Deploy to production 2024-08-22 / 1 (#54)

* Add CI to vectorizing CU-86bvyavpu  (#46)

* Add CI pipeline to run tests with gha
* Add system dependencies installer script shared between dev container and CI
* Update README documentation
* Remove 'python-dev0 as system dependency

* Upgrade vectorizing to python 3.11 CU-866aw6ung (#42)

* Update dockerfile
* Update requirements
* Update environments

* Add linting and formatting CU-86bw0yqjw  (#47)

* Linting and formatting setup using pre-commit
* Updated devcontainer with pre-commit

* Fix k8s deployment CU-86bwkb51r

* Add PR template CU-86bx2ntyx  (#50)

* Add PR template to the repository, with information aligned with guidelines in notion

* Remove PR template to use org one (#51)

* Remove PR template to use org one

* Fix UA  (#52)

* Update UA

* CU-86bze09vt Move vectorizing to new clusters (#53)

* Update Dockerfile and remove AWS AK/SAK

* Update deployment workflow

* Minor modification to the deploy workflow

* Add region_name to the client

* Upgrade boto3

* Update port

* Undo temp changes

---------

Co-authored-by: Pietro Bolcato <[email protected]>

.devcontainer/scripts/post_create.sh

@@ -1,7 +1,14 @@
 #!/bin/bash
 # this script install system dependencies for vectorizing and sets up conda
 
-sudo apt-get update
-sudo apt-get install -y build-essential python-dev libagg-dev libpotrace-dev pkg-config libffi-dev libcairo2-dev
+SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+
+# install system dependencies
+bash "$SCRIPT_DIR"/../../scripts/install_system_dependencies.sh
+
+# setup conda
 conda env create -n dev -f envs/dev.yaml
-conda init
+conda init
+
+# setup pre-commit
+pre-commit install --install-hooks

.dockerignore

@@ -0,0 +1,176 @@
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# Other files
+heroku.yml
+docker-compose.yml
+.pre-commit-config.yaml
+.vscode/
+.gitignore
+.github/
+.devcontainer/
+.env.example
+LICENSE
+README.md
+Dockerfile
+.dockerignore
+.git/

.github/workflows/ci.yml

@@ -0,0 +1,56 @@
+name: ci
+on: push
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+  id-token: write
+  packages: read
+
+jobs:
+  lint:
+    name: Lint
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: "3.11"
+      - uses: pre-commit/[email protected]
+
+  test:
+    name: Test
+    runs-on: ubuntu-latest
+    env:
+      PORT: "5000"
+      S3_BUCKET: "-"
+      S3_TEST_BUCKET: "kittl-uploads-storage-staging"
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-region: 'eu-central-1'
+          role-to-assume: 'arn:aws:iam::339713006905:role/vectorizing-github-actions'
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.11
+      - name: Set up system dependencies
+        run: |
+          bash scripts/install_system_dependencies.sh
+      - name: Set up `dev` conda environment
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+          activate-environment: dev
+          environment-file: envs/dev.yaml
+          auto-activate-base: false
+      - name: Run tests
+        shell: bash -el {0}
+        run: |
+          conda activate dev
+          python -m pytest vectorizing/tests/test.py

.github/workflows/deploy.yml

@@ -1,42 +1,15 @@
 name: deploy
+
 on:
   push:
     branches:
       - production
       - main
+      - 
 jobs:
-  publish-docker-image:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out repository code
-        uses: actions/checkout@v2
-      - name: Login to GitHub Container Registry
-        uses: docker/login-action@v1
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-      - name: Configure AWS credentials                          
-        uses: aws-actions/configure-aws-credentials@v1           
-        with:                                                    
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}        
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: eu-central-1
-      - name: Publish the Docker image
-        run: |
-          docker build . --tag ghcr.io/kittl/vectorizing:${{ github.ref_name }}
-          docker push ghcr.io/kittl/vectorizing:${{ github.ref_name }}
-      - name: Deploy vectorizing in staging cluster
-        uses: kodermax/kubectl-aws-eks@master
-        env:
-          KUBE_CONFIG_DATA: ${{ secrets.KUBE_CONFIG }}
-        if: github.ref_name == 'main'
-        with:
-          args: rollout restart deployment/vectorizing --context staging
-      - name: Deploy vectorizing in production cluster
-        uses: kodermax/kubectl-aws-eks@master
-        env:
-          KUBE_CONFIG_DATA: ${{ secrets.KUBE_CONFIG }}
-        if: github.ref_name == 'production'
-        with:
-          args: rollout restart deployment/vectorizing --context production
+  deploy-py-server-argo:
+    name: Deploy PY server Argo
+    uses: ./.github/workflows/helpers-deploy-argo.yaml
+    secrets:
+      GH_PAT: ${{ secrets.GH_PAT }}
+      ECR_ROLE_ARN: ${{ github.ref == 'refs/heads/production' && secrets.PRODUCTION_ECR_ROLE_ARN || secrets.STAGING_ECR_ROLE_ARN }}

.github/workflows/helpers-build-docker-image.yaml

@@ -0,0 +1,93 @@
+# This callable workflow builds and publish a package docker image
+
+name: helpers-build-docker-image
+
+on:
+  workflow_call:
+    inputs:
+      aws-region:
+        default: eu-central-1
+        description: The AWS region to use for ECR
+        required: false
+        type: string
+      docker_file_path:
+        description: >
+          "The path to the Dockerfile to use for building the image. For example:
+          `path/to/project/Dockerfile`"
+        type: string
+        required: true
+      extra-image-tags:
+        default: ''
+        description: Extra tags to use for the image (one per line)
+        required: false
+        type: string
+      platforms:
+        default: linux/amd64
+        description: The platforms to build for
+        required: false
+        type: string
+    secrets:
+      ECR_ROLE_ARN:
+        description: The ECR role ARN
+        required: true
+    outputs:
+      image-tag:
+        description: The docker image tag
+        value: ${{ jobs.build.outputs.image-tag }}
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+  id-token: write
+  packages: read
+
+jobs:
+  build:
+    name: Build docker image and push to ECR
+    runs-on: ubuntu-latest
+    outputs:
+      image-tag: ${{ steps.get-image-tag.outputs.image-tag }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-region: ${{ inputs.aws-region }}
+          role-to-assume: ${{ secrets.ECR_ROLE_ARN }}
+      - name: Login to Amazon ECR
+        id: login-ecr
+        uses: aws-actions/amazon-ecr-login@v2
+      - name: Get image tag output
+        shell: bash
+        id: get-image-tag
+        run: echo "image-tag=sha-${GITHUB_SHA:0:7}" >> $GITHUB_OUTPUT
+      - name: Docker meta tags
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          flavor: |
+            latest=false
+          images: |
+            ${{ format('{0}/{1}', steps.login-ecr.outputs.registry, github.event.repository.name) }}
+          tags: |
+            type=semver,pattern={{version}}
+            type=sha
+            ${{ inputs.extra-image-tags }}
+      - name: Build and push
+        uses: docker/build-push-action@v6
+        with:
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          context: .
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          platforms: ${{ inputs.platforms }}
+          provenance: false
+          push: true
+          file: ${{ inputs.docker_file_path }}