feat(infra): add airflow orchestration services

Add Apache Airflow infrastructure with webserver, scheduler, and metadata
database to enable DAG-based pipeline orchestration. Includes optimized
requirements file and Docker configuration for Airflow 2.9.3.
This commit is contained in:
2026-02-06 23:20:58 +03:00
parent d7cff5ad1e
commit d33cdb3fb0
3 changed files with 145 additions and 0 deletions
+23
View File
@@ -0,0 +1,23 @@
# Use the official Airflow image as base
FROM apache/airflow:2.9.3
# Set environment variables
ENV AIRFLOW_HOME=/opt/airflow
# Copy the project requirements file
COPY --chown=airflow:0 requirements.txt ${AIRFLOW_HOME}/requirements.txt
# Install the required Python packages
RUN pip install --no-cache-dir -r ${AIRFLOW_HOME}/requirements.txt
# Create necessary directories
RUN mkdir -p /opt/airflow/dags /opt/airflow/logs /opt/airflow/config /opt/airflow/data
# Set working directory
WORKDIR ${AIRFLOW_HOME}
# Expose the webserver port
EXPOSE 8080
# The image will use Airflow's default entrypoint
# Commands will be passed at runtime