migrate to pixi for dependency management (#185)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: andersy005

.gitattributes

@@ -0,0 +1,2 @@
+# SCM syntax highlighting & preventing 3-way merges
+pixi.lock merge=binary linguist-language=YAML linguist-generated=true

.github/workflows/main.yaml

@@ -62,27 +62,20 @@ jobs:
           role-session-name: offsets-db-ci-role-session
           aws-region: ${{ env.AWS_DEFAULT_REGION }}
 
-      - name: set up conda environment
-        uses: mamba-org/setup-micromamba@v2
+      - name: Set up pixi
+        uses: prefix-dev/setup-[email protected]
         with:
-          environment-file: environment-dev.yml
-          init-shell: >-
-            bash
-          cache-environment: true
-          cache-downloads: true
-          post-cleanup: 'all'
-
-      - name: Install package
-        run: |
-          python -m pip install -e .
+          pixi-version: v0.59.0
+          cache: true
+          locked: true
 
       - name: Database migration
         run: |
-          python -m alembic upgrade head
+          pixi run migrate
 
       - name: Run tests
         run: |
-          python -m pytest
+          pixi run test
 
       - name: Upload code coverage to Codecov
         uses: codecov/[email protected]

.github/workflows/update-db.yaml

@@ -45,22 +45,21 @@ jobs:
         id: time
         run: echo "date=$(date -u +'%Y-%m-%d %H:%M')" >> $GITHUB_OUTPUT
 
-      - uses: actions/setup-python@v6
+      - name: Set up pixi
+        uses: prefix-dev/[email protected]
         with:
-          python-version: '3.10'
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          python -m pip install fsspec requests s3fs pandas
+          pixi-version: v0.59.0
+          cache: true
+          locked: true
 
       - name: Seed Staging Database
         run: |
-          python update_database.py staging --url https://offsets-db-staging.fly.dev/files/
+          pixi run update-db-staging
 
       - name: Seed Production Database
         if: github.event_name == 'workflow_dispatch' || github.event_name == 'schedule' || github.event_name == 'repository_dispatch'
         run: |
-          python update_database.py production --url https://offsets-db.fly.dev/files/
+          pixi run update-db-production
 
       - name: Notify Slack on Failure
         if: failure() && (github.event_name == 'workflow_dispatch' || github.event_name == 'schedule')

.gitignore

@@ -135,3 +135,6 @@ offsets_db_api/_version.py
 *.gz
 cache-watch-dog/
 staging-files.json
+# pixi environments
+.pixi/*
+!.pixi/config.toml

.pre-commit-config.yaml

@@ -1,5 +1,6 @@
 ci:
   autoupdate_schedule: monthly
+exclude: ^pixi\.lock$
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v6.0.0

Dockerfile

@@ -1,30 +1,52 @@
-# Start with an official Python image
-FROM python:3.12-slim
+# Build stage using pixi
+FROM ghcr.io/prefix-dev/pixi:0.59.0 AS build
 
 # Set environment variables
 ENV PYTHONDONTWRITEBYTECODE=1
 ENV PYTHONUNBUFFERED=1
 
-# Create and set the working directory
+# Install git and ca-certificates (needed for git+https:// dependencies in pyproject.toml)
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends git ca-certificates && \
+    rm -rf /var/lib/apt/lists/*
+
+# Copy source code, pixi.toml and pixi.lock to the container
 WORKDIR /app
+COPY . .
+
+# Install dependencies using pixi (uses the default environment)
+RUN pixi install --locked
+
+# Create the shell-hook bash script to activate the environment
+RUN pixi shell-hook > /shell-hook.sh
+
+# Extend the shell-hook script to run the command passed to the container
+RUN echo 'exec "$@"' >> /shell-hook.sh
+
+# Production stage
+FROM ubuntu:24.04 AS production
 
-# Install build dependencies
+# Set environment variables
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+# Install runtime dependencies (libpq for PostgreSQL)
 RUN apt-get update && \
-    apt-get install -y --no-install-recommends \
-    git \
-    libpq-dev \
-    build-essential && \
+    apt-get install -y --no-install-recommends git libpq5 && \
     rm -rf /var/lib/apt/lists/*
-# Install Python dependencies
-COPY requirements.txt .
-RUN pip install --upgrade pip && pip install -r requirements.txt
 
-# Copy the rest of the application code
-COPY . .
+# Copy the pixi environment from the build stage
+# Note: the prefix path must stay the same as in the build container
+COPY --from=build /app/.pixi/envs/default /app/.pixi/envs/default
+COPY --from=build /shell-hook.sh /shell-hook.sh
+COPY --from=build /app /app
+WORKDIR /app
 
 # Expose the port
 EXPOSE 8000
 
-COPY entrypoint.sh /entrypoint.sh
-RUN chmod +x /entrypoint.sh
-CMD ["/entrypoint.sh"]
+# Set the entrypoint to the shell-hook script (activates the environment and runs the command)
+ENTRYPOINT ["/bin/bash", "/shell-hook.sh"]
+
+# Run the application using gunicorn (supports OFFSETS_DB_WEB_CONCURRENCY env var)
+CMD ["sh", "-c", "gunicorn -w ${OFFSETS_DB_WEB_CONCURRENCY:-2} -t 600 -k uvicorn.workers.UvicornWorker offsets_db_api.main:app --config gunicorn_config.py --access-logfile - --error-logfile -"]

README.md

@@ -30,26 +30,21 @@ OffsetsDB-API, is a fastAPI application, designed to integrate and harmonize dat
 
 ## installation
 
-To install the package, you can use pip:
-
-```console
-python -m pip install git+https://github.com/carbonplan/offsets-db-api
-```
-
-You can also install the package locally by cloning the repository and running:
+This project uses [pixi](https://pixi.sh) for dependency management. To get started:
 
 ```console
 git clone https://github.com/carbonplan/offsets-db-api
 cd offsets-db-api
-python -m pip install -e .
+pixi install
 ```
 
-## run locally
-
-To run the API locally, you can use the following command:
+## usage
 
 ```console
-uvicorn offsets_db_api.main:app --reload
+pixi run serve        # Start development server with hot reload
+pixi run test         # Run tests
+pixi run migrate      # Run database migrations
+pixi run serve-prod   # Start production server
 ```
 
 ## license