add ragbench faithfulness cards #438

	name: Test Inference Engines

	on:
	pull_request:
	paths:
	- 'src/unitxt/inference.py'
	- 'tests/inference/*.py'
	- '.github/workflows/inference_tests.yml'

	release:
	types: [published]

	concurrency:
	group: ${{ github.workflow }}-${{ github.event_name == 'pull_request' && github.event.pull_request.number \|\| github.ref_name }}
	cancel-in-progress: true

	jobs:
	inference:
	runs-on: ubuntu-latest
	env:
	OS: ubuntu-latest
	UNITXT_DEFAULT_VERBOSITY: error
	DATASETS_VERBOSITY: error
	HF_HUB_VERBOSITY: error
	HF_DATASETS_DISABLE_PROGRESS_BARS: "True"
	TQDM_DISABLE: "True"
	WML_URL: ${{ secrets.WML_URL }}
	WML_PROJECT_ID: ${{ secrets.WML_PROJECT_ID }}
	WML_APIKEY: ${{ secrets.WML_APIKEY }}
	WX_URL: ${{ secrets.WX_URL }}
	WX_PROJECT_ID: ${{ secrets.WX_PROJECT_ID }}
	WX_API_KEY: ${{ secrets.WX_API_KEY }}
	GENAI_KEY: ${{ secrets.GENAI_KEY }}
	steps:
	- uses: actions/checkout@v4

	- uses: actions/setup-python@v5
	with:
	python-version: '3.10'

	- run: curl -LsSf https://astral.sh/uv/install.sh \| sh
	- run: uv pip install --system ".[tests,watsonx,inference-tests]"
	- name: Hugging Face Login
	run: \|
	for i in {1..5}; do
	huggingface-cli login --token ${{ secrets.UNITXT_READ_HUGGINGFACE_HUB_FOR_TESTS }} && break \|\| sleep $((2 ** i));
	done
	- name: Install Ollama
	run: curl -fsSL https://ollama.com/install.sh \| sh
	- name: Pull Llama 3.2:1b model
	run: ollama pull llama3.2:1b
	- name: Start serving the model
	run: nohup ollama serve --model llama3.2:1b --port 5000 &

	- name: Run Tests
	run: python -m unittest discover -s tests/inference -p "test_*.py"

Provide feedback