Weekly Tool Benchmarks #23

	name: Weekly Tool Benchmarks

	on:
	workflow_dispatch:
	schedule:
	- cron: '0 0 * * 0' # Runs at midnight (00:00) every Sunday (UTC time)

	env:
	POETRY_VERSION: "1.6.1"
	LANGCHAIN_API_KEY: ${{ secrets.LANGCHAIN_API_KEY }}
	OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
	ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}

	jobs:
	run_tool_benchmarks:
	runs-on: ubuntu-latest

	steps:
	- uses: actions/checkout@v4

	- name: Set up Python 3.12 + Poetry ${{ env.POETRY_VERSION }}
	uses: "./.github/actions/poetry_setup"
	with:
	python-version: '3.12'
	poetry-version: ${{ env.POETRY_VERSION }}
	working-directory: .
	cache-key: benchmarks-all

	- name: Install dependencies
	shell: bash
	run: \|
	echo "Running tests, installing dependencies with poetry..."
	poetry install --with test,lint,typing,docs

	- name: Multiverse math benchmark

	run: \|
	cd scripts
	poetry run python multiverse_math_benchmark.py

	- name: Query analysis benchmark
	run: \|
	cd scripts
	poetry run python query_analysis_benchmark.py

Provide feedback