How to install additional requirements for Airflow using official docker-compose file

Question

I'm using the below docker-compose.yml. For some of my dags I need to install additional requirements. Is it possible to specify additional python packages to install while using the official docker compose file?

version: '3'
x-airflow-common:
  &airflow-common
  image: ${AIRFLOW_IMAGE_NAME:-apache/airflow:master-python3.8}
  environment:
    &airflow-common-env
    AIRFLOW__CORE__EXECUTOR: CeleryExecutor
    AIRFLOW__CORE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow
    AIRFLOW__CELERY__RESULT_BACKEND: db+postgresql://airflow:airflow@postgres/airflow
    AIRFLOW__CELERY__BROKER_URL: redis://:@redis:6379/0
    AIRFLOW__CORE__FERNET_KEY: ''
    AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: 'true'
    AIRFLOW__CORE__LOAD_EXAMPLES: 'false'
  volumes:
    - ./dags:/opt/airflow/dags
    - ./logs:/opt/airflow/logs
    - ./plugins:/opt/airflow/plugins
  user: "${AIRFLOW_UID:-50000}:${AIRFLOW_GID:-50000}"
  depends_on:
    redis:
      condition: service_healthy
    postgres:
      condition: service_healthy

services:
  postgres:
    image: postgres:13
    environment:
      POSTGRES_USER: airflow
      POSTGRES_PASSWORD: airflow
      POSTGRES_DB: airflow
    volumes:
      - postgres-db-volume:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD", "pg_isready", "-U", "airflow"]
      interval: 5s
      retries: 5
    restart: always

  redis:
    image: redis:latest
    ports:
      - 6379:6379
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 5s
      timeout: 30s
      retries: 50
    restart: always

  airflow-webserver:
    <<: *airflow-common
    command: webserver
    ports:
      - 8080:8080
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:8080/health"]
      interval: 10s
      timeout: 10s
      retries: 5
    restart: always

  airflow-scheduler:
    <<: *airflow-common
    command: scheduler
    restart: always

  airflow-worker:
    <<: *airflow-common
    command: celery worker
    restart: always

  airflow-init:
    <<: *airflow-common
    command: version
    environment:
      <<: *airflow-common-env
      _AIRFLOW_DB_UPGRADE: 'true'
      _AIRFLOW_WWW_USER_CREATE: 'true'
      _AIRFLOW_WWW_USER_USERNAME: ${_AIRFLOW_WWW_USER_USERNAME:-airflow}
      _AIRFLOW_WWW_USER_PASSWORD: ${_AIRFLOW_WWW_USER_PASSWORD:-airflow}

  flower:
    <<: *airflow-common
    command: celery flower
    ports:
      - 5555:5555
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:5555/"]
      interval: 10s
      timeout: 10s
      retries: 5
    restart: always

volumes:
  postgres-db-volume:

Answer 1

extending official image is pretty easy. Here' what I did:

in docker-compose.yml replace

  image: ...

by

  build: ./airflow

then, create a airflow folder then create a Dockerfile in it. here's what I used to avoid an unecessary warning.

FROM apache/airflow:2.0.1
# this fixes a warning in the official image, with the Azure provider
# More info here https://github.com/apache/airflow/issues/14266#issuecomment-786298240
RUN pip uninstall  --yes azure-storage && pip install -U azure-storage-blob apache-airflow-providers-microsoft-azure==1.1.0
# add your dependencies here:
# RUN pip install package1 package2....

then simply add the --build switch to you docker-compose commands

docker-compose up --build airflow-init
docker-compose up -d

enjoy!