user
+USER appuser
+
+# Expose port
+EXPOSE 8000
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:8000/health || exit 1
+
+# GPU-enabled command
+CMD ["python", "-m", "uvicorn", "src.api.main:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "2"]

config.json.sample

@@ -0,0 +1,70 @@
+{
+  "environment": "development",
+  "debug": true,
+  "database": {
+    "host": "localhost",
+    "port": 3306,
+    "user": "nameuser",
+    "password": "namepass",
+    "database": "namematching",
+    "use_ssl": false,
+    "pool_size": 10,
+    "max_overflow": 20,
+    "pool_timeout": 30,
+    "pool_recycle": 3600
+  },
+  "redis": {
+    "host": "localhost",
+    "port": 6379,
+    "db": 0,
+    "password": null,
+    "default_ttl": 3600,
+    "key_prefix": "name_match:",
+    "max_connections": 10
+  },
+  "api": {
+    "host": "0.0.0.0",
+    "port": 8000,
+    "workers": 4,
+    "reload": false,
+    "log_level": "info",
+    "cors_origins": ["*"],
+    "jwt_secret_key": "your-secret-key-change-in-production",
+    "jwt_algorithm": "HS256",
+    "jwt_expire_minutes": 30
+  },
+  "matching": {
+    "match_threshold": 0.75,
+    "non_match_threshold": 0.55,
+    "enable_gpu": false,
+    "enable_caching": true,
+    "cache_ttl": 3600,
+    "max_batch_size": 10000,
+    "default_similarity_function": "jaro_winkler",
+    "component_weights": {
+      "first_name": 0.3,
+      "middle_name": 0.2,
+      "last_name": 0.3,
+      "birthdate": 0.1,
+      "geography": 0.1
+    }
+  },
+  "monitoring": {
+    "enable_prometheus": true,
+    "prometheus_port": 8001,
+    "enable_health_checks": true,
+    "health_check_interval": 30,
+    "log_level": "INFO",
+    "log_format": "%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+    "log_file": null,
+    "max_log_size": 10485760,
+    "log_backup_count": 5
+  },
+  "gpu": {
+    "enabled": false,
+    "device_id": 0,
+    "memory_limit": null,
+    "batch_size": 1000,
+    "enable_mixed_precision": false
+  }
+}