feat: support metal GPU acceleration #32

	name: CI

	on:
	push:
	branches:
	- "main"
	paths:
	- "chatbot/**"
	- "tests/**"
	- ".github/workflows/**"
	pull_request:
	types: [opened, reopened, synchronize, ready_for_review]
	paths:
	- "chatbot/**"
	- "tests/**"
	- ".github/workflows/**"

	jobs:
	test:
	runs-on: ubuntu-latest
	timeout-minutes: 20
	steps:
	- name: Checkout
	uses: actions/checkout@v4

	- name: Get poetry version
	id: poetry-version
	run: echo "poetry-version=$(cat version/poetry)" >> "$GITHUB_OUTPUT"

	- name: Install poetry
	uses: snok/install-poetry@v1
	with:
	version: ${{ steps.poetry-version.outputs.poetry-version }}
	virtualenvs-in-project: true

	- name: Get llama-cpp version
	id: llama-cpp-version
	run: echo "llama-cpp-version=$(cat version/llama_cpp)" >> "$GITHUB_OUTPUT"

	- name: Get ctransformers version
	id: ctransformers-version
	run: echo "ctransformers-version=$(cat version/ctransformers)" >> "$GITHUB_OUTPUT"

	# Installing dependencies and llama-cpp-python without NVIDIA CUDA acceleration.
	- name: Setup environment
	run: \|
	poetry lock --check
	poetry install --no-root --no-ansi
	. .venv/bin/activate && pip3 install llama-cpp-python==${{ steps.llama-cpp-version.outputs.llama-cpp-version }}
	. .venv/bin/activate && pip3 install ctransformers==${{ steps.ctransformers-version.outputs.ctransformers-version }}

	- name: Run tests
	run: \|
	poetry run python -m pytest --durations=5 --log-cli-level=DEBUG --capture=tee-sys -v

Provide feedback