ML Tech Assessment - Martin Rios

.dockerignore

@@ -0,0 +1,75 @@
+# Git
+.git/
+.gitignore
+.gitattributes
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+*.egg
+*.egg-info/
+dist/
+build/
+pip-log.txt
+pip-delete-this-directory.txt
+.tox/
+.nox/
+.coverage
+.coverage.*
+htmlcov/
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.hypothesis/
+*.cover
+*.log
+
+# Virtual environments
+.venv/
+venv/
+ENV/
+env/
+env.bak/
+venv.bak/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+.DS_Store
+
+# Environment files (copy .env.example manually)
+.env
+.env.local
+.env.*.local
+.env.docker
+
+# Tests
+tests/
+test_*.py
+*_test.py
+conftest.py
+
+# Documentation
+docs/
+*.md
+!README.md
+
+# CI/CD
+.github/
+.gitlab-ci.yml
+.travis.yml
+
+# Docker
+Dockerfile*
+docker-compose*.yml
+.dockerignore
+
+# Other
+*.txt
+requirements*.txt

.env.example

@@ -0,0 +1,108 @@
+# ========================================
+# Application Settings
+# ========================================
+ENVIRONMENT=development
+DEBUG=true
+LOG_LEVEL=INFO
+LOG_FORMAT=colored
+
+# ========================================
+# API Configuration
+# ========================================
+# API key for authentication (optional - if not set, no auth required)
+# Set this to enable authentication for your API
+API_KEY=test-api-key-123
+
+# Server configuration
+HOST=0.0.0.0
+PORT=8000
+WORKERS=1
+
+# API metadata
+API_TITLE=Transcript Analysis API
+API_VERSION=1.0.0
+API_PREFIX=/api/v1
+
+# Feature flags
+ENABLE_DOCS=true
+ENABLE_REQUEST_LOGGING=true
+ENABLE_GZIP=true
+
+# ========================================
+# LLM Provider Configuration
+# ========================================
+# Provider selection: openai or groq
+LLM_PROVIDER=openai
+
+# OpenAI Configuration
+OPENAI_API_KEY=sk-your-api-key-here
+OPENAI_MODEL=gpt-4o
+OPENAI_TIMEOUT=30
+OPENAI_MAX_RETRIES=3
+
+# Groq Configuration (automatic fallback if OpenAI key not available)
+GROQ_API_KEY=gsk-your-groq-api-key-here
+GROQ_MODEL=llama-3.3-70b-versatile
+
+# ========================================
+# Security Configuration
+# ========================================
+# Rate limiting
+ENABLE_RATE_LIMITING=true
+RATE_LIMIT_DEFAULT=20/minute
+
+# Input/Output limits
+MAX_INPUT_TOKENS=100000
+MAX_OUTPUT_TOKENS=4000
+
+# Security features
+ENABLE_PII_DETECTION=true
+ENABLE_OUTPUT_MODERATION=true
+
+# ========================================
+# Repository Backend Configuration
+# ========================================
+# Storage backend: memory or redis
+# Use 'memory' for development/testing (data lost on restart)
+# Use 'redis' for production (persistent storage)
+REPOSITORY_BACKEND=redis
+
+# ========================================
+# Redis Configuration
+# ========================================
+# Required if REPOSITORY_BACKEND=redis
+REDIS_HOST=localhost
+REDIS_PORT=6379
+REDIS_DB=0
+
+# Optional Redis settings
+REDIS_PASSWORD=
+REDIS_MAX_CONNECTIONS=10
+REDIS_TTL_SECONDS=
+
+# Fallback IP if DNS resolution fails (optional)
+REDIS_FALLBACK_IP=
+
+# ========================================
+# Analysis Configuration
+# ========================================
+MAX_CONCURRENT_ANALYSES=10
+MAX_TRANSCRIPT_LENGTH=100000
+
+# ========================================
+# CORS Configuration
+# ========================================
+# Allowed origins (comma-separated or JSON array format)
+CORS_ORIGINS=["http://localhost:3000","http://localhost:8000"]
+CORS_ALLOW_CREDENTIALS=true
+CORS_ALLOW_METHODS=["*"]
+CORS_ALLOW_HEADERS=["*"]
+
+# ========================================
+# Notes
+# ========================================
+# 1. Copy this file to .env and fill in your actual values
+# 2. Never commit .env file to version control (it's in .gitignore)
+# 3. For production, set ENVIRONMENT=production and DEBUG=false
+# 4. At least one LLM provider key (OpenAI or Groq) is required
+# 5. If REPOSITORY_BACKEND=redis, ensure Redis is running and accessible

.gitignore

@@ -1 +1,83 @@
-.env
+# Environment variables
+.env
+.env.local
+.env.*.local
+
+# Python cache and compiled files
+**/__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.Python
+*.so
+*.egg
+*.egg-info/
+dist/
+build/
+
+# Testing and coverage
+.coverage
+.coverage.*
+htmlcov/
+.pytest_cache/
+.tox/
+.nox/
+
+# Virtual environments
+venv/
+ENV/
+env/
+.venv
+
+# UV lock file (optional - uncomment if you want to regenerate)
+# uv.lock
+
+# IDE and editor files
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+.DS_Store
+
+# Internal documentation (not for submission)
+docs/
+*_SUCCESS.md
+*_VERIFICATION.md
+*_REPORT.md
+*_SUMMARY.md
+*_INDEX.md
+CLAUDE.md
+
+# Tool state directories
+.swarm/
+.claude-flow/
+.claude/
+.mcp.json
+
+# Frontend artifacts in root (should be in frontend/ only)
+/node_modules/
+/package-lock.json
+/package.json
+/docker-compose.dev.yml
+
+# Redis data
+redis-data/
+*.rdb
+*.aof
+
+# Logs
+logs/
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+
+# OS files
+Thumbs.db
+.DS_Store
+
+# Temporary files
+*.tmp
+*.temp
+.cache/

Dockerfile

@@ -0,0 +1,63 @@
+# Multi-stage build for ml-tech-assessment FastAPI application
+# Uses uv for fast dependency management
+
+# ============================================
+# Stage 1: Builder - Install dependencies
+# ============================================
+FROM python:3.12-slim AS builder
+
+# Install uv for fast dependency management
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
+
+# Set working directory
+WORKDIR /app
+
+# Copy dependency files
+COPY pyproject.toml ./
+
+# Install dependencies with uv
+# Use --no-dev to exclude development dependencies
+RUN uv pip install --system --no-cache -r pyproject.toml
+
+# ============================================
+# Stage 2: Runtime - Minimal production image
+# ============================================
+FROM python:3.12-slim
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    # Prevent pip from checking for updates
+    PIP_DISABLE_PIP_VERSION_CHECK=1 \
+    # Application defaults
+    HOST=0.0.0.0 \
+    PORT=8000
+
+# Create non-root user for security
+RUN groupadd -r appuser && useradd -r -g appuser appuser
+
+# Set working directory
+WORKDIR /app
+
+# Copy Python 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 app/backend/ ./app/backend/
+
+# Change ownership to non-root user
+RUN chown -R appuser:appuser /app
+
+# Switch to non-root user
+USER appuser
+
+# Expose port
+EXPOSE 8000
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
+    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:8000/api/v1/health/live').read()" || exit 1
+
+# Run the application
+CMD ["uvicorn", "app.backend.main:app", "--host", "0.0.0.0", "--port", "8000"]