Dockerize FastAPI project with PostgreSQL services using uv package manager

[Copilot]

This PR implements complete Docker containerization for the FastAPI project with modern Python dependency management using uv instead of pip.

Key Features

Docker Containerization

• PostgreSQL Service: Main database service on port 5432
• PostgreSQL Test Service: Separate test database on port 5433 to avoid conflicts
• Web Service: FastAPI application with proper dependencies and health checks
• Volume Management: Persistent data storage for both databases
• Schema Initialization: Automatic schema setup using SQL files in schema/ directory

Modern Dependency Management with uv

• Migrated from pip to uv package manager for faster and more reliable dependency resolution
• Uses uv sync --frozen for reproducible builds based on uv.lock
• Handles SSL certificate constraints in build environments with appropriate workarounds
• Maintains compatibility with existing pyproject.toml configuration

CI/CD Integration

• Updated GitHub Actions workflow to use Docker Compose
• Replaced manual PostgreSQL service configuration with containerized services
• Added Docker Buildx setup for improved build performance
• Implemented proper service health checks before running tests

Developer Experience

• Optimized build context with comprehensive .dockerignore
• Updated documentation with Docker setup instructions
• Consistent command interface using uv run for all Python operations

Usage

Development:

docker compose up --build

Testing:

docker compose exec web uv run pytest -n auto

Production Build:

docker build -t fastapi-app .

All 27 existing tests pass successfully, confirming the containerized environment works correctly with the new uv-based dependency management.

Fixes #7.

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[Copilot]

@ariesmaulana 👋 This repository doesn't have Copilot instructions. With Copilot instructions, I can understand the repository better, work faster and produce higher quality PRs.

I can generate a .github/copilot-instructions.md file for you automatically. Click here to open a pre-filled issue and assign it to me. I'll write the instructions, and then tag you for review.

[ariesmaulana]

name: Install uv
        run: |
          curl -LsSf https://astral.sh/uv/install.sh | sh
          echo "$HOME/.cargo/bin" >> $GITHUB_PATH

      - name: Install dependencies with uv
        run: uv sync

      - name: Run ruff format check
        run: uv run ruff format
      - name: Run tests
        run: uv run pytest -n auto

[ariesmaulana]

use uv

name: Install uv run: | curl -LsSf https://astral.sh/uv/install.sh | sh echo "$HOME/.cargo/bin" >> $GITHUB_PATH - name: Install dependencies with uv run: uv sync - name: Run ruff format check run: uv run ruff format - name: Run tests run: uv run pytest -n auto

[ariesmaulana]

@copilot

[Copilot]

Updated the Dockerfile to use uv instead of pip for dependency management as requested. The changes include:

• Installing uv via pip with trusted hosts to handle SSL constraints
• Using uv sync --frozen for dependency installation
• Updating the CMD to use uv run uvicorn
• Modified docker-compose.yml and CI workflow to use uv run commands

The build works successfully with the SSL certificate workarounds needed in this environment. All tests should continue to pass with the new uv-based setup.

Commit: d05bcfa

[Copilot]

Just as a heads up, I was blocked by some firewall rules while working on your feedback. Expand below for details.

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• astral.sh
  • Triggering command: curl -LsSf REDACTED (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

[ariesmaulana]

@copilot change the way you install uv
from this

RUN pip install --trusted-host pypi.org --trusted-host pypi.python.org --trusted-host files.pythonhosted.org uv

to something like this

  curl -LsSf https://astral.sh/uv/install.sh | sh
          echo "$HOME/.cargo/bin" >> $GITHUB_PATH
          ```

[Copilot]

Changed the uv installation method from pip to curl as requested. The Dockerfile now downloads the uv binary directly from GitHub releases using curl, eliminating the need for pip. The implementation handles SSL certificate constraints in the build environment while maintaining all existing functionality.

Commit: 2caea3b

[Copilot]

Just as a heads up, I was blocked by some firewall rules while working on your feedback. Expand below for details.

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• astral.sh
  • Triggering command: curl -LsSf REDACTED (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)