add docker

Author: antonacio

Dockerfile

@@ -6,6 +6,16 @@
 FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim AS builder
 ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy
 
+# Install GDAL build dependencies (for fiona Python package)
+USER root
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends \
+        build-essential \
+        gdal-bin \
+        libgdal-dev \
+        python3-dev \
+    && rm -rf /var/lib/apt/lists/*
+
 # Disable Python downloads, because we want to use the system interpreter
 # across both images. If using a managed Python version, it needs to be
 # copied from the build image into the final image; see `standalone.Dockerfile`
@@ -28,12 +38,22 @@ FROM python:3.12-slim-bookworm
 # Python executable must be the same, e.g., using `python:3.11-slim-bookworm`
 # will fail.
 
+# Install GDAL runtime library (for fiona Python package)
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends \
+        libgdal-dev \
+    && rm -rf /var/lib/apt/lists/*
+
 # Copy the application from the builder
 COPY --from=builder --chown=app:app /app /app
 
 # Place executables in the environment at the front of the path
 ENV PATH="/app/.venv/bin:$PATH"
 
-# # Run the FastAPI application by default
-# CMD ["fastapi", "dev", "--host", "0.0.0.0", "/app/src/uv_docker_example"]
+# disable Kedro telemetry
+ENV KEDRO_DISABLE_TELEMETRY=1
+
+WORKDIR /app
+# Run Kedro pipelines
+CMD ["kedro", "run", "--async"]
 

Justfile

@@ -21,5 +21,12 @@ test:
 
 validate: format lint test
 
-dockerize:
+docker-build:
 	docker build -t geolocation-pipeline .
+
+docker-run:
+	# Bind‑mount the host .data/ folder into the container so that the pipelines'
+	# outputs are saved in the host's local .data/ folder
+	docker run --rm \
+		-v "$(pwd)/data:/app/data" \
+		geolocation-pipeline

README.md

@@ -117,9 +117,17 @@ The image below shows the pipelines visualization for this project:
 This project includes a multi-stage Dockerfile, which produces an image with the code and the dependencies installed. You can build the image with:
 
 ```bash
-just dockerize
+just docker-build
 ```
 
+Then, you can run the Kedro pipelines inside a container with the image you just built by running:
+
+```bash
+just docker-run
+```
+
+The outputs of the pipelines will still be saved in your local `data/` folder, because the docker container mounts the `data/` folder as a volume.
+
 ### Github Actions
 
 This project includes a Github Actions workflow that runs the formatters, linters, and tests on every push/PR to the `main` or `develop` branches. You can find the workflow file in `.github/workflows/format-lint-test.yml`.