Repository navigation

fix: don't load a partially written dataset file from the cache #1137

	name: Curator testing workflow

	on:
	push:
	branches:
	- main
	pull_request:
	branches:
	- main

	jobs:
	test-integration:
	runs-on: ubuntu-latest

	steps:
	- name: Checkout code
	uses: actions/checkout@v2

	- name: Set up Python
	uses: actions/setup-python@v2
	with:
	python-version: '3.11'

	- name: Load cached Poetry installation
	uses: actions/cache@v3
	with:
	path: ~/.local
	key: poetry-${{ runner.os }}-${{ hashFiles('**/poetry.lock') }}

	- name: Load cached venv
	uses: actions/cache@v3
	with:
	path: .venv
	key: venv-${{ runner.os }}-python-${{ matrix.python-version }}-${{ hashFiles('**/poetry.lock') }}

	- name: Set Locale
	run: \|
	sudo locale-gen "en_US.UTF-8"
	export LC_ALL=en_US.UTF-8
	export LANG=en_US.UTF-8
	export TELEMETRY_ENABLED=false

	- name: Install dependencies
	run: \|
	pip install poetry
	poetry install --with dev --extras "vllm"

	- name: Run ruff
	run: \|
	poetry run ruff check . --output-format=github
	poetry run ruff format . --check

	- name: Run tests with coverage
	run: \|
	# Scope coverage to curator itself: bespokelabs-sandbox installs into the
	# same bespokelabs.* namespace and would otherwise be measured too.
	poetry run pytest --cov='bespokelabs.curator' --cov-report=html --cov-fail-under=80 tests/