create a github action for triggering client-sdk tests on new pull-request #25

	name: auto-tests

	on:
	pull_request:
	push:
	workflow_dispatch:

	jobs:
	test:
	runs-on: ubuntu-latest
	env:
	TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
	FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
	TAVILY_SEARCH_API_KEY: ${{ secrets.TAVILY_SEARCH_API_KEY }}
	strategy:
	matrix:
	provider: [fireworks, together]
	steps:
	- uses: actions/checkout@v4

	- name: Echo branch name
	run: echo "Running on branch ${{ github.ref }}"

	- name: Install dependencies
	run: \|
	python -m pip install --upgrade pip
	pip install -r requirements.txt pytest
	pip install -e .

	- name: Build providers
	run: \|
	llama stack build --template ${{ matrix.provider }} --image-type venv

	- name: Install local llama-stack-client and llama-models
	run: \|
	pip install [email protected]:meta-llama/llama-stack-client-python.git

	- name: Run client-sdk test
	working-directory: "${{ github.workspace }}"
	run: \|
	export INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
	LLAMA_STACK_CONFIG=./llama_stack/templates/${{ matrix.provider }}/run.yaml pytest ./tests/client-sdk/inference/test_inference.py

Provide feedback